5 results about "Memory aid" patented technology

The invention relates to a computer-implemented method (100) for generating a contextual memory aid for a user, comprising at least the following steps: generating (104) a response text (32) for a user request (30) using a language model; generating (106) an environment description (36) from image information (34) of a user environment in which the user request (30) was captured, using a visual language model; generating (108) a keyword (38) from the response text (32) and the environment description (36); generating (110) a memory aid text (40) from the keyword (38), the response text (32), the environment description (36), and the user request (30); generating (112) a memory aid image (42) from the image information (34) and the memory aid text (40); Providing (114) an output signal that displays the memory aid image (42) and the memory aid text (40).The method (100) improves the effectiveness of learning.

This invention relates to the fields of computer vision, text processing, font generation, and adaptive learning, and specifically to an adaptive text display method and system for assisting memory. The method involves inputting text content to be memorized, which can be a text string and its corresponding vector font file, or a rasterized image containing the text content. Based on the input type, auxiliary display elements are generated or acquired to partially replace or cover the original text's visual form. Based on the user's memory proficiency index and / or the semantic features of the text content, several target layout rules are selected from a predefined layout rule library. According to the target layout rules, the original text data and the auxiliary display elements are logically fused to output the desired adaptive memory-assisting display interface. This invention elevates memory-assisting technology from a simple font transformation to a context-aware intelligent interactive interface, breaking the limitations of traditional font technology application scenarios.

A system and method for a cognitive training system is described. The cognitive training method includes generating a standalone sentence for a fact using a large language model (LLM), generating a mnemonic story based on the standalone sentence, and generating a mnemonic story image based on the mnemonic story using a generative artificial intelligence (AI) model. The method further includes assigning a place at a location to the fact based on an input received from a user through a user device in communication with the cognitive training system and rendering a cartoon illustration of the place. The method further includes generating a fact-memory aid associated with the fact that includes a fact component, a mnemonic component, and a place component. A user of the cognitive training system may participate in a game experience provided by a game engine to help remember the details of the fact-memory aid.

The application discloses a memory auxiliary training method based on a voice AI model, which is applied to a flash card learning App. The method is based on the recitation content preset by a user, questions related to the recitation content are obtained or generated by a voice AI model, and the user answers by voice. The AI model processes and analyzes the voice answer of the user, and carries out multi-round dialogue according to the answer result, and guides the user to finally obtain the correct answer. At the same time, the system comprehensively evaluates the performance of the user in the whole question and answer process, and obtains or directly generates the memory degree score of the user by the AI model. The memory degree score is taken as an input to drive the interval repetition memory algorithm (such as the FSRS algorithm) to dynamically adjust the review plan. The method improves the learning interactivity through voice interaction and multi-round questioning, and effectively improves the memory training effect and learning efficiency by combining the memory performance evaluation and the interval repetition algorithm linkage.

A data collection device for attachment to an injection device, such as an injector pen, includes a sensor arrangement to detect movement of a movable component of the injection device relative to the data collection device during delivery of a medicament by the injection device, and a processor arrangement configured to, based on said detected movement, determine a medicament dosage administered by the injection device. The processor arrangement may monitor the time that has elapsed since the medicament dosage was administered, and control a display to show the medicament dosage and elapsed time to provide a memory aid to the user. In an example embodiment, the sensor arrangement includes an optical encoder and the movable component includes a plurality of light barrier formations. The movable component may be a number sleeve that provides a visual indication of a dose programmed into the injection device.