27 results about "Text compression" patented technology

The invention discloses a method, a system, equipment and a medium for automatically updating cue words of a large language model system, belongs to the technical field of cue word optimization of large language models, and aims to solve the technical problem of how to optimize cue words of large language models on the basis of recent interaction historical sessions between users and large language models or agents. Automatic updating of cue words of a large language model system is achieved, the continuous and lifelong learning ability of the large language model is improved, and then the thinking depth of the large language model is improved. According to the technical scheme, the method comprises the steps of obtaining a system cue word updating model with an interactive historical text compression memory function through SFT supervised fine tuning or enhanced post-training based on a system cue data set, constructing a system cue word cue experience entry knowledge base based on the system cue word updating model and in combination with long-time interactive dialogue history of a user and a large language model, and obtaining the system cue word cue experience entry knowledge base. And on the basis of a system cue word updating model, the current dialogue history is interacted by combining the user and the large language model, so that the system cue word is automatically updated.

The invention relates to the technical field of natural language processing, and provides a multi-granularity text compression method and system for large-model multi-round dialogues, and the method comprises the steps: carrying out the semantic coding of historical question and answer pairs and a current dialogue question through a pre-training model, obtaining a semantic vector, generating a historical dialogue semantic representation through a self-attention mechanism, and carrying out the semantic representation of the historical dialogue. A semantic vector of a current dialogue problem is combined, a correlation enhancement vector is obtained through a target attention mechanism, weighted fusion is carried out on the correlation enhancement vector and historical dialogue semantic representation, a fusion vector is obtained, a feature vector is generated through a maximum pooling and average pooling combination strategy, clustering is carried out, positive and negative sample pairs are constructed, and semantic similarity loss calculation is carried out. Iteratively training the classification model; and based on the trained classification model, screening question and answer pairs related to the current dialogue question, and generating a structured abstract. Redundant content is remarkably reduced while key semantic information is reserved, and efficient context representation adaptive to large model reasoning is formed.

The invention relates to the technical field of large language model text processing, in particular to a progressive multi-level text compression system and method and a storage medium, and the system comprises a text input module, an importance evaluation module, a compression level selector, a multi-level compression engine, a compression result verification module, an output module and an alternative scheme module; the method comprises the steps that a text input module obtains a to-be-compressed text and a target Token length limit; the importance evaluation module is used for calculating importance scores of values of the text segments based on time proximity, context correlation, keyword occurrence frequency and emotion intensity; the compression level selector triggers the multi-stage compression engine to progressively compress, the compression result verification module verifies the length at each stage, and the output module outputs a final result. The storage medium stores a computer program for executing the method, and the problems of Token over-limit, resource waste, response delay and semantic loss caused by too long dialogue history in a large language model are solved.

The text compression serialization method is applied to computer equipment and comprises the steps that text features of a text are extracted, resource information of the computer equipment is collected, the text features comprise a structured index, a repetition rate and semantic entropy, and the resource information comprises a CPU utilization rate and a remaining memory proportion; screening a first candidate compression algorithm set of the text by using the structured index and the repetition rate, filtering the first candidate compression algorithm set based on the resource information, selecting a second candidate compression algorithm set according to the semantic entropy, and determining a target candidate compression algorithm set through the resource information; based on the text features and the resource information, calculating a score value of each candidate compression algorithm in the target candidate compression algorithm set, and taking the candidate compression algorithm with the highest score value as a target compression algorithm; and compressing and serializing the text by adopting a target compression algorithm to obtain a compressed serialized text. Therefore, the flexibility, the compression effect and the resource utilization rate of text compression serialization can be improved.

The invention discloses a multi-modal corpus storage method and device, computer equipment and a medium, and the method comprises the steps: carrying out the compression processing of text modal data and audio and video modal data of a multi-modal corpus, and employing a suitable compression algorithm for the characteristics of different modal data; similarity calculation is carried out on the text compression features, the audio and video compression features and corresponding modal features of the newly-added multi-modal corpus, semantic redundancy of the newly-added multi-modal corpus and historical compression corpus can be recognized, a fusion compression process is triggered to eliminate cross-modal redundancy, and repeated storage of same semantic information is avoided; corpus features which do not trigger the fusion process are independently stored, the corpus features which trigger the fusion process are fused to generate multi-modal joint features, and the stored data volume is further simplified; the corpus features are migrated to the corresponding data storage layer in combination with the access frequency and the response time, so that the storage cost is reduced.

