WO2020157939A1 - Dispositif de traitement d'informations, système de gestion d'historique d'apprentissage et programme de gestion d'historique d'apprentissage - Google Patents

Dispositif de traitement d'informations, système de gestion d'historique d'apprentissage et programme de gestion d'historique d'apprentissage Download PDF

Info

Publication number
WO2020157939A1
WO2020157939A1 PCT/JP2019/003493 JP2019003493W WO2020157939A1 WO 2020157939 A1 WO2020157939 A1 WO 2020157939A1 JP 2019003493 W JP2019003493 W JP 2019003493W WO 2020157939 A1 WO2020157939 A1 WO 2020157939A1
Authority
WO
WIPO (PCT)
Prior art keywords
version
learning history
learning
information
history information
Prior art date
Application number
PCT/JP2019/003493
Other languages
English (en)
Japanese (ja)
Inventor
鈴木　康介
昂士 市村
Original Assignee
富士通株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 富士通株式会社 filed Critical 富士通株式会社
Priority to PCT/JP2019/003493 priority Critical patent/WO2020157939A1/fr
Priority to JP2020569299A priority patent/JPWO2020157939A1/ja
Publication of WO2020157939A1 publication Critical patent/WO2020157939A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Definitions

  • the present invention relates to an information processing device, a learning history management system, and a learning history management program.
  • FIG. 21 is a diagram showing an example of an AI (Artificial Intelligence) development flow.
  • AI development first, preprocessing is performed on a data set, and the data set is divided into a data set for learning and a data set for verification and evaluation.
  • labeling, annotation, format conversion, etc. are performed on the data set.
  • labeling is to give a correct answer to data.
  • Annotation is to give meaning to data, for example, to add positions of eyes, nose, and mouth to an image of a human face.
  • Format conversion is conversion of the format of data.
  • ML Machine Learning
  • DNN Deep Neural Network
  • CNN Convolutional Neural Network
  • RNN Recursive Neural Network
  • U-net Auto Encoder
  • GAN Global System for Mobile Communications
  • statistical model Then, learning is performed using the defined ML model and the learning data set, and a learned ML model is created.
  • the trained ML model is verified and evaluated using the trained ML model, the data set for verification and evaluation, and the hyperparameters, and the evaluation result of the trained ML model is output.
  • the hyperparameter is a parameter that needs to be tuned by a human in machine learning, and includes a batch size, the number of epochs, a pooling layer size, a convolutional layer parameter, an activation layer function, and the like.
  • BATCH size is the size of the data used for one learning in NN (Neural Network).
  • the data set is divided into a plurality of subsets, and the subsets are used to perform one learning.
  • the number of epochs is the number of repeating learning N times using N subsets in the NN.
  • the pooling layer is a layer that reduces the layer in CNN.
  • the convolutional layer is a layer that performs convolution in CNN. Parameters of the convolutional layer include size, stride, padding number, and layer number.
  • the size is the size of the convolutional layer. Stride is the number of moving filters.
  • the padding number is a number that fills the periphery with zero.
  • the number of layers is the number of CNN layers.
  • the activation layer function is a function of the activation layer, and is, for example, a ramp function.
  • Preprocessing, model definition, learning, verification and evaluation are performed by executing scripts.
  • the script is a simple program.
  • Pyton registered trademark, the same applies below is used to create the script.
  • scripts and ML model versions are managed by Git etc.
  • Hyperparameters and versions of trained models are managed by MLflow (Machine Learning Data Flow), comet, etc.
  • the execution environment is managed by conda (registered trademark, the same applies below), pyenv and the like.
  • the present invention in one aspect, aims to easily reproduce the learning previously performed.
  • the information processing device has a version management unit, a storage unit, a reception unit, and an output unit.
  • the version management unit manages version numbers of learning history information including a data set used for creating and evaluating a learned learning model, the learned learning model, and an evaluation result of the learned learning model.
  • the storage unit stores the learning history information for each version number.
  • the reception unit receives the designation of one of the plurality of versions managed by the version management unit.
  • the output unit acquires the learning history information included in one version accepted by the accepting unit from the storage unit and outputs the learning history information to the display device.
  • the present invention can easily replicate the learning that was previously done.
  • FIG. 1 is a diagram for explaining asset management by the AI development management device according to the first embodiment.
  • FIG. 2 is a diagram showing another visualization example.
  • FIG. 3 is a diagram showing an example of selecting a specific plate.
  • FIG. 4 is a diagram illustrating a functional configuration of the AI development management device according to the first embodiment.
  • FIG. 5 is a diagram showing an example of a flow edit screen.
  • FIG. 6 is an enlarged view of a part of the flow shown in FIG.
  • FIG. 7 is a diagram showing an example of the script edit screen.
  • FIG. 8 is a diagram showing an example of the execution history display screen.
  • FIG. 9 is a diagram showing selection of plates.
  • FIG. 10 is a diagram showing an example of a screen displaying the flow of the selected plate.
  • FIG. 10 is a diagram showing an example of a screen displaying the flow of the selected plate.
  • FIG. 11 is a diagram showing an example of items stored in the version information storage unit.
