-
公开(公告)号：US20240193440A1
公开(公告)日：2024-06-13
申请号：US18079407
申请日：2022-12-12
发明人： Harsh SHRIVASTAVA , Sarah PANDA , Liang DU
IPC分类号： G06N5/022
CPC分类号： G06N5/022
摘要： The present disclosure relates to utilizing a dynamic knowledge graph enrichment system to dynamically and automatically maintain knowledge graphs shared between groups of user identifiers with up-to-date findings and discoveries. In particular, the dynamic knowledge graph enrichment system changes static shared knowledge graphs into dynamically evolving ones utilizing statistical guarantees that automatically incorporate new edge connections into a shared knowledge graph after verifying the reliability and veracity of the proposed edge connections being offered. Further, the dynamic knowledge graph enrichment system facilitates forming new connections between different shared knowledge graphs that previously went undetected by flexibly facilitating exploration over multiple knowledge graphs and providing synergistic knowledge graph updates.
-
公开(公告)号：US20220398274A1
公开(公告)日：2022-12-15
申请号：US17347097
申请日：2021-06-14
发明人： Robin ABRAHAM , Leo BETTHAUSER , Ziyao LI , Jing TIAN , Xiaofei ZENG , Maurice DIESENDRUCK , Andy Daniel MARTINEZ , Min XIAO , Liang DU , Pramod Kumar SHARMA , Natalia LARIOS DELGADO
IPC分类号： G06F16/35 , G06F16/45 , G06F16/44 , G06F16/383 , G06F16/483 , G06N3/08
摘要： The present disclosure relates to generating a complex entity index based on a combination of atomic and deep learned attributes associated with instances of a complex entity. For example, systems described herein generate a multi-dimensional representation of entity instances based on evaluation of digital content associated with the respective entity instances. Systems described herein further generate an index representation in which similarity of entity instances are illustrated and presented via an interactive presentation that enables a user to traverse instances of an entity to observe similarities and differences between instances of an entity that have similar embeddings to one another within a multi-dimensional index space.
-
公开(公告)号：US20200159860A1
公开(公告)日：2020-05-21
申请号：US16192688
申请日：2018-11-15
发明人： Liang DU , Ranjith NARAYANAN , Robin ABRAHAM , Vijay MITAL
摘要： Applying AI models to a search using a search engine for a user. A method includes receiving user search input at a search engine user interface. The search input is used with the search engine to obtain first search results. One or more AI models are applied to the first search results to obtain additional search data. The additional search data is searched to identify additional search results. Using the additional search results, a subset of second search results are identified from the first search results while filtering out other search results from the first search results. At least a portion of the second search results are provided to the user in the user interface while preventing the other search results that were filtered from being displayed in the user interface, such that a user at the user interface has the second search results returned as results.
-
公开(公告)号：US20240087683A1
公开(公告)日：2024-03-14
申请号：US17932212
申请日：2022-09-14
发明人： Pramod Kumar SHARMA , Andy Daniel MARTINEZ , Liang DU , Robin ABRAHAM , Saurabh Chandrakant THAKUR
摘要： A machine learning model trained with a triplet loss function classifies input strings into one of multiple hierarchical categories. The machine learning model is pre-trained using masking language modeling on a corpus of unlabeled strings. The machine learning module includes an attention-based bi-directional transformer layer. Following initial training, the machine learning model is refined by additional training with a loss function that includes cross-entropy loss and triplet loss. This provides a deep learning solution to classify input strings into one or more hierarchical categories. Embeddings generated from inputs to the machine learning model capture language similarities that can be visualized in a cartesian plane where strings with similar meanings are grouped together.
-
公开(公告)号：US20230207071A1
公开(公告)日：2023-06-29
申请号：US17565404
申请日：2021-12-29
发明人： Tingting ZHAO , Ke JIANG , Liang DU , Robin ABRAHAM
CPC分类号： G16H10/20 , G06N5/04 , G06V30/19147 , G06V30/19173
摘要： Disclosed herein is a model flow that generates eligibility criteria for a clinical trial based on eligibility criteria associated with a protocol title of the trial. Unlike standard black-box generation models, the techniques disclosed herein leverage existing knowledge to enhance the title. The enhanced title also acts as an intermediate between the title and the generated criteria clauses, enabling explicit control of the generated content as well as an explanation of why the generated content is relevant. The resulting workflow is knowledge-grounded, controllable, transparent, and interpretable.
