212 results about "Information density" patented technology

The invention provides a page structure optimization method and system for a presentation file. The method comprises the following steps: identifying visual elements in a presentation page, and carrying out logical relationship analysis on the visual elements to obtain logical relationship information of the presentation page; mapping the visual structure information into a page three-dimensional implicit field to obtain three-dimensional voxels corresponding to the visual elements; calculating a visual focus thermodynamic diagram in the page of the presentation file, and distributing a three-dimensional voxel corresponding to the target visual element to a visual sensitive area; on the basis of the position relation of the visual elements and the first typesetting information, combining an information density energy function to predict a global optimal layout, and optimizing a narrative path in the presentation file according to logic relation information and user narrative preference to obtain third typesetting information, so that the spatial arrangement relation of the visual elements conforms to the narrative logic of the user preference; and executing secondary typesetting on the PowerPoint page based on the third typesetting information to optimize the page structure of the PowerPoint page and improve the page typesetting efficiency.

The invention belongs to the field of combination of a large model and a knowledge graph, and particularly relates to a large model and knowledge graph combined reasoning method for false news detection, which breaks through the limitation of a traditional detection method in the aspects of knowledge instantaneity and reasoning controllability through heterogeneous architecture design. Based on multi-dimensional features such as timeliness, propagation mode and information density of news propagation, a double-engine-driven intelligent reasoning system is constructed, on one hand, important entity extraction and semantic understanding are carried out through a large language model, and on the other hand, structured fact verification is provided through a dynamic knowledge graph. And the inherent factual illusion problem of a large language model is effectively solved. Compared with a traditional knowledge iteration mode depending on single model parameter updating, the method supports an incremental updating strategy based on knowledge graph nodes.

The invention discloses a Token-based visual task generation method, and belongs to the technical field of intelligent task automation, and the method comprises the steps: S1, cross-modal alignment; s2, performing visual Token processing; s3, constructing a task description Token sequence: constructing the task description Token sequence based on a predefined visual task template library according to requirements of a user or a specific application scene; s4, checking task feasibility; s5, task priority scheduling; s6, training a task generation model; s7, dynamic task allocation; and S8, optimizing the model. According to the method, the long sequence processing capability is optimized through a hierarchical merging strategy, the compactness of feature expression is realized while space position information is reserved, linear projection and enhanced position coding are combined to form a visual Token sequence with strong representation capability, local detail features are contained, a global context relationship is kept, and the method is suitable for the visual Token sequence with high representation capability. High-information-density feature input is provided for subsequent task processing, and the processing precision of various visual algorithms is effectively improved.

The invention relates to an intelligent interview scoring system capable of explaining decisions based on a large language model, and the system comprises a multi-mode resume analysis and feature coding unit, a resume feature adaptive matching unit, an interactive scoring and knowledge enhancement unit, and an answer quality evaluation unit. Text, image and audio features are extracted through a cross-modal attention mechanism of a multi-modal large language model, resume features are encoded into dynamic word vectors, and entity-level feature vectors are extracted; the post description text is encoded into a demand feature vector by a resume feature adaptive matching unit; calculating semantic similarity between the resume entity feature vector and the demand feature vector; the interactive scoring and knowledge enhancement unit dynamically retrieves knowledge fragments to generate a preliminary evaluation report containing a scoring basis; and the answer quality evaluation unit fuses the information density, the fluency and the integrating degree to generate a final score. And the whole-process intelligence from demand analysis to final decision making is realized.

The invention discloses an AI digital human interactive response method based on a large language model, and relates to the technical field of digital human interaction, and the method comprises the steps: analyzing collected user voice data and visual data through a natural language processing method, generating a cross-modal feature vector, carrying out the cross-modal association analysis of the cross-modal feature vector, and carrying out the cross-modal association analysis of the cross-modal feature vector. Generating a semantic association topological graph; calculating a vertex coordinate and a joint activity threshold value of the semantic association topological graph through high-digital human correlation, inputting the vertex coordinate and the joint activity threshold value into a constructed coordinate index database to execute attention weight calibration, and outputting a multi-dimensional association graph; and performing information density analysis based on the multi-dimensional association map, generating an information density gradient vector field, and dividing a high-density core region and a low-density edge region, the high-density core region generating a semantic core coding tensor, and the low-density edge region generating an edge feature package. According to the method, the cross-modal fusion vector is converted into the cross-modal feature vector, so that the modeling of the cross-modal association relationship is realized.

