672 results about "Text generation" patented technology

A telecommunications system (100) includes network access devices (104) that couple user devices (102) to a telecommunications network (106). The user devices (102) include at least voice and preferably text display and text generation capability. A voicemail server (114) is coupled to the telecommunications network. The voicemail server (114) is also coupled to an application server (116). Selectively, speech traveling through the telecommunications network (100) from user devices (102) is converted into text, stored, and forwarded to a user device as a text message. The text message is for example a facsimile transmission, an e-mail, or a SMS message. The selectivity is based on a stored attribute, current status of the user device, attributes of the sending device and the like. Text can even be converted into speech as an option. Or, stored speech associated with a text message can be retrieved based on the text message.

A text-generation method and system includes receiving data records, such that each data record includes one or more data fields and a field value associated with each data field. A text-string is generated for each data record, such that each text-string includes one or more text-based data descriptors. Each data descriptor includes a field descriptor that defines a specific data field within the data record to which the text-string is related, and a value descriptor that defines the field value associated with the specific data field.

Normalized output texts, such as rundowns or summaries, from raw texts belonging to a given domain are produced. The normalized output text may be generated in different languages and may take into account a user's interest. To this end, linguistic resources associated with a model of the domain are used both for input text analysis and output text generation.

The present invention provides a computer-implemented system and method of text processing. The system and method include analyzing selected text units of a digitally coded parsed text file to determine text entities, determine the interconnections between the text entities, test the validity of the text entities, and determine a quantitative measure of the significance of each text entity. A multigranular relational text structure is constructed which incorporates the text entities. Output text is generated from the relational text structure using entity grouping rules. The text file is parsed using a system of natural dividers. The text units are selected from the parsed text file using windowing and scanning. The output text generated conforms to user constraints which can include the volume of output text to be generated, keywords to be reflected in the output text, and the level of generalization of the output text.

The process of text generation/creation is automated. The text to be processed is used as seed for the text generation process. The text to be processed can be in any language and can be passed to text generation process through any internal/external application or process, through speech technology or through manual entry. At the first step, word(s) are extracted from the text. Each word is considered as seed and this seed is grown up into different word(s)/sentence(s) lists according to the selected criteria. The generated lists are then processed and combined/jointed through a simple mechanism to generate text. This generated text then can be saved, analyzed, filtered or searched on the internet, intranet, extranet, in database(s) or in user defined data repositories again according to the criteria selected by the user or by some external application or process.

The invention provides an automatic text abstraction method based on a pre-training language model. According to the method, an ultra-large-scale unsupervised Chinese corpus is used for training a complex deep language model; the low-layer network structure of the model can extract and retain the grammar and structure information of a text, and the high-layer network structure can extract and retain the semantics and context information of the text, so that the richer text features and semantic information are provided for an automatic text summary task; a pre-training language model and an Encoder are combined to realize, the text features and the semantic information in the pre-training language model are fully utilized, so that a better semantic compression effect is provided, and the performance of an automatic text abstract is improved; a pre-training language model and a decoder are combined, not only the semantics in an original text are considered in the text generation process, but also the semantic information of vocabularies is also considered, so that the readability of the generated text and relevance with the original text are improved, and the performance of an automatic text abstract is improved.

A personality model is created for a population and used as an input to a text generation system. Alternative texts are created based upon the emotional effect of the generated text. Certain words or phrases are “pinned” in the output, reducing the variability of the generated text so as to preserve required information content, and a number of tests provide input to a discriminator network so that proposed outputs both match an outside objective regarding the information content, emotional affect, and grammatical acceptability. A feedback loop provides new “ground truth” data points for refining the personality model and associated generated text.

The invention provides a scalable text generation method. By means of the method, text files can be rendered faster and CPU resources of a server are used more efficiently. The method includes the steps that a whole template file is decomposed into multiple subtemplate files; a rendering task list is generated and comprises multiple rendering tasks, the rendering tasks are used for being associated with the subtemplate files corresponding to the rendering tasks, and logic of preparation data before rendering is realized; multi-thread rendering is carried out on the rendering tasks; rendering results of the rendering tasks are spliced into texts. By means of the technical scheme, development and maintenance cost of the template file is reduced, data preparation is more efficient, and the CPU resources of the server are used more reasonably.

The invention relates to a text template generator, a text generating device, a text inspection device and a method thereof, wherein the text template generator comprises a slot position determination unit for determining the positions of words needing to be replaced in an inputted text according to constraint conditions as slot positions, and a target replacement determining unit for determining targets for replacing the slot positions according to the constraint conditions in order to generate a text template comprising targets, and generate expected templates according to different constraint conditions. Furthermore, the invention further provides a text generating device and a method thereof, a text inspection device for inspecting the text whether meeting idiomatic usage and a method thereof, and a system for generating text in line with the idiomatic usage and a method thereof, thereby determining whether inputted text fits for the idiomatic usage, and outputting the text in line with the idiomatic usage.

