289 results about "Label" patented technology

Embodiments of the disclosed technologies are capable of a training pipeline to fine-tune a machine learning model given a limited set of domain-specific data. The embodiments describe using a first machine learning model to generate a pseudo label associated with a domain-specific training document. The pseudo label comprises a machine-generated text of a content type extracted from the domain-specific training document. The embodiments further describe fine-tuning a second machine learning model using the pseudo label, the domain-specific training document, a first low-rank weight matrix, and a second low-rank weight matrix. The fine-tuned second machine learning model generates text of the content type from a domain-specific document.

An online system may provide an instruction prompt to a machine-learned language model. The instruction prompt may include an instruction to generate an evaluation label of a training sample of a classification model and a textual format related to how data is arranged. The evaluation label may be used in a supervised training of the classification model. The online system may provide a batch of evaluation request prompts to the machine-learned language model. Each evaluation request prompt includes data that is at least partially arranged in the textual format described in the instruction prompt. The online system may receive a plurality of responses from the machine-learned language model. Each response includes the evaluation label corresponding to each evaluation request prompt. The online system may store at least evaluation labels and the data in the evaluation request prompts as training samples for the supervised training of the classification model.

The invention relates to the technical field of cross-language information processing, and provides a cross-language text fusion intelligent alignment method and system.The cross-language text fusion intelligent alignment method comprises the steps that a hierarchical alignment model is constructed through preprocessing and label recognition of multi-coding-type texts, deep semantic feature extraction and labeling of a multi-language pre-training model and text semantic and format information analysis; transform is taken as a core, cross-language semantic association is enhanced through a multi-head attention mechanism, character-level and paragraph-level format collaboration is realized through label weight allocation and condition constraint, the format alignment accuracy is obviously improved in a multi-language mixed typesetting scene, and the multi-language mixed typesetting efficiency is improved. The analysis capability of the model on the structured information can be extended to layout relation processing of texts, images and tables, so that the comprehensive alignment efficiency in a multi-modal fusion scene is remarkably improved. The accuracy of text and label fusion is guaranteed, the problem of confusion of messy codes and labels is avoided, and high-precision cross-language text alignment from semantics to formats, from single mode to multiple modes and from semantics to formats is achieved.

The invention discloses a label classification method and device based on a large model, equipment and a medium, and relates to the technical field of natural language processing, model fine tuning, pre-training and model optimization are performed on an initial semantic retrieval model and an initial artificial intelligence large model on a preset data set, and a semantic retrieval model and an artificial intelligence large model are obtained; inputting the to-be-classified text into a semantic retrieval model, so that the semantic retrieval model screens out an initial tag corresponding to the to-be-classified text from a preset tag library; and inputting the to-be-classified text and the initial tag into the artificial intelligence large model, so that the artificial intelligence large model screens out the target tag corresponding to the to-be-classified text from the initial tag to complete tag classification of the to-be-classified text, thereby shortening the model training period, improving the development efficiency and the business iteration speed, and improving the user experience. The classification capability of the model on the middle tail labels is enhanced, the accuracy and comprehensiveness of the model during label classification are improved, and the flexibility and efficiency of model training are improved.

The invention provides a large-model multi-label classification method, system and device based on ReAct and a vector library, and belongs to the technical field of artificial intelligence. The method comprises the following steps: constructing a multi-level label mapping tool according to each label data table corresponding to a preset multi-level label system; and constructing a label retrieval tool based on a pre-trained text similarity model and a preset label vector database. Constructing a ReAct tool chain based on a preset label dynamic adjustment tool, a multi-level label mapping tool and a label retrieval tool; the preset label dynamic adjustment tool is constructed on the basis of cue words and a large language model and is used for updating candidate labels according to the to-be-labeled text corpus, the candidate labels output by the label retrieval tool and label rules; and based on a preset ReAct cue word project, the large language model and the ReAct tool chain, constructing a large model multi-label classification module so as to input the to-be-labeled text corpus from the user terminal into the large model multi-label classification module for multi-label classification.

