33 results about "Generic knowledge" patented technology

The invention discloses an intelligent policy question-answering method and system based on retrieval enhancement generation and a medium. The method comprises the following steps: constructing a universal knowledge base and a plurality of mutually independent domain knowledge bases; in response to user input, the following steps are executed: performing routing analysis on the user input through a first large language model to generate a structured routing decision; retrieving the general knowledge base to obtain related general knowledge text segments and vectorization expressions thereof; according to the routing decision, a domain knowledge base corresponding to the at least one policy domain identifier is retrieved in parallel, and related policy text fragments corresponding to the at least one domain knowledge base and vectorization expressions of the related policy text fragments are obtained; obtaining an initial answer set based on retrieval results of the general knowledge base and the domain knowledge base; and performing intelligent fusion processing on the initial answer set through a second large language model, and generating and outputting response content. According to the method, the problem of knowledge updating lag is effectively solved, and the accuracy, timeliness and cross-domain specialty of policy questions and answers are improved.

The invention discloses a data scarcity industrial vertical field-oriented knowledge-guided retrieval enhancement generation method, belongs to the technical field of natural language processing and industrial intelligence crossing, and can improve the retrieval accuracy and generation reliability of a large language model in an industrial scene. According to the method, a'sparse vector + dense vector 'mixed knowledge base is constructed, and general knowledge and industrial field texts are fused; after the model generates an initial text, judging whether external retrieval is needed or not through multi-dimensional evaluation token confidence; extracting attention weights for the low-confidence tokens, and screening key tokens to generate a retrieval query; dynamically adjusting the weight of a retriever based on a BGE-M3 model, and optimizing a retrieval result through reordering; the retrieval knowledge is converted into a context with an index, and a prompt template is constructed to generate a correction value iteration calibration text; and finally, optimizing the text format, and generating a structured response meeting industrial requirements. The method solves the problems of lack of professional knowledge of large language models in the industrial field, shallow retrieval and generation fusion, lack of knowledge calibration mechanisms and the like.

The invention provides a method and a device for evaluating a space moving track, and relates to the technical field of artificial intelligence. The invention discloses a spatial movement track assessment method, which comprises the following steps of: generating track-risk image data according to a spatial movement track and a corresponding risk map; inputting the trajectory-risk image data and a pre-constructed task cue word into a pre-constructed visual-language large model to obtain an evaluation result; and transmitting the evaluation result to the target end. According to the technical scheme provided by the embodiment of the invention, the space movement track and the risk map which need to be evaluated are uniformly converted into the image representation as the input of the vision-language large model, and the image representation and the task cue word are input into the vision-language large model; the general knowledge and the cross-modal reasoning ability of the vision-language large model are utilized to finish track evaluation in real time, and the expansibility and the interpretability are good.

The invention discloses a method and device for relieving catastrophic forgetting of a language model, equipment and a storage medium, and relates to the technical field of machine learning. According to the method, linear interpolation is carried out between the pre-training model parameter set and the fine-tuning model parameter set, so that a linear interpolation point of the model can still keep a relatively low loss value when the model learns new task knowledge; then the pre-training model parameter set and the fine-tuning model parameter set are added to form a fusion model parameter set, and the linear interpolation operation only performs one-time simple arithmetical operation after fine-tuning is completed without introducing any additional trainable parameters or changing the model structure, so that when the model adapts to a new task, the model can be quickly and accurately trained. Original general knowledge and performance on old tasks can be reserved to the maximum extent, and meanwhile complexity and expenditure of a model reasoning stage are not increased.

The embodiment of the invention discloses a large model training data generation method, and the method comprises the steps: determining the risk control capability of a target large model and the description of a knowledge field according to a data generation task requirement of a risk control business scene, so as to determine a core concept and a format requirement based on a determined task portrait, the core concept is used for obtaining matched rich knowledge from a universal knowledge base, the format requirement is used for reprocessing the obtained knowledge, and a training sample is obtained by generating a large model to train a target large model for executing risk control business. Through the automatic training sample generation process corresponding to the demand, the existing generation and labeling problem depending on manpower is avoided, the efficiency is improved, the quality difference between samples can be reduced, and the accuracy of the training model is improved.

