82 results about "Word order" patented technology

The invention relates to the technical field of data classification management, in particular to a knowledge graph-based foreign trade data classification management system, which comprises a term word order modeling module, a graph path generation module, a path cross analysis module, a semantic category judgment module and a classification structure output module. According to the method, morpheme-level word segmentation and word order extraction are performed on foreign trade terms, an original word order template is constructed, the reduction capability of a semantic expression sequence is enhanced, a directed path is established through morpheme-level label sorting, and the level definition of a term structure and the logic relation between nodes are enhanced; a semantic intersection area is extracted through node intersection and end point frequency analysis, the accuracy of term association judgment is improved, semantic affiliation is selected according to end point label frequency, a node classification closed loop is formed by combining labels and path mapping, links of term graph modeling, path construction, intersection analysis and affiliation output are broken through, and the term association judgment accuracy is improved. And the classification management process of foreign trade data is fully improved.

The invention relates to the technical field of artificial intelligence, in particular to a family service method and system based on artificial intelligence, and the method comprises the following steps: obtaining a statement analysis action sequence and a task direction, collecting the feedback of a device to generate a state structure, judging an instruction trend, recombining a statement to generate a behavior chain, and disassembling an action recognition conflict to extract a main control path. Analyzing a behavior time sequence generation prominent trend, and adjusting a display sequence to generate a function scheme. According to the method, through semantic component extraction and equipment state mapping, the accuracy of instruction target recognition is improved, word order rearrangement and logic connection enhance the continuity of a behavior chain, a control path is optimized and sorted according to verb density and object association, the task scheduling precision is improved, and behavior time sequence analysis recognizes a high-frequency operation forward trend; according to the method, priority dynamic adjustment and rearrangement of recommended content in combination with instruction frequency and time sequence characteristics are realized, the response initiative and the service matching degree are enhanced, and collaborative optimization of semantic understanding, behavior prediction and content recommendation is integrally realized.

The invention relates to the technical field of intelligent anti-fraud, in particular to a dynamic anti-fraud decision-making method based on adversarial evolution, which comprises the following steps: firstly, constructing an original fraud sample data set as the basis of adversarial sample generation and model training; the attacker model is based on a language generation model, generates a confrontation sample with sensitive word disguise, word order disturbance and semantic concealment features through guiding prompt, and simulates a real fraud variant. And mixing the confrontation sample and the original sample to construct a training set, inputting the training set into a defender model for training, and optimizing an attacker model prompt with recognition accuracy to realize dynamic iterative lifting. A dynamic purification and semantic compensation mechanism is introduced into the defender model, a gradient sensitive area is inhibited, semantic integrity is repaired, the stability and recognition capability of the model in a complex context are enhanced, and therefore accurate recognition and interception of diversified novel fraud texts are achieved.

The invention relates to the technical field of intelligent questioning and answering workers, in particular to a power grid equipment intelligent questioning and answering optimization method and system based on a large language model. The method comprises the following steps: acquiring problem data of power grid equipment, and creating a dynamically updated power grid equipment vocabulary to store the problem data; a part-of-speech tagging model of a conditional random field is used for tagging part-of-speech of question data, power grid equipment knowledge retrieval and large language model building are performed based on the question data of tagging and semantic roles, parameter updating is performed on the built large language model, and answer optimization is performed according to a processing result of the large language model. According to the method, a position coding formula combined with semantic information is introduced, so that a large language model can better understand the relationship between a word order and semantics in a text in the field of power grid equipment, semantic logic in the text can be more deeply mastered, the ability of understanding the operation process and the equipment relationship is improved, and answers more conforming to professional logic are output.

