An entity recognition method, device, equipment and storage medium
An entity recognition and entity technology, applied in the field of information security, can solve the problems of unbalanced distribution of data labels, long length, and low accuracy of entity recognition results, and achieve the effect of improving accuracy and recognition accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0110] figure 1 A schematic flowchart of an entity identification method provided by an embodiment of the present application is shown, wherein the method includes steps S101-S104; specifically:
[0111] S101, obtain the original threat intelligence text.
[0112] Specifically, the existing entity recognition model is mainly used to recognize common types of entities such as person names, place names, and time in ordinary text data. Considering that the entities that need to be recognized in the field of threat intelligence need to involve a large number of special words, and in the field of threat intelligence There is a dearth of open source datasets in the threat intelligence field, so it is necessary to first build a sample dataset for training entity recognition models.
[0113] In the embodiment of the present application, as an optional embodiment, text data such as articles, blogs, and thesis reports related to threat intelligence may be crawled from a secure website ...
Embodiment 2
[0241] Figure 4 A schematic structural diagram of an entity identification device provided by an embodiment of the present application is shown, and the device includes:
[0242]A data collection module 401, used for acquiring original threat intelligence text;
[0243] The word segmentation marking module 402 is used to mark each word segmentation in the original threat intelligence text according to the entity type of the entity to which the segmentation belongs, for each of the original threat intelligence texts, to obtain a training sample, wherein the entity type is at least Including: threat intelligence type and non-threat intelligence type, each word segment in the training sample corresponds to an entity tag;
[0244] The model training module 403 is used to input the training sample into the entity recognition model for each of the training samples, and train the entity recognition model by using each word segment in the training sample and the entity tag correspon...
Embodiment 3
[0287] like Figure 5 As shown, an embodiment of the present application provides a computer device 500 for executing the entity identification method in the present application, the device includes a memory 501, a processor 502, and a computer device 500 stored on the memory 501 and available on the processor 502 A running computer program, wherein when the processor 502 executes the computer program, the steps of the entity identification method are implemented.
[0288] Specifically, the above-mentioned memory 501 and processor 502 may be general-purpose memory and processor, which are not specifically limited here. When the processor 502 runs the computer program stored in the memory 501, it can execute the above-mentioned entity identification method.
[0289] Corresponding to the entity identification method in the present application, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the com...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More