43 results about "Sentence recognition" patented technology

The invention relates to the technical field of oracle paraphrasing, and provides a training method and device for an oracle single-character image reasoning task. According to the method, a backbone network is trained to perform Chinese character recognition, modern Chinese character radical splitting, literal period identification and recognition, oracle-bone image recognition, oracle-bone multi-graph statement recognition, oracle-bone character meaning evolution analysis and font thinking chain reasoning on single-character images; calculating a joint loss value according to the primary output, the intermediate output and the advanced output obtained by training so as to iteratively update network parameters of the backbone network, and obtaining an intermediate model until the joint loss value meets a training ending condition; and training the intermediate model to perform font thinking chain reasoning, and finely adjusting the intermediate model by using a reward function to obtain a target model, thereby solving the problem that the oracle single-character image is difficult to accurately identify, infer and explain.

The invention relates to an access control strategy automatic generation system and method based on multi-task learning, and the method comprises the steps: carrying out the word segmentation, cleaning and embedded vector conversion of an original access control text through a data preprocessing module, and constructing a normative input format; the feature sharing layer module is used for extracting deep semantic features of a text through multi-layer bidirectional coding and an attention mechanism and providing unified representation for downstream tasks; the access control statement identification module is used for judging whether each sentence in the text is an access control statement or not and realizing automatic identification of strategy related contents; and the attribute extraction and annotation module is used for annotating words in the access control statements and extracting subject, object and operation access control attributes. A word coding layer and a sentence coding layer are shared, local and global attention mechanisms are combined, key information of a text is extracted, the semantic understanding ability is enhanced, and cooperative training of statement recognition and attribute extraction is achieved; a conditional random field CRF structure is used for sequence labeling, and the structural rationality of attribute labels is ensured.

The invention provides an auxiliary learning system for reading and understanding questions in English subjects of senior high schools, which helps students to better improve the English learning ability of the students. The method comprises the following steps: firstly, downloading our application software from an Android mobile terminal through an APK file; secondly, inquiring the specific learning level of the user, and dividing the learning mode of the software into three modes of'high ', 'medium' and'low 'according to the evaluation score input by the user, so as to provide word and sentence recognition and analysis with different difficulties; then, the learning interest of the user is further inquired, and high-quality related categories of good articles are recommended to the user in real time by accessing feature words input by the user to an interface of ChatGPT; and finally, the user can select and collect necessary words and articles, and check content and analysis in the favorite at any time. According to the auxiliary learning software for reading and understanding questions in the senior high school English subject, personalized method teaching can be accurately performed on senior high school students, the English reading learning efficiency of the user is improved, and the improvement of the English ability of the user and the popularization of culture are promoted.

Methods and systems provide for extracting filler words and phrases from a communication session. In one embodiment, the system receives a transcript of a conversation involving one or more participants produced during a communication session; extracts, from the transcript, utterances including one or more sentences spoken by the participants; identifies a subset of the utterances spoken by a subset of the participants associated with a prespecified organization; extracts filler phrases within the subset of utterances, the filler phrases each comprising one or more words representing disfluencies within a sentence, where extracting the filler phrases includes applying filler detection rules; and presents, for display at one or more client devices, data corresponding to the extracted filler phrases.

The application belongs to the field of natural language processing, and particularly relates to a method and system for paraphrase recognition based on semantic primitive knowledge and abstract semantic representation, which comprises the following steps: performing word segmentation on a sentence, and performing word-level vector representation and semantic primitive knowledge representation; performing mean value processing on the semantic primitive knowledge representation result, and extracting interactive attention feature information of the mean value processing result by using global semantic information to obtain global semantic primitive representation; performing abstract semantic analysis on a to-be-recognized paraphrase sentence from a sentence structure to obtain a single-root directed acyclic graph, and performing global semantic primitive representation and word-level vector representation; extracting global and local feature information in the order of the directed acyclic graph, and performing distance feature measurement on the information; inputting the distance feature measurement result into a neural network to obtain a recognition result; the application introduces external semantic primitive knowledge to perform semantic representation, the accuracy of the semantic primitive knowledge representation is assisted by global semantic information, and the abstract semantics of a Chinese paraphrase sentence is analyzed to obtain semantic relations, so that the accuracy of paraphrase recognition is improved.

