308 results about "Phrase" patented technology

Techniques for document recommendation based on conversational log for real time assistance are described. A first machine learning module identifies key phrases of a conversational log in real time. The first machine learning module executes multiple machine learning models trained to determine a probability that a portion of a conversation includes a key phrase. A second machine learning module identifies assistance pertaining to the identified key phrases of the conversational log. The second machine learning module executes a machine learning model trained to identify semantic similarity and word matching features of embedding representations of the key phrases and a knowledge base of assistance. The assistance is provided to a user during a conversation in real time.

Systems and methods are described for obtaining accurate responses from large language models (LLMs) and chatbots, including for question and answering, exposition, and summarization. These systems and methods accomplish these objectives via use of noun phrase avoiding processes such as a noun phrase collision detection process, a query splitting process, and a topical splitting process as well as by use of formatted facts, formatted fact model correction interfaces (FF MCIs), bounded-scope deterministic (BSD) neural networks, processes and methods, and intelligent storage and retrieval (ISAR) systems and methods. These systems and methods avoid and bypass noun phrase collisions and correct for errors caused by noun phrase collisions so that hallucinations are eliminated from LLM responses.

The invention relates to the technical field of natural language processing, in particular to an AI reading management and control method and system based on artificial intelligence, and the method comprises the following steps: carrying out text word segmentation processing on an input original text, segmenting the text into independent sentences, recognizing basic word units in each sentence, analyzing semantic adjacency relationships and syntactic structure features among vocabularies, and carrying out word segmentation processing on the word units; screening and extracting potential phrases representing paragraph meanings, and establishing a candidate semantic unit set; according to the method, through word segmentation, syntactic structure recognition and semantic adjacency analysis of the original text, potential phrases capable of representing paragraph significance are extracted, the candidate semantic unit set is constructed, and modeling of the semantic structure in the text is achieved. And associating the set with the reading fixation duration and the playback action of the user sentence by sentence to obtain a reading behavior response of each semantic fragment, and executing semantic weighting and reading behavior cross analysis according to the reading behavior response. Through the linkage mode, the semantic focus actually focused by the user at present can be recognized.

Systems and methods are described for obtaining accurate responses from large language models (LLMs) and chatbots, including for question and answering, exposition, and summarization. These systems and methods accomplish these objectives via use of noun phrase avoiding processes such as a noun phrase collision detection process, a query splitting process, and a topical splitting process as well as by use of formatted facts, formatted fact model correction interfaces (FF MCIs), bounded-scope deterministic (BSD) neural networks, processes and methods, and intelligent storage and retrieval (ISAR) systems and methods. These systems and methods avoid and bypass noun phrase collisions and correct for errors caused by noun phrase collisions so that hallucinations are eliminated from LLM responses.

The invention discloses a question answer determination method and device and electronic equipment. The method comprises the steps that a to-be-retrieved question input by a target object is obtained, a target document associated with the to-be-retrieved question is obtained, and the target document comprises an internal document in an internal database and real-time knowledge in an external knowledge base; determining a first semantic vector and a first keyword corresponding to the to-be-retrieved question, and determining a second semantic vector and a second keyword corresponding to the target document; according to the first semantic vector, the second semantic vector, the first keyword and the second keyword, determining a candidate phrase with the highest association degree with the to-be-retrieved question from the target document; and analyzing the candidate phrases by adopting a generative language model to obtain an answer to the to-be-retrieved question. According to the method and the device, the technical problems of low retrieval efficiency and inaccurate semantic matching in problem retrieval in related technologies are solved.

The invention discloses a large language model reasoning acceleration method and device based on two-stage speculative decoding and a storage medium, and the method comprises the steps: constructing and initializing a Trie tree, and inserting a historical corpus, and phrase sequences in a document library or a code library into the Trie tree one by one; in the reasoning process, longest prefix matching is carried out based on a Trie tree, and a candidate draft sequence is generated by adopting branch backtracking and recursive search; performing confidence evaluation on the candidate draft sequence, calculating a joint confidence score of the sequence through probability multiplication and a Top-K screening mechanism, and judging whether the joint confidence score reaches a confidence threshold; if the accumulated confidence of the candidate sequence reaches a threshold value, skipping a small model generation stage, and directly entering large model verification; otherwise, entering a small model draft completion stage; and the final large model takes the replaced and updated draft sequence as final output. According to the method, adaptive acceleration of the decoding process can be realized, and the long text reasoning delay of the large language model is remarkably reduced while the generation quality is ensured.