The application relates to an abstract text generation method, an abstract text generation device and computer equipment. The abstract text generation method includes acquiring word sequences of an original text; respectively encoding and decoding the word sequences through a first passage and a second passage of a machine learning model, acquiring a first hidden layer state vector and a second hidden layer state vector at the present by referring to word vectors of abstract words output by the machine learning model at previous time during decoding, and further determining abstract words output by the machine learning model at the present according to the first hidden layer state vector and the second hidden layer state vector at the present; generating abstract text according to the abstract words output by the machine learning model. According to the scheme, the abstract text generation method and device can improve readability of the generated abstract text.

The invention, which belongs to the field of the deep learning neural network, discloses a WGAN method based on text generation. The method comprises the following steps: S1, constructing a Wasserstein generative WGAN model; S2, preparing a text data set for training; S3, coding the test data by using a coder; S4, constructing random noises and acquiring obtain an output text of a generator; and S5, inputting the output text of the generator and the text after coding of the data set into a discriminator and carrying out network training. According to the invention, on the bass of characteristics of the generative WGAN model, a construction mode of combination of a deep convolution neural network and a WGAN is put forward creatively and the adversarial network training mode of the generatedtext is disclosed for the first time, so that the function that the previous generative WGAN model completes image generation is broken.

An embodiment of the invention discloses a problem text generation method and device, equipment and a medium. The method comprises the following steps: the embodiment of the invention determines the coded hidden layer state vector of each input word by adopting an encoder based on the attribute parameters of each input word; for each candidate word, the decoder and an attention mechanism model areused to determine the context vector and decoded hidden layer state vector of each candidate word as the current output word; and for at least one generation mode, the probability value of each candidate word as the current output word and the weight value of the generation mode are respectively calculated according to the context vector and the decoded hidden layer state vector, and the final probability is further determined to screen the current output word among the candidate words based on the final probability. The technical scheme improves the accuracy and diversity of generating the question text based on the answer text.

The invention relates to a text generation image method based on cross-modal similarity and a generative adversarial network. The method comprises the steps that S1, training a global consistency model, a local consistency model and a relation consistency model by using matched and unmatched data, wherein three models are used for obtaining global representation, local representation and relationrepresentation of a text and an image respectively; S2, obtaining global representation, local representation and relation representation of the to-be-processed text by utilizing the trained global consistency model, local consistency model and relation consistency model; S3, connecting the global representation, the local representation and the relation representation of the to-be-processed textin series to obtain text representation of the to-be-processed text; S4, converting the text representation of the to-be-processed text into a condition vector by utilizing an Fca condition enhancement module; and S5, inputting the condition vector into a generator to obtain a generated image. Compared with the prior art, the method has the advantages of considering local and relation informationand the like.

The present disclosure relates to a text generation method, an apparatus, an electronic device and a computer readable medium. The invention relates to the field of computer information processing. The method comprises the following steps: determining a subject term set, a song title, a song rhyme foot and a paragraph structure according to the input information of a user; and generating text through the set of subject words, the song name, the song rhyme and the paragraph structure, and a depth learning model with an attention model. The present disclosure relates to a text generation method,an apparatus, an electronic device and a computer readable medium capable of generating a variety of effective poems conforming to music.

The invention discloses a generative adversarial network technology-based medical text generation method. The method comprises the following steps of downloading multiple medical documents of a fieldwhich a department belongs to; representing words in the medical documents by utilizing word vectors; performing text classification on the medical documents, and reserving the required medical documents; obtaining optimal output sequence tags of the required medical documents; obtaining indexes of keyword sets of the required medical documents, and randomly disordering the indexes to obtain new medical documents and corresponding sequence tags; performing training by adopting a generative adversarial network-based generative model to generate medical texts; outputting the generated medical texts; obtaining BLEU parameters of the generated medical texts; and assessing the generated medical texts to finally obtain target medical texts. By disordering data to generate the new medical texts,the problems of patient privacy security and relatively few medical texts are solved.