The invention discloses a commercial customer service system based on large model emotion recognition labeling and correction, and belongs to the technical field of natural language processing and deep learning. In order to solve the problems that an existing emotion recognition system depends on large-scale manual labeling, label quality is unstable and small sample performance is poor, a multi-model collaborative labeling and iterative optimization mechanism is adopted, and fusion labels are generated through automatic basic model selection, small sample LoRA fine adjustment, double-model divergence detection and large model arbitration. And a refining training set is constructed for iterative fine tuning to form a closed-loop optimization system. The method can effectively reduce the labeling cost, improves the label consistency and the emotion recognition precision under complex semantics, and is suitable for business information, financial public opinions and intelligent customer service scenes.

Existing Convolutional Dictionary Learning (CDL) based machine fault classification do not utilize label information while learning the dictionary, hence the representation learned are not class-discriminative. Method and system disclosed herein provide a label-consistent convolutional dictionary learning approach for machine fault classification. The approach involves generating a training data for a classifier, wherein coefficients forming a plurality of class-discriminative features form the training data. The training data is then used to train a classifier, which is then used to perform machine fault classification for a given test data.

The invention discloses an instruction response method and device, equipment and a medium. The instruction response method comprises the steps that text content carried in an instruction input by a user is acquired; extracting a target keyword corresponding to the text content; the target keyword is input into a classification model for matching, a first classification label matched with the target keyword is obtained, the classification model comprises a tree created based on a page of a target system, and nodes in the tree are classification labels created based on page information of the page; and pushing a first page link corresponding to the first classification tag to a user side as a response result of the user input instruction. Therefore, the response speed can be improved, and the user experience is improved.

The invention provides an emotion index construction method and device, computer equipment and a storage medium. The method comprises the steps of obtaining multiple pieces of first comment information in a preset duration range and label information corresponding to each piece of first comment information; the label information comprises a positive label, a neutral label and a negative label; inputting the first comment information into a word embedding layer of a to-be-trained text classification model, and outputting a word vector matrix; inputting the word vector matrix into a convolutional layer, and outputting a first feature vector; inputting each first feature vector into a full connection layer, and outputting an emotion prediction result corresponding to the first comment information; completing the construction of a text classification model according to the emotion prediction result and the label information; and obtaining to-be-constructed second comment information, inputting multiple pieces of second comment information into the constructed text classification model, outputting an emotion classification result, and completing construction of emotion indexes corresponding to the multiple pieces of second comment information according to the emotion classification result.

The invention discloses a multi-round cross validation and weak supervision noise cleaning method based on a large language model. According to the method, weak supervised learning and large language model reasoning capability are fused, and multi-round cleaning and label optimization are performed on a low-confidence sample by introducing a small amount of high-quality label seeds and combining automatic rule construction and cross validation processes. According to the method, a verification and feedback system with a large language model as a core is constructed, efficient purification and enhancement of weak tags in large-scale text data are achieved, and high-quality training data and intelligent tag optimization support are provided for natural language processing tasks such as relation extraction, text classification and entity recognition.

The invention relates to an SQL (Structured Query Language) generation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of determining supplementary information corresponding to an initial problem based on the initial problem, and obtaining a target problem; based on a pre-configured label system, determining a first fine-grained label of each entity contained in the target question, and performing association matching on the first fine-grained label and a second fine-grained label of each field in each preset database table to obtain a candidate table; according to the method, the target problem is converted based on the candidate table to obtain the conversion problem, and the conversion problem is processed through the preset large language model to obtain the SQL statement, so that knowledge enhancement can be performed on the problem directly input by the user, the definition of problem description can be improved, the efficiency of data retrieval can be optimized, and the interpretability of data can be optimized; in addition, alignment processing can be carried out on text descriptions of different semantic spaces, and the accuracy degree and the generation efficiency of SQL statements generated by a large language model are improved.

The invention relates to a cross-language entity alignment method based on large language model knowledge enhancement, and belongs to the field of knowledge graph alignment. According to the method, firstly, entity and relation embedding is enhanced by applying a large language model, and the distinction degree of positive and negative samples in the training process is improved; then, adaptive fusion weighting is introduced to weaken various embedded noises, and bidirectional flexible voting is introduced to generate more reliable pseudo labels on label-free data; the CLEA-LLM uses a teacher-student structure, a teacher encoder and a student encoder generate three types of embedding according to two knowledge maps and knowledge features, features obtained by the teacher encoder are subjected to adaptive fusion weighting to generate joint features, and a pseudo-mapping probability matrix is obtained through bidirectional flexible voting and diversity correction to supervise learning of a learning encoder. Therefore, the entity alignment precision is improved.