  • FIG. 12 is a diagram for explaining branching of the plate.
  • FIG. 13 is a flowchart showing the procedure of the flow execution process by the AI development management device.
  • FIG. 14 is a flowchart showing the procedure of the version change process by the AI development management device.
  • FIG. 15 is a diagram showing an example of a script edit screen of the AI development management device without using a flow chart.
  • FIG. 16 is a diagram illustrating the functional configuration of the AI development management device according to the second embodiment.
  • FIG. 17 is a diagram illustrating a hardware configuration of a computer that executes the AI development management program according to the first and second embodiments.
  • FIG. 18 is a diagram showing the configuration of the data utilization system.
  • FIG. 19 is a diagram for explaining the use of the same data.
  • FIG. 20 is a diagram for explaining the data version management device.
  • FIG. 21 is a diagram showing an example of the flow of AI development.
  • FIG. 1 is a diagram for explaining asset management by the AI development management device according to the first embodiment.
  • the AI development management apparatus according to the first embodiment manages one combination of assets as one version by associating it with one flow.
  • the version information includes id, date or date and time, data set, script, evaluation result, trained ML model, hyperparameter, etc.
  • id is a number that identifies the version.
  • the date or the date and time is the date when the flow was executed or the date and time. It should be noted that “executing a flow” means executing a script included in the flow.
  • the flow is executed on September 21, 2018 with the hyperparameter alpha of 0.5 using the dataset #1 and the dataset #2. Made in.
  • the python version number is 3.6.5 and the library (lib) version number is scikit-learn 0.19.1.
  • the mse (Mean Square Error) of the predicted value and the correct value is 0.9
  • the rmse Root Mean Squared Error
  • the AI development management apparatus visualizes the evaluation results of a plurality of versions with a graph or the like.
  • the accuracy of each version is displayed in association with the execution date and time.
  • the accuracy is one of the evaluation results and is, for example, mse.
  • FIG. 2 is a diagram showing another visualization example.
  • two accuracies are displayed in association with execution dates and times.
  • the loss is displayed in association with the number of epochs.
  • the loss is an error between the predicted value and the correct value.
  • two flows (versions) represented by flow #1 and flow #2 are displayed. For each flow, the loss during training and the loss during verification and evaluation are displayed. In this example, evaluation is also performed during learning.
  • FIG. 3 is a diagram showing an example of selecting a specific plate.
  • the first flow execution is performed on 9/18, and the second flow execution is performed on 9/19.
  • the first executed flow (the flow when the first accuracy is good) is selected, and the selected flow is displayed.
  • the user can create and execute a new flow based on the displayed flow.
  • FIG. 4 is a diagram illustrating a functional configuration of the AI development management device according to the first embodiment.
  • the AI development management device 1 according to the first embodiment includes a front end unit 11, a flow editor 12, an editor 13, a flow execution engine 14, a version information storage unit 15, and an asset management unit. 16 and a version management unit 17.
  • the front-end unit 11 performs processing related to user interaction. For example, the front end unit 11 receives a flow creation instruction and an editing instruction from the user, and passes the flow creation instruction and the editing instruction to the flow editor 12. The front-end unit 11 also displays a flow creation screen and an edit screen on the display device based on an instruction from the flow editor 12.
  • FIG. 5 is a diagram showing an example of a flow edit screen. As shown in FIG. 5, a user arranges a script and an input/output file of each script on the screen, and creates a flow by connecting each script and the input/output file with a line.
  • the input/output files are a data set, an ML model, a learned ML model, an evaluation result of the learned ML model, hyperparameters, and the like.
  • the user can execute the flow by pressing the Run button 20 on the flow edit screen.
  • the front end unit 11 notifies the flow editor 12 that the Run button 20 has been pressed.
  • the flow editor 12 instructs the flow execution engine 14 to execute the flow.
  • FIG. 6 is an enlarged view of a part of the flow shown in FIG. As shown in FIG. 6, a script edit button 22 and an execution history confirmation button 23 are added to the script symbol 21 indicating the script. The user edits or confirms the script by pressing the script edit button 22.
  • FIG. 7 is a diagram showing an example of the script edit screen.
  • the script edit screen shown in FIG. 7 is displayed.
  • the user edits the script on the script edit screen.
  • the front end unit 11 requests the editor 13 to perform a script edit process, and passes the user operation information on the script edit screen to the editor 13. Further, the front end unit 11 displays the output of the editor 13 on the script edit screen.
  • the user specifies the variable to be logged.
  • the hyperparameter batch size (batch_size) is taken as a log.
  • FIG. 8 is a diagram showing an example of an execution history display screen.
  • the screen transitions to the execution history display screen shown in FIG.
  • a table 31 showing the execution history and a graph 32 showing the evaluation result are displayed on the execution history display screen.
  • the table 31 showing the execution history includes RUN-INFO, DATASET, SOURCE, PARAMETER, and METRICS.