The invention relates to a text compression and encryption method and system based on a large model. The method realizes safe and efficient dynamic encryption through a mixed key architecture, and comprises the following steps: generating an elliptic curve asymmetric key pair and encrypting a dynamically derived symmetric session key; processing the original text through the context input into the large model to generate a to-be-compressed text; mapping the text to be compressed to a binary bit stream through a lossless compression model based on arithmetic coding; generating a session key by adopting a symmetric encryption (AES-GCM) algorithm with authentication and encryption functions to encrypt the bit stream to generate a ciphertext; and splicing the encryption key and the ciphertext into a structured bit stream through zero-bit filling coding. According to the scheme, the context semantic modeling capability of the large language model is utilized, the grammar rule, the character type and the semantic expression of the decompressed text are maintained while the compression capability is guaranteed, the encryption strength is improved, and the method can be widely applied to scenes such as high-speed communication (such as 6G) and the like which need to give consideration to safety and high compression rate.

The invention belongs to the technical field of voice communication, and particularly relates to a voice communication method, device and equipment based on three-group decomposition. The method comprises the following steps: performing three-way parallel feature extraction on an input voice signal to obtain a text feature, a rhythm feature and a tone feature; performing text compression, rhythm compression and timbre compression on the text features, the rhythm features and the timbre features to obtain a text packet, a rhythm packet and a timbre packet; transmitting the text packet, the rhythm packet and the tone packet according to the transmission priority; and respectively decompressing the text packet, the rhythm packet and the tone packet, synthesizing and playing. According to the voice communication system, voice is explicitly decomposed into three independent dimensions of language content, rhythm expression and speaker identity, compression strategies are optimized respectively, and the normal form that all information is entangled and coded by a traditional codec and an existing semantic compression method is broken through. While the bit rate is low, the quality level close to that of natural speech can be obtained.

The invention relates to the technical field of artificial intelligence, in particular to a text compression strategy for knowledge base enhanced retrieval. The method comprises the following steps: S1, based on a pre-trained BERT answer model, identifying and extracting an input question text and an answer fragment of each retrieved related text; s2, preprocessing each segment of retrieved related text; and S3, in combination with the preprocessing result of each section of related text, performing semantic matching scoring by adopting a Reranker model, sorting the obtained scoring results of each section of related text, selecting a plurality of results according to the sorting priority, and combining the results as a combination result of the problem text. And the Reranker model evaluates the priority according to the correlation between the sentences and the questions. According to the text compression strategy for knowledge base enhanced retrieval, the pre-training question and answer model is introduced, key answer fragments in the original text are efficiently extracted to serve as core keywords, the text processing efficiency is improved, and the focusing capacity of the model on answers can be enhanced.

The invention relates to the technical field of voice semantics, and discloses a cue word determination method and device based on compression and rearrangement, equipment and a medium, and the method comprises the steps: carrying out semantic analysis and blocking processing on an original cue text, and generating an original semantic unit; calculating a correlation score based on the task description information; distributing a text compression ratio according to the correlation score; and rearranging the target compressed semantic units to generate a target prompt word sequence. Through the above mode, redundant information is eliminated through intelligent compression ratio distribution and fine-grained semantic compression based on correlation scores, so that the length of the input sequence is greatly reduced. The position weighting function and the correlation score are introduced to perform sequence rearrangement on the semantic unit, the calculation complexity during large language model reasoning is reduced, the method can be applied to the fields of financial science and technology, medical treatment, health, old-age care and the like, and the efficiency of compressing redundant information and generating cue words by an intelligent interaction system is improved.

The invention discloses a defense method and device for a context injection attack of a large language model, and relates to the technical field of artificial intelligence network security protection. The method comprises the following steps of: performing non-uniform sampling on an input context, and extracting a head system instruction area, a tail user query area and a plurality of representative text fragments in the middle; by calculating a text compression ratio feature value and an N-gram repetition rate feature value of the middle fragment, capturing structural anomaly in a non-semantic understanding mode; calculating a semantic similarity characteristic value of the tail query and the middle segment, and carrying out intention corresponding detection; a total risk score is calculated, and hierarchical non-intrusive intervention from adding a security instruction at the end of the context to applying a dynamic Logit bias in a model decoding phase is performed according to different risk levels. According to the method, the safety detection and defense of the millisecond-level delay of the ultra-long context are realized, the internal weight of the model does not need to be modified, the universality is high, and the false alarm rate is low.