The invention discloses a method for relation extraction based on reinforcement learning. The relation extraction model based on reinforcement learning comprises an instance selector based on reinforcement learning and a relation classifier based on a PCNN model. The instance selector based on reinforcement learning obtains a selection result through a reinforcement learning process, and the selection result is a sentence that best expresses a package label in a package composed of sentences of the same entity pair. The selection result is input into the relation classifier, and sentences expressing the same relationship are identified according to the input sentences, and the instance selector is fed back. A strategy function is updated according to the feedback, and a better relation classifier is trained with the selected sentences to optimize the instance selection and relation classification process. Finally, the sentence that best represents the relation label is selected as the training data of the relation extraction model based on reinforcement learning. The invention reduces the influence of noise and coarse-grained problems of a remote supervision corpus on relation extraction, and improves the performance of relation extraction.

The invention discloses a knowledge graph construction method oriented to policy text semantic understanding, and relates to the technical field of knowledge graph construction, and the method comprises the following steps: collecting and preprocessing a policy text, extracting a structural text, and screening out sentences containing fuzzy keywords; identifying policy entities and relationships, extracting subjects, operations and fuzzy modification entities, and forming a triple; constructing a localized quantitative index library, accessing a regional economic database, and extracting historical data and distribution of key indexes; dynamically generating a quantization rule, and automatically quantizing the fuzzy expression into a specific threshold rule according to regional data; fusing and storing to a knowledge graph, and storing the triad and a quantization rule node into a graph database together; and providing semantic query and reasoning services, automatically triggering a quantization rule in response to query, and returning an explainable specific result. According to the method, abstract and fuzzy policy terms can be converted into specific and executable quantitative indexes.

The present application discloses a sentence tense recognition method, device and readable storage medium based on dependency syntax, wherein the sentence tense recognition method based on dependency syntax comprises: obtaining a sentence to be parsed, and performing dependency syntax analysis on the sentence to be parsed, obtaining a dependency syntax analysis result corresponding to the sentence to be parsed, and then performing sentence tense recognition on the sentence to be parsed based on the dependency syntax analysis result, and obtaining a sentence tense recognition result. The present application solves the technical problem of low accuracy in sentence tense recognition.

According to an embodiment, electronic devices (101, 201) comprise one or more processors (120, 320) and memories (130, 330) storing instructions. The instructions, when executed by the one or more processors, may be configured to cause the electronic devices to: identify a plurality of speakers on the basis of speech data included in content; identify a sign language sentence corresponding to an utterance related to a first speaker among the plurality of speakers; identify a duration time of the utterance and a motion time for the sign language sentence; adjust motion playback times for each of words included in the sign language sentence such that the motion time for the sign language sentence corresponds to the duration time of the utterance; and express the words included in the sign language sentence by using a graphic object related to the first speaker according to the adjusted motion playback times.

The invention provides a staged medical dialogue abstract method and system based on joint reinforcement learning, and the method comprises the steps: obtaining a multi-source medical dialogue, carrying out the statement recognition of the medical dialogue through a pre-constructed dialogue statement selector, and obtaining a key statement and a redundant statement; according to the key statements and the redundant statements, the medical dialogue is truncated, the truncated medical dialogue is input into a pre-constructed abstract generator, and a final electronic health record (EHR) text is generated; wherein the pre-constructed dialogue statement selector and the pre-constructed abstract generator are obtained by adopting a two-stage medical dialogue abstract model training method based on joint reinforcement learning. The invention provides a two-stage medical dialogue abstract method based on joint reinforcement learning, a staged medical dialogue abstract model and an end-to-end joint training method of the staged medical dialogue abstract model, and aims to generate a high-quality EHR text according to a doctor-patient dialogue by utilizing an existing pre-training language model.

