111 results about "Input language" patented technology

The embodiment of the invention provides a multi-modal fusion entity retrieval enhancement generation method and device, and the method comprises the steps: carrying out the blocking and adaptive text extraction of multi-modal data in an offline stage, obtaining the text block data corresponding to each modal data, extracting the entity and relation of the text block data according to a language model, constructing an entity triple, and carrying out the segmentation and adaptive text extraction of the entity triple. Fusing the entity triad with the text block data to obtain an offline knowledge graph, and constructing a data index; in the present stage, a query statement of a user is received, text block data most similar to the query statement are retrieved in a knowledge graph through a data index, after entity aggregation is carried out on the retrieved text block data, the text block data are reordered according to retrieval scores, an entity aggregation result is obtained, entity ordering is carried out according to the entity aggregation result, and the entity aggregation result is obtained. By means of the multi-modal retrieval method and device, the efficiency and accuracy of multi-modal retrieval can be improved.

The present application discloses a test code repairing method applied to a code development platform. The method comprises: obtaining a test code corresponding to a source code, and then executing the test code to obtain execution information of the test code, wherein the execution information comprises abnormal stack tracking information output during execution of the test code; on the basis of the execution information, performing fault localization on the test code to obtain location information of a faulty code; on the basis of the location information of the faulty code, extracting context information, wherein the context information comprises at least one of a faulty test case, a fault description, or the faulty content; and inputting a prompt constructed on the basis of the context information into a language model and performing inference, so as to obtain a first repaired code. The method is used to perform fault localization in light of the execution information, extract the context information on the basis of the location information of the faulty code, and, on the basis of the context information, generate accurate and complex repaired code via an advanced language model, thereby adapting to various complex fault scenarios and improving repair efficiency and accuracy.

A data processing system and method include receiving a set of documents to summarize a trend across the set of documents, inputting the set of documents into an information extraction model, executing the information extraction model to extract a first plurality of text segments, determining a second plurality of text segments based on the first plurality of text segments, determining a third plurality of text segments from the second plurality of text segments, generating a compressed representation of the set of documents from the third plurality of text segments to include in a prompt for a language model, inputting the prompt into the language model, and executing the language model to generate the summary based on the prompt for the set of documents.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of mechanical arm grabbing, financial science and technology, medical treatment and health and the like, and discloses an action sequence generation method and device, equipment and a medium. Respectively generating a visual feature vector and a language feature vector by using a visual encoder and a language encoder; fusing the visual feature vector and the language feature vector to obtain a multi-modal fusion feature, and inputting the feature into a language model for processing to generate an initial action strategy; an action sequence is generated according to an initial action policy by an action decoder integrated with a language model. According to the method, by fusing vision and language information, self-adaptive decision making in a complex task environment is realized, and the adaptive capacity of the system in a dynamic change environment is enhanced; and through multi-modal feature fusion, the operation precision and the generalization ability of the system are effectively improved.

The invention discloses a singular value decomposition-based multi-modal task fine tuning method for enhancing a routing function, which comprises the following steps of: mapping input language and visual features from a high-dimensional space to a low-rank space by using a PEFT method, performing singular value decomposition on language features in the low-rank space, performing routing function alignment through a tensor after efficient reconstruction, and performing multi-modal task fine tuning on a multi-modal task based on a singular value decomposition-enhanced routing function. And finally, after the low-rank space is recovered to the original dimension again, performing residual connection with the original language features, and outputting the features. According to the method, singular value decomposition is applied to language features before a routing function, a low-rank dominant mode of the language features is extracted, the alignment precision of vision and language features is enhanced, interference of high-dimensional noise is eliminated, and meanwhile calculation efficiency and model stability are kept. Routing calculation is carried out through the reconstructed tensor, key information in the features can be better extracted and aligned, and therefore the precision and effect of feature alignment are improved. The method is suitable for VL tasks such as visual questioning and answering and image description generation, and model performance can be obviously improved.

The invention discloses an integrated circuit design Verilog code generation method and device based on a large language model, equipment and a medium, and relates to the technical field of computers, and the method comprises the steps that semantic analysis is conducted on an input language of an integrated circuit user side through the large language model, and a target constraint set is determined based on an obtained performance index set and through a regular expression; a candidate architecture scheme is generated by utilizing thinking chain technology reasoning, the candidate architecture scheme is predicted by utilizing an XGBoost regression model, and a target architecture scheme is determined based on an index prediction result and the candidate architecture scheme by utilizing a non-dominated sorting genetic algorithm; and determining an initial Verilog code based on the target architecture scheme and a preset code template library, and performing code style conversion on the initial Verilog code based on a code style feature corresponding to the integrated circuit user side to obtain a target Verilog code. And the efficiency and availability of integrated circuit design are improved.

