92 results about "Contextual reasoning" patented technology

An AI-based Cybersecurity System and Method enable real-time detection, analysis, and mitigation of cyber threats within computing networks using adaptive artificial intelligence. The system continuously monitors network traffic, extracts behavioral and contextual attributes, and applies deep learning-based inference to identify anomalous activities indicating security breaches. The method integrates several computational units, including a network monitoring unit, feature extraction unit, artificial intelligence processor, contextual reasoning processor, and decision synthesis unit, to compute a composite risk index quantifying threat likelihood and severity. A classification processor categorizes detected threats into types such as ransomware, phishing, or unauthorized access, while a mitigation control processor initiates automated response actions to isolate compromised nodes and restore network integrity. An adaptive learning processor updates AI models using feedback from confirmed incidents. This provides a scalable, self-evolving cybersecurity framework that minimizes human intervention and enhances resilience against dynamic and zero-day threats.

The invention relates to the technical field of artificial intelligence, can be applied to the fields of financial science and technology and medical health, and discloses a reasoning optimization method, device, equipment and medium for a multi-modal large language model.The method comprises the steps that an input long context sequence is obtained, and key value projection is conducted on the long context sequence to generate an initial key value cache; for each attention layer of the multi-modal large language model, calculating an attention matrix of the attention layer according to the vector dimension of the long context sequence and the initial key value cache; calculating a cross-modal attention entropy according to the attention matrix, and determining a cache size of an attention layer according to the cross-modal attention entropy; optimizing the initial key value cache based on a cumulative attention scoring mechanism and a window strategy to obtain a target key value cache; and reasoning the long context sequence according to the cache size and the target key value cache to generate a long context reasoning result. And the reasoning efficiency and the reasoning accuracy are improved.

The invention discloses a multi-agent task arrangement method and system, and relates to the technical field of artificial intelligence. In the method, firstly, a task demand is obtained, key information and intention of the task demand are extracted, and task semantics are obtained; secondly, based on the task semantics and the business standard process template, obtaining a business standard process template matched with the task demand; then, according to the matched business standard process template and task semantics, a task context is constructed, and a domain specific language DSL is generated through reasoning according to the task context; thirdly, the DSL is analyzed, a task dependency graph is constructed according to the DSL analysis result, and the task dependency graph is converted into BPMN process model data; and finally, sub-task scheduling and execution of the sub-agents are carried out according to the BPMN process model data. According to the method provided by the invention, the dependence on professional developers or process engineers can be reduced, the response and planning time of complex tasks can be shortened, the result predictability can be improved, and the reasoning cost can be obviously reduced.

A system for context-sensitive orchestration of autonomous agents in cloud platforms, consisting of: a hardware-based orchestration device configured for integration into a distributed cloud infrastructure; a context inference engine within the orchestration device, wherein the context inference engine is configured to receive and aggregate real-time telemetry data from a variety of distributed nodes, including at least one system-level parameter, at least one application-level parameter, and at least one environment parameter; a semantic inference module within the context inference engine, configured to generate a context-related state representation by correlating the parameters using a knowledge graph-based model of interdependencies; an optimization unit for machine learning within the orchestration device, which is communicatively connected to the context inference engine and is configured to predict resource requirements and operational states using reinforcement learning models trained on historical and real-time data streams; a policy-driven orchestration controller configured to translate the contextual state representation into actionable orchestration decisions by applying dynamic orchestration policies stored in a domain-specific policy repository; and a distributed agent interaction bus configured to delegate orchestration decisions to a variety of autonomous agents deployed on the cloud platform.

The invention discloses an algorithm method for large-model long context reasoning, which relates to the technical field of large language models and comprises the following steps of: dividing an input long text sequence into a plurality of initial text blocks; a semantic abstract is generated based on the initial text blocks, clustering analysis is conducted on the semantic abstract, the initial text blocks with similar semantics are combined into semantic hyperblocks, and a context organization structure with semantic representativeness is formed; the method comprises the following steps: generating key value cache data of each token in a large model preprocessing stage, grouping the key value cache data by taking semantic hyperblocks as logic boundaries, and establishing a mapping table for recording storage positions and states of the semantic hyperblocks; on the basis of semantic hyperblocks, semantic representative vectors of the semantic hyperblocks are combined, correlation scores between query vectors and the semantic hyperblocks are calculated, a block importance prediction model learns on the basis of context dependency features, high-order semantic prior is provided for subsequent attention screening, and key information omission caused by position offset is avoided.

