Data processing method, device, terminal device and storage medium

By setting up a data set warehouse that prohibits downloading and uploading on the AI ​​competition data processing platform, and using a virtual online development environment and functional plug-ins for video monitoring, the problem of data leakage risk in the enterprise's internal AI competition is solved, and data is realized Improved security and confidentiality of documents.

CN114266066BActive Publication Date: 2024-11-08CHINA UNITED NETWORK COMM GRP CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202111368681.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-18
Publication Date
2024-11-08
Estimated Expiration
2041-11-18

AI Technical Summary

Technical Problem

In the internal artificial intelligence competition organized by enterprises, there is a risk of leakage of internal production data and poor security. The existing technology cannot meet the company's confidentiality needs for data.

Method used

By setting up a data set warehouse on the data processing platform, downloading and uploading is prohibited. Participants obtain data files from the warehouse for processing when performing target tasks, and send the results to the server to ensure that the data files are circulated on the platform and use virtualization Online development environment and functional plug-ins perform video monitoring and screen recording to improve data security and confidentiality.

Benefits of technology

It effectively improves the security and confidentiality of data files, prevents data leakage, ensures data circulation on the platform, and meets the enterprise's needs for data security.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114266066B_ABST
    Figure CN114266066B_ABST
Patent Text Reader

Abstract

The embodiment of the present application provides a data processing method, apparatus, terminal device and storage medium. The method includes: a first terminal logs in to a server based on a data processing platform; the first terminal selects a target task in the data processing platform; when the first terminal executes the target task, it obtains the data file corresponding to the target task from the data set warehouse, and performs data processing according to the data file corresponding to the target task to obtain a processing result; the first terminal sends the processing result to the server based on the data processing platform. The method of the present application ensures that the data does not leave the platform, and improves the security and confidentiality of the data files.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a data processing method, apparatus, terminal device and storage medium. Background Art

[0002] As computer technology matures, artificial intelligence technology is also developing day by day. More and more researchers are engaged in the research of artificial intelligence. Artificial intelligence competitions provide a good platform for these people to exchange technology. "Using competitions to promote production" is a common way in the field of artificial intelligence. Obtaining the production value of artificial intelligence from the results of competitions can effectively promote the development of artificial intelligence technology. When organizing artificial intelligence competitions, an artificial intelligence competition platform is usually required.

[0003] On current AI competition platforms, participants usually download open source datasets of relevant competition questions to local storage, create a development environment through local devices, build models, and retrieve datasets from local devices to complete model training and generate result files. For some competitions involving internal production data of enterprises, downloading open source datasets to local storage cannot meet the needs of enterprises for internal data security and confidentiality. Summary of the invention

[0004] The present application provides a data processing method, apparatus, terminal device and storage medium to solve the problem of internal production data leakage risk and poor security in internal artificial intelligence competitions organized by enterprises.

[0005] In one aspect, the present application provides a method for data processing, comprising:

[0006] The first terminal logs in to the server based on the data processing platform; a data set warehouse of the server is provided with data files corresponding to a plurality of tasks, and the data set warehouse prohibits downloading and uploading from the first terminal;

[0007] The first terminal selects a target task in the data processing platform; the target task is one of the multiple tasks;

[0008] When executing the target task, the first terminal obtains the data file corresponding to the target task from the data set warehouse, and performs data processing according to the data file corresponding to the target task to obtain a processing result;

[0009] The first terminal sends the processing result to the server based on the data processing platform.

[0010] Optionally, when executing the target task, the first terminal obtains a data file corresponding to the target task from the data set warehouse, including:

[0011] The first terminal creates a virtual online development environment; the online development environment includes an image, an online integrated development environment IDE tool jupyter notebook, customized code, and a data set reference program. The online integrated development environment IDE tool jupyter notebook is used for users to enter the online development environment; the customized code is used to customize the jupyter notebook to delete the upload and download functions of the data file; the data set reference program is used to retrieve the data files in the data set warehouse;

[0012] When the first terminal executes the target task in the online development environment, it uses the data set reference program to obtain the data file corresponding to the target task from the data set warehouse.

[0013] Optionally, the online development environment is also used to connect functional plug-ins to achieve video monitoring of users and screen recording and saving of operation pages; the method also includes:

[0014] The first terminal records the user monitoring video and the operation page video of the first terminal;

[0015] The first terminal sends the user monitoring video and the operation page video of the first terminal to the server based on the online development environment.

[0016] Optionally, the processing result includes a result file and a code file corresponding to the result file, and data processing is performed according to the data file corresponding to the target task to obtain the processing result, including:

[0017] The first terminal receives the algorithm code written by the user online, introduces the data file of the user data set warehouse through the data set reference program, and generates a result file for training and testing the algorithm code and a code file corresponding to the result file.

[0018] The first terminal sends a processing result to the server based on the data processing platform, including:

[0019] The first terminal receives a submission instruction based on the data processing platform;

[0020] In response to the submit instruction, the first terminal performs a normative judgment on the processing result, and the normative judgment is used to determine whether the processing result meets the preset specification;

[0021] If the processing result meets the preset specification, the first terminal submits the processing result, the video monitoring file and the screen recording file to the server.