The invention discloses an active optical alignment method based on a local lightweight language model, and particularly relates to the technical field of precision installation and adjustment, comprising the following steps: extracting image indexes and platform attitude information through image acquisition, constructing a unified input format, verifying and inputting the language model; generating a six-degree-of-freedom pose adjustment strategy and a credibility score; the strategy is executed by the platform control device after being verified by a preset criterion; scoring is performed again after execution, and whether a feature posture is recorded or error compensation is triggered is judged according to a scoring result, so that subsequent input and strategy generation are optimized, and alignment precision and stability are improved; according to the method, the data consistency is guaranteed through a unified input format and a verification mechanism, the alignment precision is improved in combination with a dynamic scoring strategy, and the stability and fault tolerance of the system are enhanced by introducing a feature attitude recording and error back-filling mechanism, so that a strategy generation and execution process with high reliability, high adaptation and high robustness in an active optical alignment task is realized.

Disclosed herein are method and system aspects for translating between a sign language and a target language and presenting such translations. For example, a method receives input language data and translates the input language data into sign language grammar. The method retrieves phonetic representations that correspond to the sign language grammar from a sign language database and generates coordinates from the phonetic representations using a generative network. The phonetic representations are digital representations of individual signs created through manual input of body configuration information corresponding to the individual signs. Further, the method renders an avatar that moves between the coordinates. In another example, a bidirectional communication system allows for realtime communication between a signing entity and a non-signing entity.

The invention discloses a reference multi-target tracking method based on language decoupling and fine-grained multi-modal feature alignment, and relates to a computer vision technology. The method comprises the following steps: A, giving a training data set containing a video sequence and language description; b, inputting the video sequence in the step A into a backbone network to extract visual features, and inputting language description into a language model to extract text features; and C, performing multi-modal alignment and fusion through a cross attention mechanism according to the visual features and the language features extracted in the step B. And D, decoupling the language features extracted in the step B into local description and a motion state. And E, inputting the refined features extracted in the step C and the local description extracted in the step D into a static semantic enhancement module to extract target information. And F, associating the current frame target obtained in the step E with the existing trajectory by using a Hungary matching algorithm. G, inputting the matched target features in the step F and the motion state in the step D into a motion perception alignment module to enhance the target recognition capability; the tracking performance of the method is improved.

The invention provides a work order clustering and theme extraction method, system and device and a medium, and belongs to the technical field of natural language processing and data mining. The method comprises the steps of obtaining original work order data, performing data cleaning, extracting work order abstracts from the original work order data by using a text abstract generation technology according to preset abstract constraints, and generating an abstract set; inputting the work order abstract into a language model, generating a semantic vector of a preset dimension, constructing a vector index through an FAISS library, and converting the abstract set into a set of numerical vectors; clustering the numerical vectors by using an improved K-means algorithm, and outputting K groups of work order digests with balanced quantity; for each group of work order abstracts, screening representative abstracts based on text similarity; extracting keywords from the representative abstracts by adopting a keyword extraction technology, and generating a keyword list of each group of work order abstracts; and for the keyword list of each group of work order abstracts, generating a theme tag by combining keywords.

The invention discloses a test code repairing method which is applied to a code development platform and comprises the steps that a test code corresponding to a source code is obtained, then the test code is executed, execution information of the test code is obtained, and the execution information comprises abnormal stack tracking information output when the test code is executed; then error positioning is conducted on the test code according to the execution information, position information of an error code is obtained, context information is extracted according to the position information of the error code, and the context information comprises at least one of an error test case, error description or error content; and inputting a prompt constructed based on the context information into a language model for reasoning to obtain a first repair code. According to the method, error positioning is carried out by combining execution information, context information is extracted according to position information of error codes, and based on the context information, more accurate and complex repair codes are generated through an advanced language model so as to adapt to various complex error scenes, and the repair efficiency and accuracy are improved.