The invention provides a large language model long text reasoning acceleration method and device based on a speculative key value cache sparse technology, a medium, a terminal and a program product, the method is applied to electronic equipment comprising a GPU and a CPU, and the method comprises the steps that an index list of most important historical tokens is generated based on a distillation language model according to an obtained context sequence; comparing the index list generated at the current moment with the index list at the previous moment, and calculating to obtain a difference set part; asynchronously prefetching the key value cache of the difference set part from the CPU to the GPU; according to the asynchronously prefetched key value cache, performing parallel execution based on a large language model to generate a new token; obtaining a new sequence length according to the generated new token, and judging whether the new sequence length exceeds a preset threshold value or not; and if the threshold value is exceeded, executing unloading operation. According to the method, the performance and the stability of processing long text reasoning by the large language model can be improved, and key value cache optimization in the long context reasoning process is ensured to be always effective.

The invention discloses a version knowledge graph reasoning method and system based on large language model enhancement, and relates to the technical field of dynamic knowledge graphs, and the method comprises the steps: employing a semantic drift detection and compensation mechanism, comparing context coding differences of same entities of different versions in an initial knowledge graph, recognizing drift, and dynamically adjusting entity embedding vectors, outputting a compensation update atlas; an LLM enhanced multi-hop reasoning algorithm is adopted, multi-hop reasoning is carried out on the compensation updating map, symbol reasoning, vector reasoning and context reasoning are carried out in parallel in each hop, and an entity relation reasoning result is obtained through dynamic weight fusion; and superposing an entity relationship reasoning result to the compensation updating graph through a cloud collaborative node, adding an entity edge and automatically maintaining a version history log, and obtaining a reasoning fusion version knowledge graph. Through a multi-hop reasoning algorithm enhanced by a large language model, the deep semantic mining capability and reasoning accuracy of a cross-version entity relationship are effectively improved.

The invention provides an automatic focus identification and grading method for a medical image, and the method comprises the steps: carrying out the standardization of an obtained multi-modal original image based on anatomical constraint, and obtaining a standardized image; generating semantic enhancement features through a cross-modal feature compensation network based on the standardized image and associated radiological text description; performing dynamic feature adaptation processing on the semantic enhancement feature to generate a modal adaptive feature; performing context reasoning through a multi-scale feature interaction algorithm based on the modal adaptive features to generate context reasoning features; and lesion identification decoding processing is carried out on the context inference feature map, a lesion segmentation mask is generated, and the lesion segmentation mask is used for extracting lesion area feature parameters to carry out lesion classification. By adopting the method, the adaptability to the missing mode can be enhanced, and the focus identification and grading precision can be improved.

The invention relates to the technical field of artificial intelligence and big language model reasoning optimization, and discloses a big language model-oriented adaptive KV cache compression method and system, and the method comprises the steps: constructing a lexical element importance measurement mechanism; analyzing an attention head distribution structure in large language model reasoning, and constructing a plurality of pruning strategies; based on a lexical element importance measurement mechanism and the attention head distribution structure, designing a self-adaptive key value cache compression hybrid strategy set based on a pruning strategy; constructing a static self-adaptive key value cache compression method, and automatically distributing a key value cache compression strategy in a pre-filling stage of large language model reasoning; and in a decoding stage, performing adaptive compression on the key value cache based on the allocated key value cache compression strategy. According to the method, the key value cache can be efficiently compressed on the premise of not depending on explicit attention score calculation, a system-level reasoning optimization framework is compatible, the generation performance is kept, meanwhile, the video memory consumption is remarkably reduced, and the long context reasoning capability is enhanced.

The invention discloses an edge end multi-modal perception and decision cooperation method and system, and relates to the edge calculation and artificial intelligence cross technology field, and the system comprises a multi-modal perception unit used for collecting heterogeneous perception data of an environment; the data processing unit is in communication connection with the multi-mode sensing unit; wherein the data processing unit comprises a dynamic cognitive kernel, and the dynamic cognitive kernel sequentially comprises a modal credibility evaluation layer, a context reasoning layer and a decision verification layer; and the modal credibility evaluation layer is configured to receive the heterogeneous sensing data. According to the edge-end multi-modal sensing and decision-making collaboration method and system, by introducing a dynamic cognitive kernel, real-time evaluation and dynamic weight adjustment of the reliability of multi-modal sensing data are achieved, the defect that the collaboration efficiency of a traditional fixed rule system is reduced when the environment changes is effectively overcome, and the collaborative performance of the system is improved. And the adaptability and decision accuracy of the system in a complex scene are improved.

