26 results about "Generative process" patented technology

The invention discloses a question and answer interaction method, device and equipment based on artificial intelligence and a medium, and relates to the technical field of artificial intelligence in the professional service fields of finance, insurance, medical treatment, banking and the like, and the method comprises the steps: segmenting a historical dialogue into segments with coherent themes, and constructing the segments into memory units; generating a semantic embedding vector and a time decay weight for each unit to form a memory bank; retrieving related memory units from a memory bank based on user query, comprehensive semantic relevance, theme consistency and time decay weight; the query and related units are combined into a context input generative language model, and a topic consistency constraint is applied during the generation process to generate a topic consistent reply. By optimizing the memory granularity and enhancing the memory representation and timeliness, multi-dimensional accurate retrieval and constraint generation are realized, and the system improves the accuracy, coherence and service consistency of question and answer interaction.

A method for suggesting prompts on a page of a workspace includes receiving an input and displaying a prompt block configured to initiate a generative process to create in-block content in response to the input. The prompt block is embedded as an in-page object on the page. The method includes causing a large language model (LLM) system to create a set of suggested prompts. Each prompt includes instructions configured to create generative content of a respective type by the LLM system. The set of suggested prompts is created based on in-page text content or a relative location of the prompt block on the page. The method includes displaying the set of suggested prompts as a set of control items of the workspace. Each of the set of control items is selectable to input as a prompt for generating content based on existing content of the workspace.

This invention belongs to the field of computer vision technology, specifically a tree-structured video description generation method based on perceptual grammar knowledge. This invention explicitly utilizes semantic information inherent in language, using dependency structure analysis tools to transform sequential sentences into a syntax tree structure. By analyzing the connections between parent and child nodes in the tree, the dependency grammar structure within the sentence is explicitly modeled. A perceptual context attention network is used to model the contextual information generated along different paths during the generation process. Simultaneously, reinforcement learning and iterative generation training methods are introduced during the training phase to further improve model performance. Qualitative and quantitative experiments demonstrate that the model has the ability to generate more accurate and semantically richer descriptions.

The invention discloses a self-adaptive writing method and system based on support style feature extraction and template generation, and particularly relates to the technical field of self-adaptive writing. According to the method, the writing system has the active recognition and selection capability on the target style in the generation process, style drifting caused by context accumulation in long text and multi-round generation is avoided, meanwhile, a fixed semantic structure and a variable expression mode are combined based on a template constraint model automatically generated in a dominant style interval, and the method is more efficient and efficient. On the premise of ensuring logic integrity and expression normalization, the flexibility and adaptability of the writing process are improved, and a closed-loop self-adaptive regulation and control mechanism is formed by performing literary and physical feature consistency evaluation on the generated text and dynamically adjusting the template slot position weight.

The present invention relates to a device and method for generating context-aware motion using text and emotion embeddings. An electronic device according to one embodiment of the present invention includes a memory and a processor connected to the memory, and the processor receives input information including a text prompt instructing the content of a character's action and emotion information to be assigned to the action for generating three-dimensional motion from a user terminal, and vectorizes the received text prompt and the emotion information, respectively, to generate a text embedding for the content of the action and an emotion embedding that determines the nuance of the action, and generates a motion sequence based on the text embedding using a Generative AI model, but reflects the emotion embedding as a condition of the generation process to assign an emotional context to the character's action, and can generate the motion sequence with the assigned emotional context as final motion data.

The invention discloses an AI teaching interaction method based on multi-modal emotion perception and generative strategy optimization, and the method comprises the steps: generating a comprehensive emotion state vector in a robust manner through multi-modal emotion analysis with uncertainty estimation and time sequence fusion based on attention; contexts such as teaching content semantics and cognitive load are combined; a generative model with strategy elements as a vocabulary is utilized, a composite interaction strategy sequence is generated through dynamic combination, and cognitive load constraint is carried out in the generation process; optimization is carried out through reinforcement learning integrating off-line evaluation and safety exploration, and strategy rehearsal is optionally carried out through a digital twin model. Deep understanding of student states and highly personalized and safe strategy generation and optimization in a complex and real teaching scene are realized, and the intelligent level and teaching effect of an AI teaching system are significantly improved.