[0022] Optionally, the first terminal selects a target task in the data processing platform, including:

[0023] The first terminal displays the registration information page and the competition question information page. The registration information page is used for contestants to fill in registration information; the competition question information page is used for contestants to browse competition question task information; the registration information includes competition area information;

[0024] The first terminal receives first registration information for the target task on the registration information page;

[0025] The first terminal sends the first registration information to the second terminal via the server; wherein, if the first registration information is approved by the second terminal, the first registration information will be stored in the server;

[0026] The first terminal obtains information of the target task after isolation configuration from the server; the isolation configuration is used to distinguish the range of information obtained by different applicants.

[0027] In a second aspect, an embodiment of the present application provides a data processing device, including:

[0028] A login module is used for the first terminal to log in to the server based on the data processing platform; a data set warehouse of the server is provided with data files corresponding to a plurality of tasks, and the data set warehouse prohibits downloading and uploading from the first terminal;

[0029] A selection module is used for the first terminal to select a target task in the data processing platform; the target task is one of the multiple tasks;

[0030] A first processing module is used for the first terminal to obtain a data file corresponding to the target task from the data set warehouse when executing the target task, and to perform data processing according to the data file corresponding to the target task to obtain a processing result;

[0031] The first sending module is used for the first terminal to send the processing result to the server based on the data processing platform.

[0032] Optionally, the processing module is used for the first terminal to obtain a data file corresponding to the target task from the data set warehouse when executing the target task, including:

[0033] The development environment module is used for the first terminal to create a virtual online development environment; the online development environment includes an image, an online integrated development environment IDE tool jupyter notebook, customized code and a data set reference program. The online integrated development environment IDE tool jupyter notebook is used for users to enter the online development environment; the customized code is used to customize the jupyter notebook to delete the upload and download functions of the data file; the data set reference program is used to retrieve the data files in the data set warehouse;

[0034] The data set reference module is used for the first terminal to obtain the data file corresponding to the target task from the data set warehouse by using the data set reference program when executing the target task in the online development environment.

[0035] Optionally, the development environment module is also used to connect the functional plug-in to achieve video monitoring of the user and screen recording and saving of the operation page; the device also includes:

[0036] A monitoring module, used for the first terminal to record user monitoring video and operation page video of the first terminal;

[0037] The second sending module is used for the first terminal to send the user monitoring video and the operation page video of the first terminal to the server based on the online development environment.

[0038] Optionally, the processing result includes a result file and a code file corresponding to the result file. The first processing module performs data processing according to the data file corresponding to the target task to obtain the processing result, including:

[0039] The second processing module is used for the first terminal to receive the algorithm code written by the user online, introduce the data file of the user data set warehouse through the data set reference program, and generate the result file for training and testing the algorithm code and the code file corresponding to the result file.

[0040] Optionally, a first sending module, used for the first terminal to send a processing result to the server based on the data processing platform, includes:

[0041] A first receiving module, used for the first terminal to receive a submission instruction based on the data processing platform;

[0042] A judgment module, configured to respond to the submission instruction and to make a normative judgment on the processing result of the first terminal, wherein the normative judgment is used to judge whether the processing result meets the preset specification;

[0043] The submission module is used to submit the processing result, the video monitoring file and the screen recording file to the server if the processing result meets the preset specification.

[0044] Optionally, a selection module is used for the first terminal to select a target task in the data processing platform, including:

[0045] The display module is used for the first terminal to display the registration information page and the competition question information page. The registration information page is used for the contestants to fill in the registration information; the competition question information page is used for the contestants to browse the competition question task information; the registration information includes the competition area information;

[0046] A second receiving module, configured for the first terminal to receive first registration information for a target task on a registration information page;

[0047] A third sending module is used for the first terminal to send the first registration information to the second terminal via the server; wherein, if the first registration information is approved by the second terminal, the first registration information will be stored in the server;

[0048] The acquisition module is used for the first terminal to acquire the information of the target task after the isolation configuration from the server; the isolation configuration is used to distinguish the range of information obtained by different applicants.

[0049] In a third aspect, an embodiment of the present application provides a data processing system, the data processing system including a first terminal, a second terminal and a server, including:

[0050] The second terminal publishes the task to the server based on the data processing platform;

[0051] The first terminal logs in to the server based on the data processing platform; a data set warehouse of the server is provided with data files corresponding to a plurality of tasks, and the data set warehouse prohibits downloading and uploading from the first terminal;

[0052] The second terminal receives the first registration information uploaded by the first terminal when logging in and reviews the first registration information;

[0053] The second terminal isolates and configures the task data that can be selected by the first terminal according to the review result of the first registration information;

[0054] The first terminal selects a target task in the data processing platform; the target task is one of the multiple tasks after isolation configuration;

[0055] When executing the target task, the first terminal obtains the data file corresponding to the target task from the data set warehouse, and performs data processing according to the data file corresponding to the target task to obtain a processing result;

[0056] The first terminal sends the processing result to the server based on the data processing platform;

[0057] The second terminal reviews the processing result sent by the first terminal to the server.

[0058] In a fourth aspect, an embodiment of the present application provides a terminal device, including: a memory and a processor;

[0059] The memory is used to store computer instructions; the processor is used to execute the computer instructions stored in the memory to implement any method in the first aspect.