The invention discloses a global dynamic heterogeneous spatial information collaborative plotting and spatial knowledge service system. On the basis of plotting data obtained by a collaborative plotting platform, mass related heterogeneous spatial information of Africa is collected, and a plotting knowledge base is generated through data integration and knowledge reasoning; on the basis of the plotting knowledge base, a knowledge model is built by means of data mining, hot spot image-text association and the like, knowledge services with the text that 'a Chinese is attacked in Africa', and the texts of 'China-Africa international cooperation', 'Africa travel' and the like being themes are carried out, visual representation is performed on hot spot area information by means of hot spot image-text generation, network map diaries and the like, a knowledge base (stored data) is built, finally, the African spatial knowledge service system based on the collaborative plotting technology is achieved, and spatial information active services are provided for the public, the government and associated users.

The present invention provides method and apparatus for generating a natural text from at least one keyword. The keyword is input by a keyword input unit, and a text and phrase searching and extracting unit extracts any text or phrase containing keywords, if any. A text generation unit morphologically analyzes and parses the extracted text, and outputs a natural text by combining the text with the keyword.

The invention provides a multi-entity relationship joint extraction method and device based on text generation, wherein the method comprises the steps of expressing each word in a sentence to be processed through a coding vector, and obtaining a word embedding vector of each word; performing feature extraction on the word embedding vector of each word, and obtaining a high-grade feature representation vector of each word; and decoding the advanced feature representation vector, generating a target entity or a relational word at each moment to obtain a generation sequence, and generating the words generated at each three consecutive moments in the generation sequence to form an entity relationship triple. According to the method, an entity relationship extraction task is converted into a text generation task, the entity and the relation words are used as the target text to be generated, and one or more groups of relation triplets are generated, so that the joint extraction of the entityand the relation is achieved, the entity can repeatedly appear in the multiple triplets, and the entity overlapping and entity relation extraction problems under the multiple relations are solved.

The present invention relates to the technical field of problem generation, and more particularly, to a problem generation method based on a progressive multi-discriminator. As use herein, a generatoris used to generate the problem, a discriminator is used to evaluate the problem, and three kinds of discriminators are designed in this paper, namely, a true/false discriminator is used to judge whether the problem is smooth and reasonable, an attribute discriminator is used to judge whether the problem belongs to the category corresponding to the answer, and a question-answer discriminator is used to judge whether the problem can be answered by the corresponding answer. The invention aims at the question-answer mismatch problem in the text generation task, the article adds the answer attribute information to the encoder and decoder in the generator, and a progressive multi-discriminator is designed to strengthen the degree of constraint from easy to difficult, first to ensure the semantic quality of the generated questions, then to constrain the types of questions, and finally to constrain the direct answers of the questions, and to strengthen the matching degree between the questions and the answers.

The invention discloses a free text generation method. The method comprises the following steps: S1, key words input by a user are combined into a character string; S2, the character string is encoded into a group of word vectors with the dimension being i through a first recurrent neutral network, and implicit vectors are generated according to the word vectors; S3, a candidate set of the t word is generated through a second recurrent neutral network according to the word vectors and the implicit vectors, the probability distribution vector of the candidate set of the t word is predicted, and t is larger than or equal to 1; S4, the word with the largest probability distribution in the candidate set is output as a predicted word Yt according to the text format, and all texts are generated through loop iteration. According to the text generation method, mapping information and semantic information of words are trained simultaneously, texts in various formats can be used for learning, the data sparseness problem is solved, and texts in any length and any sentence pattern can be generated.

The embodiment of the invention discloses a text generation method and device and a storage medium. The method includes: acquiring a target image; Performing image classification on the target image to obtain an image type of the target image; When the image category belongs to a preset category set, according to the image category, screening out keywords corresponding to the target image in a preset word bank; Generating a corresponding text fragment according to the semantic information corresponding to the keyword; And generating a text according to the text segment. According to the scheme, the category of the target image can be identified, the corresponding keyword can be determined, and then the text is generated according to the keyword corresponding to the target image, so that the text conforming to the expression content of the image is obtained, and the universality of the technology of generating the text according to the image is improved.

The invention discloses a method for automatically generating a medical image diagnosis report based on the deep learning method. The method comprises steps that S1, a subject of the diagnosis reportis clustered based on the LDA algorithm, and the diagnosis report is saved separately according to the subject; S2, a subject vector is used as a label of each medical image; S3, CT images and PET images with different sizes are scaled to the same size as training data, subject vectors are used as labels, the VGGNet-19 is used as a network model for training, and a subject vector generation modelis obtained; S4, a text generation model is constructed; and S5, according to the subject vector of each image, the text of the corresponding subject is matched to obtain the diagnosis report of the image. The method is advantaged in that the method can be applied to scenes with images marked with lesions, a doctor has no need to manually summarize training data labels frequently, only the location and the size of the lesion should be marked, and the doctor's work is effectively reduced while the correct rate is improved.