This invention relates to the field of computer vision technology, providing a method for training a behavior recognition model, a behavior recognition method, and an apparatus. The method and apparatus utilize a frozen pre-trained image-text model (a second video feature extractor and a text encoder) as a general knowledge base to guide a finely tuned student model (a first video feature extractor) with temporal modeling capabilities. A multi-head residual projection network is used for feature-level knowledge transfer and representation alignment. The behavior recognition model trained by this method can accurately understand dynamic behaviors in videos and possesses strong zero-shot reasoning ability (i.e., generalization ability), effectively recognizing behavior categories not seen during the training phase. Furthermore, the entire model framework is clear, training is stable, and the final model exhibits excellent recognition performance for both known and unknown behavior categories under open-vocabulary settings.

The invention discloses an AI model illusion suppression method and system based on retrieval enhancement generation and cue word engineering collaboration, and aims to solve the illusion problem of an existing large language model and the defects that a traditional scheme is high in cost, low in retrieval content utilization rate, universal knowledge conflicts, high in generation randomness and the like. The method comprises the following steps: constructing a high-precision domain vector index database, performing similarity retrieval and noise filtering on user query, generating a multi-level structured cue word containing role definition, thinking chain constraint and the like, dynamically switching a general knowledge shielding or fusion mode based on recall quality, and outputting a final result through multi-path reasoning sampling and consistency verification. According to the method, underlying model parameters do not need to be modified, the illusion rate is remarkably reduced, generated content is factual and accurate, logic coherence and traceability are achieved, deployment is flexible, cost is low, and the method is suitable for factual question and answer scenes in multiple fields such as medical treatment, industry and legal consultation.

An object of a system according to an embodiment is to provide optimal advice to a user.SOLUTION: A system according to an embodiment includes a general-purpose AI, an individual-specialized AI, and a cooperation processing unit. The AI having general-purpose intelligence has general-purpose intelligence. The individual-specific AI learns a conversation record or an action history of the user. The cooperation processing unit generates an optimal advice for the user through cooperation between a AI having general-purpose intelligence and the individual-specialized AI.SELECTED DRAWING: Figure 1

The machine learning in the neural networks module can analyze an annotation and its metadata on the annotation made by a first user on a first computing device to make an embedding regarding the annotation and then cooperate with the persistence knowledge store to store the embedding of the machine learning's understanding of the annotation and its metadata. The delivery module can proactively push a notice regarding a potentially related embedding out to a second user on a second computing device based on a threshold amount of relatedness between one or more factors of i) a first task undertaken by the first user and a second task undertaken by the second user, ii) a role of the first user and a role of the second user, and iii) a subject matter of the embedding to a subject matter of a task undertaken by the second user.

The invention discloses a project management system development method based on low code configuration, relates to the technical field of computer software, and remarkably improves the prediction adaptability and practicability of a project management system in a new project type through a low code configuration and meta-learning fused architecture. A low-code interface allows non-technical users to intuitively configure project parameters, such as a construction period or a risk index, so that a system customization threshold is reduced, and enterprises can quickly respond to innovative project requirements without depending on professional development teams; the meta-learning module uses general knowledge of a pre-training model to complete model adjustment only with a small amount of new data, and overcomes the defect of weak generalization ability of a traditional model in a data sparse scene; the few-sample adaptive mechanism is optimized through internal and external loops, so that the model is ensured to be fast converged while keeping stability, and the training time and resource consumption are reduced; the verification process in the deployment stage enhances the reliability of the system, and the dynamic consistency verification can detect the output deviation of the model in time.

The invention provides an intelligent knowledge question-answering method, device and equipment, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring a plurality of sample sequences and a general knowledge vector set of power vertical domain knowledge, wherein the sample sequences comprise a plurality of word units and time steps; performing word unit prediction analysis on the global context and the local context corresponding to each time step to obtain an alignment loss item; the alignment loss item represents the prediction difference between the global context and the local context; based on the general knowledge vector set, the historical model parameters and the currently updated model parameters, performing calculation to obtain knowledge loss items; the knowledge loss item represents the disturbance of the model parameter change on the general knowledge; based on the sample sequence, constructing a loss function by using a prediction loss item, an alignment loss item and a knowledge loss item, and training to obtain a question and answer model; and predicting the question of the user through the question and answer model to obtain the answer of the question. The answer prediction accuracy can be improved.