The invention discloses a semantic text compression method based on reinforcement learning and large model optimization, and aims to solve the problems of semantic distortion and key information loss in a complex noise environment and a low signal-to-noise ratio condition in the prior art. Through combination of reinforcement learning and semantic entropy estimation, the compression strategy can be dynamically adjusted, and it is ensured that under different channel conditions, the compressed text can effectively reduce the data volume and maintain semantic integrity. Besides, key information in the text is extracted by utilizing an attention mechanism of BERT, and loss of redundant information is effectively avoided, so that balance between compression efficiency and semantic fidelity is improved. The technology is suitable for various communication environments including the fields of wireless communication, the Internet of Things, intelligent equipment and the like, and has good robustness and universality.

The invention discloses a text compression and recognition method and device based on a visual modality and a medium, and the method comprises the steps: obtaining to-be-processed original text data, rendering the original text data into a text image, and preprocessing the text image; inputting the preprocessed text image into a depth visual encoder to extract image features through a multi-layer neural network architecture, and compressing the number of visual marks by adopting a mark compression mechanism to generate a compressed visual mark sequence; and inputting the compressed visual mark sequence into a hybrid expert decoder to activate a preset number of expert networks according to the compressed visual mark sequence, and decoding the compressed visual mark sequence into a corresponding text mark sequence to realize reconstruction of the original text data.

The present application relates to a kind of training methods of clinical auxiliary diagnosis model, belong to medical information processing technical field, solve the problem of poor coordination of size model in prior art affects the accuracy of diagnosis decision.Method includes: obtaining the medical text of multiple patients and constructs sample set;Text compression model and medical diagnosis large model are constructed, and the pre-training of text compression model and medical diagnosis large model constructed respectively is carried out based on sample set;The parameter of medical diagnosis large model is fixed, and the compressed text output by text compression model is input to medical large model, and text compression model is optimized based on the diagnosis task loss of medical diagnosis large model;The parameter of text compression model is fixed, and the compressed text output by text compression model is input to medical large model, and medical diagnosis large model is fine-tuned based on the diagnosis task loss of medical diagnosis large model, and the trained clinical auxiliary diagnosis model is obtained.The accuracy of diagnosis in complex clinical scenario is improved.

Email clients typically store received email in a local device to allow faster retrieval of the email. There is a need to optimize the space for emails stored locally without sacrificing the ability to work in an offline mode. Emails for users are summarized and the summarized version of the email is stored on the local device without storing the original email. An electronic device receives an email that is summarized and provided to the user in a way that is easily digestible and saves storage space. A machine learning model is trained by the user to provide the user with a summarized version of the email. A baseline machine learning model is provided to a user and over time, based on user interactions that train the baseline machine learning model, a personalized machine learning model is generated to predict and provide summaries that are beneficial to the user.

This invention discloses an Lz4 text compression method based on a sliding dictionary, primarily addressing the problems of slow compression speed and difficulty in hardware implementation in current text compression methods. This invention establishes a sliding dictionary, a hash table, and a register for the number of unsuccessful matches. The text to be compressed is read into the sliding dictionary, hash addresses are calculated to store string position information, the sliding dictionary is used to find duplicate strings, and the information of duplicate strings is stored to compress the text information, finally outputting the compressed text stream. The parallel processing of hash address calculation is easily implemented in a pipelined hardware manner. The high probability of finding duplicate strings through pre-prediction reduces the number of hash address calculations. The compression ratio of the text to be compressed is determined by the number of unsuccessful string matches, and the input speed of the text to be compressed is adjusted accordingly, significantly improving the compression speed.

The invention discloses a digital watermark steganography method and system based on optical text compression, and the method comprises the steps: 1, carrying out the load generation and optical coding, carrying out the optical rendering of a steganography text or image, inputting a visual semantic encoder, and obtaining a semantic vector set; step 2, performing semantic vector discretization and robustness enhancement; step 3, carrying out deep steganography embedding; 4, carrying out steganography extraction and error correction recovery; and 5, performing semantic vector reconstruction and optical decoding content generation. According to the method, cross-modal long text steganography based on visual semantic compression is realized for the first time, the limitation of a traditional steganography method in the aspects of capacity, recoverability and aggressiveness resistance is broken through, and the method can be widely applied to the fields of copyright identification, secret communication, digital traceability, media asset security and the like and has important engineering value and application prospect.