[0060] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement any one of the methods in the first aspect.

[0061] In a sixth aspect, an embodiment of the present application provides a computer program product, including a computer program, which implements any method in the first aspect when executed by a processor.

[0062] The data processing method, apparatus, terminal device and storage medium provided in the embodiment of the present application, after logging into the server based on the data processing platform through the first terminal, the target task is selected in the data processing platform, the data set warehouse of the server is provided with data files corresponding to multiple tasks, the data set warehouse prohibits downloading and uploading from the first terminal, when the first terminal is executing the target task, the data file corresponding to the target task is obtained from the data set warehouse, and data processing is performed according to the data file corresponding to the target task, the processing result is obtained and sent to the server. In the above process, when the contestant executes the target task, the data file is introduced from the data set warehouse of the server, and the data set warehouse prohibits downloading and uploading from the first terminal, so that the data files in the data set warehouse are circulated on the data processing platform, and have never left the data processing platform, so that the data does not leave the platform, and at the same time, the data files cannot be downloaded to the local device by the contestant, thereby improving the security and confidentiality of the data files. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A schematic diagram of an application scenario provided for an embodiment of the present application;

[0064] Figure 2 A flowchart of a data processing method provided in one embodiment of the present application;

[0065] Figure 3 A flowchart of a data processing method provided by another embodiment of the present application;

[0066] Figure 4 A flowchart of a data processing method provided in yet another embodiment of the present application;

[0067] Figure 5 A flowchart of a data processing method provided in yet another embodiment of the present application;

[0068] Figure 6 A flowchart of a data processing method provided in yet another embodiment of the present application;

[0069] Figure 7 A schematic diagram of the structure of a data processing device provided in one embodiment of the present application;

[0070] Figure 8 A schematic diagram of the structure of a data processing terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0071] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0072] First, the terms involved in this application are explained:

[0073] Artificial Intelligence Competition: Artificial Intelligence (AI) is a branch of computer science. Artificial Intelligence is the simulation of the information process of human consciousness and thinking. It can be used for intelligent control, robotics, language and image understanding, genetic algorithms, automatic programming, aerospace applications, big data processing, and the execution of complex or large-scale tasks that cannot be performed by synthetic life forms. As the name suggests, artificial intelligence competitions are competitions organized by organizers around various artificial intelligence technologies.

[0074] The data processing method provided in the embodiment of the present application can be applied to Figure 1 The schematic diagram of the artificial intelligence competition system architecture is shown in Figure 1. Figure 1 As shown, the artificial intelligence competition system includes: a server 101, a first terminal 102 and a second terminal 103, wherein the server 101 is connected to the terminal device, and is used to monitor the competition environment of the artificial intelligence competition and rank the contestants' scores. The first terminal 102 is a terminal device for contestants to register, participate, and submit competition results. Contestants access the server 101 by registering or logging in to the contestant account on the first terminal 102; the second terminal 103 is a terminal device for managers to manage and set the artificial intelligence competition. The manager accesses the server 101 by entering the manager account on the second terminal 103. It can be understood that the first terminal and the second terminal can be one or more.

[0075] The specific application scenario of this application is that the first terminal 102 provides a competition interface for contestants. Contestants can browse related competitions, select the AI ​​competitions of interest to register, obtain the competition questions and submit the competition results within the specified time of the competition. After the contestants submit the results, they can view the ranking in real time. The second terminal 103 provides multiple management pages for managers, including: team management, competition question management, configuration isolation, review registration, and results query pages. The manager selects the target management interface to execute his corresponding management authority. For example, the "Team Management" management page provides the team name, competition area, captain name, competition time, etc. The manager can enter keywords in the search box to search for the team name, quickly find the relevant team, and edit or delete it.

[0076] In possible implementations, the AI ​​competition system still has the following problems:

[0077] Internal competitions organized by enterprises have high requirements for data confidentiality. Most competition methods use open source data sets downloaded to local devices for storage. Open source data sets are regular data sets distributed with their source code, and users can freely read, modify and expand the software. This means that the source code data in AI competitions held within enterprises will be separated from the competition platform and stored on the local devices used by the contestants. There may be a risk of internal data leakage within the enterprise, which cannot meet the enterprise's needs for data security and confidentiality.

[0078] In response to the above problems, the present application provides a method for artificial intelligence competition and designs a set of safe artificial intelligence competition solutions. In the process of managers publishing competition question data sets, contestants subscribing to competition questions and synchronizing competition questions to contestants' data set warehouses, and contestants referencing data files, data files are always circulated in the data set warehouse inside the platform, ensuring that the data of the entire process will not leave the platform, reducing the impact of using open source data sets on data security during the artificial intelligence competition process, and improving the security and confidentiality of competition data. The technical solution of the present application and how the technical solution of the present application solves the above technical problems are described in detail with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0079] Figure 2 This is a flow chart of the data processing method provided in the embodiment of the present application. Figure 2 , the method may include:

[0080] S201, a first terminal logs in to a server based on a data processing platform; a data set warehouse of the server is provided with data files corresponding to a plurality of tasks, and the data set warehouse prohibits downloading and uploading from the first terminal.