Computer-based generation of information-gathering questions in response to a user query can include parsing the user query using natural language processing and extracting from the user query one or more phrases corresponding to a predetermined category. A knowledge database can be accessed, and entities semantically related to each phrase can be extracted therefrom. A query sub-graph representing a relationship between each of the one or more phrases and the entities extracted from the knowledge database can be generated. An expanded user query can be generated by traversing the query sub-graph. Passages semantically related to the expanded user query can be retrieved from one or more passages databases and ranked. A neural question generator can generate a set of information-gathering questions based on the expanded user query and a group of select passages selected from the plurality of passages in accordance with each selected passage's ranking.

A server generates a user interface for allowing a user to rewrite portions of text for an electronic document to mitigate detected issues. For an input document, the server generates one or more indications over the one or more phrases in the sentence. An indication for a phrase may be generated based on a respective category associated with the phrase. Responsive to receiving an indication from the user to rewrite the sentence, the server generates a prompt to a machine-learned language model. The server receives a response generated by executing the machine-learned language model on the prompt. The server generates a pane user element to present the candidate sentence and an evaluation of the candidate sentence to the user, and responsive to receiving a selection of a candidate sentence, replacing the sentence in the editor with the selected sentence on the user interface.

The invention provides a retrieval method and device based on graph structure retrieval enhancement, electronic equipment and a storage medium, and the method comprises the steps: obtaining original data, screening the original data based on a preset screening rule to obtain a plurality of candidate phrases, calculating the similarity between the plurality of candidate phrases and a preset central semantic vector of each layer, the multiple candidate phrases are layered according to the similarity, feature vectors are constructed, levels and feature vectors corresponding to the multiple candidate phrases are obtained, graph entities are obtained based on the candidate phrases, context fragments of the graph entities in original data are extracted, and relation types between the graph entities are obtained based on the context fragments; according to the relationship type between the graph entities and the hierarchy of the graph entities, a multi-hierarchy knowledge graph is obtained, and retrieval is performed based on the multi-hierarchy knowledge graph and the corresponding associated information block, so that the technical problems of result redundancy and logic fracture of a retrieval enhancement generation method are solved through the method.

Disclosed herein are system, method, and computer program product aspects for textual data extraction, generation, and evaluation. Text is input into a first fine-tuned large language model (LLM) to generate an atom (e.g., a textual phrase in a particular category). The atom is input into a second LLM that has been fine-tuned for structured output corresponding to the particular category of information. A logical structure is generated based on a structured output of the second LLM, wherein the logical structure represents the textual phrase of the atom and contains a contextual attribute associated with the textual phrase. The embodiment then stores the logical structure into a knowledge graph as a modifier node having a time-variant attribute (e.g., a timestamp associated with the textual phrase and / or the contextual attribute).

Disclosed are systems, apparatuses, processes, and computer-readable media for processing one or more images. For example, an apparatus comprising one or more processors and configured to: receive a natural language response from a first machine-learning model; segment the natural language response into a set of phrases; classify each phrase in the set of phrases based on at least one corresponding phrase in at least one ground truth response; remove a first subset of phrases from the set of phrases based on respective classifications of the first subset of phrases, wherein the first subset of phrases are not verified in the at least one ground truth response; and compute a metric associated with the first machine-learning model based on respective classifications of a second subset of phrases from the set of phrases, wherein the second subset of phrases are verified in the at least one ground truth response.

A tailored interactive language learning system that teaches an individualized set of vocabulary words to users through interactive avatars and stories. The interaction is modeled through probabilistic rules in a semantic network and neural network having objects and relations. Dialog and narration is generated dynamically based on the state of the interactive story model using phrasal rewrite rules and neural network implementiung a four-valued logic system in which truth values of the objects and relations are encoded as true, false, defined, and undefined in a single memory array.

