25 results about "Summary information" patented technology

Methods for generating a categorized, ranked, condensed summary of a transcript of a conversation, involving obtaining a diarized version of the transcript of the conversation, storing textual monologues from the transcript, determining classifications as to the textual monologues based on a classifier algorithm, associating the classifications with the textual monologues, creating textually-modified rephrasings of the textual monologues based on text and classification thereof, storing the textually-modified rephrasings, aggregating the textually-modified rephrasings based on associated clustering and scoring, and transmitting summary information pertaining to the aggregated textually-modified rephrasings to a user device.

The invention provides a text generation method and device, equipment and a storage medium, in one embodiment, the text generation method comprises the steps that plot summary information is generated according to content creation indication information input by a user; based on a plot generator, after processing the plot summary information, generating detailed plot contents corresponding to the plot summary information, and organizing the detailed plot contents according to logic indicated by the plot summary information to obtain a target text; based on a multi-dimensional evaluator, the target text is evaluated from a preset dimension, and the preset dimension comprises at least one of the following items: coherence, innovation or attraction among the detailed plot contents; and if the target text passes the evaluation, outputting the target text. According to the method and the device, the text can be created by utilizing the plot generator, and the content of the text created by utilizing the plot generator is evaluated from multiple dimensions, so that the quality of the created text can be improved.

The invention discloses a content-based news duplicate removal method and device and a nonvolatile storage medium. The method comprises the steps of obtaining a to-be-processed news set, deleting to-be-processed news with text structure similarity greater than or equal to preset similarity, and obtaining residual to-be-processed news; determining a content element and a category system of each piece of residual to-be-processed news, and classifying the plurality of pieces of residual to-be-processed news with the same content element and category system into a to-be-deduplicated set; for each piece of target residual to-be-processed news in the to-be-deduplicated set, triggering a text analysis model by adopting a first cue word to output a plurality of questions related to the target residual to-be-processed news to obtain a question list, and triggering the text analysis model by adopting a second cue word to output summary information of the target residual to-be-processed news; and according to the first semantic similarity of the question list and the second semantic similarity of the summary information, determining to-be-deleted news in the to-be-deduplicated set.

The invention relates to the field of text processing, in particular to a text splitting mark generation method and device, a medium and electronic equipment. Comprising the following steps: obtaining summary information of a sub-text corresponding to each sliding window in a to-be-processed text; generating a semantic change amplitude between any two adjacent summary information; and when any semantic change amplitude is greater than a change threshold, generating a splitting mark at the tail position of the sliding window corresponding to the front summary information in two adjacent summary information. According to the method, a complete text is split into a plurality of sub-texts, then the change size between scenes described by two adjacent sub-texts is reflected through the cosine distance between semantic vectors corresponding to the two adjacent sub-texts, and the change size is used as the basis of text splitting, so that the whole to-be-processed text is reasonably split and marked. Therefore, clearer plot arrangement structures of works can be provided for creators, follow-up modification is facilitated, and meanwhile creation efficiency and quality are improved.

The invention provides a fragmented sensitive information intelligent detection method and system, and belongs to the technical field of information detection. The method comprises the following steps: creating a sensitive information knowledge base and a retrieval model; to-be-detected fragmented information is obtained from the multi-source document, and a to-be-detected text is generated; identifying sensitive information in the to-be-detected text by using a large language model; based on the sensitive information, utilizing an NLP technology to construct a knowledge graph; performing community division on the knowledge graph by using a graph algorithm, and generating summary information of communities; inputting the summary information into a retrieval model, and matching the retrieval model with entries in a sensitive information knowledge base to retrieve potential sensitive information research and judgment rules related to the summary information; performing context fusion on the potential sensitive information of the community and the potential sensitive information research and judgment rule to generate a sensitive information research and judgment prompt text; and generating an evaluation report about the sensitive information by using a large language model. According to the invention, efficient and accurate detection of fragmented sensitive information is realized.

