49 results about "Morpheme" patented technology

The application relates to the technical field of text label marking, and provides a text specification marking method and system based on a rule corpus, which comprises the following steps: analyzing a policy and regulation document, identifying and marking condition morphemes and conclusion morphemes in the policy and regulation document, constructing a logical relationship between the two by using a large language model, and forming a rule corpus composed of structured morpheme pairs; performing semantic embedding on the corpus to generate a semantic vector library; performing multi-label coding on a verification data set based on the rule corpus, and constructing a multi-label training data set; training a deep learning classification model by taking semantic vectors as features and multi-labels as targets, so that a text specification marking model is obtained; and automatically marking target text by using the model. The application significantly improves the accuracy, interpretability and business adaptability of text marking, improves the update quality of a system label data set, and reduces the system maintenance cost.

An inference method and apparatus for a large language model, which method and apparatus are used for improving the inference calculation efficiency of a large language model. The method comprises: receiving an inference task, which carries a morpheme number, wherein the morpheme number is used for identifying a morpheme to be subjected to inference calculation, the morpheme comprising one or more sub-words determined on the basis of input text of a large language model (201); on the basis of the morpheme number corresponding to the inference task, querying a global index tree to determine a target inference node, wherein the global index tree comprises sub-trees corresponding to a plurality of inference nodes in a distributed inference cluster, and a sub-tree corresponding to the target inference node is a sub-tree in the global index tree, the matching degree of similarity of which sub-tree with the morpheme number is greater than a threshold, the matching degree of similarity indicating the number of pieces of reusable key-value cache data during inference calculation (202); and on the basis of the target inference node, executing the inference task (203).

The embodiment of the invention discloses an inference method and device for a large language model, which are used for improving the inference calculation efficiency of the large language model. The method comprises the steps that an inference task is received, the inference task carries morpheme numbers, the morpheme numbers are used for identifying morphemes to be subjected to inference calculation, and each morpheme comprises one or more sub-words determined based on an input text of a large language model; a global index tree is inquired based on morpheme numbers corresponding to the reasoning tasks, target reasoning nodes are determined, the global index tree comprises sub-trees corresponding to multiple reasoning nodes in a distributed reasoning cluster, and the sub-trees corresponding to the target reasoning nodes are sub-trees with the similarity matching degree with the morpheme numbers larger than a threshold value in the global index tree; the similarity matching degree indicates the number of reusable key value cache data in reasoning calculation. And executing the reasoning task based on the target reasoning node.

The invention relates to the technical field of text label marking, and provides a text standard marking method and system based on a rule corpus, and the method comprises the steps: analyzing a policy and regulation file, recognizing and marking a condition morpheme and a conclusion morpheme in the policy and regulation file, constructing a logic relation between the condition morpheme and the conclusion morpheme by using a large language model, and marking the rule corpus; forming a rule corpus consisting of structured morpheme pairs; performing semantic embedding on the corpus to generate a semantic vector library; performing multi-label coding on the verification data set based on the rule corpus, and constructing a multi-label training data set; training a deep learning classification model by taking the semantic vector as a feature and taking multiple tags as a target to obtain a text specification marking model; and automatically marking the target text by using the model. According to the method, the accuracy, the interpretability and the service adaptability of text marking are remarkably improved, the updating quality of the system label data set is improved, and the system maintenance cost is reduced.

Systems and methods evaluate the meanings of whole words bound within the meanings of their parts by analyzing and identifying features and components of words (such as letters and syllables), using sound information, for example phoneme class structure, to find sound correlation and using synonymity to find meaning correlation between words (or word parts) and a data set of known / identifiable sound / meaning associations called morphemes to find morpheme‑word‑parts that optimally describe an input word. Various means are described of compiling morphemes into a data set. The systems and methods further include analyzing the semantic functions of word parts and their modifying interrelationships, and using identifications made by one or more analyses. The systems and methods can evaluate or improve understanding of word meanings. The systems and methods are useful in researching sound / meaning associations in language generally and for improving language processing generally by the incorporation of more semantic information.