  • RUN-INFO is information that identifies execution.
  • RUN-INFO includes RUN-ID and START-TIME.
  • the RUN-ID is an identifier that identifies execution.
  • START-TIME is the execution start time.
  • DATASET is the file name of the input data set.
  • SOURCE is the file name of the script.
  • PARAMETER is a hyperparameter and a dataset editing parameter.
  • the editing parameters of the data set include, for example, whether or not to exclude outliers, whether or not to fill blanks with zeros, parameters related to image editing, and parameters related to Fourier transform of sound.
  • METRICs is an evaluation result.
  • FIG. 9 is a diagram showing selection of plates. As shown in FIG. 9, the user can return to a specific version by selecting a specific row of the table 31 showing the execution history by, for example, mouse clicking. Alternatively, the user can return to a specific version by selecting a specific value of the graph 32 showing the evaluation result by, for example, mouse clicking.
  • FIG. 10 is a diagram showing an example of a screen displaying the flow of the selected plate. The user can edit the flow or script again from the displayed screen.
  • the flow editor 12 performs a process of editing the flow based on the user's operation on the flow edit screen, and stores the edited flow information in the version information storage unit 15. Further, when the asset management unit 16 replaces the information in the version information storage unit 15, the flow editor 12 causes the front-end unit 11 to display a flow diagram based on the replaced information.
  • the editor 13 performs a process of editing the script based on the user's operation on the script edit screen, and stores the edited script information in the version information storage unit 15.
  • the flow execution engine 14 executes a flow and performs preprocessing, model definition, learning, verification, and evaluation.
  • the flow execution engine 14 stores the value of the variable designated as the log acquisition target in the script in the version information storage unit 15.
  • the log acquisition target includes parameters including hyperparameters and evaluation results.
  • the version information storage unit 15 stores information about the version to be executed.
  • FIG. 11 is a diagram showing an example of items stored in the version information storage unit 15. As shown in FIG. 11, the version information storage unit 15 stores flow, data, notes, and log.
  • Flow is information about the flow diagram.
  • data is information of the data set.
  • notes is script information.
  • log is information described as a log in a note (script). log is information for each note.
  • the information of one note “noteA” includes para, metrics, artifacts, and graph-result.
  • Para is parameter information including hyperparameters.
  • Metrics is information on the evaluation result of the ML model.
  • Artifacts is information of the ML model.
  • graph-result is information of a graph of the evaluation result. The graph-result includes the evaluation results of the ML model from the first edition to the edition being edited.
  • the asset management unit 16 commits the information stored in the version information storage unit 15 to the version management unit 17 so that the version management unit 17 stores the version information as new version information. Further, the asset management unit 16 causes the front end unit 11 to display the execution history display screen illustrated in FIG. In addition, the asset management unit 16 acquires the information of the selected version from the version management unit 17 in response to the user's version selection, and uses the acquired version information to store the version information stored in the version information storage unit 15. Replace.
  • the version management unit 17 stores learning history information of a plurality of versions with the information stored in the version information storage unit 15 as learning history information of one version, and manages the learning history information of a plurality of versions.
  • AI development management device 1 may separately manage the version of the data set, the script, the log, etc., and use data, notes, and log as the version number information.
  • the version management unit 17 manages branching of versions.
  • FIG. 12 is a diagram for explaining branching of the plate.
  • the numbers in the circles represent the version numbers.
  • the version management unit 17 manages the branching of versions to store the version information according to the previous development route. Therefore, the user can easily return the state to any of the past states.
  • FIG. 13 is a flowchart showing the procedure of the flow execution processing by the AI development management device 1. As shown in FIG. 13, the AI development management device 1 performs a flow and note editing process based on a user's editing operation (step S1).
  • the AI development management device 1 accepts the press of the Run button 20 by the user (step S2) and executes the flow (step S3). Then, the AI development management device 1 stores the parameter information including the hyperparameters, the ML model evaluation result information, and the ML model information in the version information storage unit 15 (step S4).
  • the AI development management device 1 adds the evaluation result to the graph_result of the version information storage unit 15 (step S5) and commits it to the version management unit 17 (step S6).
  • the AI development management device 1 stores the version information in the version information storage unit 15 and commits the information in the version information storage unit 15 to the version management unit 17, and therefore manages the information of a plurality of versions. You can