The invention discloses a feature fusion optimization-based multi-modal map enhancement retrieval method and a dialogue system. The method comprises the following steps of: respectively carrying out pre-training and fine tuning on a visual model and a language model by utilizing a domain image and text data; constructing a knowledge graph based on the text data in the knowledge base and constructing a vector database containing associated image data; performing semantic analysis and optimization on the original query of the user by using the language model and forming a structured retrieval intention; searching related sub-graphs, text semantic vector information and associated image data based on the search intention; encoding the sub-images into knowledge contexts, inputting the knowledge contexts into a dynamic prompt generator to generate visual prompts, and extracting enhanced visual features from the associated image data through a visual model; and inputting the subgraph, the text semantic vector information and the enhanced visual features into a language model for collaborative reasoning, and generating and outputting a final answer. According to the method, deep fusion and accurate retrieval of multi-modal knowledge can be realized, and the accuracy and efficiency are remarkably improved.

The invention relates to the technical field of automatic driving, in particular to a multi-mode automatic driving training method based on a DeepSeek training framework. Comprising the following steps: reading multi-view camera images and text instructions of a DriveLM-nuScenes data set, and splicing the images according to a look-around layout to form panoramic representation; performing zooming, normalization and standardization processing on the panoramic image to obtain an image tensor; performing marking processing on the text instruction, inserting an image placeholder and a dialogue role mark, and structuring text input representation; dimensionality alignment, position code addition and cross-modal attention fusion of vision and text marking sequences are realized through a multi-modal alignment module, and multi-modal embedding representation is generated; and inputting the embedded representation into a DeepSeek language model to generate a decision text through autoregression, and taking the cross entropy loss with a mask as an optimization target. According to the method, the problems of insufficient multi-view fusion, weak modal alignment and the like in the prior art are solved, the cognitive reliability and the decision interpretability in a complex scene are improved, and vehicle-mounted edge deployment is adapted.

To provide an information processor for supporting the generation of a sentence using a language model.SOLUTION: The above problem is solved by an information processing device including chatbot control means for asking one or more questions to an end user according to a scenario and acquiring an answer to the question, prompt generation means for generating a prompt in which one or more variable portions included in a template prompt are replaced with an answer corresponding to the variable portion, and sentence data acquisition means for acquiring sentence data generated by inputting the generated prompt to a language model, in which the chatbot control means displays the acquired sentence data on a user terminal operated by the end user.SELECTED DRAWING: Figure 3

Described herein is a language-based camera parameter generation system that sets the parameters for the ISP and / or control of a digital camera from a user-input language prompt, such that the capture and processing of the ISP matches the visual quality described by the language prompt. The camera operator provides a language-based description, such as a short sentence (for example, “dreamy and awe-inspiring image that is well exposed”) before taking a photo, and the system will generate the control and ISP parameters such that captured image or video will have visual qualities that match the language prompt. This gives a new way for the camera user to control the visual quality of the image and enables new creative expressions. The benefit of a language-based approach is that it is more natural and intuitive than manually setting numerical values.

The invention provides a training sample generation and model training method and device, a storage medium and a product. The training sample generation method comprises the steps of obtaining original dialogue materials of a target application scene, wherein the original dialogue materials comprise a model input question and a model output reply; performing named entity recognition on the model output reply, and extracting N target entities, N being greater than 0; on the basis of the N target entities and the incidence relation between the different target entities, the original dialogue material is disassembled into a plurality of question and answer pairs, so that each question and answer pair corresponds to one target entity or a group of target entities with the incidence relation; the multiple question and answer pairs are input into a language model, so that the language model conducts logic consistency detection on all the question and answer pairs and outputs corresponding detection results, and the detection results comprise inconsistent conclusions and combination of magic view types or consistent conclusions; and based on each question and answer pair and the corresponding detection result, generating a first training sample used for training the magic vision detection model.

The embodiment of the invention provides a data processing method and a legal problem processing method.The data processing method comprises the steps that a problem to be processed is determined, and the problem to be processed is input into a language generation model; in the language generation model, reference data corresponding to the to-be-processed question is obtained from the question and answer retrieval database, the question answer of the to-be-processed question is generated, the reference data is any target question and answer pair stored in the question and answer retrieval database, and the reference data is any target question and answer pair stored in the question and answer retrieval database. The target question and answer pair is obtained by performing text processing on a plurality of different types of initial text data, the plurality of different types of initial text data are determined from a plurality of data sources, and the plurality of different types of initial text data correspond to the same target field.

