CN116090553A - Artificial intelligence automatic processing system based on meta learning - Google Patents
Artificial intelligence automatic processing system based on meta learning Download PDFInfo
- Publication number
- CN116090553A CN116090553A CN202310373222.7A CN202310373222A CN116090553A CN 116090553 A CN116090553 A CN 116090553A CN 202310373222 A CN202310373222 A CN 202310373222A CN 116090553 A CN116090553 A CN 116090553A
- Authority
- CN
- China
- Prior art keywords
- user information
- information
- automatic processing
- module
- representing
- 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.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 256
- 238000013473 artificial intelligence Methods 0.000 title claims description 22
- 238000007781 pre-processing Methods 0.000 claims abstract description 38
- 238000000034 method Methods 0.000 claims description 82
- 230000005540 biological transmission Effects 0.000 claims description 60
- 230000006870 function Effects 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 8
- 238000003672 processing method Methods 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 238000004422 calculation algorithm Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
- G06V30/19173—Classification techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an artificial intelligent automatic processing system based on meta learning, which comprises a host terminal, an edge processing terminal, a meta learning terminal and an automatic processing terminal, wherein the host terminal is used for processing the edge of the object; the edge processing terminal is used for preprocessing user data from a user and processing the user data into user information; the host terminal is used for being connected with the edge processing terminal and receiving user information from the edge processing terminal; the meta learning terminal and the automatic processing terminal are connected with the host terminal; the meta learning terminal is used for generating meta learning adjustment information according to all user information in a preset period; the automatic processing terminal is used for communicating with the host terminal and processing the user information of the host terminal according to a preset automatic processing instruction; the meta-learning adjustment information is used to update the automated processing instructions. The invention has the effect of improving the working efficiency of the automatic processing system.
Description
Technical Field
The invention relates to the technical field of meta-learning processing systems, in particular to an artificial intelligent automatic processing system based on meta-learning.
Background
Meta learning refers to the process of improving a learning algorithm over multiple learning phases. In the basic learning process, the internal learning algorithm solves the task defined by the dataset and the target. In the meta learning process, the external algorithm updates the internal learning algorithm so that the learned model improves the external target. An artificial intelligence automated processing system is a processing system that is composed of processors or automated machinery, where a person is only a manager and a monitor, and where the machine operation is not dependent on human control.
Many artificial intelligence automated processing systems have been developed and, through extensive searching and reference, the prior art artificial intelligence automated processing systems have been found to have artificial intelligence automated processing systems as disclosed in publication nos. CN111928351A, CN114936186A, EP1086567A4, US20070208875A1, JP2015166971a, which generally include: a receiving terminal and an automatic processing terminal; the receiving terminal is used for receiving the data and the files to be processed, and the automatic processing terminal is used for performing automatic processing operation according to the processing requirements of the data and the files. The automatic processing of the artificial intelligent automatic processing system is single and lacks of functions of automatically perfecting or optimizing an automatic processing process, so that the defect of reduced working efficiency of the automatic processing system is caused.
Disclosure of Invention
The invention aims to provide an artificial intelligent automatic processing system based on meta learning, aiming at the defects of the artificial intelligent automatic processing system.
The invention adopts the following technical scheme:
an artificial intelligent automatic processing system based on meta learning comprises a host terminal, an edge processing terminal, a meta learning terminal and an automatic processing terminal;
the edge processing terminal is used for preprocessing user data from a user and processing the user data into user information; the host terminal is used for being connected with the edge processing terminal and receiving user information from the edge processing terminal; the meta learning terminal and the automatic processing terminal are connected with the host terminal;
the meta learning terminal is used for generating meta learning adjustment information according to all user information in a preset period; the automatic processing terminal is used for communicating with the host terminal and processing user information of the host terminal according to a preset automatic processing instruction; the meta learning adjustment information is used to update the automatic processing instructions.
Optionally, the host terminal includes a central processing module and an information storage module, where the central processing module is used to communicate with the meta learning terminal and the automatic processing terminal; the information storage module is used for storing user information from the edge processing terminal.
Optionally, the edge processing terminal comprises a preprocessing module, a transmission ordering module and an edge communication module; the preprocessing module is used for preprocessing user data from a user to generate user information; the transmission ordering module is used for ordering all user information of the preprocessing module and generating transmission sequence information; the edge communication module is used for transmitting the user information to the information storage module according to the transmission sequence information.
