15 results about "Hypothesis" patented technology

This application provides a method for constructing a trustworthy scientific research agent based on an evidence-reasoning-verification chain, belonging to the field of agent construction technology. The method includes: parsing user-input scientific queries using a large language model; constructing a scientific knowledge graph using a high-quality evidence set obtained through formal research question representation retrieval; synthesizing multiple scientific hypotheses based on the high-quality evidence set and the scientific knowledge graph; constructing an integrated constraint reasoning path to output a structured reasoning chain; performing tuple-based processing; aligning and verifying the trustworthiness of the chain with the scientific knowledge graph; and generating a trustworthy reasoning chain as the core content output of a structured scientific report. This application addresses the technical problems in existing technologies where scientific research agents are unverifiable, untraceable, and lack scientific basis, achieving the technical effect of ensuring logical consistency, sufficient evidence, traceability, and academic credibility in the content generated by the scientific research agent.

A method, apparatus, and non-transitory computer-readable medium for generating a hypothesis from a knowledge graph. The method comprises processing the knowledge graph comprising a plurality of fact triples. Each fact triple of the plurality of fact triples comprises two concepts of a set of concepts and one relationship of a set of relationships. Each fact triple is also associated with at least one source. The method further comprises generating the hypothesis from data representing multiple triples, the hypothesis. The hypothesis includes at least one predicted triple having a concept-concept relationship not found in the knowledge graph. The method then outputs at least one source and / or explanation data for the hypothesis.

Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for video coding. In one method, a decoder obtains, for a current chroma block, a non-linear model (non-LM) mode and a linear model (LM) mode, and the LM mode includes a cross component linear model (CCLM) mode and a multi-model linear model (MMLM) mode. The decoder then combines the non-LM mode and the LM mode for a multi-hypothesis- based chroma prediction (MCP) for the current chroma block.

The system according to this embodiment aims to analyze gene expression data, predict disease mechanisms, and generate new research hypotheses. [Solution] The system according to the embodiment comprises an acquisition unit, an analysis unit, a prediction unit, a hypothesis generation unit, a treatment method proposal unit, and a report generation unit. The acquisition unit acquires gene expression data. The analysis unit analyzes the gene expression data acquired by the acquisition unit. The prediction unit predicts the disease mechanism based on the data analyzed by the analysis unit. The hypothesis generation unit generates a new research hypothesis based on the prediction results obtained by the prediction unit. The treatment method proposal unit proposes the optimal treatment method based on the hypothesis generated by the hypothesis generation unit. The report generation unit generates an experimental result as a report based on the treatment method proposed by the treatment method proposal unit.

A method, apparatus, and non-transitory computer-readable medium for generating a hypothesis from a knowledge graph. The method comprises processing the knowledge graph comprising a plurality of fact triples. Each fact triple of the plurality of fact triples comprises two concepts of a set of concepts and one relationship of a set of relationships. Each fact triple is also associated with at least one source. The method further comprises generating the hypothesis from data representing multiple triples, the hypothesis. The hypothesis includes at least one predicted triple having a concept-concept relationship not found in the knowledge graph. The method then outputs at least one source and / or explanation data for the hypothesis.

The invention discloses a multi-agent collaborative scientific hypothesis automatic generation method, and belongs to the field of creative scientific research engineering, and the method comprises the steps: inputting a to-be-researched problem and research background information of the to-be-researched problem into a creative generation agent, so as to obtain a plurality of creative hypothesis texts of the to-be-researched problem; respectively inputting the plurality of creative hypothesis texts into a hypothesis testing agent to obtain evaluation data of each creative hypothesis text under a plurality of evaluation dimensions; and according to the evaluation data of each creative hypothesis text under the plurality of evaluation dimensions, determining a target creative hypothesis text corresponding to the to-be-researched problem from all creative hypothesis texts. Through cooperative work of the creative generation agent and the hypothesis test agent, the problems of insufficient innovation, one-sided evaluation result and incomplete reasoning chain in the automatic hypothesis process are improved, and the overall working efficiency and decision quality of researchers in complex scientific research tasks are improved.

The application relates to the technical field of watershed water environment pollution tracing, and discloses a watershed non-point source pollution accurate tracing method based on deep learning, which comprises the following steps: a generation and verification double-network collaborative framework comprising a pollution source hypothesis generator and a hypothesis verifier is constructed, and a collaborative optimization mechanism of the pollution source hypothesis generator and the hypothesis verifier is established; generation and probability evaluation of pollution source hypotheses are realized; an evidence chain link tracker is constructed to analyze the relationship between pollution source candidate hypotheses and supporting evidence; the relationship between the pollution source candidate hypotheses and the supporting evidence is further analyzed; analysis results of the relationship between the pollution source candidate hypotheses and the supporting evidence are integrated; and the calculation efficiency and the system performance are optimized; the application provides probability evaluation for each pollution source hypothesis through a Bayesian posterior inference framework, quantizes the uncertainty of the tracing results, and provides reliable reliability indexes for decision making.