To provide a story generation system capable of storing a story obtained after a user as a story creator reflects user's intension about a story to tune the same.SOLUTION: A story generation system 100 includes a user terminal 110A and a server 120. The server uses pre-learned artificial intelligence means 131 to execute text data generation of a plurality of chapters of stories on the basis of title information TL and outline information AB of a story from a user terminal, and transmits the obtained generation text data to the user terminal. The server uses the pre-learned artificial intelligence means to execute a change in the generation text data on the basis of change instruction information from the user terminal, and transmits obtained changed generation text data GT1 to the user terminal. When there is a storage / disclosure operation in the user terminal, the server stores and discloses the changed generation text data GT1.SELECTED DRAWING: Figure 1

The invention relates to a review level prediction method based on a review rule and review text content, and the method comprises the following steps: collecting historical bid evaluation data, grading the historical bid evaluation data according to a scoring rule, and forming a data set D1 according to review terms and scoring levels; obtaining an evaluation rule, and analyzing a division rule of an evaluation criterion and a score condition; text content is obtained from the review terms, and key information and summary information of the overall content are extracted; the summary information and the keywords are converted into vector data, expert review grades are subjected to normalization processing, and then the expert review grades are input into a classification model to be trained; performing review grade classification prediction on the bidding key information in the bidding document by using the trained classification model; according to the method, the workload of review personnel is reduced, the review speed is increased, the efficiency of the whole review process is improved, multiple attributes and factors are comprehensively considered, the influence of subjective factors can be reduced, and the comprehensiveness and comprehensiveness of review are improved.

The embodiment of the invention provides an information analysis method and device based on a large language model, and the method comprises the steps: obtaining original data collected through a plurality of channels in a historical time period, obtaining target key information according to the original data, and obtaining target information according to the target key information; according to the method, a plurality of pieces of summary information and a plurality of pieces of expected information corresponding to a plurality of themes in a future time period are generated, and an expected time sequence diagram corresponding to each theme is generated according to the expected information corresponding to each theme in the future time period, so that a large amount of text content is analyzed based on a preset large language model; therefore, the difficulty in regular and comprehensive tracking analysis caused by insufficient manual processing capability is overcome, and the objectivity and fairness of content summarization are improved.

A system is provided.SOLUTION: This system includes a means for acquiring news information, a means for summarizing the acquired news information, a means for generating a text for explaining the news information summarized by using a plurality of explanatory characters from various viewpoints, a means for generating a moving image by using the explanatory text of the character, and a means for distributing the generated moving image.SELECTED DRAWING: Figure 1

The invention relates to the technical field of student intelligent questioning and answering, and discloses a student intelligent questioning and answering method and system based on a large language model and rapid retrieval, and the method comprises the steps: combining a student portrait to generate question vectors, rejecting noise points of a question vector set, obtaining hot questions, and storing the hot questions into a hot knowledge base after the hot questions are expanded by experts; generating a summary of the knowledge document by using a large language model, and adding the summary to each text block; generating a block summary for each text block, and storing the block summary and the text blocks into a universal knowledge base; inputting questions proposed by students into the large language model to generate a thinking chain; for sub-questions needing to be retrieved, firstly retrieving the hotspot knowledge base, if the sub-questions are not matched with the hotspot knowledge base, retrieving the block summary of the general knowledge base, and obtaining corresponding text blocks through mapping to obtain retrieval results; and guiding the big language model to fuse the thinking chain and the retrieval result to generate a structured answer. According to the method, the summary information is introduced after the text blocks are segmented, so that the information loss in the text segmentation process is reduced, and the reasonability of knowledge base construction is improved.

The invention discloses a method for automatically generating a specified format text, and relates to the technical field of artificial intelligence. Comprising the steps of 1, receiving text summary information input by a user, 2, analyzing and processing the received text summary information by utilizing a pre-trained artificial intelligence model, and understanding semantics and context relationships in the text summary information, and 3, generating a field knowledge base according to a preset text generation rule base and a field knowledge base on the basis of an analysis result, the method comprises the steps of 1, automatically generating complete text content matched with summary information, 2, automatically performing format conversion and typesetting on the generated text content according to a format requirement specified by a user to generate a text file in accordance with a format specified by the user, and 3, outputting the generated text in the specified format for the user to use or further edit.

The embodiment of the invention provides an abstract generation method and device and a computer readable medium, and the scheme does not generate abstract information directly based on initial target text content, but firstly obtains key information in the target text content; second question information used for being input into the large language model is generated in a staged mode based on the key information, and the large language model is guided to gradually generate summary information about the target text content by adopting a thinking chain mode on the whole; according to the method, details with finer granularity in the target text content can be integrated into the summary information by the large language model, and meanwhile, the advantages of the large language model in the aspects of language understanding and context understanding are combined, so that the summary information with higher quality can be finally generated.