The embodiment of the invention provides a knowledge graph fusion method and system based on a large model, and the method comprises the steps: carrying out the data standardization, entity feature enhancement and relation semantic annotation of heterogeneous knowledge graphs from different sources; through semantic similarity calculation, context reasoning and alignment confidence evaluation, a multi-stage and multi-mode entity alignment mechanism is constructed in combination with a large language model, and cross-source entity matching is performed on entities in heterogeneous knowledge maps of different sources; based on conflict detection, dynamic weight distribution and a conflict resolution strategy, generating a data fusion result, and unifying multi-source data; and generating a high-quality unified knowledge graph through missing relationship prediction, logic consistency verification and an incremental updating mechanism. According to the knowledge graph fusion method and device, full-process automation, precision and dynamics of knowledge graph fusion are realized, the problems of high manual dependence, weak semantic processing capability, poor cross-domain adaptability and the like in the prior art are effectively solved, and the efficiency and quality of knowledge graph fusion are remarkably improved.

The invention provides an information query method and device based on a large language model. The method comprises the steps that query information input by a user is received; determining a target context fragment related to the query information based on the semantic similarity between historical context fragments associated with the user in the large language model stored in a database and the query information and a predetermined comprehensive importance score of each historical context fragment; wherein the comprehensive importance score of each historical context fragment is determined on the basis of a clustering result and the generation time of each historical context fragment after the historical context fragments are clustered; and fusing the query information and the target context fragment, inputting the fused information into the large language model, and determining a query result corresponding to the query information. Through the method, the context reasoning capability of the large language model can be improved, and the query result can be more accurately generated for the user.

The embodiment of the invention provides an enterprise information architecture (4A)-based AI Agent planning enhancement system, a control device and equipment, and the system comprises a Prompt construction module which is used for analyzing an unstructured demand to obtain a structured demand, and cooperating with other modules to generate a standardized Prompt comprising a business process, a data entity and a tool strategy; the knowledge matching module is used for matching related knowledge based on a knowledge graph employment number fusion knowledge base and sorting the related knowledge into a knowledge list containing business processes, practical experience, a data list and a tool list; and the context reasoning module is used for generating a reasoning result based on the historical data and the knowledge list and feeding back the reasoning result to the Prompt construction module so as to assist in generating the normalized Prompt. According to the system, the integration capability of the AI Agent on business logic and data resources in the task planning process is remarkably improved, so that the AI Agent can more accurately understand enterprise-level business scenes, and standardized and intelligent planning support is provided for practical application of the AI technology in enterprise digital transformation.

The invention discloses a multi-source heterogeneous information extraction and structured processing method based on natural gas business data, and relates to the technical field of artificial intelligence application in the energy industry, and the method comprises the steps: analyzing a multi-modal document: carrying out the content analysis of natural gas sales documents in various formats, extracting key information, and obtaining the analyzed original data; data preprocessing: cleaning, recombining and standardizing the data to obtain preprocessed data; the mixed information extraction comprises key business index extraction, field rule base establishment, mixed extraction model establishment and context reasoning, and missing items in data are complemented by analyzing overall information and local content of a document, so that the integrity and accuracy of the information are improved; performing intelligent post-processing and constructing a relational database; according to the processing method, the natural gas service data can be accurately and efficiently extracted from the documents in various formats, and a basis is provided for subsequent data analysis and decision support.

The invention relates to the technical field of data fusion, in particular to a water conservancy teaching scene dynamic simulation method and system based on multi-modal data fusion, and the method comprises the steps: firstly, carrying out the cross-modal feature extraction and space-time alignment of multi-source heterogeneous data, generating fusion features in a unified feature space, and solving the problem of data feature inconsistency; secondly, semantic enhancement and context reasoning are carried out on the fusion features based on a water conservancy project knowledge graph, and a physical simulation algorithm and a generative model are combined to drive and generate a physically accurate dynamic simulation scene; and finally, mapping a user operation instruction to a unified feature space in real time in teaching deduction to generate an operation feature vector, and dynamically generating a corresponding virtual intervention result through deviation analysis, thereby effectively solving the problem of interactive response delay, and realizing unification of authenticity and interactivity of teaching simulation.