The invention provides an open domain label system construction method and device based on a large language model, and relates to the technical field of data processing. The method comprises the following steps: constructing a label association pool according to different to-be-labeled contents in a first time period and initial labels output by labeling the to-be-labeled contents by using a first large language model; determining an initial tag system and a tag cluster of any initial tag based on the tag occurrence frequency of each initial tag; based on a preset semantic understanding task description, determining a normalized tag of each initial tag by using the zero sample capability of the second large language model; constructing a label directed graph set; and if it is detected that the first tag in the first tag directed graph is a normalized tag of the second tag in the directed graph and the normalized tag of the first tag in the second tag directed graph is a third tag, constructing a target tag system. According to the method, the time from emerging topic appearance to label system response is shortened, and the semantic accuracy of the label system is improved.

The invention provides a method and a system for automatically marking knowledge points of a large language model. The method comprises the following steps of: acquiring to-be-identified question stem content, preprocessing, and traversing a knowledge tree to generate an option type question for the large language model to select. The big language model adopts a question sentence pattern three-layer traversal method to traverse a knowledge tree, and annotated knowledge points are given. According to the method for automatically marking the knowledge points by using the large language model, when the knowledge tree is traversed, at most three layers are traversed, and after the second layer is traversed, leaf nodes of the knowledge tree are directly jumped to, so that the traversing speed is high, the situation that the more the traversed layers are, the higher the error probability is can be avoided, and meanwhile, the accuracy of marking the knowledge points is improved. And the option type question sentences are formed for the large language model to select, so that the large language model can understand, analyze and select conveniently, and the labeling speed is improved.

Disclosure are a backdoor attack method and system for a classification task in a code model, the method includes: S1. collecting and preprocessing clean samples to obtain importance variable names; S2. classifying the variable names of the clean samples according to label categories to obtain a plurality of trigger sets; and selecting target labels from the clean samples; S3. performing score calculation on the variable names in the trigger sets corresponding to the target labels; replacing one importance variable name with the variable name having a maximum C score in the clean samples to obtain poisoned samples, and repeating the above process until the labels are changed into the target labels; and S4. randomly inserting the triggers in the poisoned samples into the clean samples to form negative samples; and performing an attack by using an attack model obtained based on the negative, poisoned and clean samples.

Disclosed in the present application are a model training method, apparatus and device, and a storage medium and a computer program product. The model training method comprises: acquiring target training data, and on the basis of the target training data, training a classification model, so as to obtain simulated data related to the classification model; acquiring a label type sequence; on the basis of the label type sequence and the simulated data related to the classification model, determining a first loss function; and using the first loss function to update parameters of a first encoder network and parameters of a second encoder network until a loss value of the first loss function converges, and generating a noisy label detection model.

The invention provides a multi-label text classification method, and relates to the field of artificial intelligence. The method comprises the steps of obtaining a to-be-classified text and a first label set, wherein the first label set comprises a plurality of labels for text classification; selecting N candidate tags of the to-be-classified text from the first tag set, wherein N is an integer greater than or equal to 2; the to-be-classified texts and the N candidate tags are input into a multi-tag text classification model, and the multi-tag text classification model is obtained by training a large language model based on text samples and corresponding tag samples in advance; and obtaining M target tags predicted from the N candidate tags by the multi-tag text classification model, wherein M is an integer greater than or equal to 1.

The invention relates to the field of artificial intelligence, can be applied to business system platforms of financial science and technology, medical health and the like, and discloses a self-adaptive fine tuning method, device, equipment and medium for a language model, comprising: collecting a fine tuning training sample set, each fine tuning training sample comprising a training text and label data corresponding to at least one fine tuning task; inputting the training text and the corresponding label data into a pre-trained language model to obtain hidden representation of the training text; performing adaptive generation processing on the hidden representation by using a pre-constructed soft prompt generator to obtain a corresponding soft prompt vector; inputting the hidden representation and the soft prompt vector into the language model again to obtain a corresponding prediction output result; and performing parameter fine tuning according to the difference between the predicted output result and the label data until a preset ending condition is met. The parameter quantity capable of being finely adjusted is improved while self-adaptive fine adjustment is achieved through the soft prompt generator, and more effective and reliable model fine adjustment is achieved.

