Automated log analysis is crucial to ensure the high availability and reliability of complex systems. The advent of Large Language Models (LLMs) in Natural Language Processing (NLP) has ushered in a new era of language model-driven automated log analysis, garnering significant interest. Within this field, two primary paradigms based on language models for log analysis have become prominent. Small Language Models (SLMs) (such as BERT) follow the pre-train and fine-tune paradigm, focusing on the specific log analysis task through fine-tuning on supervised datasets. On the other hand, LLMs (such as ChatGPT) following the in-context learning paradigm, analyze logs by providing a few examples in prompt contexts without updating parameters. Despite their respective strengths, both models exhibit inherent limitations. By comparing SLMs and LLMs, we notice that SLMs are more cost-effective but less powerful, whereas LLMs with large parameters are highly powerful but expensive and inefficient. To tradeoff between the performance and inference costs of both models in automated log analysis, this article introduces an adaptive log analysis framework known as AdaptiveLog, which effectively reduces the costs associated with LLM while ensuring superior results. This framework collaborates an LLM and an SLM, strategically allocating the LLM to tackle complex logs while delegating simpler logs to the SLM. Specifically, to efficiently query the LLM, we propose an adaptive selection strategy based on the uncertainty estimation of the SLM, where the LLM is invoked only when the SLM is uncertain. In addition, to enhance the reasoning ability of the LLM in log analysis tasks, we propose a novel prompt strategy by retrieving similar error-prone cases as the reference, enabling the model to leverage past error experiences and learn solutions from these cases. We evaluate AdaptiveLog on different log analysis tasks, Extensive experiments demonstrate that AdaptiveLog achieves state-of-the-art results across different tasks, elevating the overall accuracy of log analysis while maintaining cost efficiency. Our source code and detailed experimental data are available at https://github.com/LeaperOvO/AdaptiveLog-review .

The data generated by the structured electronic medical records is helpful for mining and extracting medical data, and it is an effective way to make effective use of valuable data resources. However, the hospitals have accumulated a large number of unstructured data in electronic medical records, which cannot be effectively searched, resulting in serious waste of resources. In this paper, we study the problem of extracting attribute values from the unstructured text in electronic medical records. By observing intestinal cancer diagnostic texts, our attributes have two categories - discriminative attributes and extractive attributes, which use the text classification and the sequence labeling to tackle attribute values extraction problems. For discriminative attributes, we firstly divide the text into sentences/segments as instances. Secondly, we fine-tune the pre-trained word embedding to capture domain-specific semantics/knowledge. Thirdly, we also use an attention mechanism to select the most important instance for different attribute extractors. Finally, multi-tasking learning is used to share useful information to get better experimental results. For extractive attributes, we propose a novel model to get attribute values, including the BiLSTM layer, the CNN layer and the CRF layer. In particular, we use BiLSTM and CNN to learn text features and CRF as the last layer of the model. Experiments have shown that our method is superior to several competitive baseline methods.

Key frames play an important role in video abstraction. Clustering is a popular approach for key-frame extraction. In this paper, we propose a novel method for key-frame extraction based on dominant-set clustering. Compared with the existing clustering-based methods, the proposed method dynamically decides the number of key frames depending on the complexity of video shots, produces key frames in a progressive manner and requires less computation. Experimental results on different types of video shots have verified the effectiveness of the method.