142 results about "Input language" patented technology

The methods, systems, and computer networking apparatuses described herein enable language models to receive input (e.g., a query or a request) from a user or application, and without any additional training data or instructions, determine to generate a function call based on the received input from the user and generate the function call based on the determination. In some embodiments, a language model may further access an external tool or application to request an output as a response to the generated function call. The disclosed methods, systems, and networking apparatuses improve the technical field by incorporating language model capabilities within the function calling process, and allowing for function-related information to be provided to a language model via input received in any number of formats or types, including structured or unstructured input, language or non-language input, or any combination thereof.

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.

The invention discloses a knowledge distillation-based Hainan dialect speech recognition optimization system, which comprises a data preprocessing module for processing Hainan dialect speech data and Hainan dialect text data, and outputting to obtain an MFCC speech feature sequence, a labeled text label and Hainan dialect text data; the teacher model module comprises an RNN (Recurrent Neural Network) language model, a CNN (Convolutional Neural Network) language model and a Transform language model, dialect text data are respectively input into the RNN language model, the CNN language model and the Transform language model, and a soft label and a middle layer feature are obtained through dynamic temperature regulation; the student model training module is used for performing knowledge distillation and parameter adjustment and optimization on a student model according to the MFCC voice feature sequence, the marked text tag, the soft tag and the middle layer feature; the output module is used for performing voice recognition on the Hainan dialect by using the student model after knowledge distillation and parameter optimization to obtain a recognition result; moreover, the trained student model is small in size and low in calculation complexity, and an accurate recognition result can be obtained finally.

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 knowledge base self-learning evolution method and system and a storage medium. The method comprises the steps that a to-be-processed text containing entity mention is received, candidate standard entities are recalled in a knowledge graph, and enhanced knowledge sub-graphs are adaptively extracted based on ambiguity scores of the candidate standard entities; encoding a to-be-processed text, the enhanced knowledge sub-graph and the like into cue words, and inputting the cue words into the language model to obtain a standardized result; when the confidence coefficient of the standardization result is lower than a threshold value or any candidate standard entity is not recalled, a generative probe instruction containing a predefined ontology mode is submitted to the language model, and the language model is guided to generate structured candidate knowledge; calculating knowledge entropy based on the candidate knowledge; pushing the candidate knowledge to a man-machine collaborative auditing queue according to the knowledge entropy; and executing transaction-based atomization write-in operation on the candidate knowledge which is checked and confirmed, so as to realize a self-learning closed loop of the knowledge base. According to the method, a credible and automatic self-learning closed-loop method is constructed, so that the knowledge base can be dynamically evolved.

The invention discloses an e-commerce platform marketing content matching method based on semantic reasoning, and the method comprises the following steps: S1, generating a multi-hop interaction chain according to a user historical behavior sequence; s2, gradually performing mask prompt and inputting a language model, performing interactive chain thinking semantic reasoning, and generating a recommended candidate content set; s3, calculating the matching degree of the candidate content and the context semantics, and determining an initial sequence; s4, iteratively updating the sorting weight by adopting a secretary bird optimization algorithm; s5, adjusting the sorting of the candidate contents according to the sorting weight; and S6, updating a language model reasoning strategy and optimization algorithm parameters according to user feedback. According to the invention, the accuracy of the recommended content and the user experience are 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 relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a response optimization method, device, equipment and medium based on term consistency. Inputting a language model to generate a candidate response; performing term consistency comparison and context consistency comparison on the candidate responses to generate a sorting result; term anomalies and safety risks in the candidate responses are detected, and the sequence is adjusted according to a detection result; and outputting the target response and obtaining feedback information, and updating the term knowledge base according to the feedback information. Through linkage of the term knowledge base and the security policy, response term consistency, semantic coherence and security are ensured, the knowledge base is dynamically updated based on feedback information, and reliability and specialty of a language model in multiple rounds of dialogues are achieved.

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.

The invention provides an LLM-based vulnerability risk repairing method, device and equipment and a storage medium, the method comprises the steps that scanning data scanned by a vulnerability scanner is processed by a first cue word generator and then input into an LLM language large model, a repairing suggestion is generated, and the scanning data comprises a request packet sent by the vulnerability scanner and a response packet received by the vulnerability scanner; finding a code snippet with the vulnerability according to a code path where the vulnerability is located, processing the code snippet through a second cue word generator, inputting the processed code snippet into the LLM language large model, and generating a repair code; and formatting the repair suggestion and the repair code to generate a vulnerability repair scheme. According to the method, multi-dimensional features of vulnerability codes are deeply analyzed by using an LLM language large model, vulnerability risk points in the codes are accurately positioned, more targeted repair suggestions and repair codes are provided, it is ensured that a generated repair scheme is matched with an actual code scene, the vulnerability risk repair cost is reduced, and the repair efficiency is improved. And a more efficient and reliable vulnerability risk management solution is provided.

The invention relates to the technical field of artificial intelligence, in particular to a large model generalization method and device for Cantonese, a terminal and a storage medium, and the method comprises the steps: converting each original text in a predetermined language type data set into an original Cantonese text; inputting the original Cantonese text and the corresponding truth tag into a language model for reinforcement learning training to obtain a Cantonese large model and a newly added Cantonese text; constructing a Cantonese database; when a to-be-recognized text is input into the Cantonese large model, Cantonese vocabularies in the to-be-recognized text are recognized, and a Cantonese database is retrieved according to the Cantonese vocabularies to obtain a target Cantonese text; and outputting a recognition result based on the to-be-recognized text and the target Cantonese text. According to the method, the number of Cantonese data sets is greatly increased, the linguistic features of Cantonese are better captured, a retrieval enhancement generation mechanism is utilized, a large amount of knowledge in a Cantonese database except for the aspect of user questioning is referred, and the recognition accuracy is improved.

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.