The invention relates to the technical field of computers, and discloses a multi-task processing-oriented Soc chip server computing power distribution method, which comprises the following steps of: acquiring execution primitive vectors of at least two tasks concurrently executed on an Soc chip; converting the execution primitive vector into an execution symbol sequence corresponding to each task; based on the execution symbol sequence, identifying an execution morpheme representing a task execution stage, and constructing a task grammar state machine, used for predicting a next morpheme, of each task; analyzing cross-task morpheme association between the execution morphemes of the concurrent tasks; and on the basis of the current morpheme of a certain task, the predicted next morpheme is associated with the cross-task morpheme, and a collaborative scheduling instruction is generated. By converting the execution primitive vector into the execution symbol sequence and identifying the execution morphemes based on the sequence to construct the task grammar state machine, the prediction of the next execution stage of the task is realized.

To provide a diagram creation method capable of conceptualizing and schematizing person's thoughts, an information processing system and a program.SOLUTION: A model diagram creation method to be executed by a computer performs processing for dividing contents of a text-converted interview in each morpheme, adding a part of speech of the morpheme to each of a plurality of divided morphemes, aggregating the plurality of morphemes attached with the part of speech to one or more groups on the basis of meaning, generating a morpheme for generalizing a plurality of morphemes included in each of the one or more groups, adding a part of speech of a morpheme to each of the generated one or more morphemes for generalization, and associating morphemes other than the plurality of morphemes included in each of the one or more groups among one or more morphemes added with a part of speech for generation and the plurality of morphemes added with a part of speech, with components of a model diagram, and creating a model diagram on the basis of a result by associating the plurality of morphemes with the components of the model diagram.SELECTED DRAWING: Figure 3

Provided are a method for segmenting sign language into morphemes, a method for predicting morpheme positions, and a method for augmenting data. A system for analyzing sign language according to an embodiment of the present invention comprises: a recognition unit which recognizes key points of a speaker from a sign language video; and a prediction unit which inputs the recognized key points into an artificial intelligence model, segments the sign language into morphemes, and predicts position information of the segmented morphemes. Accordingly, by recognizing the morphemes of the sign language video frame by frame on the basis of a skeletal model and thereby segmenting the sign language into morphemes and predicting morpheme positions, it is possible to lay the foundations for accurate sign language translation.

The invention relates to the field of text matching, in particular to a text matching method and device, computer equipment and a storage medium, which are based on morpheme-based embedded representation and word-based embedded representation, and adopt a quantum mixed state modeling method to construct quantum mixed state representation of semantic and grammatical knowledge with finer granularity. According to the method, the language complexity is effectively captured, the real human cognitive process is simulated, quantum measurement is carried out based on constructed quantum mixed state representation, the semantic probability of a text in a single direction is obtained and used for text matching, and the text matching precision and efficiency are improved.

The present invention provides an apparatus for correcting original text in an image by using a natural language processing processor. The apparatus for correcting original text in an image by using a natural language processing processor comprises a natural language processing processor and a memory, wherein the memory stores instructions that, when executed, cause the natural language processing processor to: identify text data converted from image data; classify the text data by sentence on the basis of morphemes; identify a first sentence in which a subject and / or an object is missing in the text data classified by sentence; input the first sentence and the domain of the image data into a pre-trained deep learning model; receive first modified data from the deep learning model; identify a first final sentence by including the first modified data in the first sentence; and generate modified text data for translation by including the first final sentence, instead of the first sentence, in the text data.

The present invention discloses a malicious program behavior characterization method based on a morpheme word vector model, which includes sorting and abstracting the captured malicious program function call information, extracting high-frequency sequences, and setting segmentation points; performing redundancy removal and de-obfuscation to obtain a new function sequence S'; obtaining the morphemes in the function name f to obtain the corresponding morpheme list M of the function, filling the marker Mask for the morpheme list with a non-maximum length, numbering the morphemes and function names respectively, and applying one-hot encoding to the numbers of the function names, morphemes, and placeholders to train the word vector model; calculating the feature vector of the function and calculating the TF-IDF of each function. It effectively solves the encryption and obfuscation problems existing in dynamic function calls and can quickly perceive and understand the behavior of malicious programs.