The present application relates to spaceflight measurement and control technical field, especially relate to a kind of generalized data detection and simplification method, system and equipment for improving the precision of space target positioning, comprising: obtaining the observation data of space target, construct extended Gaussian-Markov model containing potential modeling error, generate multiple hypothesis set by different combination of modeling error parameter;Utilize likelihood ratio test criterion to construct the test statistic between different hypotheses, according to the observation environment requirement self-adaptive selection executes generalized data detection process or generalized data simplification process;Determine the optimal model hypothesis of current observation by multiple hypothesis testing, based on the optimal model hypothesis parameter adaptive estimation is carried out, and the position parameter of space target is solved.This application guarantees high-precision requirement by forward selection strategy, enhances robustness under complex environment by backward elimination strategy, realizes the effective identification and elimination of multiple modeling error, significantly improves the precision and reliability of space target positioning.

A computer-implemented method for determining static occupancy information, comprising the following steps performed by a computer hardware component: determining a plurality of predicted hypotheses based on a plurality of existing hypotheses of static occupancy information; correcting the plurality of predicted hypotheses to obtain predicted and corrected hypotheses based on the measurements; merging the predicted and corrected hypotheses to obtain a merged hypothesis; and trimming at least a portion of the merged hypothesis to obtain a final hypothesis; wherein the method further comprises at least one of the following: during pruning, a hypothesis having a covariance above a predetermined covariance threshold is ignored; and / or during merging, for each of the merged hypotheses, at most two predicted and corrected hypotheses are merged; and / or after trimming, at least one of the measurements is added to the final hypothesis at the location of at least one of the measurements that is not covered by one of the hypotheses.

The invention discloses a potential hypothesis relationship prediction method based on a causal symbol network. The method comprises the following steps: scientific hypothesis variable identification and multi-dimensional causal relationship discrimination; constructing a causal symbol network; hypothesis inspiration heuristic search is carried out; predicting a potential hypothesis relationship; ranking the credibility of the potential hypothesis relationship; according to the method, the mediation and regulation effects can be effectively captured and utilized, so that new hypotheses including the complex mechanisms can be generated, and the method is closer to the scientific problem of the real world; scientific researchers can preferentially pay attention to the assumption which is most likely to be established, and screening and verification time is saved.

A computer implemented method for determining information of static occupancy comprises the following steps carried out by computer hardware components: based on a plurality of existing hypotheses for the information of static occupancy, determining a plurality of predicted hypotheses; based on measurements, correcting the plurality of predicted hypotheses to obtain predicted and corrected hypotheses; merging the predicted and corrected hypotheses to obtain merged hypotheses; and pruning at least a portion of the merged hypotheses to obtain final hypotheses; wherein the method further comprises at least one of the following: during pruning, hypotheses with a covariance above a pre-determined covariance threshold are disregarded; and / or during merging, for each of the merged hypotheses, at most two predicted and corrected hypotheses are merged; and / or after pruning, at least one hypothesis is added to the final hypotheses at a location of at least one measurement of the measurements which is not covered by a hypothesis of the hypotheses.

The application discloses a potential hypothesis relationship prediction method based on a causal signed network, and comprises the following steps: scientific hypothesis variable identification and multi-dimensional causal relationship discrimination; construction of a causal signed network; hypothesis inspiration heuristic search; potential hypothesis relationship prediction; and potential hypothesis relationship credibility sorting. The application can effectively capture and utilize intermediary and regulation effects, thereby generating new hypotheses containing the complex mechanisms and being closer to scientific problems in the real world, and enabling scientific researchers to preferentially focus on the most likely established hypotheses and save the time for screening and verification.

An object of a system according to an embodiment is to efficiently test and verify hypotheses formulated by a generative AI in the real-world.SOLUTION: A system according to an embodiment includes a generation AI, an experimental facility, and an analysis unit. The generative AI makes hypotheses. The experimental set-up experiments the hypotheses raised by the generative AI. The analysis unit analyzes an experimental result obtained by the experimental facility.SELECTED DRAWING: Figure 1

The application discloses a pre-training model fine-tuning and scientific hypothesis information extraction method and device, equipment, medium and product, and relates to the technical field of artificial intelligence, which comprises the following steps: injecting a trainable adapter into a to-be-trained linear layer of a target pre-training model; inputting a sample data set into the target pre-training model, determining sample prompt word information and sample text information through the target pre-training model, and outputting predicted scientific hypothesis information according to the sample prompt word information and the sample text information; determining labeled scientific hypothesis information through the target pre-training model, and training the trainable adapter according to the predicted scientific hypothesis information and the labeled scientific hypothesis information to obtain an updated weight matrix; and obtaining a scientific hypothesis extraction model of the fine-tuned target pre-training model according to the updated weight matrix. The application improves the accuracy and integrity of scientific hypothesis information extraction, and is beneficial to helping researchers quickly refine innovation points in literature and improving subject design efficiency.

An object of a system according to an embodiment is to extract a useful hypothesis from data and provide the customer with the useful hypothesis.SOLUTION: A system includes a collection unit, an analysis unit, a hypothesis generation unit, and a provision unit. The collection unit collects data. The analysis unit analyzes the data collected by the collection unit. The hypothesis generator derives a hypothesis based on the data analyzed by the analyzer. The provider provides the customer with the hypothesis derived by the hypothesis generator.SELECTED DRAWING: Figure 1