The application discloses a feature editing method for large model content security, which compares and analyzes the sparse coding features of a chat assistant constructed based on a large language model under positive user input and negative user input, extracts the internal response differences of the model to different semantic directions, and the mechanism can automatically and accurately identify the key feature dimensions highly related to the semantic direction of the target attribute. The model activation is mapped to a sparse feature space by using a sparse autoencoder, and each dimension of the feature has independent and interpretable semantic meaning. By injecting a feature guide vector in the space, the interference of the control process on the text grammar, fluency and information density is significantly reduced. The sparse representation mechanism is introduced to structure the intermediate activation features in the reasoning process of the large language model and to intervene in a targeted manner, so that the reply of the chat assistant to the user input conforms to the preset safety specification, and the safety and controllability of the chat assistant in the interaction with the user are improved.

The invention provides an intelligent teaching system based on an AI robot coach, and relates to the field of intelligent teaching. Comprising a hardware equipment module, a software platform module, a safety control module, a hierarchical intervention module, a physiological monitoring module and a cognitive load regulation module, the hardware equipment module collects vehicle state, environment and student physiological data in real time through a multi-mode sensor; the software platform module generates a teaching strategy based on a deep reinforcement learning model and analyzes a student behavior mode; the safety control module triggers an automatic braking mechanism through the obstacle distance and the vehicle speed; the grading intervention module is divided into three-level intervention strategies of an L1 unit, an L2 unit and an L3 unit according to the operation error type, and voice prompt and braking intervention are dynamically adjusted; the physiological monitoring module non-inductively evaluates a tension index through micro-expression, grip strength and voice data; the cognitive load adjusting module dynamically adjusts the teaching content difficulty and the information density in combination with the steering frequency, the accelerator and brake alternating times and the tension index.

The invention discloses a public opinion event multi-mode semantic fusion modeling and abstract generation method and system, and relates to the field of natural language processing and social network analysis. Through the multi-mode semantic fusion technology, the short text understanding ability is improved, and the problems of semantic fuzziness and network language diversification are solved. Meanwhile, through a cross-window event cluster matching technology, an event evolution path with time continuity is constructed, and comprehensive capture of event dynamic characteristics is realized. Besides, the structured event abstract is automatically generated by utilizing the generative model, so that the consistency and the information density of the abstract are improved, and the actual application requirements are met. Through the innovations, the defects in the aspects of semantic comprehension, dynamic modeling and abstract generation in the prior art can be effectively overcome, a more efficient and accurate solution is provided for monitoring and analysis of public opinion events, and the method has wide application prospects in the fields of public opinion monitoring, emergency early warning, social media data analysis and the like.

The embodiment of the invention provides an AI-based vehicle intelligent interaction method and system, and belongs to the field of artificial intelligence interaction. The method comprises the following steps: dynamically judging a cognitive load level in a current driving scene through collaborative perception of a driver state and an environment state; determining a target man-machine interaction strategy of the vehicle based on the cognitive load level; wherein the target man-machine interaction strategy comprises a voice output mode, information density of screen display content and a feedback prompt mode; determining a corresponding trigger rule based on a switching relationship between the current man-machine interaction strategy and the target man-machine interaction strategy; and responding to a trigger signal of the determined trigger rule, executing man-machine interaction strategy switching, and executing vehicle interaction based on the switched target man-machine interaction strategy. According to the scheme of the invention, closed-loop adaptive control of a human-vehicle interaction strategy on a cognitive state is realized.

The invention relates to the technical field of voice signal processing, and discloses a voice segmentation intelligent editing system based on deep learning. The system comprises a voice feature extraction module, a segmentation boundary detection module, a semantic content analysis module, an editing strategy generation module and a real-time quality evaluation module. The voice feature extraction module collects multi-dimensional voice features and timestamp information, and verifies feature integrity and timeliness; the segmentation boundary detection module identifies voice pause intervals and semantic turning nodes and divides segmentation units and boundary types; a semantic content analysis module extracts text content and emotion features of each segment, and analyzes semantic topic relevance and information density; an editing strategy generation module formulates a segmentation retention rule and a sequence adjustment scheme, and matches user preferences and scene demands; the real-time quality evaluation module monitors voice fluency and information integrity in the editing process and analyzes splicing errors and user feedback. According to the system, intelligent processing of the whole voice editing process is realized.