A method of processing a natural language may include generating a grammar used for analyzing a natural language by compressing a plurality of languages including common elements so that resources and time required for recognizing a grammar of an input sentence may be reduced. The method of processing a natural language may include separating an input sentence in units of morphemes, recognizing a grammar of the input sentence separated in units of morphemes, and analyzing a meaning of the input sentence based on the recognized grammar. The recognizing of the grammar may include recognizing a grammar that matches the input sentence separated in units of morpheme from among a plurality of pre-stored grammars, and the plurality of pre-stored grammars may include at least one grammar obtained by compressing two or more grammars to which at least one element among a plurality of elements constituting a single grammar is common.

The invention discloses a boundary perception and pre-training enhanced low-resource Tibetan language recognition method and system, and the method comprises the following steps: 1, carrying out the standardization processing of data and texts, and enabling the language knowledge and pre-training model enhanced low-resource Tibetan language voice to be converted into text. Unified modeling of Tibetan language boundaries, normal characters and morphemes is realized under a low-resource condition; remarkable and stable alignment is realized through a tsheg-perception adapter and three-head joint learning; language knowledge is fused into search in a learnable mode through the micro WFST soft constraint, and illegal font and language / case marking errors are greatly reduced. Training data are effectively expanded through teacher semi-supervised and coverage rate active learning, and cross-domain and accent robustness is improved; the end side maintenance cost is remarkably reduced through'adapter + atlas' hot updating; iCR and a boundary F1 are introduced as closed-loop indexes, so that the quality of an optimization target is consistent with that of a Tibetan Chinese character method, and the whole method has the advantages in engineering landing, interpretability and maintainability.

A translating method using visually represented elements, and device therefor is provided. According to an embodiment, a translation method performed by a computing device, may include acquiring data of a first sentence in a first language, the first sentence including a first morpheme of a first type and a second morpheme of a second type different from the first type, generating a first graph representing the first sentence, a first node of the first graph corresponding to the first morpheme of the first type of the first sentence, a first edge of the first graph corresponding to the second morpheme of the second type of the first sentence, and each node and each edge of the first graph being concatenated to each other so that the first sentence is completed when representations corresponding to each node and each edge of the first graph are concatenated while traversing the first graph in a first order, replacing the representations of the first language corresponding to each node and each edge of the first graph with representations of a second language, acquiring a second sentence of the second language by concatenating the representations of the second language corresponding to each node and each edge of the first graph while traversing the first graph in a second order at least in part different from the first order, and outputting the second sentence as a translation result of the first sentence into the second language.

An information processing apparatus outputs answer information corresponding to inquiry information that is input. The information processing apparatus includes a memory and circuitry. The memory is configured to store a plurality of databases each having at least a first field and a second field. The circuitry is configured to: perform morphological analysis on the inquiry information, to divide the inquiry information into morphemes; perform a first matching process based on the morphemes and the first field of each of the plurality of databases, to determine whether to adopt the database as an extraction source from which the answer information is to be extracted; and perform a second matching process based on the morphemes and the first field of the database, which is determined to be adopted as the extraction source, to output, as the answer information, data in the second field corresponding to data in the first field.

The invention discloses a code generation method, device and system based on deep learning. The method comprises the following steps: receiving code data input by a user; standardizing the code data to obtain standardized code data; dividing the standardized code data into morphemes, and encoding the morphemes to obtain an integer index; inputting the integer index into an embedding layer to obtain a fixed dimension vector; inputting the fixed dimension vector into a pre-trained encoder to obtain a feature vector sequence; the encoder firstly adopts a self-attention mechanism to obtain a long-distance dependency relationship in a fixed-dimension vector, and obtains a feature vector sequence through feature transformation and aggregation operation; and generating a code according to the feature vector sequence. According to the code generation method based on deep learning, a large number of codes do not need to be understood, the code generation accuracy and efficiency can be remarkably improved, and the cost is low.