The invention relates to the technical field of semantic processing and knowledge maps, and provides an AI-based intelligent question-answering method and system, and the method comprises the steps: collecting a knowledge map of an intelligent question-answering library, and obtaining an inquiry text of a user; performing word segmentation on the inquiry text to obtain a plurality of vocabularies; obtaining a reply design scale of the inquiry text; determining the number of analysis queues and establishing a plurality of analysis channels; obtaining the semantic intensity of each marked vocabulary and obtaining a high-intensity semantic vocabulary sequence; quantizing the analysis contribution of each mark vocabulary at each moment and the initial analysis limit at each moment, and further obtaining the buffer semantic integrity retention degree at each moment; judging and establishing a buffer space in real time, adjusting an analysis process, and finally outputting a semantic weight of each vocabulary; and screening a plurality of core vocabularies, obtaining a relation path in combination with the knowledge graph, and further generating a reply text. The invention aims to solve the problem that semantic weight acquisition is inaccurate due to word order interference in text keyword analysis.

The invention provides a real-time translation method and interaction system based on streaming voice segmentation and semantic verification. The method comprises the following steps: receiving a conference audio stream, identifying effective audio frames based on dual-channel voice activity detection, and pressing the effective audio frames into a dynamic buffer area; according to a preset dynamic segmentation strategy, outputting an initial voice segment from the dynamic buffer area for voice recognition, and obtaining a corresponding initial text segment; performing multi-stage reliability verification on the initial text fragment, and dynamically correcting or complementing the initial text fragment according to a verification result to obtain a reliable recognition result; and after the reliable identification result is obtained, triggering an asynchronous parallel translation task. According to the method, a semantic correction mechanism cooperating with the adaptive truncation depth is designed, so that the semantic fragmentation problem of the long-sequence audio during streaming truncation is solved, and the translation accuracy of a complex word order language is greatly improved while low delay is ensured.

The invention discloses an intelligent engineering quantity list matching method, which comprises the following steps of: firstly, performing deep analysis on project description to form a key feature dictionary and form a basis for subsequent accurate matching; then, adopting a two-stage process of coarse screening and fine arrangement: in the coarse screening stage, combining project codes pointing to professional classification with key features capable of quickly locking core elements, performing efficient filtering on a huge standard quota library, and quickly generating a candidate matching list which is controllable in scale and highly related; and in a fine ranking stage, turning to more detailed semantic and feature dual verification, comprehensively utilizing the deep semantic similarity of a complete item description text and an accurate comparison result of a key feature dictionary, and performing fusion calculation to obtain a final score so as to realize accurate ranking of candidate lists. In this way, the semantic gap caused by synonyms, inverted word order, non-standard expression and the like in traditional text matching can be effectively overcome, and the matching accuracy is greatly improved.

The invention discloses a short video retrieval method combining a pre-training model and a dependency syntax tree, and relates to the technical field of multi-modal learning, computer vision and information retrieval cross fusion. The semantic information in the context is captured by using the advantages of BERT, and the deep semantic representation is generated, so that the meaning of the sentence is more accurately understood. A clear syntactic relationship is provided by using the dependency syntactic tree, and the structured dependency relationship between words can be revealed. The relationship can help the model to better understand logic semantics in sentences and extract text features related to tasks in a more targeted manner. Through the dependency syntax tree and the model, primary and secondary information in the long sentences can be distinguished more accurately, the problems of word order ambiguity and the like are eliminated, feature extraction is more stable, and robustness is improved. The dependency syntactic tree is explicit grammatical representation, and structured information of the dependency syntactic tree can assist in analyzing BERT implicit features, so that more explainable basis is provided for the decision process of the model, and the interpretability is remarkably enhanced.

The invention relates to a railway traffic field semantic recognition method and device based on few sample data and a medium, and the method comprises the steps: carrying out the preprocessing of the obtained railway traffic field data, and constructing a field dictionary and a rule base; converting the preprocessed domain data into enhanced voice, forming a training pair by the enhanced voice and a corresponding text, and performing domain fine tuning on the ASR model; inputting a voice instruction in the railway traffic field into the field fine-tuned ASR model, and outputting an ASR initial transcription text; on the three levels of sentence level, local word order level and semantic tag level, word legality judgment is performed on the ASR initial transliteration text through a multi-scale model, and a high-credibility anchor point set and uncertain content are recognized; and field semantic rewriting is carried out based on the legitimacy judgment result of the words, and finally a structured instruction text is output. Compared with the prior art, the method has the advantages of realizing accuracy and adaptability of semantic recognition in the field of railway traffic and the like.