[0081] The embodiments of the present application can be applied to a data processing system. The data processing system includes a first terminal, a second terminal and a server. The first terminal is a terminal device used by a contestant. Optionally, the first terminal can be a mobile phone, a tablet computer, a notebook or other device. The second terminal is a terminal device used by an administrator. The data processing platform is mainly a platform for users (administrators, contestants or non-contestants) to collect, process, review, score and display data. It can support multiple different terminal devices to log in at the same time. The data processing platform can display visual operation pages with different functions, and users perform corresponding operations based on the visual operation pages.

[0082] The company's internal data platform mainly provides data processing, analysis, and display for each business. It is used by all internal department personnel and involves data collection (filling), data integration, business report production, salesperson data analysis, and visual data display.

[0083] The first terminal logs in to the server based on the data processing platform and establishes a connection with the server. Optionally, the contestant can log in through an account, scan a QR code, or use facial recognition to verify user information to log in to the data processing platform. The embodiment of the present application does not specifically limit the login method. The manager publishes tasks and data files corresponding to the data sets based on the data processing platform. A data set warehouse for storing data sets is set in the server. The data files in the data set warehouse cannot be downloaded to the local device of the first terminal.

[0084] S202: The first terminal selects a target task in the data processing platform; the target task is one of the multiple tasks.

[0085] After logging into the data processing platform, the contestant can browse the task page provided on the first terminal and select the task of interest as the target task. The target task is one of the multiple tasks published on the data processing platform. Optionally, if the contestant is interested in more tasks, he or she can select multiple tasks, but any two tasks among the multiple tasks cannot be executed at the same time. It is understandable that the same contestant cannot participate in two AI competitions at the same time.

[0086] S203: When executing the target task, the first terminal obtains the data file corresponding to the target task from the data set warehouse, and performs data processing according to the data file corresponding to the target task to obtain a processing result.

[0087] The data set warehouse of the data processing platform stores data files corresponding to the target task. When the contestant executes the target task on the first terminal, the data file corresponding to the target task is imported from the data set warehouse, and the target task is processed according to the data file corresponding to the target task to generate a processing result.

[0088] Specifically, data processing is performed according to the data file corresponding to the target task to obtain the processing result, including: the first terminal receives the algorithm code written online by the contestant, introduces the data file of the contestant's data set warehouse through the data set reference program, and generates a result file for training and testing the algorithm code and a code file corresponding to the result file. The processing result includes the result file and the code file corresponding to the result file.

[0089] S204: The first terminal sends a processing result to the server based on the data processing platform.

[0090] After the processing results are generated, the contestant can send the result file of the processing results to the server on the submission page provided by the first terminal, so that the server can subsequently score and review the result file.

[0091] The data processing method provided in this embodiment is to log in to the server through the first terminal based on the data processing platform, select the target task in the data processing platform, set the data files corresponding to multiple tasks in the data set warehouse of the server, and prohibit the download and upload from the first terminal. When the first terminal is executing the target task, it obtains the data file corresponding to the target task from the data set warehouse, and performs data processing according to the data file corresponding to the target task, obtains the processing result and sends the processing result to the server. In the above process, when the contestant executes the target task, the data file is introduced from the data set warehouse of the server, and the data set warehouse prohibits downloading and uploading from the first terminal. In this way, the data files in the data set warehouse are circulated on the data processing platform and have never left the data processing platform, so that the data does not leave the platform. At the same time, the data files cannot be downloaded to the local device by the contestant, thereby improving the security and confidentiality of the data files.

[0092] Figure 3 A flowchart of a method for obtaining a data file corresponding to a target task from a data set warehouse when a first terminal performs a target task provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, in Figure 2 Based on the illustrated embodiment, S203 includes:

[0093] S301. The first terminal creates a virtual online development environment; the online development environment includes an image, an online integrated development environment IDE tool jupyter notebook, customized code and a data set reference program. The online integrated development environment IDE tool jupyter notebook is used for users to enter the online development environment; the customized code is used to customize the jupyter notebook to delete the upload and download functions of the data files; the data set reference program is used to retrieve the data files in the data set warehouse.

[0094] When issuing a task, the administrator can determine whether the development environment in the data processing platform meets the development environment conditions of this task. If the development environment conditions of this task are met, the contestant can use the development environment in the data processing platform when performing this task. Otherwise, the administrator can upload the development environment that supports this task to the data processing platform. This application does not impose any restrictions on the development environment.

[0095] For example, the online development environment includes images, online integrated development environment IDE tool jupyter notebook, customized code and data set reference program. Participants build a development environment based on images suitable for the competition and online integrated development environment IDE tool jupyter notebook, and develop on the first terminal. The image is a basic file system that contains the application and its related dependencies. The environment created by the image is equivalent to a new virtual machine for contestants to enter and develop. In one possible way to obtain the image, contestants can obtain a manually packaged image from the data processing platform. The image includes a python environment and all necessary python development packages, including pandas, sklearn, xgboost, tensorflow, etc.), and use the online IDE tool jupyter notebook to enter the development environment.