  • FIG. 14 is a flowchart showing the procedure of the version change processing by the AI development management device 1. As shown in FIG. 14, when the user presses the execution history confirmation button 23, the AI development management device 1 displays the execution history (step S11).
  • the AI development management device 1 accepts the selection of the version by the user (step S12) and changes the version (step S13). As the process of changing the version, the AI development management device 1 changes the information stored in the version information storage unit 15 into the information of the selected version, and displays the flow chart of the selected version.
  • the AI development management device 1 performs the process of changing the version, the user can return to the state before the AI development and redo the development.
  • the version management unit 17 sets the learning history information of one edition to the evaluation result of the flow diagram, the data set, the script, the parameter, the ML model, the learned ML model, and the learned ML model. Stores and manages the learning history information of a plurality of editions. Then, when the front-end unit 11 receives the designation of one of the plurality of versions from the user, the asset management unit 16 acquires the information of the designated version from the version management unit, and the version information storage unit Replace the information of with the information of the obtained version. Then, the flow editor 12 displays the flow diagram on the display device based on the information of the replaced version. Therefore, the AI development management device 1 can easily reproduce the previously performed combination of assets.
  • the front end unit 11 displays the execution history display screen including the graph 32 showing the evaluation result based on the instruction from the asset management unit 16, and the version 32 by the user is displayed from the graph 32 showing the evaluation result. Is accepted. Therefore, the user can easily specify the previous version.
  • FIG. 15 is a diagram showing an example of the script editing screen of the AI development management device without using a flow chart.
  • the script edit screen has a Run button 26 and an execution history confirmation button 27. The user can execute the script by pressing the Run button 26. Further, the user can confirm the execution history and move to the previous development state by pressing the execution history confirmation button 27.
  • FIG. 16 is a diagram illustrating a functional configuration of the AI development management device according to the second embodiment.
  • the AI development management device 4 according to the second embodiment includes a front end unit 41, an editor 43, an execution engine 44, a version information storage unit 45, an asset management unit 46, and a version management unit. 47 and.
  • the front end unit 41 performs processing related to user interaction. Specifically, the front end unit 41 receives a script edit request from the user, requests the editor 43 to perform a script edit process, and passes the user operation information on the script edit screen to the editor 43. Further, the front end unit 41 displays the output of the editor 43 on the script edit screen.
  • the front end unit 41 instructs the execution engine 44 to execute the flow.
  • the front end unit 41 instructs the asset management unit 46 to perform the processing for displaying the execution history display screen shown in FIG.
  • the editor 43 performs a process of editing the script based on the user's operation on the script edit screen, and stores the edited script information in the version information storage unit 45.
  • the execution engine 44 executes a script and performs preprocessing, model definition, learning, verification, and evaluation.
  • the execution engine 44 stores the value of the variable designated as the log acquisition target in the script in the version information storage unit 45.
  • the log acquisition target includes parameters including hyperparameters and evaluation results.
  • the version information storage unit 45 stores information about the version to be executed. However, unlike the version information storage unit 15 according to the first embodiment, the version information storage unit 45 does not store the information of the flow chart.
  • the asset management unit 46 commits the information stored in the version information storage unit 45 to the version management unit 47 so that the version management unit 47 stores the new version information.
  • the asset management unit 46 also causes the front end unit 41 to display the execution history display screen illustrated in FIG. 8.
  • the asset management unit 46 acquires the information of the selected version from the version management unit 47 in response to the user's version selection, and uses the acquired version information to store the version information stored in the version information storage unit 45. Replace.
  • the version management unit 47 stores learning history information of a plurality of versions with the information stored in the version information storage unit 45 as learning history information of one version, and manages the learning history information of a plurality of versions.
  • the AI development management device 4 displays the Run button 26 and the execution history confirmation button 27 on the script edit screen, so that the user can perform AI development without creating a flow chart. it can.
  • the AI development management device has been described, but an AI development management program having the same function can be obtained by implementing the configuration of the AI development management device with software. Therefore, a computer that executes the AI development management program will be described.
  • FIG. 17 is a diagram illustrating a hardware configuration of a computer that executes the AI development management program according to the first and second embodiments.