A method including applying a language model to datasets to generate topics assigned to the datasets. Each of the topics includes at least one of a natural language text word and a natural language phrase. The method also includes applying an encoding model to the topics to generate a corresponding vector data structures storing embedded topics. Each embedded topic of the embedded topics is associated with one corresponding vector in the vector data structures. The method also includes applying a clustering model to the vector data structures to generate a cluster including a subset of the vector data structures. The subset includes a reduced number of the vector data structures. The method also includes modifying, according to the cluster, the datasets.

Method, software, and apparatus for improved Augmentative and Alternative Communication (AAC) solutions. In one aspect, a user interface is provided with a set of suggestions comprising text, phrases, etc., and navigation buttons that enable users to select words and phrases to add to be written and / or spoken in a manner that reduces the number of user inputs. The suggestions are displayed in alphabetical order in rows with navigation buttons adjacent to the rows, with activation of a navigation button resulting in generation of updated suggestions having alphabetical ranges that are bounded by suggestions in associated rows. This approach may be combined with predictive text means to enable users to easily formulate text and / or speech content.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sanitizing artificial intelligence prompts. One of the methods includes receiving a message a) for an external system and b) that comprises two or more phrases; for at least one phrase from the two or more phrases: determining a context of the phrase in the message; determining, using the context, whether modification of the phrase will likely maintain an intent of the message; determining whether to permit unedited transmission of the message to the external system using a result of at least one of one or more determinations whether modification of the phrase will likely maintain the intent of the message; and performing one or more actions using a result of the determination whether to permit unedited transmission of the message to the external system.

The invention discloses a hierarchical rhythm mapping-driven short video copywriting mood automatic adjustment method, and relates to the technical field of video processing, and the method comprises the steps: 1, receiving a text character string and a language type identifier, and building an occupation column for bearing a tone mark, an accent mark and a duration mark at each level; 2, dividing each sentence into phrase segments based on the hierarchical index table, freezing boundaries by taking the phrase segments as units, presetting sentence end termination styles according to punctuations, determining kernel phrases according to semantic anchor points, initializing trends of the kernel phrases, and performing time sequence elastic alignment and hierarchical backfilling to obtain a sentence end termination pattern; and finally outputting a triple sequence which covers all syllables and is composed of tone marks, accent marks and duration marks as a target rhythm control sequence. And step 3, performing audio generation based on the target rhythm control sequence to obtain new dubbing. According to the method, the tone accuracy and expressive force of short video dubbing are improved, and the time and cost of manual adjustment are remarkably reduced.

Systems and methods are used to detect underlying themes from a collection of documents at an aggregated level. A representative set of documents may be selected from a cluster of documents, with the representative set of documents corresponding to a general theme of the cluster. Candidate theme phrases may then be extracted from the documents and used to generate document embeddings and candidate phrase embeddings, which may be ranked, such as with a diversity-based ranking approach. Certain candidates may be selected from the ranking. Each of the documents forming the representative set may then be concatenated and a query embedding may be generated and ranked against the candidate phrases. In this manner, a collection of phrases associated with both the general underlying theme of the cluster, along with granular topics associated with that theme, may be identified.

An information processing method includes: obtaining, as text information, information related to communication by a person; performing emotion analysis on a plurality of words or phrases after breaking down the text information into the plurality of words or phrases by performing morphological analysis on the text information; and visualizing an analysis result of the emotion analysis according to each row and column of a matrix table by forming the matrix table by arranging, in a first direction, a plurality of emotional expression-related items that represent human emotions and arranging, in a second direction, an attribute category-related item that indicates an attribute of the person or an organization.

The invention relates to the technical field of natural language processing, in particular to a long text matching method and system based on key information and difference characteristics, and solves the problems that in the prior art, key information is dispersed due to noise interference in long text processing, and semantics of words or phrases in long text processing are more fuzzy and diversified. According to the method, a long text is preprocessed to obtain a test set sentence pair, a training set sentence pair and a verification set sentence pair, then a training model is obtained through sentence-level information entropy screening, word-level dynamic filtering, semantic difference enhancement and adaptive feature fusion, and finally after verification is conducted through the verification set sentence pair, the test set sentence pair predicts and outputs a result. The system comprises a long text matching system data preprocessing unit, a long text matching system function module training unit and a long text matching system function module result output unit. Key information is extracted for learning in long text matching, a large amount of computing power does not need to be consumed, and the matching effect is improved.