The invention discloses an ancient language machine translation method for syntactic perception and knowledge enhancement, and belongs to the technical field of natural language processing. Aiming at the difficulties of complex sentence patterns and scarcity of historical knowledge of ancient Chinese, three innovation modules are designed: firstly, a dynamic dependency syntactic analysis module explicitly models an ancient Chinese syntactic structure by utilizing probability analysis and a graph network; secondly, a retrieval enhancement generation module accurately extracts related knowledge fragments from the high-quality ancient language corpus, and semantic comprehension is enhanced; and finally, the stream grammar constraint decoder fuses the source language syntax and the target language generation process through a double-stream mechanism and a stream mechanism, and loyalty and smooth modern text output is realized. The three modules are deeply fused, so that the accuracy and interpretability of ancient language translation are effectively improved, and a reliable technical path is provided for ancient book digitization.

The invention discloses a multi-modal large language model generation method and system based on visual information backtracking, and belongs to the technical field of artificial intelligence and multi-modal information processing. The implementation method comprises the following steps: 1, acquiring an image token sequence and a text token sequence; 2, obtaining the real attention of the model on the input image; screening the ROI set by using overlapping penalty; 3, generating statement sequence token prediction distribution and obtaining hierarchical normalized entropy; 4, when the normalized entropy of the hierarchy is greater than an entropy threshold and the screened ROI set injection is triggered for the first time, performing feedforward network residual injection; 5, the ROI set is injected into a feed-forward layer of the multi-modal large language model, visual information in the model is updated, and then attention-enhanced visual features are obtained; compared with the prior art, the method has the advantage that the phenomenon that the image is inconsistent with the fact in the image-based generation process due to strong priori brought by text corpora in the pre-training process of the model is solved.

The application relates to the technical field of space automatic layout generation and generation process control, and discloses a multi-room consistency layout generation method and system based on generation process constraint modulation. The method comprises the following steps: acquiring space structure information of a target residential space; constructing a multi-room generation state model; constructing and updating a multi-room consistency constraint set in a layout gradual generation process; performing consistency constraint modulation processing on a candidate layout action in a current generation step, so that each room shares a consistency control condition in the generation stage; and outputting a multi-room overall layout scheme satisfying the multi-room consistency constraint set. Compared with the prior art in which each room is independently generated and then subjected to rule checking or scoring screening to realize consistency, the application cooperatively controls consistency relationships such as layout density, furniture scale and space blank proportion in the generation stage, so that the structural rationality, stability and generation efficiency of the multi-room overall layout result are improved.

The invention relates to the technical field of image generation, in particular to a severe weather image generation method based on a generative diffusion model, and the method comprises the steps: obtaining the multi-scale features of an original image through ViT; carrying out statistics on the real severe weather image set to obtain prompt basic information; performing instance sampling, scene construction processing and scene description processing on the prompt basic information to obtain scene information, and performing scene description processing on the scene information by adopting a large language model to generate a text prompt; converting the text prompt into text embedding, and enabling the text embedding to be consistent with the multi-scale feature dimension; performing multi-step diffusion on the text embedding and multi-scale features by adopting a diffusion model, updating a text prompt and updating the corresponding text embedding by adopting the LLM module in each step of diffusion process, and finally obtaining a severe weather image; according to the method, the controllability and the accuracy of the diffusion model generation process can be improved.

This provides an information provision method that enables the easy generation of optimal landscape plans by utilizing generation AI. [Solution] The information provision method performed by the information provision device 3 includes: a question reception process that receives question information D1, which is construction target information relating to the construction target of the landscaping work; a prompt generation process that generates prompt information D3 that instructs the generative artificial intelligence model 20 to output answer information D4, which is plan information indicating a plan for carrying out landscaping work on the construction target, based on the question information D1; and an answer provision process that provides the answer information D4 output from the generative artificial intelligence model 20 by inputting the prompt information D3 to the generative artificial intelligence model 20.

The invention belongs to the technical field of artificial intelligence, and relates to an AI-based performance analysis optimization method and related equipment thereof, and the method comprises the steps: collecting multi-source isomerized performance analysis data from a target system; analyzing and identifying system performance defects; inputting the system performance defects into the generative large language model, and generating a system performance optimization scheme according to system performance defect repair or optimization data in the generative large language model; and analyzing the system performance optimization scheme, and performing performance optimization on the target system. In the process of data acquisition, data analysis and subsequent system performance optimization scheme generation, an AI processing component is fully utilized, so that a large amount of manpower consumption is saved, manual analysis steps are reduced, and the accuracy of an analysis result can be ensured as much as possible. When the performance analysis optimization method is applied to system performance data analysis, especially in a financial business scene with a large and miscellaneous business data volume, the analysis efficiency can be remarkably improved, and business performance abnormity can be found in time.