The invention discloses a medical examination report processing method and device, electronic equipment and a storage medium, and the method comprises the steps: processing a medical examination report, and determining report text data corresponding to the medical examination report; processing the report text data based on a big language model, and obtaining structured data which is output by the big language model and corresponds to the medical examination report; and converting the structured data into standardized data based on a standard document format, and mapping the standardized data to a medical coding system. Based on the technical scheme, a prompt project and context reasoning mechanism is utilized to guide a large language model to automatically identify the medical entity and output the structured representation, and the structured data is mapped to a medical coding system, so that seamless joint with various medical information is realized; and the real-time adaptive analysis and structuring requirements of the multi-source medical examination report can be met.

The present disclosure relates to a method and system for enhancing inference in large language models (LLMs) over long input sequences. A segmented inference strategy may be employed, wherein the long context can be divided and sequentially processed through a key-value (KV) cache of the LLM. At each step, the model may generate auxiliary outputs (or margins), which may include extractive summaries or intermediate signals based on the segment's relevance to an instruction. These margins may then be classified and selectively retained to guide final inference on the instruction. The retained margins may be prepended to the instruction to facilitate improved generation without modifying the model's internal weights. The disclosed approach provides efficient localization of relevant content, improves comprehension of extended contexts, and reduces computational overhead. Moreover, the disclosed technique is particularly effective for retrieval-based NLP tasks and supports long-context reasoning in LLMs while enhancing inference efficiency and user experience.

The invention provides an autonomous driving control system based on LLM context reasoning, and the system comprises an LLM engine module which is used for receiving and analyzing a semantic natural language request, and outputting a semantic map fusing a context reasoning result; the navigation agent module is used for initiating a semantic analysis request to the LLM engine module and initiating a path planning request to the path planner module; the security agent module is used for querying security rules based on a semantic map and dynamically constructing a security feasible area; the path planner module is used for generating and optimizing the optimal driving path of the vehicle through a multi-objective optimization algorithm; the edge controller module is used for converting the optimal driving path into a bottom layer control instruction of an execution mechanism; the interpretation agent module is used for tracking the decision-making process of each module and generating natural language interpretation corresponding to the optimal driving path and the control instruction; the invention aims to adapt to the autonomous driving requirements of different types of mobile devices, and improve the safety, adaptability and user credibility of control.

The invention relates to a system and a method for realizing risk early warning adaptive dynamic enhancement based on a large model. The method comprises the following steps: an adaptive data acquisition module dynamically acquires risk early warning data from a plurality of heterogeneous data sources; the element extraction module is used for realizing structured high-precision extraction of risk early warning elements; the performance threshold regulation and control module dynamically adjusts fine adjustment of the model or prompts an optimization strategy; the retrieval enhancement module supplements external knowledge in real time; the entity extraction and analysis double-decoupling module separates an information extraction layer from a deep analysis layer; the context reasoning module realizes semantic understanding and reasoning; and the whole-process feedback closed loop and RLHF optimization module optimizes a prompt template and model parameters. After the system and the method for realizing risk early warning self-adaptive dynamic enhancement based on the large model are adopted, obvious and inevitable technical effects can be generated in multiple dimensions such as data acquisition, semantic recognition, logical reasoning, dynamic tuning and man-machine collaboration after the system and the method are operated in a computer software environment.

The invention relates to the technical field of intelligent dialogue management, and discloses an intelligent dialogue management method and system for adaptive reinforcement learning, and the method comprises the steps: obtaining a dialogue sequence in multiple rounds of interaction of a user, extracting context correlation features and user feedback real-time data, and generating an initial dialogue sequence propagation model, constructing a dynamic propagation path and adjusting the weight of the path; adjusting the priority sequence of the dialogue content in combination with real-time feedback; generating a final dialogue sequence propagation scheme according to the optimized propagation path and the priority sequence; through combination of a graph neural network and a context reasoning mechanism, context information can be effectively maintained in multiple rounds of dialogues, the efficiency and accuracy of information transmission are improved, and intelligent response can be performed according to real-time requirements of a user; the technical method can be widely applied to intelligent customer service, virtual assistant and other dialogue systems, and has high intelligence, flexibility and user experience.

