NOTA, INC.

Provided are a method and apparatus for compressing a neural network model by using device characteristics. The method includes: obtaining the neural network model that is executed by a device; adjusting a target number of output channels of a target layer included in the neural network model, based on an arithmetic intensity obtained from a roofline model and a latency characteristic of a staircase pattern of the device; and compressing the neural network model such that the number of output channels of the target layer is equal to the adjusted target number of output channels.

Disclosed is a method for providing a benchmark result, which is performed by a computing device. The method may include obtaining a first input data including an inference task and a dataset. The method may include determining a target model which is a subject of a benchmark for the inference task and at least one target node at which the inference task of the target model is to be executed. The determined target model corresponds to an artificial intelligence-based model, and the benchmark for the inference task of the determined target model is performed at the at least one target node based on the dataset. The method may include providing the benchmark result obtained by executing the target model at the at least one target node.

Provided is a quantization method of an artificial neural network model including a plurality of layers. The quantization method includes identifying an outlier from among activation elements output from a first layer among the layers of the artificial neural network model, determining and regularizing a weight to be regularized among weights applied to the first layer based on relevance with the identified outlier, and quantizing the artificial neural network model after the quantization.

A method for determining a target device to execute an artificial intelligence (AI) model, performed by a computing device, is disclosed. Upon receiving the AI model from a user terminal, the method extracts model-related information, including runtime, layer, memory, and file size details. The process begins with a first check, sending a signal to a device database to retrieve information about a specific device. It determines whether the model is executable on that device by comparing its runtime information with the model's requirements. If executable, a second check evaluates whether the device's resources—such as memory, file size capacity, and layer support—meet the model's resource conditions. Based on the results, the device may be added to a candidate list of recommended devices for executing the AI model. This ensures optimal device selection for AI model execution.

Provided is an inference method using a vision-language model (VLM). The VLM is pretrained to sequentially generate inference results for consecutive inputs according to an input prompt, and the inference method includes caching information associated with the input prompt acquired during an operation for generating a first inference result for a first input among the consecutive inputs to the VLM, maintaining the cached information after the first inference result is generated; and generating a second inference result for a second input following the first input among the consecutive inputs to the VLM, based on the cached information.

A method for providing a user interface to replace abnormal traffic data on a computing device is disclosed. The method involves displaying target traffic data for a site where a replacement task will occur. Upon user input specifying a replacement period, the interface shows performance data for AI models mapped to the site and candidate inference results generated by these models. The user selects a target inference result or AI model, and the interface displays the replacement result. The interface includes a verification screen with a chart highlighting the replacement period and a list detailing performance data and replacement results for sub-periods. Each sub-period replacement is linked to corresponding AI model performance, using models pre-stored and mapped to the site. This may ensure accurate and detailed data replacement guided by AI model performance and user input.

Disclosed is a method for providing an alarm based on a behavior of a driver in a driver monitoring system. The method includes receiving a first image corresponding to the driver within a vehicle, generating first model output information which indicates possibility that an anomaly which compromises safety of the driver exists in the first image, from the first image, by using an artificial intelligence model. The method includes generating a first anomaly primary prediction result indicating whether the anomaly exists in the first image by comparing the first model output information with a first threshold, generating a first anomaly secondary prediction result by performing a first voting using the first anomaly primary prediction result and determining an anomaly alarm corresponding to the first image by performing a second voting using the first anomaly secondary prediction result.

Disclosed are a method and system for changing a structure of a deep learning model based on a change in resolution of input data. The method of changing a structure of a deep learning model may include generating, by the at least one processor, a plurality of input data having different resolution by performing various resolution changes on input data having given resolution, performing, by the at least one processor, inference on each of the plurality of generated input data through a deep learning model, checking, by the at least one processor, the size of a feature map output by each of layers included in the deep learning model while the inference is performed, and changing, by the at least one processor, the structure of at least one of the layers based on the checked size of the feature map.

According to an embodiment of the present disclosure, a method for providing an artificial intelligence-based model, performed by a computing device, is disclosed. The method includes providing a candidate model list comprising a plurality of candidate models which are artificial intelligence-based models. The method includes determining a target model to be converted or benchmarked, based on a first user input on the candidate model list. The method includes providing a candidate node list comprising a plurality of candidate nodes. The method includes determining a target node to be converted or benchmarked, based on a second user input on the candidate node list. The method includes converting the target model into a model supportable by the target node, based on information of the determined target model and information preset on the target node.

Disclosed is a method and system for readjusting granularity of search results according to complexity of a query for generative search. An inference method may include extracting a length-by-length phrase from a document retrieved for a query of a user; determining a ranking of the length-by-length phrase in consideration of complexity of the query; and configuring a prompt for input to a generative language model based on the determined ranking. Here, the ranking of the length-by-length phrase may be determined such that a relatively long phrase has a higher ranking according to an increase in the complexity of the query.