To provide an automatic counseling system which can satisfy a cognitive aspect of a user to give a response with which the user has empathy.SOLUTION: An automatic counseling system 100 includes: a storage device 1 including an interaction scenario storage unit 11 storing therein an interaction scenario in which a plurality of question sentences and causal relations between the plurality of question sentences are registered; a question sentence generation unit 21 which outputs the question sentences registered in the interaction scenario to a user through an output unit 4; a response sentence recognition unit 22 which recognizes a response obtained from the user; and an emotional empathy response generation unit 26 which outputs an emotional empathy response corresponding to the polarity of an emotional expression detected from the response obtained from the user and satisfying the causal relations.SELECTED DRAWING: Figure 1

The present application discloses a sentence recognition method, device and computer-readable medium, which obtains an original combination of multiple words arranged in word order; inputs the original combination into a target N-gram grammar model, and if the original combination contains a name in a list of names of people and places, the target N-gram grammar model replaces the name contained in the original combination with a corresponding category label in the list of names of people and places, obtains the replaced combination, and calculates the probability associated with the replaced category label, and obtains the probability of the original combination as a sentence according to the probability associated with each word in the replaced combination, the probability associated with the category label, and the proportion of all names under the corresponding category label in the list of names of people and places. Compared with the existing N-gram grammar model, the target N-gram grammar model of the present application makes it easier to correctly recognize sentences containing names of people or places.

The application relates to an information input method and device, computer equipment, a storage medium and a program product. The application relates to the field of big data. The method comprises the following steps: obtaining customer voice information required by a target service, and identifying the customer voice information to obtain a sentence recognition result; obtaining a question and answer matching text according to the sentence recognition result and a question and answer library for a resource loan system which is constructed in advance; determining target question and answer information corresponding to the target service according to the question and answer matching text and an input domain matching library for the resource loan system which is constructed in advance; and sending the target question and answer information to a target terminal; and the target question and answer information is used for displaying the target question and answer information on the target terminal. The method can improve the service efficiency of input information.

The invention relates to the field of language and character information processing, in particular to a supplementation labeling system for uniquely distinguishing three groups of homomorphic abnormal sound phonemes of'machine / product, odd / seven and sparse / west 'through machine-readable symbols in a Chinese pinyin system, an input method, electronic equipment and a computer readable storage medium, and aims to provide a pinyin supplementation labeling system. On the premise of keeping the original spelling of the Pinyin scheme unchanged, the pronunciation of the product, the pronunciation of the seven and the pronunciation of the west are uniquely distinguished by using the recorded symbols (. J.q.x) of the Unicode, namely the prefix points and the original letters, so that the blind test of 100 thousand news corpora can be achieved, and after the method is adopted, the TTS misreading rate is reduced from 2.8% to 0.07%; the ambiguity of the ASR post-processing homomorphic and abnormal sound field is reduced by 62%, and the recognition accuracy of the whole sentence is improved by 3.4%; in a class test of Chinese as a foreign language, the correct rate of distinguishing initial consonants of learners is improved by 28%, and class hours are shortened by 30%; the symbol occupies 2 bytes, and the expansion rate is stored as lt; 0.5%, almost negligible; the method is completely compatible with Unicode, GB 18030 and ISO 10646, and a new character does not need to be made.

To allow for associating a more likely tag with a sentence.SOLUTION: A tag specification unit 101 identifies a skill of an employee from an inputted sentence and estimates at least one tag corresponding to the skill of the employee from a plurality of tags. A score calculation unit 102 calculates scores indicating likelihoods of the at least one estimated tag. An additional question presentation unit 103 presents an additional question sentence prompting a change of contents of the sentence if the scores calculated for the at least one estimated tag do not exceed a first threshold at all. A tagging unit 104 associates a tag which the score calculated for exceeds the first threshold, with the sentence if the tag which the score calculated for exceeds the first threshold out of the scores calculated for the at least one estimated tag.SELECTED DRAWING: Figure 1

The invention discloses a named entity recognition enhancement method and system based on a large language model, and belongs to the technical field of natural language processing, and the method comprises the steps: firstly, training the large language model through direct preference alignment, and enabling a generated rewritten text to be more adaptive to a recognition mode of a named entity recognition model in a semantic or syntactic structure; secondly, performing context rewriting on the input text for multiple times by utilizing a preference alignment large language model, and converting a difficult sample which causes recognition failure of the named entity recognition model or low-confidence output into a high-confidence recognizable candidate text; and finally, integrating a plurality of rewritten statement recognition results through a majority voting mechanism, and outputting a final entity recognition result in combination with an original sentence entity recognition result. According to the method, the recognition accuracy and robustness of the named entity recognition model in long-tail entity, unregistered word and complex context scenes are effectively improved.