The invention relates to the technical field of speech recognition, in particular to an NLP-based AI assistant speech recognition dialogue system, which comprises an audio time sequence acquisition module, a spectrum interference suppression module, a semantic structure analysis module, a context association module and a semantic response generation module. According to the invention, through time sequence acquisition and spectrum analysis of environmental audio, user voice is effectively captured and analyzed, environmental noise interference is significantly reduced, the processing improves the definition of voice signals, accurate capture of voice data in a complex environment is ensured, and the spectrum stability is dynamically adjusted to allow the system to adapt to sudden noise change. According to the method, the processing adaptability is improved, deep semantic structure analysis enables a system to understand the emotion and word order structure of statements, more humanized responses are generated, historical interaction data are utilized in the generation of context matching information, the continuity and logicality of dialogues are improved, and dialogue assistants can better understand long-term intentions and requirements of users.

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.

The invention discloses a steganographic text detection technology based on text reconstruction and word order semantic features, and belongs to the technical field of information hiding. The method comprises the following steps: selecting an open source English steganography text data set containing three fields of social platform speaking, news manuscripts and film review; words in non-steganographic text sentences in the data set are randomly disorganized and sent to a large language model for reconstruction training, and the training target of reconstruction is an original text; and randomly disorganizing a data set text, and inputting the disorganized data set text into the trained model to generate a reconstructed text. And finally, inputting the original text, the disordered text and the reconstructed text into a steganography detection model, calculating a cosine similarity matrix, extracting a semantic difference feature map through a CNN, flattening, splicing semantic vectors of the original text, and inputting the semantic vectors into a classifier to output a binary detection result. Through continuous training, an error between a classifier output result of the model and a real labeling result is continuously reduced, so that parameters of a feature extractor and a classifier are optimized, and the model steganography detection accuracy is improved. According to the method, semantic information and word order features are utilized for classification, high accuracy, low cost and good interpretability are achieved, steganographic texts can be effectively detected, and information safety is improved.

The invention discloses a method and system for constructing a civil aviation supervisor dictionary card based on deep learning. And constructing a broken line classification network according to the mining degree value. And constructing a matrix detection network according to the word order. And obtaining the current discrimination statement. And based on the current discriminant statement, associating the discriminant statement with a performance standard corresponding to the dictionary card through a broken line classification network and a matrix detection network to obtain a current performance standard. And finding the influence of different key adjectives of each keyword key value pair on the judgment of the performance standard. And the influence of the word order on performance standard discrimination is detected according to the word order.

The invention provides an eye movement tracking system for aphasia rehabilitation training, a vocabulary difficulty adaptive adjustment method, equipment and a medium. The method comprises the following steps: determining semantic diffusion characteristics of a current vocabulary for representing a target user; determining a semantic recognition gradient of a target user on the initial rehabilitation training voice; performing response feedback analysis on speech recognition of the target user in the initial rehabilitation training process based on the semantic diffusion features and the semantic recognition gradient to obtain a semantic response deviation of the target user in the current stage; determining a gaze association relationship of the target user under different semantic structure features; and adaptively adjusting the vocabulary difficulty of the rehabilitation training voice in the next stage according to the cognitive performance index of the target user in the current stage determined by the semantic response deviation and all the gaze association relationships. By adopting the scheme of the invention, the eye movement fixation characteristics of the patient can be deeply associated with the word order structure of the training voice content, and then the training voice in the rehabilitation training process can be adaptively adjusted.