The invention relates to a multi-label text classification method based on positive and negative label learning and label correlation, and belongs to the field of multi-label classification. Comprising the following steps: constructing a feedforward neural network model with double hidden layers; initializing a model component; reading features and label information of samples in the training set, and generating a feature matrix and a label matrix; randomly initializing a weight matrix and an offset parameter of the model; inputting the feature matrix into an input layer of the model, and calculating neuron output layer by layer; calculating gradients of weight matrixes and bias parameters among layers in the model by adopting a composite error function, dynamically adjusting the gradients by utilizing an Adam optimization algorithm, and updating the weight matrixes and the bias parameters; when the error change amplitude is lower than a threshold value or reaches a preset number of iterations, stopping training; and after model convergence, predicting the test set to form a final multi-label classification result. According to the method, the limitation of traditional text classification is broken through through a deep learning technology, and high-precision and high-efficiency classification of complex text data is realized.

The invention relates to the technical field of multi-label text classification, and discloses a small-sample multi-label text classification method based on machine reading understanding, which comprises the following steps of: firstly, preprocessing a multi-label text data set, unifying formats and labeling labels; secondly, designing an auxiliary problem based on the label, and combining the auxiliary problem with the text instance to form input data; a RoBERTa model is used as a joint encoder trunk, semantic correlation between texts and questions is learned, and a label graph representing a label relation is constructed. Through feature fusion, the model is trained to minimize a loss function, and a verification set is used to carry out hyper-parameter tuning. And finally, evaluating the model performance on the test set, and verifying the advantages and component contribution compared with the traditional method. By converting multi-label text classification into a machine reading understanding task, the semantic correlation between the text and the labels can be better captured, and the accuracy of multi-label text classification is remarkably improved.

A method and system of UI automation includes receiving a demonstration of an automation to be performed on an application. One or more objects and one or more corresponding labels associated with the demonstration are detected on the application. The demonstration is transformed into one or more natural language instructions. An object is semantically selected during a runtime action based on a large language model (LLM). The semantic selection is reflective of an intention captured in the natural language instruction despite any change in a corresponding label of the object.

The invention relates to the technical field of intelligent label recommendation, and discloses a standardized label framework collaborative recommendation system based on artificial intelligence. The system comprises a multi-level professional label knowledge base, a large language model reasoning unit, a semantic consistency verification module, a path verification module, a collaborative decision module and a label recommendation engine. The multi-level professional label knowledge base stores a standardized label system containing a multi-level structure; after receiving the input content, the large language model reasoning unit generates an initial label set according to label system level constraint reasoning; a semantic consistency verification module compares the label and content semantic matching degree and outputs a result, and a path verification module verifies whether a label generation path accords with a hierarchical structure and gives a compliance indication; the collaborative decision-making module corrects the initial label set according to a preset rule when the semantic verification result conflicts or the confidence coefficient is insufficient; and integrating the corrected label set by the label recommendation engine, and outputting a final standardized label recommendation result to adapt to multi-field labeling requirements.

The invention discloses a label classification method and device for a long text, equipment, a storage medium and a product, relates to the technical field of computers, and discloses a label classification method for the long text, which comprises the following steps: obtaining a to-be-classified text; and based on the to-be-classified text, performing label classification processing through a preset large language model to obtain a label classification result. According to the method, the to-be-classified texts are converted into the text sequence vectors by the large language model through position coding, and then correlation among the text sequence vectors is calculated in parallel by utilizing a multi-head self-attention mechanism, that is, the large language model can process the text sequence vectors in parallel, so that the video memory utilization rate of the large language model is improved, and the classification efficiency is improved. Due to the improvement of the utilization rate of the video memory, the large language model can process the long text with more characters, namely, the large language model does not need to segment the long text, so that semantic loss caused by segmentation is avoided, and the tag classification accuracy of the long text is improved.

The invention relates to a commodity marking method and device, equipment and a medium in the technical field of e-commerce, and the method comprises the steps: determining prediction implicit representations corresponding to all layers in a label path corresponding to a hierarchical label system, wherein a target commodity title is mapped to the prediction implicit representations, and obtaining each instance demonstration classification set corresponding to the plurality of instance implicit representations matched with the instance demonstration classification sets. Constructing a plurality of corresponding classification instances corresponding to each layer, traversing each layer according to a father-child hierarchical relationship, obtaining a classification label of a father layer of the layer and a same-layer candidate label set formed by the classification labels of the same layer in a hierarchical label system, constructing a corresponding prompt text input large language model, and inputting the prompt text into the same-layer candidate label set according to the classification labels of the father layer and the same-layer candidate label set. And determining a target classification label to which the layer belongs from the same-layer candidate label set by referring to a plurality of classification instances according to a given instruction by the control model. And forming a target multi-layer label set by using the target classification labels of each layer output by the model. According to the method and the device, accurate hierarchical labels can be efficiently labeled for commodities.