Optionally, the meta learning terminal comprises an edge processing full-flow reading module, a host full-flow reading module and a meta learning module; the edge processing full-flow reading module is used for reading first full-flow information of the edge processing terminal for processing user data; the host full-flow reading module is used for reading second full-flow information of the user information processed by the host terminal; the meta learning module is used for generating meta learning adjustment information according to all user information, first full-flow information and second full-flow information in a preset period.
Optionally, the automatic processing terminal comprises an automatic processing instruction reading module and an automatic processing module; the automatic processing instruction reading module is used for reading a preset automatic processing instruction from the host terminal; the automatic processing module is used for processing the user information of the host terminal according to the corresponding automatic processing instruction.
Optionally, the transmission ordering module comprises a transmission order calculation sub-module and a transmission order information generation sub-module; the transmission sequence calculating submodule is used for calculating transmission sequence indexes of all user information; the transmission sequence information generation sub-module is used for generating transmission sequence information of all user information according to the transmission sequence index;
when the transmission sequence calculation sub-module works, the following equation is satisfied:
wherein ,a transmission order index indicating corresponding user information; />Representing a coefficient selection function based on the type of user information; />A capacity value representing user information; />A time base representing a number of received hours based on user data; />Indicating the number of hours after the user data corresponding to the user information is received by the preprocessing module; />A time base representing a preprocessing duration based on user data; />The number of hours of the user data preprocessing process corresponding to the user information is represented; />、/> and />Respectively representing different types of coefficients, which are set by a programmer according to experience; />The type of the user information is a text type; />The type of the user information is represented as a picture type; />The type of the user information is represented as a video type;the type of the user information is a text type and a picture type; />The type of the user information is represented as a picture type and a video type; />The type of the user information is a text type and a video type; />The type of the user information is a text type, a picture type and a video type; the transmission sequence information generation sub-module generates a transmission sequence information according to the transmission sequenceAnd sequencing the numerical values of the indexes to generate transmission sequence information of all user information.
Optionally, the meta learning module includes a meta learning adjustment value calculation sub-module and a meta learning adjustment information generation sub-module; the element learning adjustment value calculation submodule is used for calculating corresponding element learning adjustment values according to all user information, first full-flow information and second full-flow information in a preset period; the meta learning adjustment information generation sub-module is used for generating corresponding meta learning adjustment information according to the meta learning adjustment value;
when the meta learning adjustment value calculation submodule calculates, the following equation is satisfied:
wherein ,representing meta learning adjustment values corresponding to a preset period; />A first reference value selection function representing information based on all users in a preset period; />A comparison function for representing the quantity of various user information in a preset period; />A first reference value is expressed and empirically set by a programmer; />Representing from->Selecting the maximum value; />A comparison index for representing the user information of the text type in a preset period; />Representing +.>First->The number of the user information of the Chinese character type in the period of time is increased; />User information reference number representing the text type of each time period of the preset period; />A comparison index for representing the user information of the picture type in a preset period; />Representing +.>First->The number of the user information of the picture type in the time period is increased; />User information reference number representing the picture type of each time period of the preset period; />A comparison index for representing the user information of the video type in a preset period; />Representing +.>First->The new number of the user information of the video type in the time period is increased; />User information reference number representing video type of each time period of the preset period; />A second reference value selection function based on the first full-flow information; />A comparison function for representing the quantity of various user information in the first full-flow information; />Representing a second reference value empirically set by a programmer;representing from->Selecting the maximum value; />Representing the number of Chinese character type user information in the first ten user information in the preprocessing process in the first full-flow information; />Representing the number of picture type user information in the first ten user information in the preprocessing process in the first whole flow information; />Representing the number of video type user information in the first ten user information in the preprocessing process in the first full-flow information; />A third reference value selection function based on the second full-flow information; />A comparison function for representing the quantity of various user information in the second full-flow information; />A third reference value is expressed and empirically set by a programmer; />Representing from->Selecting the maximum value; />Representing the number of Chinese character type user information in the first ten user information in the automatic processing process in the second full-flow information; />Representing the number of picture type user information in the first ten user information in the automatic processing process in the second full-flow information; />Representing the number of video type user information in the first ten user information in the automatic processing process in the second full-flow information;
when the meta learning adjustment information generation sub-module works, the following equation is satisfied:
wherein ,representing a meta learning adjustment information selection function; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: driving the automatic processing module to process 50% of the total number of text type user information in the next period, and then processing other types of user information; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: the automatic processing module is driven to process all text type user information in the next period, and then process other types of user information; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: the automatic processing module is driven to process 50% of the total number of the picture type user information in the next period, and then process other types of usersInformation; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: the automatic processing module is driven to process all the picture type user information in the next period, and then process other types of user information; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: the automatic processing module is driven to process 50% of the total number of the video type user information in the next period, and then process other types of user information.