Techniques for causing an LLM to generate semantically related phrase variations for an identified phrase are disclosed. An LLM that is generally pre-trained on an arbitrary corpus of language training data is accessed. Seed data is fed as input to the LLM. The seed data includes multiple phrases that are semantically related and that describe a command. When any one of the phrases is received as utterance input, the utterance input triggers execution of the command. The LLM generates multiple phrase variations based on the phrases, where each phrase variation is semantically related to the other phrases. When any one of the phrase variations is received as new utterance input, the new utterance input also triggers execution of the command. The phrases and phrase variations are then stored together in a data storage.

The invention provides an intelligent processing method and system from structured data to a text based on a natural language, and relates to the technical field of data processing.The method comprises the steps that the text chunk analysis process is optimized and adjusted according to analysis optimization parameters, sentences are segmented into non-overlapping phrases with syntactic function labels, and the text after chunk analysis is obtained; performing syntactic and semantic structure analysis on the text subjected to block analysis, and establishing a semantic association relationship between internal structures of sentences through component analysis, dependency analysis and semantic dependency graph analysis to obtain structured semantic information; performing multi-sentence logic association analysis on the structured semantic information on a chapter level to obtain semantic information of the whole chapter; and based on the semantic information of the overall chapter, obtaining a target natural language text by utilizing a pre-trained large language model. According to the method, the accuracy and fluency of conversion from the structured data to the text are improved.

Improve the accuracy of dependency analysis. [Solution] A program to be executed by a computer having a processor and a memory. The program causes the processor to execute the following steps: restoring case particles using a case frame; determining a modifier clause from among multiple phrases based on the restored case particles; and presenting information about the destination of the identified predicate based on the properties of the modifier clause. The step of determining the modifier clause includes the steps of extracting a part of speech or a part of speech group from a subordinate clause included in the restored sentence; determining whether the part of speech or the part of speech group can be connected to at least one of the subject and the topic included in the sentence based on connection information; and determining the modifier clause based on the determination result. The connection information has a data structure that associates, for each part of speech or part of speech group, whether the part of speech or the part of speech can be connected to at least one of the subject and the topic, with connection constraints.

To provide a translation device 110 capable of displaying an easily understandable translation even when an original text contains words that are difficult to translate literally. A translation device 110 according to the present disclosure includes an original text acquisition unit 10 that acquires an original text to be translated; an annotation target extraction unit 20 that inputs the original text acquired by the original text acquisition unit 10 to an artificial intelligence unit 200 and acquires and outputs annotation target phrases contained in the original text that are difficult to translate from the artificial intelligence unit 200; an annotation addition unit 30 that acquires annotation information corresponding to the annotation target phrases output by the annotation target extraction unit 20 and generates an annotated original text by adding the annotation information to the annotated target phrases; a translation unit 40 that translates the annotated original text generated by the annotation addition unit 30 into a language to be translated, thereby generating an annotated translation; and a display processing unit 50 that displays the annotated translation translated by the translation unit 40 on a display device 400.

Techniques for performing contextualized intent and slot extraction using a large language model (LLM) are disclosed. The LLM is generally pre-trained on an arbitrary corpus of language training data. A prompt is provided to the LLM. This prompt includes a limited number of prompt phrases. The prompt phrases share a semantic relationship with one another. A spoken utterance is recorded and then converted to text, resulting in generation of a transcription. The transcription is provided to the LLM. The LLM extracts, from the transcription, an extracted intent and an extracted slot. The extracted intent is determined to be related to a prompt-described intent that was included in the prompt. The prompt is supplemented by adding the extracted intent and the extracted slot to the prompt, resulting in the extracted intent being identified as sharing the semantic relationship with the other prompt phrases in the prompt.