The present application relates to a kind of general english tweet preprocessing method and computer equipment, belong to data processing technical field;Solved the problem that a large number of subjective words and non-standard morphemes exist in english tweet, affect tweet preprocessing result and named entity recognition performance;The method of the present application includes: based on multiple field english text, subjective word table is obtained by construction;The non-standard morpheme in the english tweet to be processed is carried out semantic reduction and information extraction, and the tweet text after preprocessing is obtained;Based on the tweet text after preprocessing, double stack structure is constructed to extract clause;Based on subjective word table, using syntax dependency analysis model and tree parent-child level structure, the tweet text after preprocessing is carried out named entity extraction, and the named entity recognition result of english tweet is obtained;The preprocessing result of english tweet is obtained by outputting the tweet text after preprocessing, the clause contained in english tweet and the named entity recognition result of english tweet.

Disclosed in the present application are an animation rendering method and apparatus, and an electronic device. The method comprises: acquiring text information and animation data that are required for animation rendering, wherein the text information is used for describing the animation data; determining speech data and morpheme data that correspond to the text information; converting the morpheme data into weight coefficients of corresponding control points in the animation data, wherein the control points are used for controlling the shape of a model in the animation data; and on the basis of the weight coefficients and the speech data, rendering the animation data.

The present disclosure relates to a server for providing multimedia content on the basis of text analysis, and an operation method therefor. A method for providing multimedia content by a server on the basis of text analysis according to an embodiment may comprise the steps of: acquiring a core keyword for each paragraph from an electronic device, the core keyword being determined on the basis of morpheme analysis on text including at least one paragraph; on the basis of whether the core keyword for each paragraph is a polysemous word or a homonymous word, determining a target meaning for the core keyword for each paragraph; on the basis of whether two or more paragraphs including the core keyword indicating the same target meaning are identified in the text, matching an image resource for each of the paragraphs; generating multimedia content by synthesizing the image resource matched for each of the paragraphs; and transmitting the generated multimedia content to the electronic device.

The embodiment of the utility model provides a morpheme training device. The morpheme training device comprises a morpheme panel and a plurality of morpheme cards, a plurality of base areas are arranged on the surface of the morpheme panel, a hollow area is arranged in the middle of the morpheme card, and the morpheme card is used for being placed on the morpheme panel, so that the hollow area and the base areas form a composite morpheme specified by a task instruction. By adopting the scheme provided by the invention, the morpheme awareness of an individual can be enhanced and improved, so that the vocabulary growth of the individual is promoted, and subsequent Chinese character learning is facilitated.

A system, method, and computer program product for implementing automated digital text optimization is provided. The method includes receiving during execution of an Internet search process, digital textual content comprising embedded words, morphemes, and phrases. A specified format for generating a summary for the digital textual content is identified and probability distribution attributes are generated with respect to target vocabulary of the digital textual content. Content of the digital textual content is replaced with replacement content and an automated digital summary of the digital textual content is generated thereby enabling optimized operational functionality of a recurrent neural network (RNN) encoder-decoder hardware device. A decoded version of the automated digital summary is presented via a specialized graphical user interface.

This invention discloses a method and apparatus for rapid conversion of singing voice timbre based on zero-shot sampling. The method includes constructing a singing dataset containing dry vocals and lyrics; extracting the audio codebook index sequence of the dry vocals using a singing feature decoupler incorporating a Hubert model and residual quantization codebook; introducing a text encoder to extract morpheme features and morpheme index sequences from the lyrics; optimizing the singing feature decoupler through cross-prediction to improve the accuracy of speech content feature extraction; introducing pitch and timbre features to represent prosody; and enhancing the quality of synthesized vocals generated by the generator based on speech content features, pitch features, and timbre features through adversarial training. This achieves rapid conversion of song vocal timbre to the user's timbre while ensuring conversion quality.