The invention provides a multi-theme dialogue processing method and device for real-time news based on a large model, and relates to the technical field of dialogue processing of real-time news, and the method comprises the steps: obtaining a first theme corresponding to current request information, a real-time news event and corresponding first summary information; according to the authenticity of each real-time news event and the first summary information, determining a target real-time news event and corresponding current summary information; performing relevance matching on the first theme and a second theme corresponding to each piece of historical request information, and updating a node tree according to a matching result; according to the updated node tree, determining target historical request information of which the association degree with the first theme meets a preset requirement; inputting the current request, the current abstract, the target historical request and the corresponding historical abstract and historical response into a multi-modal large model, and outputting a response for the current request information; the technical problem that in the prior art, the response accuracy of real-time news is not high is solved.

The present invention provides a method and device for processing multi-round dialogues for real-time news based on a large model, which relates to the technical field of multi-round dialogue processing for real-time news, and includes: based on a first preset template in a multimodal large model, determining the current summary information of the real-time news event corresponding to the current request information; filling the current summary information, current request information, historical summary information, historical request information and historical responses in the multi-round dialogue into a second preset template of the multimodal large model, and determining the first response of each current summary information in the multi-round dialogue under the action of each historical request information, and the second response of each historical summary information in the multi-round dialogue under the action of each current request information; inputting the multimodal large model according to the first response, the second response and the historical response, determining the response to the current request information in the multi-round dialogue; so as to alleviate the technical problem of poor accuracy of the request answer of real-time news in the multi-round dialogue.

The invention relates to the technical field of artificial intelligence, in particular to a multi-round dialogue processing method and device and a storage medium. The method includes: acquiring a current dialogue statement of a user; when a target keyword is matched in a preset lexicon according to the current dialogue statement, determining a final answer statement by using the target keyword and a preset corresponding relationship; the preset word bank comprises at least one keyword of a vehicle-mounted text language style, and the preset corresponding relation is the corresponding relation between the keyword and the answer statement; when the target keyword is not matched in the preset word bank according to the current dialogue statement, obtaining a historical dialogue statement; extracting summary information from the historical dialogue statement, and generating a final answer statement by using the summary information through the language model; the language model is a language model pre-trained according to a text of a vehicle-mounted text language style. The embodiment of the invention is used for solving the problem that a user may not answer questions or cannot answer the questions in multiple rounds of dialogues.

The invention relates to the technical field of book management, and discloses a library book automatic searching method and system, and the method comprises the steps: taking any book in a library as a target book, and obtaining the summary information of the target book; extracting a first feature from the summary information of the target book; calculating a correlation degree between the first feature and a plurality of preset tags; taking the label of which the association degree with the first feature is higher than a preset threshold value as the label of the target book; obtaining a demand of a user for searching for a book; extracting a second feature from the demand of searching the book by the user; calculating a correlation degree between the second feature and the plurality of tags; and setting a search condition according to the label of which the association degree of the second feature is higher than a threshold value, searching the book with all the labels in the search condition from all the books in the library, and pushing the book to the user. According to the method, a plurality of related labels can be distributed to complex books related to a plurality of fields, so that the books can be found by readers with different professional backgrounds more easily.

The invention provides a narrative emotion controllable long-term story generation method and system, and the method comprises the steps: generating a target story outline according to story summary information, target emotion track information and lower-layer control parameters which are generated based on upper-layer control parameters, the control module is used for providing plot guidance and emotion control for a story generation process; the upper-layer control parameters are used for determining an overall basic tone and an emotion trend in a story generation process; generating role control parameters according to the upper-layer control parameters and the target story outline; based on each story fragment in the target story outline, generating an emotion control parameter; and based on a hierarchical generation strategy, performing story generation operation on the target story outline, the role control parameters and the emotion control parameters to obtain a long story text. The emotional evolution of the long stories is accurately controlled, the long stories conforming to the specified emotional development trajectory are generated, and the user experience is improved.

The invention provides a multi-round dialogue processing method and device for real-time news based on a large model, and relates to the technical field of real-time news multi-round dialogue processing, and the method comprises the steps: determining the current summary information of a real-time news event corresponding to the current request information based on a first preset template in a multi-modal large model; filling the current summary information, the current request information, the historical summary information, the historical request information and historical responses in the multi-round dialogues into a second preset template of the multi-modal large model, and determining a first response of each piece of current summary information in the multi-round dialogues under the action of each piece of historical request information, obtaining a second response of each piece of historical summary information under the action of each piece of current request information in multiple rounds of dialogues; inputting a multi-mode large model according to the first response, the second response and the historical response, and determining a response for the current request information in the multi-round dialogue; the technical problem that the request answering accuracy of real-time news in multiple rounds of conversations is poor is solved.