An artificial intelligence automatic processing method based on meta learning is applied to an artificial intelligence automatic processing system based on meta learning, and the automatic processing method comprises the following steps:
s1, preprocessing user data from a user, and processing the user data into user information;
s2, generating element learning adjustment information according to all user information in a preset period;
s3, processing the user information of the host terminal according to a preset automatic processing instruction;
s4, updating the automatic processing instruction.
The beneficial effects obtained by the invention are as follows:
1. the host terminal, the edge processing terminal, the meta learning terminal and the automatic processing terminal are arranged to be beneficial to preprocessing, optimizing user data and generating user information, and then the host terminal, the meta learning terminal and the automatic processing terminal are utilized to process the user information, so that the meta learning terminal and the automatic processing terminal continuously optimize the automatic processing process in the processing process, and further the working efficiency of an automatic processing system is improved;
2. the arrangement of the central processing module and the information storage module is beneficial to improving the communication efficiency and the space for storing user information, thereby improving the working efficiency of the automatic processing system;
3. the arrangement of the preprocessing module, the transmission sequencing module and the edge communication module is beneficial to improving the preprocessing efficiency, optimizing the transmission sequence and further improving the transmission efficiency, thereby improving the working efficiency of an automatic processing system;
4. the edge processing full-flow reading module, the host full-flow reading module and the meta learning module are arranged to be beneficial to efficiently and accurately generating meta learning adjustment information according to all user information, first full-flow information and second full-flow information in a preset period, so that an automatic processing process is better optimized, and the working efficiency of an automatic processing system is improved;
5. the automatic processing instruction reading module and the automatic processing module are arranged to be beneficial to further optimizing the automatic processing process, so that the working efficiency of an automatic processing system is improved;
6. the transmission sequence calculation sub-module and the transmission sequence information generation sub-module are arranged in cooperation with a transmission sequence index algorithm, so that the accuracy and the calculation efficiency of the transmission sequence index are improved, the accuracy and the generation efficiency of the transmission sequence information are further improved, and the working efficiency of an automatic processing system is further improved;
7. the setting of the meta learning adjustment value calculation sub-module and the meta learning adjustment information generation sub-module is matched with the meta learning adjustment value calculation algorithm, so that the accuracy of the meta learning adjustment information is further improved, the automatic processing process is more efficient, and the working efficiency of an automatic processing system is improved;
8. the meta-learning adjustment information generation unit and the processing sequence unit are arranged in cooperation with a processing sequence judgment algorithm, so that the generation efficiency and adjustment accuracy of the meta-learning adjustment information are further improved, and the working efficiency of an automatic processing system is improved.
For a further understanding of the nature and the technical aspects of the present invention, reference should be made to the following detailed description of the invention and the accompanying drawings, which are provided for purposes of reference only and are not intended to limit the invention.
Drawings
FIG. 1 is a schematic diagram of the overall structure of the present invention;
FIG. 2 is a schematic diagram of the distribution effect of an edge processing terminal and a host terminal according to the present invention;
FIG. 3 is a schematic flow chart of an artificial intelligence automatic processing method based on meta-learning in the invention;
fig. 4 is a schematic diagram of the overall structure of the meta learning module in the present invention.
Detailed Description
The following embodiments of the present invention are described in terms of specific examples, and those skilled in the art will appreciate the advantages and effects of the present invention from the disclosure herein. The invention is capable of other and different embodiments and its several details are capable of modification and variation in various respects, all without departing from the spirit of the present invention. The drawings of the present invention are merely schematic illustrations, and are not drawn to actual dimensions, and are stated in advance. The following embodiments will further illustrate the related art of the present invention in detail, but the disclosure is not intended to limit the scope of the present invention.