  • the computer 50 has a main memory 51, a CPU (Central Processing Unit) 52 which is an example of a processor, a LAN (Local Area Network) interface 53, and a HDD (Hard Disk Drive) 54. ..
  • the computer 50 has a super IO (Input Output) 55, a DVI (Digital Visual Interface) 56, and an ODD (Optical Disk Drive) 57.
  • IO Input Output
  • DVI Digital Visual Interface
  • ODD Optical Disk Drive
  • the main memory 51 is a memory that stores a program, a mid-execution result of the program, and the like.
  • the CPU 52 is a central processing unit that reads a program from the main memory 51 and executes the program.
  • the CPU 52 includes a chip set having a memory controller.
  • the LAN interface 53 is an interface for connecting the computer 50 to another computer via the LAN.
  • the HDD 54 is a disk device that stores programs and data
  • the Super IO 55 is an interface for connecting an input device such as a mouse and a keyboard.
  • the DVI 56 is an interface for connecting a liquid crystal display device
  • the ODD 57 is a device for reading and writing DVDs and CD-Rs.
  • the LAN interface 53 is connected to the CPU 52 by PCI Express (PCIe), and the HDD 54 and the ODD 57 are connected to the CPU 52 by SATA (Serial Advanced Technology Attachment).
  • the Super IO 55 is connected to the CPU 52 by LPC (Low Pin Count).
  • the AI development management program executed in the computer 50 is stored in the CD-R, which is an example of a recording medium readable by the computer 50, read from the CD-R by the ODD 57, and installed in the computer 50.
  • the AI development management program is stored in a database or the like of another computer system connected via the LAN interface 53, read from these databases, and installed in the computer 50.
  • the installed AI development management program is stored in the HDD 54, read into the main memory 51, and executed by the CPU 52.
  • the AI development management device has been described, but the AI development management device functions as a part of a data utilization system that promotes sharing of data and tools stored in the company. Therefore, the data utilization system will be described.
  • FIG. 18 is a diagram showing the configuration of the data utilization system.
  • the data utilization system 6 includes an AI development management device 1, a data lake 61, an analysis device 62, a preparation device 63, and a loading device 64.
  • the data utilization system 6 may include the AI development management device 4 instead of the AI development management device 1.
  • the data lake 61 is a repository of data and tools stored in-house.
  • the data and tools stored in the data lake 61 are shared and used internally.
  • the AI development management device 1 has an acquisition unit 18.
  • the acquisition unit 18 acquires the data set from the data lake 61.
  • the analysis device 62 analyzes the data accumulated in the data lake 61 and outputs the analysis result.
  • the preparation device 63 performs preparation processing required for data use, such as conversion of formats required for data use and data composition.
  • the capturing device 64 captures siloized data and open data in the data lake 61.
  • the AI development management device 1 manages assets for a plurality of AI development projects. Therefore, the version information storage unit 15 stores information on a plurality of projects, and the version management unit 17 stores and manages information on a plurality of projects. Each project uses the data set by copying it from the data lake 61. At this time, the same data may be used in multiple projects.
  • FIG. 19 is a diagram for explaining the use of the same data.
  • project A and project B use the same data.
  • the version information storage unit 15 and the version management unit 17 store a plurality of the same data, waste occurs.
  • the data utilization system 6 may have a data version management device that manages the data set.
  • FIG. 20 is a diagram for explaining the data version management device.
  • the data version management device 65 takes out the data used by the AI development management device 1 from the data lake 61 as a snapshot and manages it.
  • the AI development management device 1 instructs the data lake 61 to read data
  • the read instruction is transmitted to the data version management device 65.
  • the data version management device 65 sends the version information corresponding to the data together with the data to the AI development management device 1 if the data instructed to be read is cached in the device itself. On the other hand, if the data instructed to be read is not cached in the device itself, the data version management device 65 reads the data from the data lake 61 and caches the data. Then, the data version management device 65 associates the cached data with the version and transmits version information to the AI development management device 1 together with the data. When the data version management device 65 receives a commit instruction from the AI development management device 1, the data version management device 65 manages the committed data as a new version. The AI development management device 1 stores version information instead of storing data.
  • the AI development management device 1 can eliminate the waste of storing a plurality of the same data. Further, the AI development management device 1 can transparently access the data lake 61.
  • 1,4 AI development management device 6 Data utilization system 11,41 Front end part 12 Flow editor 13,43 Editor 14 Flow execution engine 15,45 Version information storage part 16,46 Asset management part 17,47 Version management part 18 Acquisition Part 20, 26 Run button 21 Script symbol 22 Script edit button 23, 27 Execution history confirmation button 31 Execution history table 32 Graph showing evaluation result 44 Execution engine 50 Computer 51 Main memory 52 CPU 53 LAN interface 54 HDD 55 Super IO 56 DVI 57 ODD 61 data lake 62 analyzer 63 preparation device 64 importer 65 data version management device