The application provides a construction method of a knowledge distillation model suitable for power line fitting detection, comprising the following steps: inputting image data of power line fittings into a basic knowledge distillation model to extract multi-scale feature data; performing redundant compression processing and convolution kernel learning on the multi-scale feature data to obtain a light knowledge vector and fitting detection general knowledge; training the basic knowledge distillation model using the knowledge and teacher-student global knowledge prototypes, and performing differential distillation training on classification heads and regression heads based on objects and information effectiveness respectively in the process to obtain a preliminary knowledge distillation model; and combining a comprehensive loss function to perform end-to-end weighted optimization on a student model in the preliminary knowledge distillation model to obtain an optimized final knowledge distillation model. The application can solve the problems of high model complexity and insufficient adaptability to complex power fitting detection scenes in related art knowledge distillation-based detection methods.

The invention belongs to the field of customer service, and particularly relates to a cross-library question answering system and method based on natural language, and the system comprises a multi-terminal access layer which is used for receiving natural language questions inputted by different types of clients; the intelligent matching core layer is used for performing semantic analysis and intention recognition on an input natural language question, outputting a retrieval instruction containing a region tag and a user intention, and obtaining corresponding knowledge entries from the double-layer knowledge base layer according to the retrieval instruction; the double-layer knowledge base layer comprises a nationwide universal knowledge base and a regional localization database, the nationwide universal knowledge base is used for storing nationwide universal rules, and the regional localization database is used for storing local rules in different regions; and the result output layer is used for integrating the retrieved knowledge entries and returning a final answer to the user through the multi-terminal access layer.

The invention discloses a federal recommendation method based on dual decoupling, which relates to the field of federal learning, and comprises the following steps: performing dual additive decoupling on user embedding and article embedding, and decomposing each representation into a private component reserved locally and a universal component globally shared by a server. Private components capture personalized preferences of users and unique understanding of items, and generic components learn generic knowledge of a group of users and a set of items. When a client is trained locally, each component is updated by minimizing a composite loss function including prediction loss, a component differentiation regular term and a global component rarefaction regular term, and the weight of the regular term is dynamically adjusted. And the client only uploads the universal component update to the server for aggregation. Through a dual decoupling and dynamic regularization mechanism, on the premise of not leaking original data, personalized and common information is effectively separated and learned, the recommendation accuracy and the personalized level are remarkably improved, meanwhile, the communication cost is greatly reduced, and privacy protection is enhanced.

The invention discloses a general knowledge construction method and system based on vertical and horizontal multi-dimensional linkage and a storage medium. The method comprises the following steps: receiving a user operation instruction; acquiring data of longitudinal analysis dimensions (including a basic information layer, a logic association layer and a significance principle layer) and transverse application dimensions (including a resource attribute layer, a rule technique layer and a comprehensive scheme layer) from a domain knowledge graph database according to the instruction; an intelligent linkage mechanism is triggered through a rule engine, and the intelligent linkage mechanism comprises longitudinal internal linkage, transverse internal linkage and cross linkage (including learning-to-use, use-to-learn and reflection backtracking). The system comprises a processor, a memory and a corresponding software module. Through longitudinal and transverse multi-dimensional knowledge organization and intelligent linkage, seamless connection and deep fusion of knowledge from analysis to application, from learning to practice and from problems to principles are realized, and the efficiency and effect of knowledge acquisition, understanding and application are improved.