A test case generation method. The method comprises: acquiring a structured rule for a first application programming interface (API) and a natural language description for the first API; querying a domain-specific language (DSL) database on the basis of the natural language description for the first API to obtain a query result, wherein the query result comprises at least one of: a DSL sample where a natural language description part matches the natural language description for the first API, a DSL error correction example, or a DSL syntax; constructing a prompt on the basis of the query result, the natural language description and the structured rule; and inputting the prompt into a language model to generate a target DSL code, wherein the target DSL code is used for testing the first API, or is used for generating a test case for performing integration testing on the first API and a second API. In the method, a DSL sample, an error correction example, and a syntax are dynamically matched from a DSL database to generate a highly controllable and structured context, and a test case is generated by means of language model inference on the basis of the context, thereby integrating unit testing and integration testing, and reducing repeated development.

The present disclosure relates to a model prompt generation method and device, electronic equipment and computer readable medium, belonging to the field of artificial intelligence. The method comprises: obtaining a corresponding input question vector according to an input question text; matching the input question vector with text segment vectors in a vector database to determine a plurality of candidate text segment vectors; the text segment vectors in the vector database include a plurality of parent segment vectors, and child segment vectors in each parent segment vector; converting the candidate text segment vectors into corresponding candidate text segments, and filtering and processing according to parent-child relationship data between each candidate text segment to obtain a target text segment; obtaining a language model prompt used in a language model according to the input question text and the target text prompt. The present disclosure can make the content of the language model prompt more reasonable and sufficient, thereby improving the correct rate of the language model in the private knowledge field.

The disclosure provides a language model training method and a translation method for multilingual translation, and relates to the technical field of artificial intelligence, in particular to the fields of natural language processing, deep learning, machine translation and the like. The language model training method for multilingual translation comprises: obtaining a sample text pair, the sample text pair comprising a first text in a first language and a second text in a second language, the semantics of the first text being the same as the semantics of the second text; inputting the first text and the second language into a language model to obtain a first translated text in the second language output by the language model; inputting the second text and the second language into the language model to obtain a second translated text in the second language output by the language model; determining a loss value of the language model based on a first difference between the first translated text and the second text and a second difference between the first translated text and the second translated text; and adjusting parameters of the language model based on the loss value.

The system appropriately generates output language signals that represent linguistic information related to the vehicle's operation. [Solution] The signal generation system comprises a first arithmetic unit configured to generate a route signal representing the planned route of a vehicle based on sensor signals output from sensors mounted on the vehicle, and a second arithmetic unit configured to generate an output language signal representing language information to be provided to the occupants by inputting an input language signal representing the content of speech by the vehicle occupants in natural language form into a trained language model. At least one of the first and second arithmetic units has a conversion unit that converts at least one of the sensor signal and the signal generated based on the sensor signal into a route data signal expressed in a format that can be input into the trained language model. The second arithmetic unit generates a route language signal relating to the planned route as an output language signal based on the route data signal.

The invention discloses an electric power system risk management and control method, device and system and a storage medium. The method comprises the following steps: receiving inquiry data which is input by a user and is related to electric power system risk management and control; inputting the inquiry data into a language model for semantic analysis to obtain a semantic vector, and inputting the semantic vector into a classification model to determine a target intention category of the user; extracting scene keywords related to a power grid system from the target intention category, mapping the scene keywords into a preset professional knowledge base to obtain retrieval fields, performing retrieval in the professional knowledge base based on the retrieval fields to obtain risk knowledge fragments related to risk management and control, and performing risk management and control on the risk knowledge fragments. Filling the risk knowledge fragment into a preset answer template to generate a risk management and control scheme; and managing and controlling the risk prevention and control process of the power system based on the risk management and control scheme. The accuracy of risk management and control of the power system can be improved based on the professional knowledge base.

A training data generation method for training an artificial neural network model including inputting a first prompt related to at least one first object in a specific context into a language model, acquiring first text data related to the at least one first object output from the language model, acquiring a first image related to the specific context, generating, based on at least one of the first text data or the first image, arrangement information related to an arrangement of the at least one first object for the first image, generating, based on at least one of the first text data, the first image, or the arrangement information, a second image in which the at least one first object is arranged in the first image, and outputting the second image.