The present invention discloses a hybrid expert multi-classification method and system combining an embedded dual-model architecture, which is applied to the field of data processing technology. By performing deep learning on a pre-trained model based on a data distribution consistency threshold and a corpus of scientific value sentence training materials, a scientific value sentence recognition model is constructed. Based on a hybrid expert mechanism, a scientific value sentence multi-classification model is built, wherein the scientific value sentence multi-classification model includes an academic value expert sub-model, an application value expert sub-model, an innovation value expert sub-model, and a gating network. The scientific value sentence recognition model and the scientific value sentence multi-classification model are encapsulated into a scientific value sentence detection dual model to obtain a scientific and technological literature. The scientific and technological literature is input into the scientific value sentence detection dual model to obtain a comprehensive classification result of scientific value sentences. It solves the technical problems of low processing efficiency and difficult accuracy guarantee in the existing scientific literature value sentence classification method when dealing with scientific and technological literature in the prior art.

The invention provides a statement recognition method, an electronic terminal and a computer readable storage medium. Comprising the following steps: processing a to-be-identified statement to obtain a feature vector corresponding to the to-be-identified statement; processing the feature vector to obtain boundary information, type information and segment information corresponding to the to-be-identified statement; wherein the boundary information represents the boundary of an entity in the to-be-recognized statement, the type information represents the type of each word in the to-be-recognized statement, and the segment information represents an entity segment in the to-be-recognized statement; and obtaining an identification result of the to-be-identified statement based on the boundary information, the type information and the segment information. According to the method and the device, when the statement is identified, the segment information is added as a reference, the segment information can support the identification of the long entity, and the segment information, the boundary information and the type information are combined, so that the segment-level information and the word-level information can be mutually dependent, the identification accuracy of the long entity in the statement is improved, and the statement identification accuracy is further improved.

The invention relates to a method for analyzing a language structure by using a language expression, which is suitable for analyzing structures of more than 7,000 languages on the earth. The method comprises the following steps of: analyzing a morphologic element and a syntactic structure of a target sentence by a morphologic element and syntactic analysis unit; and based on a pre-training language expression learning algorithm provided by a language expression learning algorithm unit, a language expression calculation unit generates a language expression for the morphologies and syntactic structures of the sentences. Wherein the language expression calculation unit is used for dividing a sentence into an upper left area, a lower left area, an upper right area and a lower right area by taking a sentence center symbol as a benchmark, a subject symbol is distributed in the upper left area, a core verb symbol is distributed in the lower left area, and a verb type symbol is distributed in the lower right area; non-predicate symbols representing remaining phrases other than subjects and verbs are assigned to the right upper region. Furthermore, symbolization specific information including marks (1-4) indicating a person and a character number mark (.) indicating the number of word characters such as nouns and adjectives is added to at least one of the left upper mark, the left lower mark, the right upper mark and the right lower mark of each symbol. By means of the method, the sentences in the specific language can be accurately analyzed into structured syntactic expressions, and therefore the efficiency of language processing such as sentence recognition, semantic understanding, translation and retrieval is improved.

The application relates to the technical field of intelligent interaction, in particular to an artificial intelligence interactive robot, which comprises a sentence recognition module for analyzing a sentence structure, separating a main stem and subsidiary content, marking a grammatical role to generate a semantic structure, a time labeling module for identifying and labeling a time sequence, a path construction module for extracting a historical path and rearranging, an expression cleaning module for identifying and removing redundancy, and an output generation module for connecting a buffer area and a path to generate a complete output. The application separates and reconstructs semantic elements by analyzing and identifying the main stem and subsidiary components through multiple rounds of sentence structure, realizes accurate separation and reconstruction of semantic elements by combining word class role marking, generates a time arrangement list according to a time expression sequence, improves semantic evolution judgment, matches a historical path to construct an expression rearrangement structure and enhance semantic connection, identifies redundant sentences to optimize structure and clarity, and realizes continuity and logical consistency of interactive content.

