20 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 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 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.

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 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 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 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 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 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.

The invention provides a computer-implemented method and system for analyzing texts. The method comprises the steps of identifying one or more sentences of a first text in a first language; identifying one or more sentences of a second text in a second language; translating the identified one or more sentences of the first text from the first language into the second language; processing the sentences of the first text in the second language and the sentences of the second text in the second language into a first representation of the sentences of the first text, and a second representation of the sentences of the second text; and comparing the first representation of sentences of the first text with the second representation of sentences of the second text to identify one or more sentences of similarity between the first text and the second text.

To provide computer programs, information processing devices, and communication systems that enable more accurate and convenient information presentation. [Solution] The computer program causes the computer to receive a first sentence in natural language via a predetermined communication application, identify related data for the first sentence, and provide the identified related data along with the first sentence to a first language model that has been trained to output a response sentence for a given natural language sentence. The program then outputs response data based on the response sentence output by the first language model via the predetermined communication application.

This application proposes a communication statement recognition method, apparatus, computer device, and readable storage medium. The method includes: splitting communication text converted from current communication audio into multiple first communication statements; selecting multiple second communication statements from the multiple first communication statements based on attribute information corresponding to each first communication statement; determining the target complaint tendency of each second communication statement based on each second communication statement and a preset classification model; and determining the overall complaint tendency of the current communication audio based on the target complaint tendency of each of the multiple second communication statements. The technical solution of this application can automatically determine the level of complaint tendency in communication audio, reducing the manual and time costs consumed in determining complaint tendency, while improving the accuracy of complaint tendency recognition.

The application provides a sentence processing method and device, electronic equipment and a readable storage medium. When a server for sentence recognition set by an operator acquires voice data to be processed, a first machine learning model or a second machine learning model with different calculation amounts is selected according to the intelligibility of the voice data to be processed, and the sentences in the voice data to be processed are processed by word segmentation and part-of-speech tagging, so as to ensure the accuracy of processing the sentences while improving the speed and efficiency of processing the sentences.

The application provides an auxiliary learning system for high school English subject reading comprehension questions, which helps students better improve their English learning ability. First, download our application software through APK file on Android mobile terminal; second, ask the specific learning level of the user, and divide the learning mode of the software into "high", "medium" and "low" three modes according to the evaluation score input by the user, so as to provide different difficulty word and sentence recognition and analysis; then, further ask the learning interest of the user, and recommend high-quality related category good articles for the user in real time through the interface of ChatGPT by inputting the characteristic words of the user; finally, the user can select the necessary words and articles to be collected, and view the content and analysis in the collection folder at any time. The auxiliary learning software for high school English subject reading comprehension questions can accurately carry out personalized teaching on the high school student group, improve the English reading learning efficiency of the user, and promote the improvement of the English ability of the user and the popularization of culture.