Embodiment one: the embodiment provides an artificial intelligence automatic processing system based on meta learning. Referring to fig. 1 and 2, an artificial intelligence automatic processing system based on meta learning includes a host terminal, an edge processing terminal, a meta learning terminal and an automatic processing terminal;
the edge processing terminal is used for preprocessing user data from a user and processing the user data into user information; the host terminal is used for being connected with the edge processing terminal and receiving user information from the edge processing terminal; the meta learning terminal and the automatic processing terminal are connected with the host terminal;
the meta learning terminal is used for generating meta learning adjustment information according to all user information in a preset period; the automatic processing terminal is used for communicating with the host terminal and processing user information of the host terminal according to a preset automatic processing instruction; the meta learning adjustment information is used to update the automatic processing instructions. The unit of the preset period may be, but is not limited to: seconds, minutes, hours, and days.
Optionally, the host terminal includes a central processing module and an information storage module, where the central processing module is used to communicate with the meta learning terminal and the automatic processing terminal; the information storage module is used for storing user information from the edge processing terminal.
Optionally, the edge processing terminal comprises a preprocessing module, a transmission ordering module and an edge communication module; the preprocessing module is used for preprocessing user data from a user to generate user information; the transmission ordering module is used for ordering all user information of the preprocessing module and generating transmission sequence information; the edge communication module is used for transmitting the user information to the information storage module according to the transmission sequence information.
Optionally, the meta learning terminal comprises an edge processing full-flow reading module, a host full-flow reading module and a meta learning module; the edge processing full-flow reading module is used for reading first full-flow information of the edge processing terminal for processing user data; the host full-flow reading module is used for reading second full-flow information of the user information processed by the host terminal; the meta learning module is used for generating meta learning adjustment information according to all user information, first full-flow information and second full-flow information in a preset period.
Optionally, the automatic processing terminal comprises an automatic processing instruction reading module and an automatic processing module; the automatic processing instruction reading module is used for reading a preset automatic processing instruction from the host terminal; the automatic processing module is used for processing the user information of the host terminal according to the corresponding automatic processing instruction.
It should be noted that, in this embodiment, the application scenario of the artificial intelligence automatic processing system based on meta learning may be, but is not limited to: server systems for factories, businesses, medical facilities, and educational facilities.
Optionally, the transmission ordering module comprises a transmission order calculation sub-module and a transmission order information generation sub-module; the transmission sequence calculating submodule is used for calculating transmission sequence indexes of all user information; the transmission sequence information generation sub-module is used for generating transmission sequence information of all user information according to the transmission sequence index;
when the transmission sequence calculation sub-module works, the following equation is satisfied:
wherein ,a transmission order index indicating corresponding user information; />Representing a coefficient selection function based on the type of user information; />A capacity value representing user information; />A time base representing a number of received hours based on user data; />Indicating the number of hours after the user data corresponding to the user information is received by the preprocessing module; />A time base representing a preprocessing duration based on user data; />The number of hours of the user data preprocessing process corresponding to the user information is represented; />、/> and />Respectively representing different types of coefficients, which are set by a programmer according to experience; />The type of the user information is a text type; />The type of the user information is represented as a picture type; />The type of the user information is represented as a video type;the type of the user information is a text type and a picture type; />The type of the user information is represented as a picture type and a video type; />The type of the user information is a text type and a video type; />The type of the user information is a text type, a picture type and a video type; and the transmission sequence information generation sub-module is used for sequencing according to the numerical value of the transmission sequence index to generate the transmission sequence information of all user information.