The invention relates to an ultra-large text transmission optimization method based on dynamic block compression and routing, which belongs to the technical field of ultra-large text transmission, and comprises the following steps: performing semantic analysis on an ultra-large text to construct a semantic relation graph, dividing the ultra-large text into logic paragraphs according to semantic correlation, dynamically adjusting the size of the block data according to the access frequency of the logic paragraph; according to the data feature of each piece of block data, matching an optimal compression algorithm for the block data, and compressing the block data; dynamically predicting the congestion condition of the transmission network according to the current network state monitored in real time, and transmitting the compressed data blocks to the target node one by one according to the original path if the transmission network is not congested; and if the compressed data block is congested, re-planning an optimal path, updating the SDN route, and continuously transmitting the compressed data block to the target node according to the updated path. According to the method, the super-large text transmission efficiency is improved, the text compression performance is optimized, and the stability and high efficiency of data transmission are guaranteed.

The embodiment of the application discloses a long text compression method and device based on a language model, wherein the method comprises the following steps: performing sentence division on a first initial long text by a regular method to obtain a first sentence sequence, and performing sentence division on a second initial long text by the regular method to obtain a second sentence sequence; obtaining a third sentence sequence from the first sentence sequence according to a Top K algorithm, and obtaining a fourth sentence sequence from the second sentence sequence according to the Top K algorithm; determining a sixth sentence sequence with the maximum similarity to the third sentence sequence from a fifth sentence sequence, and determining an eighth sentence sequence with the maximum similarity to the fourth sentence sequence from a seventh sentence sequence; splicing the third sentence sequence and the eighth sentence sequence to obtain a ninth sentence sequence, and splicing the fourth sentence sequence and the sixth sentence sequence to obtain a tenth sentence sequence. The application can improve the accuracy of long text compression.

The invention relates to a training method of a clinical auxiliary diagnosis model, belongs to the technical field of medical information processing, and solves the problem that the diagnosis decision accuracy is influenced by poor collaboration of large and small models in the prior art. The method comprises the following steps: acquiring medical text construction sample sets of a plurality of patients; constructing a text compression model and a medical diagnosis large model, and pre-training the constructed text compression model and medical diagnosis large model based on the sample set; fixing parameters of the large medical diagnosis model, taking a compressed text output by the text compression model as input of the large medical diagnosis model, and optimizing the text compression model based on diagnosis task loss of the large medical diagnosis model; and fixing parameters of the text compression model, taking a compressed text output by the text compression model as input of the large medical diagnosis model, and performing fine adjustment on the large medical diagnosis model based on diagnosis task loss of the large medical diagnosis model to obtain a trained clinical auxiliary diagnosis model. And the diagnosis accuracy in a complex clinical scene is improved.

This invention relates to an optimization method for ultra-large text transmission based on dynamic block compression and routing, belonging to the field of ultra-large text transmission technology. The method includes: constructing a semantic relationship graph from the ultra-large text through semantic analysis; dividing the ultra-large text into logical segments based on semantic relevance; dynamically adjusting the size of the block data based on the access frequency of the logical segments; matching the optimal compression algorithm to the block data according to the data characteristics of each block data; and dynamically predicting the transmission network congestion status based on real-time monitoring of the current network status. If there is no congestion, the compressed data blocks are transmitted to the target node one by one according to the original path; if there is congestion, the optimal path is replanned, the SDN route is updated, and the compressed data blocks are transmitted to the target node according to the updated path. This invention improves the efficiency of ultra-large text transmission, optimizes text compression performance, and ensures the stability and efficiency of data transmission.

The invention provides a text compression method and device, equipment and a storage medium, and the method comprises the steps: carrying out the word segmentation of an obtained original text, obtaining at least one text word segmentation result, obtaining a combination matrix of each text word segmentation result, and enabling the combination matrix to be determined according to at least one of a word segmentation matrix, a word segmentation feature matrix and a word segmentation position matrix. And performing compression processing on each combined matrix by using a plurality of preset compression matrixes to obtain target matrixes, merging the target matrixes corresponding to each combined matrix to obtain a merged matrix, determining target candidate words of each row of vectors of the merged matrix from a preset dictionary, and merging all the target candidate words to obtain a compressed text. By performing multi-dimensional representation on the original text, the core knowledge point understanding accuracy of the text can be improved, and then the text compression accuracy and compression rate and the meaning integrity of the original text content can be improved.