The invention relates to the technical field of intelligent questioning and answering, and discloses a fire safety knowledge questioning and answering method and a machine questioning and answering system. The method comprises the following steps: performing multi-level semantic analysis on a fire safety problem input by a user to generate structured problem data; matching the data with the dynamically updated fire safety knowledge graph, and intelligently triggering dual-mode response according to a matching result; when the matching succeeds, immediately extracting answer elements; and when the matching is incomplete, starting a deep inference engine to perform intention splitting, and linking a user portrait database to obtain personalized information so as to complement the context. And fusing the general knowledge elements and the personalized information to construct an answer framework, and generating and outputting natural language answers. According to the method, the response efficiency and depth are considered through a dynamic routing mechanism, and active personalized information is utilized for complementing, so that the conversion from universal response to precise customized suggestions is realized, and the practicability and accuracy of a question answering system are improved.

The application discloses a large language model field adaptation fine-tuning method based on knowledge dimension and task dimension collaborative courses, and belongs to the technical field of artificial intelligence and natural language processing. The application comprises the following steps: firstly, a general field training set and a target field training set are constructed, and the general field training set is filtered to remove the field, so as to reduce the field overlap between the two types of corpus; secondly, the general field samples and the target field samples are mapped to a unified semantic space, a plurality of knowledge clusters are obtained through knowledge clustering, and a knowledge specificity score is calculated according to the distance between each knowledge cluster and the general field center, so as to construct a knowledge dimension course from general to professional; then, the target field training samples are annotated for task complexity, and are merged to form three types of task complexity levels, i.e. low, medium and high, so as to construct a task dimension course from shallow to deep; finally, a two-dimensional course sequence is generated by combining the knowledge dimension sorting and the task dimension sorting, an exponential mixing strategy is adopted to dynamically improve the proportion of the target field samples in the training batch, the basic large language model is fine-tuned for field adaptation, and a target field adaptation model is obtained. The application can improve the performance of the target field while effectively maintaining the original general knowledge and reasoning ability of the model, reduce the catastrophic forgetting, improve the training stability and the cross-field application ability.

The present disclosure relates to a natural language processing method and device, a model training method and device, and a storage medium. The present disclosure pre-trains a machine learning model through each triple, so that the pre-trained machine learning model can seamlessly and naturally process various natural language understanding tasks under the machine reading comprehension paradigm. In addition, because the data format used for model training in the pre-training stage is consistent with the data format used for model training in the fine-tuning stage, the pre-training target and the fine-tuning target are the same, thereby enabling seamless connection between the pre-training stage and the fine-tuning stage. After pre-training the model using a large amount of low-cost data, the pre-trained machine learning model can be calibrated using a small amount of target task data, thereby enabling the general knowledge learned in the pre-training stage to be successfully transferred to the fine-tuned model, and ensuring the accuracy of the fine-tuned model.

The invention relates to the technical field of data processing, and particularly provides a general knowledge graph construction method, system and device and a medium, and the method comprises the steps: constructing a general framework based on a modular hierarchical architecture, the general framework comprises a basic data layer, a model service layer and a knowledge service layer, and each layer is decoupled through a standardized interface; field self-adaptive fine tuning is carried out on the core extraction model in the model service layer through a field adapter, and efficient adaptation to a specific field is achieved; based on a dynamic Schema mapping mechanism, generating a knowledge extraction task according to an entity and relationship type defined by a user; calling a core extraction model to execute a task, and extracting domain knowledge from the multi-source heterogeneous data; knowledge is stored in the basic data layer, and derivative knowledge is generated by using an inference model of the model service layer, so that a complete knowledge graph is constructed. According to the method, the construction efficiency and the cross-domain adaptation capability are remarkably improved, and the deployment period is greatly shortened.

The embodiment of the invention provides an intelligent question and answer method and device and a storage medium, and the method comprises the steps: judging the belonging field of a question input by a user, the belonging field comprising a general knowledge field and a professional knowledge field; determining a language model adopted for analyzing the question input by the user according to the field to which the question belongs; and analyzing the user input question according to the language model, and generating a reply to the user input question. The field to which the question input by the user belongs is judged, and the questions in the professional knowledge field and the general knowledge field are analyzed by adopting different models, so that the models can adopt targeted processing strategies according to the field to which the question input by the user belongs, the continuity of multiple rounds of dialogues is ensured, and the user experience is improved. And the solving capability of the model for complex problems is improved.