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Stored Programmes (AREA)

Abstract

Une unité de gestion de version stocke et gère des informations d'historique d'apprentissage d'une pluralité de versions avec un ensemble de données, un modèle de d'apprentissage machine (ML) appris et un résultat d'évaluation du modèle de ML appris en tant qu'informations d'historique d'apprentissage d'une version. En outre, lorsqu'une unité d'extrémité avant (11) reçoit une instruction pour sélectionner une version parmi la pluralité de versions d'un utilisateur, une unité de gestion de contenus (16) acquiert les informations d'historique d'apprentissage de la version spécifiée à partir de l'unité de gestion de version (17), et échange des informations d'une unité de stockage d'informations de version (15) pour les informations d'historique d'apprentissage de la version acquise. En outre, sur la base des informations d'historique d'apprentissage de la version échangée, un éditeur de flux (12) affiche un diagramme de flux sur un dispositif d'affichage.
PCT/JP2019/003493 2019-01-31 2019-01-31 Dispositif de traitement d'informations, système de gestion d'historique d'apprentissage et programme de gestion d'historique d'apprentissage WO2020157939A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2019/003493 WO2020157939A1 (fr) 2019-01-31 2019-01-31 Dispositif de traitement d'informations, système de gestion d'historique d'apprentissage et programme de gestion d'historique d'apprentissage
JP2020569299A JPWO2020157939A1 (ja) 2019-01-31 2019-01-31 情報処理装置、学習履歴管理システム及び学習履歴管理プログラム

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2019/003493 WO2020157939A1 (fr) 2019-01-31 2019-01-31 Dispositif de traitement d'informations, système de gestion d'historique d'apprentissage et programme de gestion d'historique d'apprentissage