The invention discloses an end exchange method and system based on AI optimization, and efficient deployment and safe application of enterprise-level AI assistants are realized through multi-service provider model parallel calling, dynamic dialogue grouping management, a unified API scheduling mechanism and a localized knowledge base technology. The system supports multi-format content generation, real-time retrieval and data encryption, the multi-model calling efficiency is optimized through a load balancing algorithm and a cache mechanism, and the API cost is reduced. A segmented retrieval and export function is provided, an existing data sample is modified to obtain a similar sample, and topic semantics of an original statement can be learned by using information as little as possible, so that statement representation output by a natural language model does not greatly depend on local information of the statement; and the topic semantics of the original sentences can be learned from a disordered word sequence, so that the model can learn robust representation, representation with higher distinction degree can be learned by comparing statement representation and paragraph representation under different granularities, and the paragraph topic prediction performance can be improved.

This invention discloses a product classification and recognition method and system based on AI technology, belonging to the field of AI recognition technology. By constructing a semantic alignment master vector Edis, the system achieves structured extraction and ambiguity resolution of the overall semantic representation of the product. On this basis, the system introduces the construction of a product classification label semantic vector set Gvec and a semantic similarity score set Sset, enabling the system to perform fine-grained matching of multiple classification labels based on contextual semantic features. This constructs a confidence score Conf reflecting the classification credibility, which is then compared with a preset classification judgment threshold Thrs to ensure that product labels are output only when the classification judgment credibility is sufficient. Through the connection of the above processes and the linkage of output results, this method not only significantly reduces the probability of misjudgment caused by expression ambiguity and word order reversal, but also provides a reliable rejection mechanism when accurate classification is not possible, effectively improving the overall robustness and practical value of the classification system.

This invention relates to the field of information retrieval structure technology, specifically to a method and system for monitoring data during the investment promotion process in industrial parks. The method includes the following steps: extracting investment promotion text, identifying combinations of verbs and resource nouns, analyzing word order and semantic features, filtering action-driven segments, dividing structural sequences and identifying connection relationships, establishing semantic jump paths, reorganizing sentence order, and generating a data monitoring structure template for investment promotion in industrial parks. In this invention, by extracting verbs and resource nouns to construct sentence content, combining word order features and semantic tags to classify and filter segments, dividing structural sequences based on the position of resource nouns and merging content with consistent semantic direction, mapping connectors to jump paths to construct task behavior sequences, and realizing the logical organization and sequential reorganization of sentences, this generates a data expression method with traceability and structured features, improving the semantic recognition efficiency and data monitoring capabilities during the investment promotion process in industrial parks.

The embodiment of the invention provides a natural language processing method and equipment, and the method comprises the steps: obtaining a lexical item set corresponding to a to-be-processed initial input statement, and enabling the lexical item set to comprise an initial lexical item included in the initial input statement, and an extended lexical item of the initial lexical item; performing word order reduction on lexical items in the lexical item set to obtain an extended statement of the initial input statement; and obtaining a processing result based on the extension statement and a natural language processing model. According to the embodiment of the invention, the initial lexical item and the extended lexical item included in the initial input statement can be acquired and restored into the extended statement with a smooth word order, so that the initial input statement can be extended and enhanced, and the obtained extended statement can be better understood by a natural language processing model; and then natural language processing is performed in combination with the natural language processing model, so that the accuracy and stability of a processing result can be improved.

This invention discloses a speech prosody recognition method, system, device, and storage medium. First, the voice from a customer service call is captured to obtain a dialogue speech signal. Then, the dialogue speech signal is preprocessed to obtain a preprocessed dialogue speech file. Next, the preprocessed dialogue speech file is vectorized to obtain a corresponding feature matrix. The feature matrix is ​​input into a trained prosody model to obtain the model calculation result. Then, based on Mandarin and dialect templates, corresponding template thresholds are obtained. Using the model calculation result and template thresholds, the prosody recognition result of the feature matrix is ​​obtained. Finally, based on the prosody recognition result, the feature matrix is ​​processed by text mapping to obtain the dialogue word order text. This invention effectively improves the recognition accuracy and efficiency for speech containing dialects.

Embodiments of the present disclosure provide a method and a device for processing natural language. The method comprises obtaining a set of terms corresponding to an initial input sentence to be processed, wherein the set of terms comprises initial terms included in the initial input sentence and extended terms of the initial terms; performing word order restoring on terms in the set of terms to obtain an extended sentence of the initial input sentence; and obtaining a processing result based on the extended sentence and a Natural Language Process (NLP) model.