Methods for generating a categorized, ranked, condensed summary of a transcript of a conversation, involving obtaining a diarized version of the transcript of the conversation, storing textual monologues from the transcript, determining classifications as to the textual monologues based on a classifier algorithm, associating the classifications with the textual monologues, creating textually-modified rephrasings of the textual monologues based on text and classification thereof, storing the textually-modified rephrasings, aggregating the textually-modified rephrasings based on associated clustering and scoring, and transmitting summary information pertaining to the aggregated textually-modified rephrasings to a user device.

The application provides an intention context analysis method and device, electronic equipment and storage medium, wherein the method comprises: determining a text to be analyzed and summary information of the text; performing segment division on the text to obtain a plurality of segments, and identifying semantic representations of each of the plurality of segments; obtaining role representations of each of the plurality of segments in the text according to the summary information and the semantic representations of each of the plurality of segments; obtaining a connection relationship between the plurality of segments and intention representations of each of the plurality of segments according to the semantic representations and the role representations of each of the plurality of segments; and obtaining a context analysis result of the text according to the plurality of segments, the role representations, the connection relationship and the intention representations. The accuracy of extraction and analysis of intention context information of a chapter-level article is improved, and a more accurate basis is provided for article evaluation.

The invention relates to the technical field of data processing, in particular to a story text evaluation method and device, equipment and a readable storage medium. According to the method, the evaluation result of each plot plot in the plot text is quantified into the plot grade score through the role description information and the plot summary information, and the plot distribution trend capable of reflecting the overall trend of the plot grade score is further obtained; and the quality of the plot text is measured by using the similarity between the plot distribution trend and the preset plot distribution index, so that the objectivity and intuitiveness of plot text evaluation are improved.

The present invention provides a text summary generation method, device, and storage medium, belonging to the field of language processing. The method comprises: performing word segmentation processing on a text dataset to obtain multiple original text information and summary information; training a training model based on each original text information to obtain an original prediction sequence; performing loss function analysis on the training model based on the multiple original prediction sequences and the multiple summary information, and obtaining a summary generation model based on the analysis results; and inputting each original text information and summary information into the summary generation model for prediction analysis to obtain a text summary generation result. The present invention improves the word order problem in the generated summary, making the text more fluent and the word order more fluent, thereby improving the readability of the summary.

The invention provides a similar text retrieval method and system based on multi-dimensional information reordering, and relates to the technical field of information retrieval. According to the method, firstly, a to-be-processed text is obtained, the text is subjected to sentence segmentation, then the text subjected to sentence segmentation is processed through a pre-trained text key information extraction model and a pre-trained text summary information generation model, and two representation type similar text retrieval results are obtained; and finally fusing the similar text retrieval results of the two representation expressions to obtain a final similar text retrieval result. According to the method, the problems of long documents and low accuracy in the retrieval process are solved by utilizing a multi-dimensional information re-ranking mode. Wherein the multi-dimensional information comprises text key information and text summary information, re-ranking is carried out by utilizing a re-ranking mode of parts based on positions, the text key information is extracted by a text key information extraction model, and the text summary information is generated by a text summary information generation model, so that the retrieval quality is optimized.

The embodiment of the invention provides an AI-based customer admission auxiliary auditing method and system, and belongs to the technical field of data processing. The method comprises the steps of obtaining initial structured information and initial text information of a target building company; performing paragraph splitting on the initial text information to obtain a target paragraph title and associated text information corresponding to the target paragraph Performing abstract generation processing on the associated text information to obtain target abstract information; performing statement recognition on the target summary information to obtain a target key statement; determining a first key feature vector by using the target paragraph title, the target summary information and the target key statement; performing key feature identification on the initial structured information to obtain target structured information of the target building company; obtaining a second key feature vector by using the target structured information; determining a target risk identification result according to an artificial intelligence algorithm in combination with the first key feature vector and the second key feature vector; and determining an auxiliary auditing result of the target building company according to the target risk identification result.

The application provides a model training method, a text summary generation method, a device, equipment and a medium. The method comprises the following steps: encoding a training text by using an encoder in a summary generation model to obtain an encoded hidden layer state; determining a second decoding hidden layer state output this time by using a decoder in the summary generation model according to a first decoding hidden layer state output last time and a corresponding first predicted word, or according to a set initial first decoding hidden layer state and a corresponding first predicted word; determining a decoding probability of a second predicted word according to the encoded hidden layer state and the second decoding hidden layer state; and training the summary generation model to maximize the decoding probability in response to the second predicted word being contained in annotated summary information of the training text. Thus, the summary generation model is trained based on the decoding probability of each predicted word and whether each predicted word is contained in the annotated summary information of the training text, so that the prediction effect of the model can be improved.