Optionally, the meta learning module includes a meta learning adjustment value calculation sub-module and a meta learning adjustment information generation sub-module; the element learning adjustment value calculation submodule is used for calculating corresponding element learning adjustment values according to all user information, first full-flow information and second full-flow information in a preset period; the meta learning adjustment information generation sub-module is used for generating corresponding meta learning adjustment information according to the meta learning adjustment value;
when the meta learning adjustment value calculation submodule calculates, the following equation is satisfied:
wherein ,representing meta learning adjustment values corresponding to a preset period; />A first reference value selection function representing information based on all users in a preset period; />A comparison function for representing the quantity of various user information in a preset period; />A first reference value is expressed and empirically set by a programmer; />Representing from->Selecting the maximum value; />A comparison index for representing the user information of the text type in a preset period; />Representing +.>First->The number of the user information of the Chinese character type in the period of time is increased; />User information reference number representing the text type of each time period of the preset period; />A comparison index for representing the user information of the picture type in a preset period; />Representing +.>First->Picture type in a period of timeThe number of the user information is increased; />User information reference number representing the picture type of each time period of the preset period; />A comparison index for representing the user information of the video type in a preset period; />Representing +.>First->The new number of the user information of the video type in the time period is increased; />User information reference number representing video type of each time period of the preset period; />A second reference value selection function based on the first full-flow information; />A comparison function for representing the quantity of various user information in the first full-flow information; />Representing a second reference value empirically set by a programmer;representing from->Selecting the maximum value; />Representing pre-preparation in first full-flow informationThe number of Chinese type user information in the first ten user information in the process; />Representing the number of picture type user information in the first ten user information in the preprocessing process in the first whole flow information; />Representing the number of video type user information in the first ten user information in the preprocessing process in the first full-flow information; />A third reference value selection function based on the second full-flow information; />A comparison function for representing the quantity of various user information in the second full-flow information; />A third reference value is expressed and empirically set by a programmer; />Representing from->Selecting the maximum value; />Representing the number of Chinese character type user information in the first ten user information in the automatic processing process in the second full-flow information; />Representing the number of picture type user information in the first ten user information in the automatic processing process in the second full-flow information; />Representing video type user information in the first ten user information in the automatic processing process in the second full-flow informationIs the number of (3);
when the meta learning adjustment information generation sub-module works, the following equation is satisfied:
wherein ,representing a meta learning adjustment information selection function; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: driving the automatic processing module to process 50% of the total number of text type user information in the next period, and then processing other types of user information; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: the automatic processing module is driven to process all text type user information in the next period, and then process other types of user information; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: driving the automatic processing module to process 50% of the total number of the picture type user information in the next period, and then processing other types of user information; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: the automatic processing module is driven to process all the picture type user information in the next period, and then process other types of user information; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: driving the automatic processing module in the next cycle50% of the total number of video type user information is processed before other types of user information are processed.
An artificial intelligence automatic processing method based on meta learning is applied to an artificial intelligence automatic processing system based on meta learning as described above, and is shown in combination with fig. 3, the automatic processing method includes:
s1, preprocessing user data from a user, and processing the user data into user information;
s2, generating element learning adjustment information according to all user information in a preset period;
s3, processing the user information of the host terminal according to a preset automatic processing instruction;
s4, updating the automatic processing instruction.
Embodiment two: the embodiment includes the whole content of the first embodiment, and provides an artificial intelligent automatic processing system based on meta learning, and referring to fig. 4, the meta learning adjustment information generation sub-module includes a meta learning adjustment information generation unit and a processing sequence unit; the meta learning adjustment information generation unit is used for generating corresponding meta learning adjustment information according to the meta learning adjustment value; the processing sequence unit is used for adding processing sequence information to the meta learning adjustment information.
When the processing sequence unit works, judging according to the quantity of meta-learning adjustment information and other types of user information:
wherein ,representing a processing sequence judgment function; />Representing 50% of the total number of the processed text type user information on the premise of driving the automatic processing module to process 50% of the total number of the text type user information in the next cycle and then process other types of user informationThen, firstly processing the picture type user information, then processing the video type user information, and finally, processing the remaining 50% of the total number of the text type user information; />On the premise of driving the automatic processing module to process 50% of the total number of the text type user information and then process other types of user information in the next period, after processing 50% of the total number of the text type user information, processing the video type user information and then processing the picture type user information, and finally processing the remaining 50% of the total number of the text type user information; />On the premise of driving the automatic processing module to process all text type user information and then process other types of user information in the next period, after 100% of the total number of the text type user information is processed, processing the picture type user information and then processing the video type user information; />On the premise of driving the automatic processing module to process all text type user information and then process other types of user information in the next period, after 100% of the total number of the text type user information is processed, processing the video type user information and then processing the picture type user information;
on the premise of driving the automatic processing module to process 50% of the total number of the picture type user information and then process other types of user information in the next period, after 50% of the total number of the picture type user information is processed, processing the text type user information and then processing the video type user information, and finally processing the remaining 50% of the total number of the picture type user information; />Representation drives the saidThe automatic processing module processes the video type user information and then processes the text type user information on the premise that 50% of the total number of the picture type user information is processed in the next period and then processes other types of user information, and finally processes the remaining 50% of the total number of the picture type user information; />On the premise of driving the automatic processing module to process all the picture type user information and then process other types of user information in the next period, after 100% of the total number of the picture type user information is processed, the text type user information is processed and then the video type user information is processed;on the premise of driving the automatic processing module to process all the picture type user information and then process other types of user information in the next period, after 100% of the total number of the picture type user information is processed, the video type user information is processed and then the text type user information is processed;
on the premise of driving the automatic processing module to process 50% of the total number of the video type user information and then process other types of user information in the next period, after processing 50% of the total number of the video type user information, processing the text type user information and then processing the picture type user information, and finally processing the remaining 50% of the total number of the video type user information; />On the premise of driving the automatic processing module to process 50% of the total number of the video type user information before processing other types of user information in the next period, processing the picture type user information before processing the text type user information after processing 50% of the total number of the video type user information, and finally processing the videoThe remaining 50% of the total number of type user information; />On the premise of driving the automatic processing module to process all video type user information and then process other types of user information in the next period, after 100% of the total number of the video type user information is processed, processing text type user information and then processing picture type user information;the method is characterized in that the automatic processing module is driven to process all video type user information and then process other types of user information in the next period, and then process picture type user information and then process text type user information after processing 100% of the total number of the video type user information.