The invention relates to a model training method, a text processing method and device, electronic equipment and a computer program product, and relates to the technical field of machine learning, the method comprises the following steps: obtaining a training text set, and generating the training text set based on text annotation data of a specified field; obtaining a pre-constructed initial model, wherein the initial model comprises a specific task layer of which the hierarchical structure is higher than that of the basic network layer; model pre-training is conducted on the initial model through the training text set, an intermediate model and intermediate model parameters are obtained, and the intermediate model parameters comprise task layer parameters of the specific task layer; and obtaining target task data, and adjusting the task layer parameters based on the target task data to obtain a target model. According to the method and the device, model training can be carried out based on a small amount of annotation data, the pre-trained model can learn rich general knowledge on the basis of model pre-training, then the model is finely adjusted, the general knowledge can be migrated to a specific task, and effective utilization of the knowledge is realized.

The invention relates to the technical field of information processing, in particular to a man-machine interaction method and system based on a natural language large model, and the method comprises the steps: collecting and preprocessing multi-modal input data, and obtaining multi-modal fusion features; analyzing the initial intention of the user by adopting a time sequence semantic model and capturing a semantic evolution trajectory, capturing the initial emotional state of the user through a multi-mode emotional time sequence model and generating an emotional evolution trajectory, and synthesizing to obtain double-track evolution information; calculating a three-dimensional dynamic weight through a cross-scene three-dimensional linkage feedback adaptation method to obtain a scene adaptation weight set; an emotional language double-drive enhancement mechanism is adopted to obtain accurate intention emotion core information; the personalized knowledge and the general knowledge of the user are adapted through a knowledge adaptation closed-loop mechanism, a customized knowledge adaptation result is obtained, and a multi-modal personalized response is generated in combination with the scene adaptation weight set and the precise intention emotion core information. According to the scheme, through emotional language double-drive enhancement optimization, the accuracy of user intention and emotion recognition is improved.

The application discloses an enterprise knowledge question and answer analysis method and system based on a large model, and belongs to the technical field of natural language processing. The method comprises the following steps: acquiring a candidate text block set; constructing a semantic dimension list, and distinguishing an already covered dimension set from an uncovered dimension set in the semantic dimension list; acquiring a new text block; obtaining a final candidate text block set; constructing an inference prompt text with integrity state annotation, and executing inference to generate a structured answer text. The application introduces semantic dimension recognition based on a user query question and item-by-item coverage checking process after preliminary vector retrieval is completed, solves the problem that a large language model in the prior art cannot perceive material missing and thus calls general knowledge of the large language model to fill in the blank, and thus generates an answer inconsistent with actual business regulations of an enterprise.

This invention provides a model fine-tuning method, apparatus, and device based on adversarial thinking to alleviate knowledge forgetting. It relates to the field of natural language processing (NLP) technology and aims to address the problem of significant forgetting of general knowledge in existing supervised instruction fine-tuning of Small Language Models (SFTs), achieving the effect of learning domain knowledge while preserving as much general knowledge as possible. The method includes: determining a candidate set of adversarial samples from a general dataset based on model fine-tuning samples (samples obtained from an air defense and anti-missile dataset); determining the target adversarial sample with the highest PPL based on the PPL of each adversarial sample in the candidate set; performing adversarial training on the target model's parameters based on the model fine-tuning samples and the target adversarial sample to determine the trained model parameters; and obtaining the fine-tuned target model based on the trained model parameters.

The invention discloses a point cloud processing method and electronic equipment, and relates to the technical field of computers. In the method, an input point cloud is input into a pre-training language model for reasoning, and an output point cloud which corresponds to the input point cloud and is subjected to semantic completion and dense reconstruction is obtained based on the pre-training language model. A priori knowledge fusion mechanism based on a pre-training language model is introduced in the whole point cloud complementing process, so that the model can be used for deeply understanding and reasoning general knowledge of a three-dimensional object and a scene; therefore, the reasonable geometric structure and semantic information of the shielded or unscanned area can be accurately deduced and complemented based on the sparse input point cloud, so that the technical problems that in the prior art, the point cloud complementation precision is insufficient, and the complementation result reliability is low due to the lack of object complete priori knowledge are solved; and the accuracy, integrity and semantic richness of scene completion are improved.