The invention relates to a cross-language software vulnerability detection method and device, and the method comprises the steps: carrying out the analysis of a Joern static analysis pair, carrying out the integration and semantic enhancement of an abstract syntax tree, a control flow graph and a data dependence graph, and obtaining a cross-warehouse heterogeneous code graph; obtaining cross-language intermediate representation based on a compiler framework; after the cross-language intermediate representation and the cross-warehouse heterogeneous code graph are modeled, weighted fusion is carried out through a gated cross attention mechanism, and a multi-modal data set is obtained; carrying out migration training on the multi-modal cross-language vulnerability detection model, and carrying out vulnerability detection on cross-language software to obtain a detection result; through multi-modal data fusion and modeling, in combination with cross-language intermediate representation and a cross-warehouse heterogeneous code graph, the defects of a traditional method in the aspects of cross-language generalization ability and context reasoning ability are effectively overcome; the method has the advantages that the generalization ability of cross-language vulnerability detection is improved, the false alarm rate and the missing report rate are reduced, and the comprehensive utilization effect of global structure information is enhanced.

The invention discloses a grid member intelligent task scheduling system based on dynamic behavior perception and intention understanding, and the system comprises the steps: collecting space trajectory data, business interaction data and environment situation data of a grid member mobile terminal and an area Internet of Things device, and constructing a grid member dynamic behavior portrait through time sequence feature extraction and fusion calculation; based on the portrait and the to-be-scheduled task queue, generating a personalized task scheduling scheme through a multi-objective optimization algorithm, and decomposing the personalized task scheduling scheme into a task instruction set and an auxiliary information packet by a central scheduling engine; in the execution process, the system collects task execution process data in real time, recognizes the intention of a grid member through natural language processing and context reasoning in combination with environment situation data, and dynamically updates a behavior portrait and task matching strategy by using an online learning algorithm to realize continuous optimization of a scheduling scheme. According to the system, the conversion of task scheduling from static allocation to dynamic perception is realized, the task matching accuracy and the resource utilization efficiency are improved, and the self-adaptive capability of the gridding service is enhanced.

The invention discloses a knowledge question-answering method and device fusing data completion and space-time anomaly perception, and belongs to the field of intelligent question-answering and credible generation in artificial intelligence, and the method comprises knowledge anomaly detection, retrieval enhancement generation, and question-answering based on artificial intelligence. According to the method, under the complex conditions that grammar errors, information loss, space-time dislocation or sensitive expression exist in user input, a space-time consistency constraint mechanism penetrating through the whole process of input-retrieval-generation-verification is constructed, so that a system actively recognizes and corrects multi-dimensional anomalies, wrong intention analysis and fact distortion propagation are avoided, and the user experience is improved. And the end-to-end question and answer service with high robustness and high credibility is realized. Meanwhile, prompt words and generated contents can be intelligently complemented according to context reasoning and domain knowledge under the condition of lacking a complete user instruction, and meanwhile it is ensured that output is strictly aligned with a real scene in the aspects of time, space and logic. Furthermore, in order to improve the factual accuracy and safety of the generated content, a'detection-correction-verification 'dual-stage closed-loop governance architecture is realized by utilizing an anomaly detection model (NN1 / NN3) and a correction generation model (NN2 / NN4) which are jointly trained, and landing application of a credible intelligent question-answering system in high-risk professional scenes such as medical treatment, law and industrial maintenance is effectively supported.

The invention discloses a universal streetscape multi-dimensional perception method based on a multi-modal large language model, and relates to the technical field of computer vision, and the method comprises the steps: obtaining a multi-source streetscape image, carrying out the preprocessing, generating a streetscape text description result, carrying out the analysis processing of the streetscape text description result based on a preset rule, and generating a streetscape text description data set; based on the streetscape text description data set, training a pre-configured multi-modal large language model through a low-rank adaptation mechanism to obtain a streetscape perception model; and carrying out secondary training on the streetscape perception model by utilizing an improved thinking chain mechanism to obtain a second-order streetscape perception model which is used for perceiving multi-dimensional complex information such as visual sense, emotion, sound sense and the like. According to the method, the multi-modal large language model is utilized, the cross-modal representation capability, the context reasoning mechanism and the zero sample migration capability are achieved, and large-scale pre-training data and an advanced deep learning architecture are utilized, so that deep fusion understanding of vision and language information and intelligent analysis of complex scenes are achieved.