The foregoing disclosure is only a preferred embodiment of the present invention and is not intended to limit the scope of the invention, so that all equivalent technical changes made by the application of the present invention and the accompanying drawings are included in the scope of the invention, and in addition, the elements in the invention can be updated with the technical development.
Claims (8)
1. An artificial intelligent automatic processing system based on meta learning is characterized by comprising a host terminal, an edge processing terminal, a meta learning terminal and an automatic processing terminal;
the edge processing terminal is used for preprocessing user data from a user and processing the user data into user information; the host terminal is used for being connected with the edge processing terminal and receiving user information from the edge processing terminal; the meta learning terminal and the automatic processing terminal are connected with the host terminal;
the meta learning terminal is used for generating meta learning adjustment information according to all user information in a preset period; the automatic processing terminal is used for communicating with the host terminal and processing user information of the host terminal according to a preset automatic processing instruction; the meta learning adjustment information is used to update the automatic processing instructions.
2. The artificial intelligence automatic processing system based on meta learning according to claim 1, wherein the host terminal comprises a central processing module and an information storage module, the central processing module is used for communicating with the meta learning terminal and the automatic processing terminal; the information storage module is used for storing user information from the edge processing terminal.
3. The artificial intelligence automatic processing system based on meta learning as claimed in claim 2, wherein the edge processing terminal comprises a preprocessing module, a transmission ordering module and an edge communication module; the preprocessing module is used for preprocessing user data from a user to generate user information; the transmission ordering module is used for ordering all user information of the preprocessing module and generating transmission sequence information; the edge communication module is used for transmitting the user information to the information storage module according to the transmission sequence information.
4. The artificial intelligence automatic processing system based on meta learning as claimed in claim 3, wherein the meta learning terminal comprises an edge processing full-flow reading module, a host full-flow reading module and a meta learning module; the edge processing full-flow reading module is used for reading first full-flow information of the edge processing terminal for processing user data; the host full-flow reading module is used for reading second full-flow information of the user information processed by the host terminal; the meta learning module is used for generating meta learning adjustment information according to all user information, first full-flow information and second full-flow information in a preset period.
5. The artificial intelligence automatic processing system based on meta learning according to claim 4, wherein the automatic processing terminal comprises an automatic processing instruction reading module and an automatic processing module; the automatic processing instruction reading module is used for reading a preset automatic processing instruction from the host terminal; the automatic processing module is used for processing the user information of the host terminal according to the corresponding automatic processing instruction.
6. The artificial intelligence automatic processing system based on meta learning according to claim 5, wherein the transmission ordering module comprises a transmission order calculation sub-module and a transmission order information generation sub-module; the transmission sequence calculating submodule is used for calculating transmission sequence indexes of all user information; the transmission sequence information generation sub-module is used for generating transmission sequence information of all user information according to the transmission sequence index;
when the transmission sequence calculation sub-module works, the following equation is satisfied:
wherein ,a transmission order index indicating corresponding user information; />Representing a coefficient selection function based on the type of user information; />A capacity value representing user information; />A time base representing a number of received hours based on user data; />Indicating that the user data corresponding to the user information is pre-locatedThe hours after the receiving of the processing module; />A time base representing a preprocessing duration based on user data; />The number of hours of the user data preprocessing process corresponding to the user information is represented; />、/> and />Respectively representing different types of coefficients, which are set by a programmer according to experience; />The type of the user information is a text type;the type of the user information is represented as a picture type; />The type of the user information is represented as a video type;the type of the user information is a text type and a picture type; />The type of the user information is represented as a picture type and a video type; />The type of the user information is a text type and a video type; />The type of the user information is a text type, a picture type and a video type; and the transmission sequence information generation sub-module is used for sequencing according to the numerical value of the transmission sequence index to generate the transmission sequence information of all user information.