This invention relates to the field of natural language generation technology, specifically to a text generation system and method based on visual topology and color orthogonal modulation. In this invention, a graph neural network is used to calculate node association weights and generate node state vectors, ensuring that character interactions and plot progression in the generated text always adhere to strict topological constraints, significantly improving narrative coherence and structural integrity. By introducing a support vector machine to calculate the correlation between content vectors and style vectors and adjusting the update direction when limits are exceeded, precise control of the emotional tone and linguistic style of the generated content is achieved without interfering with the core semantic expression, avoiding the risks of repeated deadlocks and semantic drift in the generation process. Furthermore, by using style-controlled context vectors and entity-consistent context vectors to expand the paths of candidate lexical sequences and accumulate evaluation values, repeated loops and logical deadlocks in the generation process are avoided, thus producing digital media content with both high logical rigor and rich stylistic expressiveness.

The invention discloses a GEO anti-fraud method and system based on multi-source contact information conflict modeling, and mainly relates to the technical field of generative artificial intelligence. Comprising the following steps: extracting a structured triple from multi-modal content associated with a result returned by a generative engine; constructing a cross-modal heterogeneous conflict graph by taking each triple as a node; giving an initial confidence coefficient based on a source authority identifier to each node in the conflict graph, executing belief propagation of conflict perception on the conflict graph, iteratively updating the confidence coefficient of each node, and performing fraud judgment based on the confidence coefficient of each contact way under the same brand obtained after propagation; and based on a fraud judgment result, carrying out dynamic intervention on a retrieval enhancement generation process of the generative large model, and reducing contact ways judged to be fraud from appearing in a finally generated answer. The method has the beneficial effects that high-precision fraud identification can be realized by dynamically inhibiting a propagation path of mutually exclusive false information.

This invention discloses a multimodal creative content generation method and system. The method includes: receiving multimodal input data such as text, images, and audio and converting it into feature vectors; calculating the cross-modal correlation between features of each modality using a self-attention mechanism and performing weighted fusion to obtain a unified multimodal fusion representation; generating creative content based on this representation through a generator network; collecting multi-dimensional feedback information from user ratings, market testing, or sentiment analysis; dynamically adjusting the weights of each modality in subsequent fusion processes based on this feedback, and outputting optimized creative content. This invention achieves deep cross-modal information understanding and fusion through a self-attention mechanism and introduces a dynamic feedback loop, enabling the creative content generation process to have adaptive optimization capabilities, significantly improving the relevance, diversity, and market adaptability of creative content.

The invention provides a cultural relic interactive repair method and system, and the method comprises the steps: carrying out the on-site three-dimensional scanning of a damaged cultural relic through an augmented reality terminal, so as to obtain a three-dimensional geometric model, surface texture information and spatial position coordinates of the damaged cultural relic, and constructing a cultural relic prior knowledge base; generating constraint conditions corresponding to the damaged cultural relics according to a cultural relic prior knowledge base, adopting a constraint-driven three-dimensional generative model, and taking the three-dimensional geometric model and the surface texture information as input; in the generation process, sampling constraint conditions for verification and guidance so as to generate a plurality of restoration hypothesis schemes conforming to the constraint conditions in parallel, and calling a large language model to automatically extract basis literatures and reference examples of each restoration hypothesis scheme so as to generate restoration reason elaboration; and on the basis of the spatial position coordinates, the restoration scheme and the restoration reason are elaborated and superposed on the damaged cultural relic through an augmented reality technology, so that restoration of the damaged cultural relic is completed. The cultural relic repairing efficiency can be effectively improved.

This invention discloses a GEO anti-fraud method and system based on multi-source contact conflict modeling, primarily relating to the field of generative artificial intelligence technology. It includes: extracting structured triples from multimodal content associated with results returned by a generative engine; constructing a cross-modal heterogeneous conflict graph using each triple as a node; assigning an initial confidence level to each node in the conflict graph based on its source authority identifier, and performing conflict-aware confidence propagation on the conflict graph, iteratively updating the confidence level of each node; and determining fraud based on the confidence levels of contact methods under the same brand obtained after propagation; and dynamically intervening in the retrieval enhancement generation process of the generative large model based on the fraud determination results to reduce the appearance of contact methods judged as fraudulent in the final generated answers. The beneficial effect of this invention is that it can achieve high-precision fraud identification by dynamically suppressing the propagation paths of mutually exclusive false information.