[0096] In one possible way, after entering the development environment, contestants can perform Linux terminal operations, py file development, notebook file development, and other code development.

[0097] The created development environment also includes customized code, which restricts the development environment so that contestants who enter the development environment cannot upload or download data files.

[0098] Optionally, the online development environment is also used to connect functional plug-ins to achieve video monitoring of users and screen recording and saving of operation pages.

[0099] When the first terminal is performing the target task, the online development environment monitors the contestant's behavior and operation in real time;

[0100] Optionally, the first terminal records user monitoring video and the operation page video of the first terminal. The online development environment can be connected to a functional plug-in to turn on the camera of the first terminal and record the facial expressions, behavioral movements and voice content of the contestants during the task execution. The online development environment can be connected to a functional plug-in to turn on the screen recording of the operation page of the first terminal to monitor whether there are any illegal operations of the contestants on the operation page of the first terminal during the task execution. While recording the screen, the development environment can also capture abnormal operation behaviors in the contestants' page operations Internet Protocol (IP). In one possible way, the online development environment can use the Google Chrome plug-in function to achieve forced video monitoring and video storage; the online development environment can also use the Google Chrome plug-in function to achieve forced screen recording and content storage;

[0101] Optionally, the first terminal sends the user monitoring video and the operation page video of the first terminal to the server based on the online development environment. In one possible way, the monitoring video and the operation page video can be sent to the server by the first terminal after the task is completed, and the monitoring video and the operation page video can be automatically reviewed or manually reviewed later; the monitoring video and the operation page video can also be sent to the server in real time, and once the participant's violation is detected, his / her qualification for the current round will be cancelled.

[0102] S302: When executing a target task in an online development environment, the first terminal uses a data set reference program to obtain a data file corresponding to the target task from a data set warehouse.

[0103] Customized code limits the upload and download of data files. The platform has developed a set of programs with dataset reference functions within the environment. When the first terminal is executing a task, it can reference the data file corresponding to the target task from the dataset warehouse through the dataset reference program with dataset reference function. In this way, data files are introduced and code development is carried out.

[0104] In the data processing method provided in this embodiment, the first terminal creates a virtual online development environment. When the first terminal executes the target task in the online development environment, the first terminal uses the data set reference program to obtain the data file corresponding to the target task from the data set warehouse. The online development environment restricts the upload and download of data files, and by obtaining the data file corresponding to the target task from the data set warehouse, it ensures that the data does not leave the platform, thereby improving the security and confidentiality of the data files.

[0105] Figure 4 A schematic diagram of a data processing method provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, based on the above embodiment, S204 includes:

[0106] S401. The first terminal receives a submission instruction based on a data processing platform.

[0107] Specifically, the first terminal provides a task submission interface. After the contestant clicks the submit button, the page jumps to the result submission page. The contestant submits the result file and the code file at the corresponding position of the result submission page.

[0108] S402: In response to the submit instruction, the first terminal performs a normative judgment on the processing result, where the normative judgment is used to determine whether the processing result meets a preset specification.

[0109] S403: If the processing result meets the preset specification, the first terminal submits the processing result, the video monitoring file and the screen recording file to the server.

[0110] After the contestant submits the result file, the first terminal will make a normative judgment on the format of the result file (the number of lines is consistent with the requirements, no non-numeric values ​​appear, etc.). If the format of the result file meets the norms, it can be successfully submitted. Otherwise, the first terminal will report an error to remind the contestant to modify the corresponding format and resubmit. After the result file is successfully submitted, the code file, video monitoring file and screen recording file are sent to the server together for subsequent manual review.

[0111] S404: The server receives the result file and calculates the score of the result file.

[0112] The server compares the result file submitted by the first terminal with the standard answer uploaded by the administrator from the second terminal. The corresponding scoring method is selected according to the task type of the contestant, which includes: classification task and regression task.

[0113] Optionally, for classification tasks, which are tasks that can clearly identify the number of standard answers, the F1 value of the Macro method is used to calculate the score:

[0114] A1. Get the F1-score for each category i :

[0115] Calculate precision / precision and recall:

[0116]

[0117]

[0118]

[0119] Precision refers to the proportion of positive samples in the positive examples determined by the classifier, Recall refers to the proportion of samples predicted to be positive examples in the total positive examples, TP (True Positive) means the predicted answer is correct, FP (False Positive) means predicting other classes as the label of this class, and FN (False Negative) means predicting the label of this class as other classes.

[0120] A2. Calculate the macro F1score.

[0121]

[0122] The macro F1score is the total F1-score i The average of the sum, n is the number of categories.

[0123] Optionally, for regression problems, use MAE value for evaluation:

[0124] B1.

[0125] Among them, MAE is the mean absolute error, y i is the actual value, Yes i The predicted value, n is the total amount.

[0126] S405: The server performs ranking based on the score statistics of the result files, and sends the ranking information to the first terminal and the second terminal.

[0127] The server ranks the scores of the result files. For classification problems, the ones with an F1 value close to 1 are ranked higher. For regression problems, the ones with smaller MAE are ranked higher. For those with the same score, the submission time of the result files is used as the judging basis. The ones with earlier submission time are ranked higher. The contestants obtain the ranking information through the first terminal and check the ranking. The administrator checks the ranking information through the second terminal and prepares for the subsequent prize distribution.

