5 results about "Contextual similarity" patented technology

The application relates to a robot control method based on a multimodal large model and relates to the technical field of robots. The method comprises the following steps: acquiring multimodal input data and extracting context features; analyzing semantic features and extracting a core instruction intention; extracting constraint conditions from user instruction text to obtain key constraint conditions; recursively decomposing a complex instruction into an atomic task sequence according to the core instruction intention and the key constraint conditions to generate a time-space continuous action planning candidate set; outputting cross-modal correlation features in a joint embedding space; calculating the context similarity of the cross-modal correlation features and historical interaction data features; screening an optimal action planning candidate with the highest similarity from the action planning candidate set based on the context similarity; and controlling the robot to move based on the optimal action planning candidate. The application can improve the decision-making capability of the robot in a complex scene.

This application provides a method for protecting prompt words in large models based on differential privacy. By constructing a perturbation mapping table, differential privacy perturbation is applied only to the first token encountered in a multi-turn dialogue, and the mapping relationship is stored. Subsequent repeated tokens directly reuse the historical perturbation results, thus avoiding the accumulation of privacy budget with the increase of dialogue turns. Simultaneously, an attention-based context-aware utility function is combined to integrate the static embedding similarity of tokens with dynamic context similarity to maintain semantic consistency across turns. Finally, a two-stage bucketing index mechanism is adopted, first bucketing candidate tokens according to utility, and then fine-sampling within the selected buckets, effectively mitigating the long-tail effect under large vocabulary and improving the stability of perturbation selection. This application achieves a balance between privacy protection strength and semantic usability in multi-turn dialogues, and only requires perturbing the input prompt words without accessing the model's internal architecture, making it suitable for black-box large language model inference scenarios.

Disclosed is an artificial intelligence-based matchmaking system (100) for suggesting compatible user profiles on a graphical user interface (GUI). The system (100) includes a user device (102) comprising an input unit adapted to receive one or more input data from a user and an output unit communicatively coupled with a server (104) through a communication network (106). The server (104) includes a processing unit configured to receive and store profile inputs comprising textual, categorical, or behavioral data such as occupation, interests, and intent parameters, process the profile inputs to generate a prioritized list of candidate profiles based on semantic correlation, contextual similarity, and inferred intent, display the candidate profiles sequentially on the GUI, receive gesture inputs indicating interest or skip actions and update a dynamic parameter-weighted preference model to adaptively reorder subsequent profiles in real-time. The present disclosure also relates to a method (200) for artificial intelligence-based matchmaking system (100).

The application discloses a kind of knowledge graph pipeline multi-strategy entity disambiguation incremental alignment method and system.The method normalizes candidate entity and generates fingerprint, to block key in bucket generation candidate entity pair, comprehensive similarity is obtained by fusing character, semantic embedding and structural context similarity, when comprehensive similarity is not lower than class correlation threshold, similar graph is constructed and representative entity is determined, only incremental alignment is executed to change fingerprint set and historical fingerprint index, and output incremental change set and conflict details.Compared with full amount pairwise comparison, the application reduces the scale of candidate pair and improves the processing efficiency in continuous updating scenario.

This invention relates to the field of deep learning technology, particularly to a Transformer optimization method and system based on a token graph-based query propagation mechanism. The method comprises an input processing layer, a dynamic graph construction layer, a propagation control layer, a computational optimization layer, a feedback adjustment layer, and an output integration layer. This invention captures the contextual similarity or relationship between tokens by constructing a token-graph (dynamic or static structure) and introduces a stochastic propagation of Q vectors mechanism. Only the seed token generates a complete Q vector, while the remaining tokens generate approximate Q vectors through graph propagation. Furthermore, K and V are projected only onto the central node, and a local error control feedback module is included. This solves the problems of computational resource constraints, memory limitations, and accuracy stability in long sequence processing of Transformers. It provides a practical and feasible technical path for its application in complex tasks such as long document understanding, multi-turn dialogue, and code generation.