The present invention discloses a sentence recognition method and device, a storage medium, and an electronic device, which can be applied to smart transportation scenarios. The method comprises: determining a set of characters to be corrected in an original sentence; correcting the set of characters to be corrected in the original sentence to obtain a corrected sentence; obtaining the perplexity of the original sentence and the perplexity of the corrected sentence; and determining that the original sentence is incoherent if the perplexity of the corrected sentence decreases by a ratio greater than a preset threshold relative to the perplexity of the original sentence. This invention solves the technical problem of low sentence recognition efficiency.

The invention belongs to the technical field of document processing, and particularly relates to a synonymous sentence recognition method based on semantic feature analysis. Comprising the following steps: segmenting and splicing an input text, and establishing a statement set; performing normalization processing on the statements, eliminating invalid data and performing word segmentation processing; clue words of the candidate synonymous sentences are extracted according to the word segmentation result; screening and filtering, and establishing a statement set index; and generating a translated text by using a machine translation technology, and respectively performing embedded representation on the original statement and the translated text to obtain a polymorphic text representation result. On the basis of semantic representation of the generated words and sentences and translations thereof, word and sentence semantic representation results in various forms can be obtained, synonym features in original words and sentences and translated words are fully utilized to further enhance the accuracy and recognition approach of synonym recognition, judgment on whether the words and sentences are synonymous or not is enhanced, the synonym recognition effect is improved, and the recognition efficiency of the synonym sentences is improved. Efficient data processing of words and sentences and translations thereof is achieved, and a technical basis is provided for practical application of the synonymous sentence recognition method.

The invention discloses a hybrid expert multi-classification method and system combined with an embedded double-model organization structure, is applied to the technical field of data processing, and constructs a scientific value sentence recognition model by performing deep learning on a pre-training model based on a data distribution consistency threshold and a scientific value sentence training corpus. Based on a hybrid expert mechanism, a scientific value sentence multi-classification model is built, and the scientific value sentence multi-classification model comprises an academic value expert sub-model, an application value expert sub-model, an innovation value expert sub-model and a gating network. And packaging the scientific value sentence recognition model and the scientific value sentence multi-classification model into a scientific value sentence detection double model to obtain scientific and technical literatures. And inputting the scientific and technical literature into the scientific value sentence detection double model to obtain a scientific value sentence comprehensive classification result. The technical problems that in the prior art, when an existing scientific literature value sentence classification method is used for processing scientific literatures, the processing efficiency is low, and the accuracy is difficult to guarantee are solved.

An embodiment of the present invention provides a method, device, terminal device, and storage medium for generating official document content based on artificial intelligence. The method includes performing sentence recognition on a first text to obtain key sentences and a first position; performing recognition on the key sentences to obtain a first word and a first type; performing word replacement on the first word in the first text according to the first type to obtain a second text; performing clustering on the second text to obtain a clustering result and performing similar text analysis on the clustering result to obtain a general sentence and its second position; performing recognition on the general sentence to obtain a second word and a second type; extracting a first rule from the key sentences according to the first word and the first type; extracting a second rule from the general sentence according to the second word and the second type; obtaining a target keyword and a third type of the event to be announced; and generating target official document content according to the target keyword and the third type in combination with the first rule and the second rule according to the first position and the second position.

The present invention relates to a method for analyzing the structure of more than 7,000 languages existing on the earth, by using linguistic expressions, the method comprising the steps of: analyzing a morpheme and a syntax of a target sentence by a morpheme and syntax analysis unit; and calculating, by a linguistic expression calculation unit, on the basis of a pre-learned linguistic expression learning algorithm provided from a linguistic expression learning algorithm, a linguistic expression for the morpheme and the syntax of the sentence analyzed by the morpheme and syntax analysis unit, wherein the linguistic expression calculation unit divides the sentence into four parts including an upper left part, a lower left part, an upper right part, and a lower right part, around a sentence center symbol, assigns a subject symbol to the upper left part, assigns a core verb symbol to the lower left part, assigns a verb type symbol (or a predicate symbol) to the lower right part, assigns a non-predicate symbol for the remaining phrase, except for the subject and the verb, in the upper right part, and then inputs symbolized specific information such as a character count symbol (.) indicating the character count of a noun, an adjective, and the like with a number, along with person symbols (1 to 4) indicating a first person, a second person, a third person, and a non-person to at least one of four subscripts including an upper left script, a lower left subscript, an upper right subscript, and a lower right subscript of each assigned symbol. Accordingly, a specific sentence of a specific language is precisely analyzed into an accurate sentence structure, thereby improving the efficiency of linguistic usages such as sentence recognition, interpretation, translation, search, and the like.