Disclosed is a foreign language phrases learning system based on basic sentence pattern unit decomposition, and implemented in a computing device including at least one processor and at least one memory for storing instructions executable by the processor, which includes: a sentence decomposition unit, when a natural language composed of a foreign language is input from a user, for decomposing a compound sentence corresponding to the input natural language into a plurality of basic sentences; a sentence pattern determination unit for checking one of morphemes or words contained in each of the decomposed basic sentences when the compound sentence is completely decomposed by the sentence decomposition unit, thereby determining a sentence pattern for each of the basic sentences; an additional information designation unit, when the sentence pattern for each of the basic sentences is completely determined by the sentence pattern determination unit, for designating some of the morphemes or the words contained in each of the basic sentences as additional information; and an additional information storage unit for matching the additional information with one of the morphemes or the words, which are not designated as the additional information, when the designation of the additional information is completed, thereby storing the additional information in a basic morpheme category included in a pre-stored basic morpheme dictionary table. In addition, various embodiments identified through the present document are possible.

The application discloses a morphological enhancement based tensorized word embedding compression system, which comprises a morpheme segmentation module, a morpheme index and embedding module and a word embedding generation module; the morpheme segmentation module divides each word in a word table of a text task into morphemes; the morpheme index and embedding module firstly generates a morpheme table by counting the division result of the morpheme segmentation module, then defines a morpheme index matrix and a plurality of trainable morpheme embedding matrices, each row of the morpheme index matrix represents the position of the morpheme of a corresponding word in the word table in the morpheme table, and each row of the morpheme embedding matrix represents an embedding vector of a corresponding morpheme in the morpheme table; the word embedding generation module indexes the morpheme vector from the morpheme embedding matrix and performs a tensor product on each word in the word table, adds the results of a plurality of tensor products to generate a word embedding vector; and the application overcomes the problems of a large amount of parameters and storage space occupation in general word embedding technology, and the problem of task effect loss when high compression word embedding is performed.

Extraction means and output means are included, the extracting means extracting one group of words of interest of a group of first words of interest, a group of second words of interest, and a group of third words of interest in accordance with a first evaluation score, a second evaluation score, and a third evaluation score for each of morphemes contained in character data that is posted on each of web pages included in a result of a search that has been conducted by a search engine by using a search query, the output means outputting data for displaying at least the extracted group of words of interest.

A device and method for providing recommended words for a character input by a user are provided. The method by which the device provides recommended words includes: receiving an input for inputting a character in a character input window; recommending at least one pseudo-morpheme including the input character by analyzing the input character; recommending at least one extended word including a selected pseudo-morpheme in response to receiving an input for selecting one of the at least one pseudo-morpheme; and displaying a selected extended word in response to receiving an input for selecting one of the at least one extended word.

Methods and systems for tokenization of textual input for training and use in large language models are disclosed. Some embodiments may include receiving text input by an algorithm, algorithmically splitting the text input into word tokens, referring each word token to a MorphTable containing morphological segmentations for words, tokenizing words found in the MorphTable into morphemes by breaking the word into morphological constituents, tokenizing words not found in the MorphTable using a statistical component algorithm trained on a corpus and providing the tokenized words as input to a language model or another algorithm. Additionally, receiving word tokens either from a model trained with the proposed algorithm or from the algorithm itself and combining the tokens using Reverse MorphTable and statistical tokenizer to obtain back the original text.

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.

An information processing apparatus outputs answer information corresponding to inquiry information that is input. The information processing apparatus includes a memory and circuitry. The memory is configured to store a plurality of databases each having at least a first field and a second field. The circuitry is configured to: perform morphological analysis on the inquiry information, to divide the inquiry information into morphemes; perform a first matching process based on the morphemes and the first field of each of the plurality of databases, to determine whether to adopt the database as an extraction source from which the answer information is to be extracted; and perform a second matching process based on the morphemes and the first field of the database, which is determined to be adopted as the extraction source, to output, as the answer information, data in the second field corresponding to data in the first field.