The invention provides an efficient annotation-driven hierarchical fault positioning method, which comprises the following steps of: guiding a large language model to intelligently analyze and generate semantic annotations of a text based on a positioning algorithm of large model annotations, and performing fine-grained software fault positioning from a file level to a function level and then to a position level by using the annotation-based hierarchical positioning method. And an efficient hierarchical progressive sorting and screening algorithm is used for ensuring the software fault positioning efficiency. According to the method, the defect positioning efficiency can be ensured while the positioning accuracy is ensured. The positioning algorithm based on large model annotation strategically balances the information density, provides enough context clues, and improves the model understanding ability; according to the annotation-based hierarchical positioning method, positioning is divided into file / function / position hierarchies, and annotations are added by using a large model cue word project in sequence, so that the positioning accuracy is improved; and an efficient hierarchical progressive sorting and screening algorithm is provided, so that the optimal balance between the performance and the cost is realized.

The invention discloses a large model content security-oriented feature editing method, which comprises the following steps of: comparing and analyzing sparse coding features of a chat assistant constructed on the basis of a large language model under positive user input and negative user input, and extracting internal response differences of the model in different semantic directions; the mechanism can automatically and accurately identify key feature dimensions highly related to the semantic direction of the target attribute. A sparse auto-encoder is utilized to activate and map the model to a sparse feature space, and each dimension of feature has an independent and interpretable semantic meaning. By injecting a feature guide vector into the space, the interference of a control process on text grammar, fluency and information density is remarkably reduced. A sparse representation mechanism is introduced, structural modeling and targeted intervention are carried out on intermediate activation features in a big language model reasoning process, replies input by a chat assistant to a user are guided to conform to a preset safety specification, and the safety and controllability of the chat assistant in interaction with the user are improved.

The invention provides an industrial part abnormal target detection method and system. According to the model, a YOLOv10 framework is used as a basic framework to construct a lightweight model, and the detection performance and efficiency are improved through three-stage optimization. Firstly, a multi-head self-attention mechanism is introduced to reconstruct a feature space, and cross-modal feature interaction is promoted by using CSP structure balance calculation efficiency and feature representation capability and combining a channel grouping shuffling strategy. Secondly, designing a context guide perception module in a feature fusion stage, enhancing multi-scale feature expression through a parallel multi-branch architecture and a spatial self-calibration mechanism, and enhancing up-sampling information density in cooperation with a dynamic interpolation fusion module; the detection head adopts a parameter sharing group convolution structure, and the calculation amount is reduced through a convolution kernel parameter sharing and feature decoupling mechanism. The method effectively solves key problems in industrial part detection, and is of great significance to industrial part automatic anomaly detection scenes on an industrial production line.

The invention discloses a multi-stream chain type perception enhanced multi-modal aspect level sentiment analysis method, which is called MCPE model for short, and relates to the technical field of multi-modal sentiment analysis. According to the method, the problem of low accuracy of fine-grained sentiment analysis caused by information density difference in modals and information imbalance between modals in the prior art is solved. The method comprises the steps of obtaining a to-be-analyzed multi-modal text-image pair, inputting the text-image pair into a trained MCPE model, and obtaining aspect words and emotional polarities thereof; the MCPE model comprises a feature extraction module, a chain enhancement module, a multi-stream interaction module and a classifier; feature extraction adopts BART to extract text features and Faster R-CNN to extract image features; the chained enhancement module suppresses image and text noise and enhances fine-grained semantics through an IFE-TFE double-chain architecture; the multi-stream interaction module adopts bidirectional cross-modal attention to realize dynamic complementary fusion of text reasoning and visual evidence; and the classifier outputs an analysis result based on the fusion feature without an external tool. The method is suitable for sentiment analysis of social media comments.

The invention is suitable for the technical field of intelligent content generation and personalized recommendation control, and provides an AIGC-based retail client interaction content generation and push system, which comprises an information acquisition module, a track recognition module, a behavior association judgment module, a correction parameter generation module and a content complexity regulation and control module. According to the method, the user behavior track and the wearable equipment data are fused, and a content complexity level correction mechanism based on the combined driving of the fixation time trend and the physiological state change trend is constructed. Different from an existing mode of setting a recommendation strategy only according to a behavior label or a single-dimensional feature, the method introduces a final correction parameter to dynamically adjust the complexity level of the original content, so that the generated content better fits the current attention intention and cognitive state of the user in the aspects of expression level, information density and logic structure.