The invention relates to the technical field of health informatics, in particular to an intelligent management method and system for health big data, and the method comprises the steps: recognizing sentences from a handwritten character region of a prescription image to be recognized; determining candidate characters of each character in the sentence; combining the candidate characters of each character to obtain a candidate character group; according to the similarity between the candidate characters in the candidate character group and the corresponding characters, determining the possible degree of the candidate character group as the recognition result of the sentence; according to the occurrence frequency of vocabularies formed by the candidate characters in the candidate character group in the database, determining the comprehensive reasonability degree of the recognition result of taking the candidate characters in the candidate character group as the sentences; determining the recognition accuracy of the recognition result of taking the candidate characters in the candidate character group as the sentences by utilizing the possible degree and the comprehensive reasonability degree; and selecting the candidate character in the candidate character group with the highest recognition accuracy as a sentence recognition result. Therefore, the recognition accuracy of the prescription content in the prescription image is improved.

The embodiment of the present application relates to the technical field of character recognition, and specifically discloses a picture recognition method and system for a scanning pen, comprising: determining a character picture containing one character and a sentence picture containing multiple characters according to a picture sequence output by a camera, performing character recognition on each character picture to obtain N candidate characters of each character picture and the probability of each candidate character, inputting the sentence picture into a pre-trained sentence recognition model to obtain a candidate sentence, inputting the candidate sentence into a semantic analysis model to obtain a first score of the candidate sentence, calculating a second score of the candidate sentence using the probability of each character in the candidate sentence, calculating the confidence of the candidate sentence according to the first score and the second score, and determining the candidate sentence as a target output sentence when the confidence is greater than a preset threshold, the embodiment is fast and efficient in recognizing character pictures and sentence pictures, and the accuracy is high in determining the target output sentence through the confidence of the candidate sentence.

The invention relates to a statement recognition method and device, electronic equipment, a storage medium and a program product. The method comprises the steps of obtaining a to-be-recognized statement; performing word segmentation processing on the to-be-recognized statement to obtain a plurality of segmented words included in the to-be-recognized statement; inserting a plurality of flag bits into the plurality of segmented words to obtain a target statement feature; performing coding processing on the target statement features to obtain a plurality of first vectors; performing cross attention enhancement processing on the plurality of first vectors to obtain a plurality of second vectors, one second vector being enhanced by other first vectors based on the corresponding first vector; and decoding the plurality of second vectors to generate a plurality of recognition results matched with the to-be-recognized statement, the plurality of recognition results including an intention classification result matched with the intention classification flag bit and at least one recognition result matched with the at least one target flag bit.

The present application relates to a method, device, equipment, storage medium and program product for identifying a target sentence. The method comprises: obtaining a document to be processed and a target entity; performing word segmentation processing on the document to be processed to obtain a number of word segments; generating a word vector for each word segment according to a preset rule; generating a target sentence syntax tree corresponding to each sentence in the document to be processed according to the word segmentation; judging each sentence according to the word vector and the target sentence syntax tree to obtain a target sentence corresponding to the target entity. The method can accurately identify the target sentence corresponding to the entity.

The present application belongs to the technical field of power file rule extraction and change comparison, and particularly relates to a policy file intelligent rule extraction and change comparison method for electricity charge verification, comprising: analyzing, reconstructing and optimizing the electricity-related policy files, and retaining the original context and logical level information; designing core sentence recognition Prompt templates and rule extraction conversion Prompt templates, constructing a policy rule extraction intelligent agent, guiding a large language model to recognize core sentences, extract rule element information and form standardized policy rule descriptions; searching for similar policy rules from a historical policy rule description knowledge base, constructing a policy rule comparison intelligent agent, and performing deep semantic comparison and change analysis on the current standardized policy rule description and the historical similar policy rule description, so as to realize the automatic identification of the added and modified contents of the current rule and the historical rule, and provide key technical support for the automation and intelligentization of electricity charge verification business rule generation.