The embodiment of the invention provides a target object positioning method, and the method comprises the steps: obtaining a positioning rule which comprises one or more target labels matched with a target object, and a target label value corresponding to each target label; generating a first language type statement according to the positioning rule; label metadata is obtained, the label metadata is determined according to user data in a preset database, the user data comprises label values of all users under one or more labels, and the one or more labels comprise the one or more target labels; generating a second language type statement for database query according to the first language type statement and the tag metadata; and determining the target object according to the second language type statement and the preset database. According to the technical scheme, the complex query statement of the bottom layer can be automatically generated, the positioning result is returned, real-time interactive query is achieved, and usability is high.

The invention provides a short text clustering method and device based on large language model assistance, equipment and a storage medium. The method comprises the following steps: firstly, converting a short text into vector representation by utilizing Sension-BERT, and performing pre-clustering through an HDBSCAN model; sampling inter-class fuzzy samples based on information entropy, and performing cluster attribution discrimination on the samples by using a large language model to obtain pseudo labels; then performing data enhancement through modes of synonym replacement, random deletion, word order adjustment and the like, and generating a positive example for each sample; and finally, taking the pseudo tag as an additional positive example, participating in example-level contrast learning together with a positive example generated by data enhancement, and realizing clustering in combination with category-level self-supervised representation learning. According to the method, data does not need to be preprocessed, the category boundary fuzzy samples can be effectively processed, and the short text clustering effect is improved. The invention further provides a corresponding device, electronic equipment and a storage medium.

Aspects of the present disclosure provide techniques for training an item extraction machine learning model. Embodiments include extracting text and bounding box coordinates from a structured document and creating structured text by adjusting formatting of the extracted text based on the extracted bounding box coordinates and adding table delimiter tags to the extracted text based on detecting one or more tables in the structured document. Embodiments include providing the structured text to a language processing machine learning model along with a prompt instructing the language processing machine learning model to generate a label indicating variables present in the structured text and values for the variables. Embodiments include receiving the label from the language processing machine learning model in response to the structured text and the prompt and training the item extraction machine learning model through a supervised learning process based on training data comprising the structured text and the label.

The invention provides a marking task-oriented training course generation method and device, a medium and a product. The method comprises the steps of obtaining label sets corresponding to a plurality of service platforms respectively, wherein each label set comprises a label field and a corresponding label rule; based on entities pointed by the semantic information of the annotation fields in each annotation set, constructing an annotation knowledge graph; the annotation knowledge graph comprises a first node for representing an entity and a second node for representing an annotation field, a connection relationship for indicating semantic association is established between the first node and the second node, and each second node is associated with a corresponding annotation rule; if the annotation rules corresponding to different second nodes connected with the same first node in the annotation knowledge graph have differences, generating a cross-platform contrast training course based on the differences; and if the labeling rules corresponding to different second nodes connected with the same first node in the labeling knowledge graph are the same, generating a cross-platform unified training course.

A system performs a batch selection process on a small model and uses the results of batch selection to train a large language model (LLM). The system receives training examples and splits the training examples into a holdout set and an evaluation set. Each training example corresponds to a label. The system uses trains a small model using the training examples of the holdout set. The system evaluates the small model on the training examples of the evaluation set, generating a prediction for each training example and computing a loss between the prediction and the training example's label. The system generates an LLM training set by selecting a set of training examples from the evaluation set with the highest loss. The system trains the LLM using the LLM training set.

An example apparatus disclosed includes interface circuitry, machine readable instructions, and programmable circuitry to at least one of execute or instantiate the machine readable instructions to identify a first source of object label representation and a second source of object label representation, the first source or the second source including an estimated label prototype vector associated with an input text-based object query, determine a first contextualized embedding for the first source and a second contextualized embedding for the second source, and combine the first contextualized embedding and the second contextualized embedding to generate a candidate object representation associated with the input text-based object query.