The application relates to the technical field of natural language processing, financial technology and medical technology, and discloses a standard time conversion method and device based on natural language, equipment and a medium, which comprises the following steps: collecting current session text information in real time; when target text representing a time attribute appears in the text, acquiring corresponding collection time and standardizing the collection time into a specified format reference time; extracting preset time period text containing the target text as context information; reasoning the target text and the context by combining the reference time with a preset natural language model to determine a target date, a target time word and a target number of days; and performing consistency verification on the target time word and the target number of days, and outputting the target date if the verification is passed. The application can be applied to a data processing platform in the fields of financial technology and medical health, improves the standardization conversion efficiency of time text strings, improves the accuracy of large models, and improves the convenience of the corresponding platform.

The present application relates to the technical field of GPU computing optimization, and in particular to a sparse attention computing method, device and medium for GPU, wherein the method realizes the high efficiency of long context reasoning through the geometric perception sparse attention framework of ball hashing, and combines a large-scale parallel hashing optimization algorithm and a load adaptive computing kernel. Compared with the existing sparse attention methods based on heuristics or gradient learning, the present application realizes higher retrieval recall rate, lower preprocessing overhead and efficient hardware adaptation to irregular sparse patterns.

The application discloses a version knowledge graph reasoning method and system based on large language model enhancement, relates to the technical field of dynamic knowledge graph, and comprises the following steps: adopting a semantic drift detection and compensation mechanism, comparing the context coding differences of the same entities in different versions in an initial knowledge graph, identifying drift, dynamically adjusting entity embedding vectors, and outputting a compensation update graph; adopting a multi-hop reasoning algorithm enhanced by an LLM, performing multi-hop reasoning on the compensation update graph, performing symbolic reasoning, vector reasoning and context reasoning in parallel in each hop, and obtaining entity relationship reasoning results through dynamic weight fusion; and superimposing the entity relationship reasoning results on the compensation update graph through a cloud collaborative node, adding entity edges and automatically maintaining version history logs, and obtaining a reasoning fusion version knowledge graph. Through the multi-hop reasoning algorithm enhanced by the large language model, the deep semantic mining capability and reasoning accuracy of the cross-version entity relationship are effectively improved.

The embodiment of the invention provides a multi-source data processing method and device, equipment, a storage medium and a program product, and relates to the field of big data and financial science and technology. The method comprises the following steps: acquiring multi-source heterogeneous data, wherein the multi-source heterogeneous data comprises a set of data from different systems or formats; based on the knowledge graph, performing entity recognition on the multi-source heterogeneous data to obtain entities in the multi-source heterogeneous data; performing relation mapping on the entities to obtain semantic alignment data; and through context reasoning and a dynamic updating mechanism, when the business rule changes, optimizing the semantic alignment data to obtain a target data view. According to the method, the problem of semantic islands of cross-system data is solved, semantic unification and format standardization of multi-source data are realized, a high-quality and traceable unified data view is provided for subsequent data processing, and data fusion efficiency and business suitability are remarkably improved.

This invention relates to the field of artificial intelligence and large language model inference optimization technology, and discloses an adaptive key-value cache compression method and system for large language models. The method includes: constructing a lexical importance measurement mechanism; analyzing the attention head distribution structure in large language model inference and constructing multiple pruning strategies; designing an adaptive key-value cache compression hybrid strategy set based on the lexical importance measurement mechanism and the attention head distribution structure, and based on the pruning strategies; constructing a static adaptive key-value cache compression method to automatically allocate key-value cache compression strategies during the pre-filling stage of large language model inference; and adaptively compressing the key-value cache based on the allocated key-value cache compression strategies during the decoding stage. This invention can achieve efficient compression of the key-value cache without relying on explicit attention score calculation, and is compatible with system-level inference optimization frameworks, maintaining generation performance while significantly reducing memory consumption and enhancing long-context inference capabilities.

The invention provides a construction method and device for user data modeling, and relates to the technical field of artificial intelligence. The construction method for user data modeling comprises the following steps: generating user behavior snapshot information according to user original information; generating model input data according to the user behavior snapshot information; training a pre-trained data generation model according to a pre-constructed supervision fine tuning data set to obtain a user data modeling reasoning model; the model input data and a predefined modeling reasoning cue word are input into the user data modeling reasoning model, a user data modeling reasoning result is obtained, and the modeling reasoning cue word comprises model role positioning information, a reasoning behavior rule and a task execution logic sequence. Based on the world knowledge and context reasoning ability of the model, end-to-end joint reasoning of multi-dimensional modeling is achieved, the overall process is low in manual dependence degree, cross-dimensional reasoning can be achieved only through one model, and expansibility is good.