[0128] The data processing method provided in this embodiment is that the first terminal receives a submission instruction based on the data processing platform. In response to the submission instruction, the first terminal makes a normative judgment on the processing result. The normative judgment is used to judge whether the processing result meets the preset specification. If the processing result meets the preset specification, the first terminal submits the processing result, video monitoring file and screen recording file to the server. The server receives the result file, counts the score of the result file, and ranks based on the score statistics of the result file. The first terminal obtains the ranking information through the data processing platform. In the above process, a set of specific methods for sending processing results and judging processing results is provided. The processing results, video monitoring files and screen recording files are added to the anti-cheating measures, which improves the fairness and justice of the artificial intelligence competition.

[0129] Figure 5 The flowchart of the first terminal selecting a target task in the data processing platform provided in the embodiment of the present application is as follows. Figure 5 As shown, including:

[0130] S501, the first terminal displays a registration information page and a competition question information page, the registration information page is used for contestants to fill in registration information; the competition question information page is used for contestants to browse competition question task information; the registration information includes competition area information;

[0131] The first terminal provides a registration information page and a competition question information page. Participants fill in the registration information on the registration information page. The registration information includes team name, avatar, slogan, personal name, mobile phone, email, company department, teammate information and competition area information. This operation is completed by the team leader.

[0132] S502, the first terminal receives first registration information for the target task on the registration information page;

[0133] S503, the first terminal sends the first registration information to the second terminal via the server; wherein, if the first registration information is approved by the second terminal, the first registration information will be stored in the server;

[0134] After receiving the first registration information filled in by the contestant, the first terminal sends the first registration information to the server, which then sends it to the second terminal for the administrator to review the first registration information. After the review is passed, the first registration information will be stored in the server.

[0135] S504, the first terminal obtains information of the target task after isolation configuration from the server; the isolation configuration is used to distinguish the range of information obtained by different applicants.

[0136] Configuration isolation can isolate data for different users, including data isolation between contestants and non-contestants and data isolation between contestants in different competition areas. Non-contestants cannot browse the competition questions, rankings, etc. on the data processing platform. Contestants can only browse the competition questions in their own competition area and cannot browse the competition question information of different competition areas.

[0137] This embodiment provides an operation flow for a contestant to select a target task in a data processing platform. The first terminal displays a registration information page and a competition question information page. The first terminal receives the first registration information for the target task on the registration information page. The first terminal sends the first registration information to the second terminal via the server. The first terminal obtains the information of the target task after isolation configuration from the server. Manual review of registration information effectively standardizes the information and number of participating teams, isolates and configures the contestants, and improves the security and confidentiality of data files on the data processing platform.

[0138] Figure 6 A method flow chart of a data processing system provided in an embodiment of the present application, such as Figure 6 As shown, including:

[0139] S601: The second terminal publishes the task to the server based on the data processing platform.

[0140] The second terminal provides a "Question Release" management page, through which the administrator releases the task. Tasks include: question cover, question name, question type, question data set, question standard answer, maximum number of submissions allowed, question start time, question deadline, question description, etc. After the task is successfully released, the contestant can browse the task information through the first terminal. If the start time has not been reached or the deadline has passed, the task cannot be operated.

[0141] S602: The first terminal logs in to the server based on the data processing platform; a data set warehouse of the server is provided with data files corresponding to a plurality of tasks, and the data set warehouse prohibits downloading and uploading from the first terminal.

[0142] S603: The second terminal receives the first registration information uploaded by the first terminal when logging in and verifies the first registration information.

[0143] After the contestant fills in the first registration information, the "Registration Review" management page of the second terminal displays the first registration information. The manager can view and review the first registration information. During the review, the manager can choose to approve or reject. If rejected, the registration record will be deleted and the contestant needs to resubmit. After the review is passed, the first registration information is saved to the server. The second terminal also provides a "Team Management" management page, based on which the manager can browse, delete and edit the first registration information.

[0144] S604: The second terminal isolates and configures the task data that can be selected by the first terminal according to the review result of the first registration information.

[0145] After the first registration information is reviewed and approved, the contestant will be automatically added to the isolation configuration. The administrator can also manually add or delete isolation configurations through the "Isolation Configuration" management page.

[0146] S605: The first terminal selects a target task in the data processing platform; the target task is one of the multiple tasks after isolation configuration.

[0147] S606: When executing the target task, the first terminal obtains the data file corresponding to the target task from the data set warehouse, and performs data processing according to the data file corresponding to the target task to obtain a processing result.

[0148] S607: The first terminal sends the processing result to the server based on the data processing platform.

[0149] S608: The second terminal reviews the processing result sent by the first terminal to the server.

[0150] The second terminal can retrieve the processing results, video surveillance files and screen recording files submitted by the first terminal to the server, and the administrator can manually review them. The second terminal obtains ranking information from the server, and the administrator distributes prizes based on the ranking information.

[0151] This embodiment develops a set of operating procedures in the data processing platform. The administrator reviews the registration information and effectively standardizes the information and number of participating teams. The release of competition questions can support customized release of different types of competition questions, and freely configure the competition time and number of submissions, which improves the administrator's user experience. At the same time, the data does not leave the platform, which increases the security and confidentiality of data files.