The invention discloses a knowledge hypergraph-based power system query method and related equipment, and the method comprises the steps: obtaining a description document and a data file of a power system, and generating a power system knowledge graph; analyzing each independent data card in the data file, converting each independent data card into a corresponding hyperedge, connecting the hyperedge with all entity nodes related to the corresponding card to form a power system multivariate relation knowledge hypergraph, and converting the hypergraph into a power system bipartite graph for storage; when a query instruction is received, entity nodes matched with key entities in the query instruction and hyperedge nodes related to semantics are retrieved in the bipartite graph of the power system, and after a context subgraph is constructed through bidirectional expansion, a language model is input to generate a query feedback result. The problems that a traditional mode is poor in expansibility, information is lost, retrieval is low in efficiency and answers are fuzzy are solved, and construction efficiency, association integrity, retrieval performance and query accuracy are greatly improved.

A method including advancing a computer-automated workflow a step. The method also includes retrieving an image template including a computer renderable data structure for rendering an image. The image template is specific to the step. The method also includes retrieving a prompt template including a prompt data structure for input to a language model. The prompt template is specific to the step. The method also includes combining the image template and the prompt template to generate a combined prompt. The method also includes executing a language model with the combined prompt to generate an output of the language model. The method also includes rendering the output to generate a rendered data structure.

The embodiments of this application relate to the field of computer model-based image processing, and particularly to a system and method for processing brain images. The system for processing brain images provided by the embodiments of this application utilizes an encoder and a large language model to encode electromagnetic signals acquired by the signal acquisition unit into words and perform deep semantic processing on these words. This allows the image decoder to process the processed words and obtain an image. The encoder, the large language model, and the image decoder work together to transform electromagnetic signals into accurate brain images. The method for processing brain images provided by the embodiments of this application compresses electromagnetic signals and extracts effective information to obtain words, ensuring signal authenticity and reducing data volume. By inputting the words into a large language model for processing, the brain image obtained after decoding the processed words is more accurate.

A data processing method is applied to the field of artificial intelligence and comprises the steps of obtaining a first text; determining a plurality of first retrieval results related to the first text according to the first text; obtaining a first quality evaluation of each first retrieval result; and obtaining a reply text of the first text through a language model according to the first text, the plurality of first retrieval results and the first quality evaluation. According to the method, the quality of the retrieval result can be evaluated, the quality evaluation result is used as the input of the language model, when the language model processes the first text and the retrieval result, the quality evaluation of the retrieval result can be known, the quality of the retrieval result is sensed by the language model, and the user experience is improved. According to the method, the language model can generate the reply by using the information of the retrieval result more effectively, so that the generation effect of the language model is improved.

The application provides a fault positioning method and device, electronic equipment and storage medium. The method comprises: acquiring a plurality of sensor parameters and alarm information of a target device; determining abnormal sensor information in the plurality of sensor parameters; performing splicing processing on the abnormal sensor information and the alarm information to obtain an alarm statement; inputting the alarm statement into a language model to obtain fault component information of the target device, wherein the language model is obtained by training alarm statements and corresponding component information. The language model in the above scheme can determine fault component information according to sensor parameters and alarm information of a target device, and the efficiency of positioning fault components is higher than relying on artificial experience.

The invention discloses a wind turbine blade defect small sample classification method based on a double-language prompt optimization adapter, and the method aims at the types of cracks, erosion, peeling, caving, normality and the like, and achieves the precise recognition under the condition of extremely few labeled samples. According to the method, a double-language text encoding module comprising a CLIP English text encoder and a Chinese RoBERTa encoder is constructed, and Chinese features are aligned to a CLIP feature space through a lightweight projection network to realize cross-language consistent representation. For the difficult categories, a category specificity prompt optimization process is provided, the difficult categories are screened based on initial evaluation, a multi-semantic-dimension candidate template is constructed, and a positive contribution prompt set is formed by contribution degree filtering of a leave-one-out method, so that the difficult category distinguishing ability is improved. Further generating unified category text features by adopting a double-language feature fusion strategy (gating self-adaption or fixed weight fusion), and combining a TIP-Adapter cache mechanism to complete training of small-sample-free adaptation by performing hyper-parameter and weighted fusion on zero-sample similarity output and cache matching output, so as to obtain a training result; meanwhile, a language perception strategy is introduced to automatically adjust Chinese and English branch weights according to an input language so as to give consideration to efficiency and stability.

A method includes inputting an input text sequence into a language model to generate a plurality of speech samples; applying one or more preference models to the plurality of speech samples to generate a set of preferred samples and a set of non-preferred samples; applying direct performance improvement optimization to preference data associated with the set of preferred samples and the set of non-preferred samples to generate optimized samples; and training the language model based on the optimized samples.