This application provides a radar text processing method and related apparatus. The method includes: processing the radar text to be processed to obtain a first word vector set; extracting contextual semantic features from the first word vector set to obtain a first semantic feature set; extracting word features from the first word vector set to obtain a first part-of-speech feature set; weighting the first part-of-speech feature set with the corresponding semantic features based on importance to obtain a second part-of-speech feature set; concatenating the second part-of-speech feature set and the first word vector set according to the word order of the radar text to be processed to obtain a second word vector set; extracting contextual semantic features from the second word vector set to obtain a second semantic feature set; and performing label classification processing on the second semantic feature set to obtain a classification label corresponding to each first word vector in the first word vector set, thereby improving the accuracy of word classification processing in radar text.

The invention discloses a multi-language recognition inter-translation system based on offline double models, and belongs to the technical field of artificial intelligence. The objective of the invention is to solve the problem of poor accuracy of an existing translation system during special industry translation. The translator is adopted to translate original text information to be translated into a required language form, then the artificial intelligence adjustment module is adopted to perform word order and coherence adjustment on the translated text information, and the adjusted information is translated into original text language text information through the translation result and original text proofreading module. Comparing the translated original text language characters with the to-be-translated original text, judging whether there is a difference, extracting a difference fragment, translating again, replacing the translated difference fragment with a corresponding fragment of the translated original text language character information, then comparing the translated difference fragment with the to-be-translated original text again, and if there is still a difference, marking and outputting. The multi-language translation method is suitable for multi-language translation.

The present invention discloses a method and system for constructing a civil aviation inspector dictionary card based on deep learning. A polyline classification network is constructed based on the mining degree value. A matrix detection network is constructed based on the word order. The current discriminant statement is obtained. Based on the current discriminant statement, the polyline classification network and the matrix detection network are used to associate the discriminant statement with the performance standard corresponding to the dictionary card to obtain the current performance standard. The influence of different key adjectives in each keyword-value pair on the performance standard is determined. Furthermore, the influence of word order on the performance standard is detected based on the word order.

The invention relates to the technical field of machine question answering, in particular to a personalized health question answering system based on reinforcement learning, which comprises an input positioning module, an anaphora freezing module, a state injection module, a path screening module and a content splicing module. According to the method, the fuzzy region is marked by identifying semantic features such as subject separation, pointing missing and intention interruption, and unstable content is frozen and screened by combining semantic chain consistency, word order change and context distance judgment; the internal structural integrity and semantic closure of the statement are enhanced by means of subject-called structure reconstruction, verb-object combination recognition and modification chain judgment, and semantic tripping content is further eliminated through subject affiliation matching, upper and lower concept connection and logic consistency screening. Content recombination and linkage optimization are realized based on objective word positioning, tail word sequence adjustment and semantic ending complementation, and semantic undertaking stability, content coherence and reply pertinence in ambiguous input, structure disorder or multi-turn jump scenes are improved.

The invention discloses a method and device for recognizing and reconstructing vector characters of a CAD drawing, and relates to the technical field of data processing. The method comprises the steps that a PDF file is analyzed, and vector elements and attribute information of the vector elements are extracted; character stroke candidate lines are screened out according to attribute grouping; carrying out connectivity analysis and density-based spatial clustering on the lines, and identifying a text region; rendering the vector lines of the text region into an image with high resolution, carrying out single character segmentation, and recognizing characters by combining drawing-level font library template matching with a single character recognition model; combining the single characters into word groups according to the positions and the context information, and performing word order correction by adopting a language model; the recognition result is written back into an editable CAD text object; according to the method, vector geometric information is directly utilized, distortion of bitmap sampling is avoided, the small character recognition rate and the anti-jamming capability are effectively improved, and end-to-end semantic recovery from vector lines to searchable and editable texts is achieved.