[0152] Figure 7 This is a schematic diagram of the structure of a data processing device provided in one embodiment of the present application. Figure 7 As shown, the data processing device 70 provided in this embodiment may include:

[0153] The login module 701 is used for the first terminal to log in to the server based on the data processing platform; the data set warehouse of the server is provided with data files corresponding to multiple tasks, and the data set warehouse prohibits downloading and uploading from the first terminal.

[0154] The selection module 702 is used for the first terminal to select a target task in the data processing platform; the target task is one of the multiple tasks.

[0155] The first processing module 703 is used for the first terminal to obtain the data file corresponding to the target task from the data set warehouse when executing the target task, and to perform data processing according to the data file corresponding to the target task to obtain a processing result.

[0156] The first sending module 704 is used for the first terminal to send the processing result to the server based on the data processing platform.

[0157] Optionally, the first processing module 703 is used for the first terminal to obtain a data file corresponding to the target task from the data set warehouse when executing the target task, and specifically includes:

[0158] The development environment module is used for the first terminal to create a virtual online development environment; the online development environment includes an image, an online integrated development environment IDE tool jupyter notebook, customized code and a data set reference program. The online integrated development environment IDE tool jupyter notebook is used for users to enter the online development environment; the customized code is used to customize the jupyter notebook to delete the upload and download functions of the data files; the data set reference program is used to retrieve the data files in the data set warehouse.

[0159] Optionally, the development environment module is also used to connect functional plug-ins to achieve video monitoring of users and screen recording and saving of operation pages, including: a monitoring module and a second sending module:

[0160] The monitoring module is used for the first terminal to record the user monitoring video and the operation page video of the first terminal.

[0161] The second sending module is used for the first terminal to send the user monitoring video and the operation page video of the first terminal to the server based on the online development environment.

[0162] The data set reference module is used for the first terminal to obtain the data file corresponding to the target task from the data set warehouse by using the data set reference program when executing the target task in the online development environment.

[0163] Optionally, the first processing module 703 is used to perform data processing according to the data file corresponding to the target task to obtain a processing result, where the processing result includes a result file and a code file corresponding to the result file, specifically including:

[0164] The second processing module is used for the first terminal to receive the algorithm code written by the user online, introduce the data file of the user data set warehouse through the data set reference program, and generate the result file for training and testing the algorithm code and the code file corresponding to the result file.

[0165] Optionally, the first sending module 704 is used for the first terminal to send the processing result to the server based on the data processing platform, specifically including:

[0166] The first receiving module is used for the first terminal to receive the submission instruction based on the data processing platform.

[0167] The judgment module is used for the first terminal to respond to the submission instruction, and the first terminal performs a normative judgment on the processing result, and the normative judgment is used to judge whether the processing result meets the preset specification.

[0168] The submission module is used to submit the processing result, the video monitoring file and the screen recording file to the server if the processing result meets the preset specification.

[0169] Optionally, the selection module 702 is used for the first terminal to select a target task in the data processing platform, and specifically includes:

[0170] The display module is used for displaying the registration information page and the competition question information page on the first terminal. The registration information page is used for contestants to fill in the registration information; the competition question information page is used for contestants to browse the competition question task information; the registration information includes the competition area information.

[0171] The second receiving module is used for the first terminal to receive the first registration information for the target task on the registration information page.

[0172] The third sending module is used for the first terminal to send the first registration information to the second terminal via the server; wherein, if the first registration information is approved by the second terminal, the first registration information will be stored in the server.

[0173] The acquisition module is used for the first terminal to acquire the information of the target task after the isolation configuration from the server; the isolation configuration is used to distinguish the range of information obtained by different applicants.

[0174] The data processing device of the embodiment of the present application can be used to execute the technical solution of the above-mentioned data processing method embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0175] Figure 8 This is a schematic diagram of the structure of a data processing terminal device provided in an embodiment of the present application. Figure 8 As shown, the data processing terminal device 80 provided in this embodiment may include:

[0176] Processor 801; and

[0177] Memory 802, used to store executable instructions of the terminal device;

[0178] Among them, the processor is configured to execute the technical solution of the above-mentioned data processing method embodiment by executing executable instructions. Its implementation principle and technical effect are similar and will not be repeated here.

[0179] A computer-readable storage medium is also provided in an embodiment of the present application, on which a computer program is stored. When the computer program is executed by a processor, the technical solution of the above-mentioned data processing method embodiment is implemented. The implementation principle and technical effect are similar and will not be repeated here.

[0180] A computer program product is also provided in an embodiment of the present application, including a computer program. When the computer program is executed by a processor, the technical solution of the above-mentioned data processing method embodiment is implemented. The implementation principle and technical effect are similar and will not be repeated here.

[0181] In the specific implementation of the above-mentioned terminal device or server, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0182] Those skilled in the art will appreciate that all or part of the steps of any of the above method embodiments may be completed by hardware associated with program instructions. The aforementioned program may be stored in a computer-readable storage medium, and when the program is executed, all or part of the steps of the above method embodiments are executed.