7. The artificial intelligence automatic processing system based on meta learning according to claim 6, wherein the meta learning module includes a meta learning adjustment value calculation sub-module and a meta learning adjustment information generation sub-module; the element learning adjustment value calculation submodule is used for calculating corresponding element learning adjustment values according to all user information, first full-flow information and second full-flow information in a preset period; the meta learning adjustment information generation sub-module is used for generating corresponding meta learning adjustment information according to the meta learning adjustment value;
when the meta learning adjustment value calculation submodule calculates, the following equation is satisfied:
wherein ,representing meta learning adjustment values corresponding to a preset period; />A first reference value selection function representing information based on all users in a preset period; />A comparison function for representing the quantity of various user information in a preset period; />A first reference value is expressed and empirically set by a programmer; />Representing from->Selecting the maximum value; />User information representing type of text within preset periodIs a comparison index of (2); />Representing +.>First->The number of the user information of the Chinese character type in the period of time is increased; />User information reference number representing the text type of each time period of the preset period; />A comparison index for representing the user information of the picture type in a preset period; />Representing +.>First->The number of the user information of the picture type in the time period is increased; />User information reference number representing the picture type of each time period of the preset period; />A comparison index for representing the user information of the video type in a preset period; />Representing +.>First->The new number of the user information of the video type in the time period is increased; />User information reference number representing video type of each time period of the preset period; />A second reference value selection function based on the first full-flow information; />A comparison function for representing the quantity of various user information in the first full-flow information; />Representing a second reference value empirically set by a programmer;representing from->Selecting the maximum value; />Representing the number of Chinese character type user information in the first ten user information in the preprocessing process in the first full-flow information; />Representing the number of picture type user information in the first ten user information in the preprocessing process in the first whole flow information; />Representing a first full flowThe number of video type user information in the first ten user information in the preprocessing process in the information; />A third reference value selection function based on the second full-flow information; />A comparison function for representing the quantity of various user information in the second full-flow information; />A third reference value is expressed and empirically set by a programmer; />Representing from->Selecting the maximum value; />Representing the number of Chinese character type user information in the first ten user information in the automatic processing process in the second full-flow information; />Representing the number of picture type user information in the first ten user information in the automatic processing process in the second full-flow information; />Representing the number of video type user information in the first ten user information in the automatic processing process in the second full-flow information;
when the meta learning adjustment information generation sub-module works, the following equation is satisfied:
wherein ,representing a meta learning adjustment information selection function; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: driving the automatic processing module to process 50% of the total number of text type user information in the next period, and then processing other types of user information; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: the automatic processing module is driven to process all text type user information in the next period, and then process other types of user information; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: driving the automatic processing module to process 50% of the total number of the picture type user information in the next period, and then processing other types of user information; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: the automatic processing module is driven to process all the picture type user information in the next period, and then process other types of user information; />The representation element learning adjustment information is used for adjusting the corresponding automatic processing instruction to: the automatic processing module is driven to process 50% of the total number of the video type user information in the next period, and then process other types of user information.