A system is disclosed, including a display, a processor and a memory. The memory stores instructions that, when executed by the processor, configure the system to perform operations. Active region data is generated that includes, for each of one or more active regions, active region location data and active region content. The active region data is transmitted to a display having a display area. For each active region, the active region content is displayed at an active region location of the display area based on the active region location data, the active region content being displayed at a higher spatiotemporal information density than content displayed in the display area outside of the active regions.

The invention relates to the technical field of deep learning, in particular to a forage grass yield prediction model construction method based on deep learning, which comprises the steps of constructing a multi-source data fusion module, establishing a cold start mechanism, designing a multi-modal deep learning prediction network, integrating a physical constraint mechanism and constructing a management decision support system. A seasonal attribution analysis function is realized; in the prior art, a simple data superposition or static weighted fusion scheme is generally adopted, and inherent defects of deficiency, different scales and heterogeneity of multi-source data are difficult to process, so that the fusion feature quality is poor; according to the method, firstly, a data blank is accurately filled through an intelligent algorithm based on space-time continuity, then heterogeneous data is unified to a standard grid by using a multi-scale pyramid engine, and finally, deep fusion is performed through an attention mechanism for dynamically calculating importance of each data source; the integrity, the consistency and the information density of the input data are remarkably improved, and a solid and reliable data foundation is laid for subsequent accurate prediction.

The invention discloses an RAG content generation method and system based on dynamic slicing and self-adaptive fusion, and relates to the field of natural language process.The method comprises the steps that in response to a user query instruction, semantic fusion processing is conducted on a plurality of related text blocks, and a preliminary text sequence is traversed; detecting a logic breakpoint between adjacent text blocks through a context association identifier, recalling a middle connection text block corresponding to the logic breakpoint, and inserting the middle connection text block into a sequence to generate a fusion text stream; performing adaptive information density adjustment on the fused text stream to obtain optimized context content; generating structured prompt information based on the optimized context content and the user query instruction; and calling the target large language model to generate a user query result based on the structured prompt information. The answer accuracy and logic continuity of the target large language model for user query are effectively improved, and the utilization efficiency of model computing resources is optimized.

The invention discloses a desulfurization optimization control method and system based on a multi-modal model, and relates to the technical field of industrial intelligent control, and the method comprises the steps: constructing a gas-liquid interface boundary point set, and generating a control feature vector; calculating fractal dimensions of control feature vectors by using a box counting method, constructing a disturbance point set, multiplying disturbance intensity by an expansion trend to obtain an unstable diffusion grade, matching key propagation points with nearest disturbance points by using nearest neighbor matching, and generating a control priority sequence; and defining a control unstable diffusion level, defining an optimization objective function, and solving by using constraint optimization to obtain a final control variable. According to the method, a composite strength factor is constructed through an image gradient field and a signal response ratio, a gas-liquid interface boundary point set and a control feature vector are constructed, the robustness and information density of features are improved, a main resonance frequency is recognized by combining a fractal interference field and short-time Fourier transform, key propagation points are screened by using wavelet transform and information entropy analysis, and a high-precision gas-liquid interface is obtained. The desulfurization efficiency and the stability of the reaction tower are improved.

The embodiment of the invention provides an intelligent operation and maintenance method and system based on a large language model. According to the method, firstly, at least M multi-modal original logs generated by a micro-service cluster are collected, compression processing is conducted on the multi-modal original logs by means of a large language model, at least N multi-modal target logs are obtained, the log data volume can be greatly reduced, and the effective information density is improved; synchronously collecting system operation indexes of timestamps corresponding to the multi-modal target logs and determining an association relationship between the system operation indexes to reduce invalid diagnosis workload; a multi-type heterogeneous operation and maintenance topological graph is constructed based on the incidence relation, a current fault is accurately positioned, the problem that root causes are difficult to quickly position through traditional manual analysis of mesh topology is solved, and the root cause recognition time is shortened; and finally, a preset historical fault knowledge base is called, a target repairing script matched with the current fault is generated in combination with the large language model, repairing of the current fault is achieved, time consumed by manual intervention is shortened, and therefore the fault diagnosis efficiency is remarkably improved.