[0183] If the technical solution of the present application is implemented in the form of software and sold or used as a product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the technical solution of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a computer program or a number of instructions. The computer software product enables a computer device (which can be a personal computer, a server, a network device or a similar electronic device) to perform all or part of the steps of the method described in Example 1 of the present application. The aforementioned storage medium can be a U disk, a mobile hard disk, a ROM, a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0184] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A data processing method, It is characterized in that include: The first terminal logs in to the server based on the data processing platform; The data set warehouse of the server is provided with data files corresponding to a plurality of tasks, and the data set warehouse prohibits downloading and uploading from the first terminal; The first terminal selects a target task in the data processing platform; The target task is one of the multiple tasks; The first terminal creates a virtual online development environment; the online development environment includes an image, an online integrated development environment IDE tool jupyter notebook, customized code and a data set reference program, the online integrated development environment IDE tool jupyter notebook is used for users to enter the online development environment; the customized code is used to customize the jupyter notebook to delete the upload and download functions of the data file; the data set reference program is used to retrieve the data files in the data set warehouse; When the first terminal executes the target task in the online development environment, the first terminal uses the data set reference program to obtain the data file corresponding to the target task from the data set warehouse; and performing data processing according to the data file corresponding to the target task to obtain a processing result; The first terminal sends the processing result to the server based on the data processing platform.

2. The method according to claim 1, It is characterized in that The online development environment is also used to connect the functional plug-in to realize video monitoring of the user and screen recording and saving of the operation page; the method also includes: The first terminal records a user monitoring video and an operation page video of the first terminal; The first terminal sends the user monitoring video and the operation page video of the first terminal to the server based on the online development environment.

3. The method according to claim 1 or 2, It is characterized in that The processing result includes a result file and a code file corresponding to the result file. The data processing is performed according to the data file corresponding to the target task to obtain the processing result, including: The first terminal receives the algorithm code written by the user online, introduces the data file of the data set warehouse through the data set reference program, and generates a result file for training and testing the algorithm code and a code file corresponding to the result file.

4. The method according to claim 3, It is characterized in that The first terminal sends the processing result to the server based on the data processing platform, including: The first terminal receives a submission instruction based on the data processing platform; In response to the submit instruction, the first terminal performs a normative judgment on the processing result, wherein the normative judgment is used to determine whether the processing result meets a preset specification; If the processing result meets the preset specification, the first terminal submits the processing result, the video monitoring file and the screen recording file to the server.

5. The method according to any one of claims 1 to 2, It is characterized in that The first terminal selects a target task in the data processing platform, including: The first terminal displays a registration information page and a competition question information page, wherein the registration information page is used for contestants to fill in registration information; the competition question information page is used for contestants to browse competition question task information; the registration information includes competition area information; The first terminal receives first registration information for the target task on the registration information page; The first terminal sends the first registration information to the second terminal via the server; wherein, if the first registration information is approved by the second terminal, the first registration information will be stored in the server; The first terminal obtains the information of the target task after isolation configuration from the server; the isolation configuration is used to distinguish the range of information obtained by different applicants.

6. A data processing method, It is characterized in that Applied to a data processing system, the data processing system includes a first terminal, a second terminal and a server, the method includes: The second terminal publishes the task to the server based on the data processing platform; The first terminal logs in to the server based on the data processing platform; a data set warehouse of the server is provided with data files corresponding to a plurality of tasks, and the data set warehouse prohibits downloading and uploading from the first terminal; The second terminal receives the first registration information uploaded by the first terminal when logging in and reviews the first registration information; The second terminal isolates and configures the task data that can be selected by the first terminal according to the review result of the first registration information; The first terminal selects a target task in the data processing platform; the target task is one of the multiple tasks after the isolation configuration; The first terminal creates a virtual online development environment; the online development environment includes an image, an online integrated development environment IDE tool jupyter notebook, customized code and a data set reference program, the online integrated development environment IDE tool jupyter notebook is used for users to enter the online development environment; the customized code is used to customize the jupyter notebook to delete the upload and download functions of the data file; the data set reference program is used to retrieve the data files in the data set warehouse; When the first terminal executes the target task in the online development environment, the first terminal uses the data set reference program to obtain the data file corresponding to the target task from the data set warehouse; and performs data processing according to the data file corresponding to the target task to obtain a processing result; The first terminal sends the processing result to the server based on the data processing platform; The second terminal reviews the processing result sent by the first terminal to the server.

7. A terminal device, It is characterized in that include: Memory and processor; The memory is used to store computer instructions; the processor is used to execute the computer instructions stored in the memory to implement the method described in any one of claims 1-5.

8. A computer-readable storage medium, It is characterized in that A computer program is stored thereon, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 5.

9. A computer program product, It is characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 5 when being executed by a processor.

Citation Information

Patent Citations

  • Online competition method, device and server

    CN109343912A

  • Offline identity authentication system and device and computer readable storage medium

    CN109885994A

  • Competition data set automatic processing system and method based on multiplexing

    CN110389978A

  • Whole-process artificial intelligence competition system based on local model and cloud feedback and data processing method thereof

    CN110427983A

  • Competition data processing system and method based on virtual environment

    CN110704135A