The present invention discloses a method for improving the performance of a neural machine translation system, and the steps are as follows: processing training data and initializing the parameters of the neural machine translation system; adjusting the generation rule of the absolute position encoding in the neural machine translation system to a multiplicative sine-cosine encoding generation rule; inputting the training data, reading the absolute position encoding into the neural machine translation system, adding it to the word vector of the input source sentence to obtain a word vector fused with position information, and feeding it into the neural machine translation model; training the neural machine translation system using the gradient descent method until convergence, and the training process is the same as that of the existing neural machine translation system; during the decoding process, for the absolute position encoding generation rule, it is kept consistent with the multiplicative sine-cosine encoding generation rule. Without changing the number of parameters and the amount of computation of the neural machine translation system, the present invention improves the recognition ability of the translation system for the word order of the input language and effectively improves the translation performance of the neural machine translation system.

The present invention relates to the technical field of data classification management, specifically a foreign trade data classification management system based on a knowledge graph. The system includes a term word order modeling module, a graph path generation module, a path intersection analysis module, a semantic category determination module, and a classification structure output module. In the present invention, by performing morpheme-level word segmentation and word order extraction on foreign trade terms, an original word order template is constructed to enhance the restoration ability of semantic expression order. A directed path is established through morpheme-level label sorting to strengthen the hierarchical clarity of the term structure and the logical relationship between nodes. The semantic intersection area is extracted by using node intersection and end point frequency analysis to improve the accuracy of term association determination. The semantic attribution is selected according to the end point label frequency, and a node classification closed loop is formed by combining the label and the path mapping, connecting all links of term graph modeling, path construction, intersection analysis and attribution output, and fully improving the classification management process of foreign trade data.

The application discloses an end exchange method and system based on AI optimization, realizes efficient deployment and safe application of enterprise-level AI assistants through multi-service provider model parallel calling, dynamic dialogue grouping management, unified API scheduling mechanism and localization knowledge base technology, and the system supports multi-format content generation, real-time retrieval and data encryption, optimizes multi-model calling efficiency and reduces API cost through a load balancing algorithm and a cache mechanism. The segmented retrieval and export functions are provided, similar samples can learn the theme semantics of the original sentence with as little information as possible by modifying the existing data samples, so that the sentence representation output by the natural language model is not greatly dependent on the local information of the sentence, and the theme semantics of the original sentence can be learned from the chaotic word order, which is more helpful for the model to learn robust representation, and through comparison of sentence and paragraph representation under different granularity, more discriminative representation can be learned, which can improve the paragraph theme prediction performance.

The invention discloses a product classification and identification method and system based on an AI technology, relates to the technical field of AI identification, and realizes structured extraction and ambiguity resolution of overall semantic representation of a product by constructing a semantic alignment main vector Edis; on the basis, construction of a product classification label semantic vector set Gvec and a semantic similarity score set Sset is introduced, so that the system can perform fine-grained matching on a plurality of classification labels according to context semantic features, a confidence score Conf reflecting classification credibility is constructed, the confidence score Conf is compared with a preset classification judgment threshold Thrs, and a classification result is obtained. According to the method, the product labels are output only when the classification judgment credibility is sufficient, the probability of misjudgment caused by expression ambiguity and word order inversion is remarkably reduced through linkage of series connection of the processes and output results, a reliable rejection mechanism is provided when accurate classification cannot be achieved, and the reliability of the product labels is improved. And the overall robustness and the practical value of the classification system are effectively improved.

This invention discloses a high-performance semantic recognition method, belonging to the field of natural language semantic recognition. The method first converts a sentence into a corresponding word vector sequence according to word order, and then inputs the word vectors into a semantic recognition network to obtain the recognition result. The semantic recognition network includes several sequentially arranged semantic recognition units; each semantic recognition unit includes hidden neurons, a value prediction network, an output neuron, and a classifier. During computation, the value prediction value determines whether each unit is retained. After all word vectors have been processed, the classification result output by the classifier in the last semantic recognition unit marked as "retained" is taken as the semantic recognition result of the sentence. This invention can reduce the computational load while ensuring that semantic features are not lost, significantly improving the performance of semantic recognition.