The invention belongs to the technical field of artificial intelligence, and particularly relates to an AI-based file data content accurate and deep analysis and interpretation method, which comprises the following steps: acquiring multi-format file data and file meta-information, constructing an AI analysis network, extracting text semantic vectors, image visual features, table structure information and document layout features, and constructing a multi-dimensional semantic map. According to a user query intention, semantic extension is performed in combination with a domain knowledge base, an enhanced semantic description vector is generated through a graph attention mechanism, semantic reasoning and relation mining are performed by adopting an improved knowledge distillation Transform model, and a deep analysis conclusion is generated through a multi-hop reasoning model in combination with file data complexity, information density and user requirements. And generating a personalized interpretation report in combination with a user role and a task scene, and outputting an analysis result through a visual interface. Therefore, the problems of poor understanding ability, poor file adaptability and the like in the prior art are solved.

The invention provides a small target detection method for unmanned aerial vehicle data, and the method can effectively improve the detection precision, achieves better balance in three aspects of light weight, high precision and real-time performance, and can be suitable for more small target detection scenes. The method comprises the following steps: constructing a PLDP-SPP module, calculating a regional significance score S and a texture complexity score T for each pixel point in an input feature map in a feature content analysis module, and calculating to obtain a comprehensive score V by taking S and T as quantitative indexes; different pooling scales are preset according to the comprehensive scores V in different ranges, and it is ensured that more detailed context information extraction can be carried out on an area with large information density; in a size decision mechanism module, feature densities of different areas are matched through dynamic pooling, the scale adaptability is higher, and particularly, the detection precision of small targets and medium targets is remarkably improved.

The invention discloses a tracking method of a semi-structured dialogue state, a medium and electronic equipment, and belongs to the technical field of computers, a dialogue state model based on UML is designed to represent and track the dialogue state, the dialogue state model comprises multiple rounds of decision making processes, priori knowledge of a service is abstracted, and the decision making efficiency is improved. According to the method, the information density of a single dialogue sample is increased in the state of each round of dialogue process, so that the search space of the dialogue state is reduced, the requirement of a DST model for the number of training corpus samples is reduced, the cold start problem of model training is solved, the samples are generated on the basis of the dialogue state model, and the efficiency is improved. The DST model can continuously learn and adjust in a dynamic environment within a certain range through reinforcement learning to adapt to new data or tasks, the content output by the model can be controllable, the precision of processing complex tasks is improved, and the problem that the model cannot track a long dialogue state is solved.

The invention discloses a multi-modal large model question and answer method, device and equipment based on attention entropy and a medium, and relates to the field of artificial intelligence and machine learning. Comprising the following steps: inputting a target image and a problem text into a multi-modal large model to obtain an image marking sequence and a text lexical element sequence; connecting an rth pruning layer in front of an rth decoding layer of the decoder, calculating an attention matrix from rth vision to text and an attention matrix from rth text to vision according to an rth image mark sequence and an rth text lexical element sequence, and determining an ith information density weight corresponding to an ith image mark in the rth image mark sequence; based on the information density weight corresponding to each image mark in the rth image mark sequence, screening out an rth reserved image mark sequence; and inputting the rth reserved image mark sequence and the rth text lexical element sequence into the rth decoding layer to obtain an answer text output by the large language model, so as to effectively balance the calculation efficiency and the semantic integrity under the condition of not needing additional training.

The invention discloses an AI-based quantum communication optimization method and system, and relates to the technical field of quantum communication optimizing.A quantum element reinforcement learning strategy library is locally deployed at a terminal, a self-adaptive spectrum feature extraction mechanism is combined, the channel mutation response rate is improved, and compared with centralized AI needing a cloud end to return a decision and avoid a network delay bottleneck, the AI-based quantum communication optimization method and system have the advantages that the reliability is high; the instantaneous anti-interference requirement of battlefield communication is met; under the federated learning framework, the terminal only uploads the model gradient, and the original data does not leave the local; the strategy migration unit is used for enabling a new terminal or a strange environment to quickly obtain a benchmark decision-making capability by using a pre-stored feature vector of an interference pattern library, and cracking the cold start defect of traditional federal learning; in addition, the quantum state parameters and the electromagnetic spectrum are fused through gating weighting, and the feature discrimination is enhanced while the original physical characteristics are reserved. The three-channel tensor structure provides high information density input for the lightweight CNN, and the misjudgment rate rise caused by model compression is avoided.