Publications (1)

Publication Number Publication Date
WO2020157939A1 true WO2020157939A1 (fr) 2020-08-06

Family

ID=71840181

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2019/003493 WO2020157939A1 (fr) 2019-01-31 2019-01-31 Dispositif de traitement d'informations, système de gestion d'historique d'apprentissage et programme de gestion d'historique d'apprentissage

Country Status (2)

Country Link
JP (1) JPWO2020157939A1 (fr)
WO (1) WO2020157939A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7549140B2 (ja) 2020-10-13 2024-09-10 ヒタチ ヴァンタラ エルエルシー アクションへの傾向についての表現特徴空間における自己適応マルチモデル方法

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017141517A1 (fr) * 2016-02-17 2017-08-24 ソニー株式会社 Procédé de traitement d'informations et dispositif de traitement d'informations
WO2017175434A1 (fr) * 2016-04-06 2017-10-12 ソニー株式会社 Dispositif de traitement d'informations, procédé de traitement d'informations et procédé de fourniture d'informations

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6746139B2 (ja) * 2016-09-08 2020-08-26 公立大学法人会津大学 携帯端末を用いた察知エージェントシステム、察知エージェントシステムにおける機械学習方法、及びこれを実施するためのプログラム

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017141517A1 (fr) * 2016-02-17 2017-08-24 ソニー株式会社 Procédé de traitement d'informations et dispositif de traitement d'informations
WO2017175434A1 (fr) * 2016-04-06 2017-10-12 ソニー株式会社 Dispositif de traitement d'informations, procédé de traitement d'informations et procédé de fourniture d'informations

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7549140B2 (ja) 2020-10-13 2024-09-10 ヒタチ ヴァンタラ エルエルシー アクションへの傾向についての表現特徴空間における自己適応マルチモデル方法

Also Published As

Publication number Publication date
JPWO2020157939A1 (ja) 2021-10-14

Similar Documents

Publication Publication Date Title
US20190317944A1 (en) Methods and apparatus for integrated management of structured data from various sources and having various formats
US7596546B2 (en) Method and apparatus for organizing, visualizing and using measured or modeled system statistics
US7418453B2 (en) Updating a data warehouse schema based on changes in an observation model
US8843883B2 (en) System and method for model-driven dashboard for business performance management
US20080163187A1 (en) Graphical representation of dependencies between changes of source code
US20130055197A1 (en) Modeling and code generation for sql-based data transformations
US8683435B2 (en) System and method for configuring electronic data capture and data management systems for clinical trials
CN111611458A (zh) 大数据治理中基于元数据和数据分析技术实现系统数据架构梳理的方法
CN111190814B (zh) 软件测试用例的生成方法、装置、存储介质及终端
Garcia et al. Constructing a shared infrastructure for software architecture analysis and maintenance
CN116226112A (zh) 数据清洗方法、装置、存储介质及电子设备
WO2020157939A1 (fr) Dispositif de traitement d'informations, système de gestion d'historique d'apprentissage et programme de gestion d'historique d'apprentissage
CN109669868A (zh) 软件测试的方法及系统
EP4439309A1 (fr) Système et procédé de génération intelligente de données de test synthétique
Da Cruz et al. Conformance analysis on software development: an experience with process mining
CN117785698B (zh) 一种软件测试用例方法、装置、电子设备和存储介质
da Silva Web-Based Application for Assisted Elimination of Duplicate Photographs
Alspaugh Understanding Data Analysis Activity via Log Analysis
Kantipudi Business insights of user usage records of data cards
Jadeja et al. Big Data—A New Technology Trend and Factors Affecting the Implementation of Big Data in Australian Industries
Khan Self-Service Analytics Simplified: How to Plan and Implement
DISKIN Computer Processing in the Statistical Offices of Developing Countries
CN118259874A (zh) 一种产品设计的分析方法、系统和电子设备
WO2024076385A1 (fr) Détection de défaut par apprentissage automatique à l'aide d'un traitement de données basé sur des métadonnées
Schüller Rule-Based Assessment of Solution Architecture Alignment

Legal Events

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

Ref document number: 19912585

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020569299

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19912585

Country of ref document: EP

Kind code of ref document: A1