Efficient keyword filtering method for FPGA (Field Programmable Gate Array)

A filtering method and keyword technology, applied in the field of network security, can solve the problem of low efficiency of keyword search methods, and achieve the effects of fast search speed, small space consumption and large storage capacity

Pending Publication Date: 2022-04-08
无锡宏创盛安科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This patented technology allows an algorithm called Hierarchy Search (HSL) that quickly searches through specific parts of data without storing all relevant words or characters at once. By performing this process over these areas instead of just searching each bit separately, it improves efficiency while reducing errors caused by incorrect matches made during previous attempts. Overall, HSL provides faster and efficient ways to find important things like keys from documents.

Problems solved by technology

Technologies described include various techniques for improving key word searching performance during computer networks' analysis tasks like web crawling or firewall attacks. These technics aim to improve upon existing algorithms while also enhancing their ability to handle larger amounts of data efficiently without sacrificing accuracy.

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
  • Efficient keyword filtering method for FPGA (Field Programmable Gate Array)
  • Efficient keyword filtering method for FPGA (Field Programmable Gate Array)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] This embodiment provides a high-efficiency keyword filtering method for FPGA implementation, which adopts the hierarchical processing mechanism of the host and the FPGA accelerator card, and can be used for keyword filtering of offline application content data, see figure 1 , the method includes:

[0038] S1: keyword preprocessing;

[0039] Sort by keyword word count. If the word count of a certain keyword exceeds 31, then divide the super-long keyword into multiple keywords (the keyword length cannot be cut too short, and the distribution of the entire keyword (2-31) should be considered as a whole). Keywords with the same number of words constitute a keyword set (kw_i), where i represents the number of words in the keyword, and kw represents keywords with the same length.

[0040] Calculate the hash value of each keyword in the same set, and build a hash-key value table (hash_i_array) and a hash keyword comparison table.

[0041] S2: Load the keyword hash key value ta

Embodiment 2

[0050] This embodiment provides a specific application of an FPGA-oriented high-efficiency keyword filtering method, which can be used for online real-time search and filtering of network message data, such as figure 2 As shown, the method includes:

[0051] Step1: Keyword preprocessing, and calculate the hash value of each keyword, and get the hash value-keyword comparison table;

[0052] In keyword preprocessing, keywords are classified according to length, and keywords with the same number of words constitute a keyword set, and each length uses a hash function. This method supports the hash of 2 to 31 Chinese characters, and a total of 30 are obtained. The set of hash values, that is, hash2~hash31, the value range of each hash function is 0~511, recorded as hash_array[0:511], the hash function value of the keyword is calculated in turn, and the corresponding bit is set to 1.

[0053] For example, assuming that the existing keyword set is: {"Secret", "Sensitive", "Military",

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 discloses an efficient keyword filtering method for FPGA (Field Programmable Gate Array) implementation, and belongs to the technical field of network security. According to the method, a keyword set is preprocessed, rapid matching can be carried out by adopting a method for carrying out hash calculation on keywords and to-be-searched data, the parallel capability of an FPGA is fully utilized, a parallel search engine is realized on the FPGA, rapid keyword search with a certain false alarm rate is carried out, and according to a feedback result searched by the FPGA, the keyword set can be quickly matched with the to-be-searched data. According to the technical scheme, accurate keyword matching searching is carried out without storing keywords on the FPGA, the parallel searching capability of FPGA hardware can be fully utilized, the characteristic that the host and the FPGA are large in off-chip storage capacity can also be utilized, the overall processing performance can reach 40 Gbps or above, and the method has the advantages of being high in searching speed, small in space consumption, free of storing the keywords and the like.

Description

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

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
Owner 无锡宏创盛安科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products