Unlock instant, AI-driven research and patent intelligence for your innovation.

Data screening method and device, electronic equipment and storage medium

A data screening and data technology, applied in the computer field, can solve the problems of large manual workload, large amount of data, and low accuracy.

Active Publication Date: 2020-06-16
BEIJING BYTEDANCE NETWORK TECH CO LTD
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to ensure that the content uploaded by people meets certain requirements, for example: the uploaded content is non-pornographic, or non-violent, or non-reactionary, it is necessary to recall the suspected uploaded content, and then determine the recalled content through manual investigation. Whether the content meets the requirements, when recalling suspicious uploaded content, it is usually recalled through the neural network model, but the amount of content data recalled through the neural network model is relatively large, and there is content that meets the requirements in the recalled content, so , the accuracy rate of recall through the above method is low, which leads to a large manual workload during manual investigation

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Data screening method and device, electronic equipment and storage medium
  • Data screening method and device, electronic equipment and storage medium
  • Data screening method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0076] figure 1 A schematic flow chart of a data screening method provided in Embodiment 1 of the present disclosure, such as figure 1 As shown, the data screening method includes the following steps:

[0077] Step 101: Obtain a plurality of data units to be screened related to preset content types recalled from a content recall pool based on a neural network model; each data unit to be screened includes data to be screened corresponding to at least one data type.

[0078] Here, a data unit to be screened may refer to a data unit that exists as a logical whole such as an article, a video, or a picture.

[0079] In the implementation, all the data uploaded on the specified platform can be used as a content recall pool, and the type of content to be recalled is preset before the data recall, for example: recalling pornographic content, or recalling violent content, or recalling reactionary content etc. After setting the type of content to be recalled, it can be recalled from a...

Embodiment 2

[0116] Figure 4 A schematic structural diagram of a data screening device provided in Embodiment 2 of the present disclosure, such as Figure 4 As shown, the data screening device includes:

[0117] The acquisition unit 41 is configured to acquire a plurality of data units to be screened related to preset content types recalled from the content recall pool based on the neural network model; each of the data units to be screened includes at least one data type corresponding to the data unit to be screened data;

[0118] The determining unit 42 is configured to, for each of the data units to be screened, determine the data unit to be screened and the preset content type according to the characteristic information of the data to be screened under each data type in the data unit to be screened degree of matching;

[0119] A judging unit 43, configured to judge whether the determined matching degree is within a preset range;

[0120] The sending unit 44 is configured to send t...

Embodiment 3

[0148] Figure 5 A schematic structural diagram of an electronic device provided in Embodiment 3 of the present disclosure, including: a processor 501, a storage medium 502, and a bus 503. The storage medium 502 stores machine-readable instructions executable by the processor 501. When When the electronic device runs the above data screening method, the processor 501 communicates with the storage medium 502 through the bus 503, and the processor 501 executes the machine-readable instructions to perform the following steps:

[0149] Obtain a plurality of data units to be screened related to preset content types recalled from the content recall pool based on the neural network model; each of the data units to be screened includes data to be screened corresponding to at least one data type;

[0150]For each data unit to be screened, according to the feature information of the data to be screened under each data type in the data unit to be screened, determine the matching degree b...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a data screening method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a plurality of to-be-screened data units which are recalled from a content recall pool based on a neural network model and are related to a preset content type, wherein each to-be-screened data unit comprises to-be-screened data corresponding to at least one data type; for each to-be-screened data unit, determining the matching degree of the to-be-screened data unit and the preset content type according to the feature information of the to-be-screened data under each data type in the to-be-screened data unit; judging whether the determined matching degree is within a preset range or not; and if the determined matching degree is within the preset range, sending the to-be-screened data unit to target equipment. Compared with a mode of manually checking data recalled through a neural network model, the method and the device are beneficial to reduction of the data volume of the data subjected to manual checking, so that reduction of the manual workload is facilitated.

Description

technical field [0001] The present disclosure relates to the field of computer technology, in particular, to a data screening method, device, electronic equipment and storage medium. Background technique [0002] With the development of network technology, the relationship between people and the network is getting closer, people will upload a large amount of data to the network, for example: people can upload some video, pictures or text data to the network through a social platform, and for other users to view. [0003] In order to ensure that the content uploaded by people meets certain requirements, for example: the uploaded content is non-pornographic, or non-violent, or non-reactionary, it is necessary to recall the suspected uploaded content, and then determine the recalled content through manual investigation. Whether the content meets the requirements, when recalling suspicious uploaded content, it is usually recalled through the neural network model, but the amount...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F16/9535G06K9/62G06N3/04G06N3/08
CPCG06F16/9535G06N3/08G06N3/045G06F18/22
Inventor 冯爱迪侯新雨李常青
Owner BEIJING BYTEDANCE NETWORK TECH CO LTD