-
公开(公告)号：US20230067528A1
公开(公告)日：2023-03-02
申请号：US17410701
申请日：2021-08-24
发明人： Zhihui GUO , Pramod Kumar SHARMA , Liang DU , Robin ABRAHAM
摘要： Systems and methods are provided for building and training machine learning models configured to generate in-domain embeddings and perform multimodal analysis inside the same domain. The models include a first encoder trained to receive input from one or more entities represented in a first modality and to encode the one or more entities in the first modality, such that the first encoder is configured to output a first set of embeddings. The models also include a second encoder trained to receive input from one or more entities represented in the second modality and to encode the one or more entities in the second modality, such that the second encoder is configured to output a second set of embeddings. The models also include a projection layer configured to project the first set of embeddings and the second set of embeddings to a shared contrastive space.
-
公开(公告)号：US20190354872A1
公开(公告)日：2019-11-21
申请号：US16022596
申请日：2018-06-28
发明人： Vijay MITAL , Liang DU , Ranjith NARAYANAN , Robin ABRAHAM
摘要： The improved exercise of artificial intelligence by providing a systematic way fora computing system to interface with output from AI models. To do this, the computing system obtains results of an input data set being applied to an AI model. The results are then refined based characteristic(s) of the AI model and perhaps the input data set. Based upon characteristic(s) of the AI model and perhaps the input data set, interface element(s) are identified that can be used to interface with the refined results. The interface element(s) are then communicated to an interface element that interfaces with the refined results. The interface element(s) may include, for instance, operator(s) or term(s) that may be used to query against the refined results and/or an identification of visualization(s) that may be used to present to a user results of queries against the refined results.
-
公开(公告)号：US20240296294A1
公开(公告)日：2024-09-05
申请号：US18144802
申请日：2023-05-08
发明人： Shima IMANI , Harsh SHRIVASTAVA , Liang DU
IPC分类号： G06F40/40 , G06F16/332
CPC分类号： G06F40/40 , G06F16/3325 , G06F16/3329
摘要： Disclosed are techniques for an AI system with a large language mode (LLM) with improved accuracy and reliability in solving mathematical problems. An initial query is transformed into a template query by replacing the original input values with variables. Multiple prompts are sent to the LLM, each being different from one another, and contextually related to the template query. Multiple results are responsively received from the LLM, each result including an analytical expression to solve the mathematical problem. Each of the expressions is evaluated using a numerical evaluation tool with variables of the expression being assigned a common set of randomly sampled values. A consensus is achieved when the evaluated expressions satisfy a consensus condition, such as when all outputs match consistently over N experiments or trials. After the consensus condition is reached, the original inputs are evaluated with one or more of the expressions, and the solution is output.
-
公开(公告)号：US20230074788A1
公开(公告)日：2023-03-09
申请号：US17469751
申请日：2021-09-08
发明人： Yao LI , Liang DU , Robin ABRAHAM
IPC分类号： G06F16/901 , G06F16/93 , G06F16/903 , G06K9/00 , G06N3/02 , G06N5/02 , G06N20/00
摘要： Machine learning to predict a layout type that each of a plurality of portions of a document appears in. This is done even though the computer-readable representation of the document does not contain information at the granularity of the prediction to be made that identifies which layout type that each of the plurality of document portions belongs in. For each of a plurality of the portions, the machine-learning system predicts the layout type that the respective portion appears in, and indexes the document using the predictions so as to result in a computer-readable index. The index represents a predicted layout type associated with each of the plurality of portions of the document. Thus, the index can be used to search based on position of a searched term within the document.
-
公开(公告)号：US20190354632A1
公开(公告)日：2019-11-21
申请号：US15985415
申请日：2018-05-21
发明人： Vijay MITAL , Liang DU , Ranjith NARAYANAN , Robin ABRAHAM
摘要： The improved exercise of artificial intelligence. Raw output data is obtained by applying an input data set to an artificial intelligence (AI). Such raw output data is sometimes difficult to interpret. The principles defined herein provide a systematic way to refine the output for a wide variety of AI models. An AI model collection characterization structure is utilized for purpose of refining AI model output so as to be more useful. The characterization structure represents, for each of multiple and perhaps numerous AI models, a refinement of output data that resulted from application of an AI model to input data. Upon obtaining output data from the AI model, the appropriate refinement may then be applied. The refined data may then be semantically indexed to provide a semantic index. The characterization structure may also provide tailored information to allow for intuitive querying against the semantic index.
-
-
-
-
-
-
-
-
-
搜索结果
21 条记录 (耗时 0.016 秒)