The invention discloses a recursive deep text query method, system and device and a storage medium, and the method comprises the steps: firstly creating an initial query and initializing a hierarchical depth, executing a first-layer query, carrying out evolution processing, and then carrying out retrieval; if the information density is insufficient, sub-query is generated to execute second-layer query, and retrieval is performed after second evolution processing; if the second-layer retrieval is contradictory, third-layer query is executed, retrieval is performed after timeline query and information source tracing verification are passed, and a third-layer retrieval result is finally output; through multi-level query and targeted evolution processing, query can be optimized step by step, more information dimensions can be covered, information gaps can be filled up, and retrieval comprehensiveness and accuracy can be improved; and a third-layer verification mechanism can effectively check contradictions by means of timelines and source tracing, so that the accuracy and reliability of results are guaranteed, and better retrieval results are provided for users.

This invention discloses an efficient RNA data preprocessing method to address the problems of low processing efficiency and low information density in high-throughput sequencing data. Its core steps include: (1) introducing a parallel processing scheme for high-throughput sequence data, rapidly mapping RNA-seq data to a reference genome to generate a BAM file; (2) extracting base sequences and expression levels and storing them as compact PKL format files; (3) extracting all exon position information by parsing the genome annotation file; (4) combining multi-sample expression level data to screen for highly variable exons and constructing a high-information-density feature list based on the sample set; and (5) accurately extracting target sequences from the preprocessed file based on this list. Compared to traditional methods, this innovative approach achieves triple optimization: full-process parallel processing for accelerated computation, high-compression data storage, and adaptive feature selection. Processing speed is increased by 3-5 times, and data volume is reduced by more than 90%, making it suitable for high-throughput RNA-seq data analysis with large sample sizes.

The invention provides a locomotive fault prompting method and device, a medium and electronic equipment, and relates to the technical field of rail transit. The locomotive fault prompting method comprises the following steps: determining fault characteristics of a locomotive according to original fault data corresponding to a locomotive fault; determining a target fault prompting strategy in the plurality of candidate fault prompting strategies; under the condition that the target fault prompt strategy comprises visual prompt, auditory prompt and somatosensory prompt, determining a prompt mode and content of the visual prompt according to the first-level fault attribute feature, and determining a prompt mode and content of the auditory prompt according to the first-level fault attribute feature and the second-level fault attribute feature, according to the first-level fault attribute feature and the second-level fault attribute feature, determining a prompt mode and content of somatosensory prompt; and executing prompt operation based on the prompt mode and content of the visual prompt, the prompt mode and content of the auditory prompt and the prompt mode and content of the somatosensory prompt. According to the invention, the intuition and information density of locomotive fault prompt can be improved.

The embodiment of the invention provides an information processing method and related equipment, and the method comprises the steps: displaying a service interface, and displaying received itinerary planning request information in the form of a first session message in the service interface; in response to the itinerary planning request information, itinerary planning information and at least two browsing modes are output, any browsing mode is used for performing simplified display on the itinerary planning information, and the itinerary planning information and the at least two browsing modes are displayed on the service interface in the form of a second session message; and in response to the triggering of any browsing mode, presenting the itinerary plan in the itinerary planning information according to the triggered browsing mode. According to the embodiment of the invention, the travel route planning content can be displayed in a simplified manner, the information density is reduced, and the reading experience of a user is improved.

The application discloses a code library UML diagram automatic generation method and system based on cooperation of abstract syntax tree and large language model, comprising an AST analysis and structure extraction layer, which is used for being responsible for abstract syntax tree analysis on source files in the code library and extracting skeleton structure information of the code library, and a large language model semantic analysis layer, which is used for receiving structured code skeleton data output by the AST analysis layer and submitting the structured data to the large language model for semantic analysis through a carefully designed prompt word (Prompt), wherein the application extracts structured skeleton information of the code library through AST analysis instead of directly processing original source code, compresses the information volume to 10% to 20% of the original code amount, greatly improves the effective information density of the input large language model, enables a larger scale code library to be covered in a limited context window, and solves the problem that the existing large language model scheme cannot process a large scale code library due to Token waste.