This invention discloses a semantically guided conditional flow matching generative recommendation method, comprising: generating user profile text based on user information using a pre-trained large language model, and obtaining user semantic embedding vectors through a text embedding model, pre-computing and storing them as a user semantic embedding matrix; constructing a behavior-guided Bernoulli prior distribution based on the interaction frequency of items in the training data; constructing a conditional flow matching network, injecting the user semantic embedding vectors as conditions into the flow matching generation process; training the conditional flow matching network using a random mask interpolation method, with the training objective being to predict the user's actual interaction vectors; and generating a recommendation score vector by gradually denoising the user's historical interactions during the inference phase. This invention achieves an effective fusion of LLM semantic knowledge and flow matching generation model, exhibiting significant advantages in sparse data scenarios.

(12) INTERNATIONAL APPLICATION PUBLISHED UNDER THE PATENT COOPERATION TREATY (PCT) (19) World Intellectual Property Organization International Bureau (10) International Publication Number (43) International Publication Date WO 2025 / 096028 A1 08 May 2025 (08.05.2025) WIPOIPCT (51) International Patent Classification: (72) Inventors: LU, He; 2300 Harrison Street, San Francisco, G06F 40 / 10 (2020.01) G06N 20 / 00 (2019.01) California 94110 (US). SCALES, Jordan; 2300 Harrison G06F 40 / 166 (2020.01) Street, San Francisco, California 94110 (US). VARMA, At- ul; 2300 Harrison Street, San Francisco, California 94110 (21) International Application Number: (US). PCT / US2024 / 038250 (74) Agent: SIITONEN, Anni et al.; P.O. Box 1247, Patent Pro- (22) International Filing Date: curement, Seattle, Washington 98111-1247 (US). 16 July 2024 (16.07.2024) (81) Designated States (unless otherwise indicated, for every (25) Filing Language: English kind of national protection available): AE, AG, AL, AM, (26) Publication Language: English AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CV, CZ, DE, DJ, DK, DM, (30) Priority Data: DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, 63 / 594,524 31 October 2023 (31.10.2023) US HN, HR, HU, ID, IL, IN, IQ, IR, IS, IT, JM, JO, JP, KE, KG, 18 / 408,429 09 January 2024 (09.01.2024) US KH, KN, KP, KR, KW, KZ, LA, LC, LK, LR, LS, LU, LY, 18 / 408,449 09 January 2024 (09.01.2024) US MA, MD, MG, MK, MN, MU, MW, MX, MY, MZ, NA, 18 / 408,454 09 January 2024 (09.01.2024) US NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, 18 / 408,479 09 January 2024 (09.01.2024) US RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, ST, SV, SY, TH, (71) Applicant: NOTION LABS, INC. [US / US]; 2300 Harri- TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, WS, son Street, San Francisco, California 94110 (US). ZA, ZM, ZW. (54) Title: PROVIDING GENERATIVE ARTIFICIAL INTELLIGENCE (AI) CONTENT BASED ON EXISTING IN-PAGE CON- TENT IN A WORKSPACE 300 Compan. / / Al bio. Share is 305 AI Blocks 306 Al blocks are placed like ordinary Notion blocks, but contain as part of their metadata a prompt to a large language model. By default, the blocks display their intent (e.g. Summary this page) and a button to do SO. When the result of the large language model appears, the block updates to be a "container" of the AI output, with the ability to edit the prompt and re-run... + # "= Summarize this page with AI 302 Generate 304 309 308 Link The AI feature provides advantages such as displaying AI output at a specific position in the page and WO 2025 / 096028 A1 FIG. 3A (57) Abstract: A method for creating in-block content presented in a block on a page of a workspace. The block is configured to initiate a generative process to create in-block content of a particular type. The method includes determining a selection of in-page content based on a location of the block relative to the in-page content and the particular type of in-block content. The method can include causing a generative function to create generative content of the particular type based on the selection of the in-page content. The method can further include populating a block area to present the generative content. [Continued on next page] 20 26 20 54 06 08 J ul 2 02 6 0 8 J u l 2 0 2 6 W O 2 0 2 5 / 0 9 6 0 2 8 A 1 W I P O I P C T P C T / U S 2 0 2 4 / 0 3 8 2 5 0 2 0 2 6 2 0 5 4 0 6 U S M A , M D , M G , M K , M N , M U , M W , M X , M Y , M Z , N A , ( 5 4 ) T i t l e : P R O V I D I N G G E N E R A T I V E A R T I F I C I A L I N T E L L I G E N C E ( A I ) C O N T E N T B A S E D O N E X I S T I N G I N - P A G E C O N - 3 0 0 i s 3 0 5 3 0 6 + # A I 3 0 2 3 0 9 3 0 8 W O 2 0 2 5 / 0 9 6 0 2 8 A 1 F I G . 3 A