The invention provides a credit granting approval process analysis method and device. Comprising the steps of performing word segmentation on text content in a credit granting approval document set, and combining the obtained segmented words to obtain combined phrases; calculating weighted word frequency-inverse document word frequency of the combined phrases; target phrases with weighted word frequency-inverse document word frequency larger than a word frequency threshold value are screened out from the combined phrases, and an amplified word list is generated according to the target phrases and the original word list; training a target word segmentation device based on the amplified word list; finely adjusting the basic vector model according to the training corpus to obtain a term vector model; analyzing the auditing opinion information based on a large language model to obtain an initial risk analysis rule containing a preset dimension; based on a similarity algorithm, a target word segmentation device and a term vector model, grouping and integrating the initial risk analysis rules to obtain risk analysis rules; and processing the information of each examination and approval stage by using a big language model and adopting a risk analysis rule to obtain examination and approval suggestion information.

The invention provides a multi-word expression-oriented machine translation differential test method aiming at the problem of inaccurate multi-word expression semantic translation in a mainstream machine translation system. The method comprises the following steps that a word segmentation tool based on deep learning is adopted to divide words into vocabulary units, syntactic labels are distributed in combination with a pre-training sequence marking model, and a dependency analysis tool spaCy is utilized to mark the syntactic relation between the words; converting the tagged corpus into a standard CoNLL format, extracting a multi-word expression of a sentence through an automatic tool, and establishing a test data set of a sentence-level and phrase-level corresponding relationship; inputting the test set into a multi-translation system to generate a translation, and using an alignment tool AWESOME to accurately locate a corresponding relationship between a source language and a target language MWEs; the translation similarity is calculated based on BERTScore, mistranslation, translation omission and non-translation are recognized through an intra-group and inter-group dual check mechanism in combination with a dynamic threshold value, and evaluation of the translation accuracy of machine translation on multi-word expression is completed. According to the method provided by the invention, multi-word expression translation errors can be accurately recognized, and the accuracy of phrase-level semantic translation of a machine translation system is finely evaluated through a differential test method.

Disclosed herein are system, method, and computer program product embodiments for machine learning systems to process interactive communications between at least two participants. Speech and text, within the interactive communications, are analyzed using machine learning classifiers to extract prosodic, semantic and key phrase cues located within the interactive communications to identify changes to emotion, sentiments and key phrases. A summary of the interactive communications between a first participant and a second participant is generated at least, in-part, based on the extracted prosodic, semantic and key phrase cues and the summary is highlighted based on any of the changes to emotion, the sentiments or the key phrases.

Techniques for performing contextualized intent and slot extraction using a large language model (LLM) are disclosed. The LLM is generally pre-trained on an arbitrary corpus of language training data. A prompt is provided to the LLM. This prompt includes a limited number of prompt phrases. The prompt phrases share a semantic relationship with one another. A spoken utterance is recorded and then converted to text, resulting in generation of a transcription. The transcription is provided to the LLM. The LLM extracts, from the transcription, an extracted intent and an extracted slot. The extracted intent is determined to be related to a prompt-described intent that was included in the prompt. The prompt is supplemented by adding the extracted intent and the extracted slot to the prompt, resulting in the extracted intent being identified as sharing the semantic relationship with the other prompt phrases in the prompt.

A system and method of identifying, by at least one processor, an occurrence of a semantic variant of a phrase in a paragraph may include calculating a phrase embedding vector representing a semantic meaning of the phrase; extracting at least one hierarchical set of nested sequences of words from the textual representation of the paragraph; calculating, for each sequence, a corresponding sequence embedding vector representing the semantic meaning of the sequence; calculating, for one or more sequence embedding vectors, a corresponding vector similarity value representing a similarity of the sequence embedding vector and the phrase embedding vector; identifying a sequence corresponding to a maximum vector similarity value of the one or more vector similarity values; and determining the identified sequence as a semantic variant of the phrase based on the maximum vector similarity value.

The application provides a passage-level relation extraction method and device, electronic equipment and a storage medium, wherein the passage-level relation extraction method comprises: obtaining a target passage text, the target passage text being a passage text identified with pronouns and noun phrase references aligned with the pronouns; based on the target passage text and a preset relation extraction model, obtaining semantic relations between different entity pairs in the target passage text and relation categories of the semantic relations. The application can effectively improve the accuracy and reliability of passage-level relation extraction.