8. An artificial intelligence automatic processing method based on meta learning, which is applied to an artificial intelligence automatic processing system based on meta learning as claimed in claim 7, wherein the automatic processing method comprises the following steps:
s1, preprocessing user data from a user, and processing the user data into user information;
s2, generating element learning adjustment information according to all user information in a preset period;
s3, processing the user information of the host terminal according to a preset automatic processing instruction;
s4, updating the automatic processing instruction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310373222.7A CN116090553B (en) | 2023-04-10 | 2023-04-10 | Artificial intelligence automatic processing system based on meta learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310373222.7A CN116090553B (en) | 2023-04-10 | 2023-04-10 | Artificial intelligence automatic processing system based on meta learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116090553A true CN116090553A (en) | 2023-05-09 |
CN116090553B CN116090553B (en) | 2023-06-16 |
Family
ID=86212349
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310373222.7A Active CN116090553B (en) | 2023-04-10 | 2023-04-10 | Artificial intelligence automatic processing system based on meta learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116090553B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110689523A (en) * | 2019-09-02 | 2020-01-14 | 西安电子科技大学 | Personalized image information evaluation method based on meta-learning and information data processing terminal |
CN111046193A (en) * | 2019-12-27 | 2020-04-21 | 南京邮电大学 | Domain knowledge graph completion method based on meta-learning |
US20220188690A1 (en) * | 2020-12-11 | 2022-06-16 | International Business Machines Corporation | Machine learning security threat detection using a meta-learning model |
WO2022121155A1 (en) * | 2020-12-10 | 2022-06-16 | 平安科技(深圳)有限公司 | Meta learning-based adaptive speech recognition method and apparatus, device and medium |
US20220359079A1 (en) * | 2021-05-06 | 2022-11-10 | January, Inc. | Systems, methods and devices for predicting personalized biological state with model produced with meta-learning |
-
2023
- 2023-04-10 CN CN202310373222.7A patent/CN116090553B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110689523A (en) * | 2019-09-02 | 2020-01-14 | 西安电子科技大学 | Personalized image information evaluation method based on meta-learning and information data processing terminal |
CN111046193A (en) * | 2019-12-27 | 2020-04-21 | 南京邮电大学 | Domain knowledge graph completion method based on meta-learning |
WO2022121155A1 (en) * | 2020-12-10 | 2022-06-16 | 平安科技(深圳)有限公司 | Meta learning-based adaptive speech recognition method and apparatus, device and medium |
US20220188690A1 (en) * | 2020-12-11 | 2022-06-16 | International Business Machines Corporation | Machine learning security threat detection using a meta-learning model |
US20220359079A1 (en) * | 2021-05-06 | 2022-11-10 | January, Inc. | Systems, methods and devices for predicting personalized biological state with model produced with meta-learning |
Non-Patent Citations (1)
Title |
---|
张文君 等: "基于双域注意力和元学习的移动应用行为识别", 西南大学学报(自然科学版), vol. 43, no. 12, pages 198 - 208 * |
Also Published As
Publication number | Publication date |
---|---|
CN116090553B (en) | 2023-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11544588B2 (en) | Image tagging based upon cross domain context | |
US11783227B2 (en) | Method, apparatus, device and readable medium for transfer learning in machine learning | |
CN110532397B (en) | Question-answering method and device based on artificial intelligence, computer equipment and storage medium | |
WO2020258487A1 (en) | Method and apparatus for sorting question-answer relationships, and computer device and storage medium | |
CN111143613B (en) | Method, system, electronic device and storage medium for selecting video cover | |
KR20190108378A (en) | Method and System for Automatic Image Caption Generation | |
CN109033220B (en) | Automatic selection method, system, equipment and storage medium of labeled data | |
CN110619772A (en) | Data processing method, device, equipment and medium | |
CN115695950B (en) | Video abstract generation method based on content perception | |
CN113222057A (en) | Data prediction model training method, data prediction device, data prediction equipment and data prediction medium | |
CN112132232A (en) | Medical image classification labeling method and system and server | |
CN116090553B (en) | Artificial intelligence automatic processing system based on meta learning | |
WO2024074042A1 (en) | Data storage method and apparatus, data reading method and apparatus, and device | |
CN107679635A (en) | Client's follow-up method, system and readable storage medium storing program for executing based on priority | |
US11074317B2 (en) | System and method for cached convolution calculation | |
CN111708880A (en) | System and method for identifying class cluster | |
CN112559641B (en) | Pull chain table processing method and device, readable storage medium and electronic equipment | |
CN110704650A (en) | OTA picture tag identification method, electronic device and medium | |
CN116108276A (en) | Information recommendation method and device based on artificial intelligence and related equipment | |
CN112231590B (en) | Content recommendation method, system, computer device and storage medium | |
CN113496256B (en) | Image annotation model training method, annotation method, device, equipment and medium | |
CN117748500B (en) | Photovoltaic power prediction method, device, equipment and medium | |
CN112765479B (en) | Information recommendation method and device, electronic equipment and readable storage medium | |
CN117591485B (en) | Solid state disk operation control system and method based on data identification | |
CN117217499B (en) | Campus electric scooter dispatching optimization method based on multi-source data driving |
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 |