A kind of fusion probability constraint power industry big model training method, system and equipment, method includes introducing dynamic fine-tuning method in the industry of power industry big model continues pre-training phase, for each token configuration dynamic weight, dynamic weight is the prediction probability of power industry big model corresponding label for current token;The propagation gradient of big model is scaled to tend to 1;Reference model is introduced, the prediction probability of reference model is calculated, the prediction probability is set as the initial probability lower limit of dynamic weight, the fixed probability upper limit is set to dynamic weight, the initial probability constraint of dynamic weight is completed;In the process of model training, reference annealing thought, set dynamic constraint lower limit to dynamic weight, gradually weaken the probability constraint of dynamic weight with the advance of training process, until training is completed.The present application can avoid that model produces overfitting phenomenon to power field professional data, and guarantee the general knowledge and instruction compliance ability of model.

The invention discloses a conversation recommendation generation method and system based on a collaborative knowledge graph, and belongs to the field of recommendation and natural language processing. A collaborative knowledge graph containing user entities corresponding to all users, dialogue related entities extracted from dialogue histories of all the users, the relation of any two dialogue related entities in an external general knowledge graph and the dialogue derivative relation of any two dialogue related entities in the corresponding dialogue histories is constructed; the atlas can link preferences of different users through interaction behaviors; on the basis of the collaborative knowledge graph, the similarity between the dialogue related entities mentioned by all the users and the relevance between all the dialogue related entities connected through the dialogue derivative relation and the external relation can be extracted, the users with similar preferences are extracted more accurately, recommendation is carried out based on the assistance of the associated entities provided by the associated users, and the user experience is improved. And the suitability of the entity recommendation and the dialogue response with the user preference is improved.

The invention discloses a large model and lightweight model collaborative harmful information detection method, which specifically comprises a first-stage model processing unit and a second-stage model processing unit, the first-stage model processing unit analyzes input content, screens out suspicious content, and sends the suspicious content to the second-stage model processing unit; the second-stage model processing unit receives the suspicious content and outputs a final judgment result about whether the suspicious content is harmful or not; and the two stage models are cascaded in sequence to work. According to the method, a two-stage knowledge distillation framework is constructed, and knowledge of a large model is divided into two levels of general knowledge distillation and task specific knowledge distillation to be gradually transferred to a student model. In the first stage, general characterization capability is extracted from a large model which is not finely adjusted, in the second stage, harmful content discrimination knowledge is extracted from a large model which is finely adjusted, the staged distillation structure ensures that student models fully draw knowledge essence of the large model in different levels, and unification of wide coverage and high precision is achieved.

The application provides an intelligent question and answer method and system based on a large language model and electronic equipment, and relates to the field of application of the large language model. The method gradually guides the user to perform intelligent question and answer by extracting semantic features in real-time user questions, and comprises the following steps: preferentially matching the semantic features of the real-time user questions in a preset question feature set, so as to directly call out the answer content; when the matching fails, matching the real-time user questions again by using a general knowledge document, so as to generate an answer after understanding by the large language model; when the general knowledge document cannot solve the user question, judging the completeness of the question, and answering after intelligent counter questioning by the large language model or directly understanding the user question. The scheme fully considers the conditions of different users, intelligently guides the user to perform different businesses in the traffic management office or to understand the business requirements in advance, improves the business efficiency and the utilization rate of human resources, and improves the business experience.

The application provides an operation and maintenance knowledge graph natural language retrieval method and device based on contrast learning, equipment and a storage medium, comprising: using the contrast learning method to pre-train the original pre-training model, retaining the general knowledge learned by the original pre-training, and adding new features of the contrast learning that fit the target task; based on the contrast pre-training model, completing the vector representation of the retrieval sentence, recalling from the candidate sentences generated by the knowledge graph, and obtaining the retrieval answer. The method greatly reduces the time cost and material cost of manual labeling, simplifies the retrieval process, reduces the use of supervised learning models, uses the contrast pre-training model to meet the model requirements of the whole process, improves the retrieval efficiency while reducing the computing power consumption.