The application discloses a video sign language question and answer method, system, device and storage medium, which are one-to-one corresponding solutions, wherein, in the solutions, a sign language recognition and translation technology utilizes self-supervised pre-training technology to enhance the representation ability of a model, realizes sign language video translation, fully utilizes training data, and improves recognition accuracy; and a large language model and knowledge retrieval technology are utilized to perform generative question and answer under the constraint of a knowledge base, while a user's intention is understood through multiple interactions, context is maintained, and intelligent conversation under a complex task is completed; in addition, in a sign language generation process, a first step is to convert a text into a gloss conforming to a sign language word order, and a second step is to convert the gloss into an action sequence and drive a digital person; in this step, an action smoothing and transition generation technology is used to process the action sequence of the sign language word, reduce the shaking problem of the action, and obtain a more smooth action sequence for driving the digital person.

One example method includes receiving, such as by a virtual assistant for example, input from a user, such as a query, using the input to identify sources in a RAG (Retrieval Augmented Generation) database, selecting, from the sources, excerpts with information deemed responsive to the user input, performing an auto-regressive generation of trustworthy content, based on the information contained in the excerpts, post-processing the trustworthy content, and, returning the post-processed trustworthy content to the user.

The application provides an interactive repair method and system for cultural relics, which comprises the following steps: through an augmented reality terminal, in-situ three-dimensional scanning of a damaged cultural relic is performed to obtain a three-dimensional geometric model, surface texture information and spatial position coordinates of the damaged cultural relic, and a cultural relic prior knowledge base is constructed; constraint conditions corresponding to the damaged cultural relic are generated according to the cultural relic prior knowledge base, and a constraint-driven three-dimensional generative model is adopted, with the three-dimensional geometric model and the surface texture information as input; in the generation process, the constraint conditions are sampled for checking and guiding, a plurality of repair assumption schemes conforming to the constraint conditions are generated in parallel, and a large language model is called to automatically extract the basis literature and reference examples of each repair assumption scheme to generate a repair reason statement; through augmented reality technology, the repair scheme and the repair reason statement are superimposed on the damaged cultural relic based on the spatial position coordinates to complete the repair of the damaged cultural relic. The application can effectively improve the repair efficiency of cultural relics.

Aligning generative systems and processes to user preferences is disclosed. A curated dataset that includes question / answer (QA) pairs is generated from a source. The QA pairs include a question, a squashing instruction, and an RPI. The QA pairs are subject to a feedback loop, which may include user input. The QA pairs, when curated, reflect final user preferences. The alignment of a generative system to the final user preferences can be measured and / or tracked using the curated dataset in a repeatable and automated verification operation. The answers generated by the generative system to the QA pairs can be compared with the RPIs to determine a correctness of the answer in the verification method. A cumulative score for all of the QA pairs represents how aligned the generative system is to the final user preferences. This allows modifications to be made to align the generative system with desired user preferences.

A computer-implemented system and method transform text within documents using a generative process that enables automated application of action definitions across multiple document elements while maintaining user control. For each element in a document, the system identifies an action definition and applies it to generate output by providing prompts to a large language model. The system manifests generated outputs to users for review and, upon approval, revises corresponding elements based on approved outputs. This enables efficient processing of multiple document elements while preserving precise user control over content updates. The system supports various levels of user involvement, from fully automated processing to interactive refinement, allowing users to review outputs before document updates while maintaining coherence and quality. The implementation integrates sophisticated text transformations seamlessly into document creation workflows through systematic identification and application of action definitions, combining the efficiency of automated generation with manual oversight control.