One example method includes receiving, by a large language model (LLM), input text to be compressed, defining a size of a rolling window of previous tokens, generated prior to receipt of the input text, that the LLM is permitted to consider in a conditional probability estimate, generating, by the LLM, tokenized text based on the input text, and the tokenized text comprises a sequence of tokens, based on the previous tokens, obtaining a probability mass function of a next token of the sequence, providing the probability mass function as an input to an arithmetic coding (AC) scheme, and assigning, by the AC scheme, a respective binary code to the token with a highest probability as assigned by the LLM.

The application discloses a defense method and device for large language model context injection attack, and relates to the technical field of artificial intelligence network security protection. The method comprises the following steps: non-uniform sampling is performed on input context, a head system instruction area, a tail user query area and a plurality of representative text segments in the middle are extracted; a text compression characteristic value and an N-gram repetition rate characteristic value of the middle segment are calculated to capture structural abnormalities in a non-semantic understanding manner; a semantic similarity characteristic value of the tail query and the middle segment is calculated to perform intention echo detection; a total risk score is calculated, and according to different risk levels, a graded non-intrusive intervention is performed from appending a safety instruction at the end of the context to applying a dynamic Logit bias in the model decoding stage. The application realizes millisecond-level delay safety detection and defense for an ultra-long context, and does not need to modify the internal weight of the model, so that the generality is high and the false alarm rate is low.

The application belongs to the technical scheme of human-computer interaction interface optimization, and particularly relates to a self-adaptive area Chinese text compression display method and system. Step one: dynamic display parameters are collected, and the collected parameters are preprocessed; step two: the input English text is subjected to semantic structure analysis through a Chinese semantic analysis module; step three: based on the display parameters preprocessed in step one and the Chinese text subjected to semantic structure analysis in step two, the text compression level is calculated based on a space density evaluation matrix, and a compression strategy is implemented; step four: the original text data and character rendering are stored through a reversible compression marking system. The application is used to solve the core problems existing in the field of intelligent terminal text display, such as semantic integrity damage, cross-platform adaptation error, unreliable data restoration and lagging behind of technology evolution.

The application discloses a multi-modal corpus storage method and device, computer equipment and medium. The compression method respectively performs compression processing on the text modal data and audio-video modal data of the multi-modal corpus, adopts a suitable compression algorithm according to the characteristics of different modal data, and performs similarity calculation on the text compression features, audio-video compression features and corresponding modal features of the newly added multi-modal corpus, so that the semantic redundancy of the newly added multi-modal corpus and the historical compressed corpus can be identified, the fusion compression process is triggered to eliminate cross-modal redundancy and avoid repeated storage of the same semantic information. Furthermore, the corpus features of the corpus not triggering the fusion process are independently stored, and the corpus features triggering the fusion process are fused to generate multi-modal joint features, so that the amount of data stored is further reduced. The corpus features are migrated to the corresponding data storage layer in combination with the access frequency and response time, thereby reducing the storage cost.

A text compression method, module, chip, electronic device and storage medium, the method comprising: performing word segmentation processing on the text to be compressed, and performing word length and word frequency statistics on the words obtained after word segmentation processing, and constructing a corresponding keyword list; based on the constructed keyword list, the text to be compressed is compressed. The above scheme improves the compression rate of text compression.

The application provides a summary generation system based on multi-modal key information analysis, comprising the following modules: a text encoder module for obtaining encoding information of a text; an image encoder module for obtaining feature information at different angles of an image; a selection gate mechanism module for mining key information of text and image modalities, comprising a multi-modal selection gate network and a visual selection gate network; a multi-head selection attention module for mining key object information in the image; a multi-modal feature fusion module for obtaining multi-modal context representation; and a decoder module for generating a summary sentence; when generating the summary, the system introduces object information of the image, and simultaneously shares the multi-modal key information extraction process of text compression to the encoding end; by mining key information of the text and the image, the application models the mutual dependence relationship between the object and the text sequence, highlights the key object information of the image, and thus generates a high-quality text summary.