377 results about "Cross lingual" patented technology

The invention relates to an industrial equipment maintenance intelligent question-answering system based on multi-agent collaboration. Wherein the input unit is used for receiving text, voice, image or equipment scanning and other multi-mode user input information and analyzing the information into structured problem information; the scheduling unit performs semantic understanding and problem classification on the structured problem information based on the fine-tuned cross-language pre-training language model and an incremental training mechanism; the processing unit calls a corresponding domain agent according to the classification result, and generates an intelligent question and answer processing result including predictive maintenance suggestions, structured reply content and semantic annotation information; and the fusion unit fuses the local knowledge base, the graph database and the networking retrieval information, performs multi-hop semantic reasoning on the intelligent question and answer processing result, and generates multi-modal reply information including text description, image screenshots, prediction curves and recommendation links. The system can support multi-language and multi-mode intelligent question answering and predictive maintenance in a complex industrial maintenance scene.

The embodiment of the invention provides a code exception analysis method and device, a storage medium and a program product. In the embodiment of the invention, in the preset plug-in, the global knowledge graph is constructed through the logic syntax tree of the plurality of original business codes, so that intelligent anomaly analysis is carried out on the modified to-be-detected codes, multi-language and heterogeneous programming styles and complex dependency limitation are broken through, and cross-language and cross-file analysis is supported; change code snippets and associated influence code snippets thereof are accurately identified, and a data basis is tamped and analyzed; the analysis depth is deepened and the accuracy is improved through a multi-dimensional anomaly analysis large model and four-dimensional collaborative analysis in combination with an adaptive review rule and a knowledge graph; and finally, performing correction based on the generated repair scheme. Through the technical fusion of an MCP protocol, a multi-AI model, a syntax tree and a knowledge graph, the high efficiency, accuracy and real-time performance of code examination and repair are realized, and the service development quality and the system operation stability are remarkably improved.

The invention provides an interface communication method, device, medium and equipment adaptive to a swan-monk system, and the method comprises the steps: deploying an interface adaptation layer adaptive to a universal underlying library in a client of the swan-monk system; the method comprises the following steps: acquiring a callback instruction (including a callback function identifier and parameter data which need to be executed by a client of the swan-mong system) issued by a server on the basis of a service request of the client of the swan-mong system, and determining a corresponding target callback function reference from a method mapping table on the basis of the callback function identifier in the callback instruction; the method mapping table comprises a plurality of registered callback functions, and the registered callback functions form key value pairs through callback function identifiers and callback function references; and based on the parameter data and the reference of the target callback function, initiating cross-language calling of the target function of the general underlying library so as to complete execution of the callback instruction and realize processing of the service request. According to the scheme, cross-language communication of the client of the swan-mong system can be realized, and seamless connection between the swan-mong system and the existing general underlying library is realized.

The invention discloses a cross-language code semantic alignment method, which constructs a shared semantic space through a unified abstract syntax tree (AST) and a graph matching network (GMN) so as to reduce the difference of different programming languages in syntax structure and node representation. The method comprises the following steps: (1) mapping a multi-language AST node to a unified general label set and performing structure enhancement; (2) performing node feature coding on the unified AST, and realizing cross-language interaction in combination with a cross-graph attention mechanism; (3) node representation is generated through intra-graph loop updating, and an overall semantic vector is obtained through global attention pooling; and (4) through comparative learning training in the shared space, the distance between semantically equivalent positive sample vectors is shortened, and the distance between non-equivalent negative sample vectors is shortened, so that the discrimination capability of cross-language semantic representation is enhanced. According to the method, the semantic consistency of the functional level can be effectively captured, and the accuracy and efficiency of cross-language code understanding, multiplexing and retrieval are remarkably improved.

The invention discloses a code change influence analysis method and device, equipment and a storage medium, and relates to the technical field of software, the method comprises the following steps: performing grammar analysis on a multi-programming language code to obtain a back-end abstract syntax tree and a front-end abstract syntax tree, and converting the back-end abstract syntax tree and the front-end abstract syntax tree into a uniform syntax tree structure through a front-end and back-end calling mapping chain; a cross-language dependency graph is constructed according to the unified syntax tree structure, the cross-language dependency graph is composed of nodes and edges, the nodes represent code entities, and the edges represent dependency relations; and when the code change of the bank business is detected, traversing the cross-language dependency graph through a graph traversal algorithm to obtain a code change influence result. Due to the fact that the back-end abstract syntax tree and the front-end abstract syntax tree of the multi-programming language codes are constructed and connected in series, the perfect cross-language dependency graph is constructed, the front-end link and the rear-end link are connected, cross-language tracking can be achieved when the codes of the banking business are changed, and the influence of code change can be accurately analyzed.

The invention provides a voice synthesis method and system based on VITS improvement, and the method comprises the steps: optimizing a text encoder of a VITS model, introducing a large language model, and enabling the emotion, intention and speaking style of an input text to be captured when the text is encoded; a random disturbance item is introduced when the Q value is dynamically planned and solved, the alignment flexibility in the initial training stage is improved, meanwhile, monotonicity constraint is strictly kept, and it is avoided that a suboptimal solution is obtained through convergence too early; a ConvNeXt module is used as a basic backbone network of a decoder, and ISTFT is utilized to efficiently reconstruct a time domain signal, so that waveform up-sampling is realized, redundant calculation of traditional transpose convolution is avoided, and reasoning is accelerated. According to the method, the reasoning speed, the emotion expression ability and the style control flexibility of speech synthesis can be effectively improved, a new solution is provided for cross-language diversified speech synthesis, and a reference is provided for the more efficient and more intelligent development of the speech synthesis technology.

The invention discloses an intelligent retrieval and hierarchical authorization utilization system and method for archive resources, and belongs to the field of intelligent retrieval. Natural language query of a user is received, the language type of the user is recognized, a semantic vector is generated in combination with a multi-language natural language processing model, and then the semantic vector is matched with each archive semantic representation in an archive database; for the situation related to cross-language matching, a cross-language similarity offset rate and a language context consistency score are further calculated, the semantic generalization ability is divided into a high level, a middle level and a low level according to a preset weight model, and for the middle level situation, a misjudgment risk assessment mechanism is introduced to judge whether additional authorization is needed or not; and when the file is low in level and the languages are inconsistent, the user is directly prohibited from accessing the high-security-level file, so that the information leakage risk caused by semantic generalization is effectively prevented, and the high-sensitivity file is safely and accurately controlled in a multi-language environment.

The invention discloses a multi-language code generation method based on self-supervised pre-training, which comprises the following steps: acquiring and cleaning multi-language code data to form a training corpus; the method comprises the following steps: representing code data as an abstract syntax tree, extracting a control flow diagram and a data flow diagram of the code data, and obtaining unified semantic representation through combination of a diagram encoder and a sequence encoder; designing a self-supervised pre-training task, and pre-training the semantic representation based on the training corpus; constructing a multi-language pre-training model based on the structure-improved recurrent neural tensor network and the multi-language embedding matrix; when a user inputs a natural language, generating a target language code by using the multi-language pre-training model; and target language code correction is carried out through conventional function testing and grammar checking. According to the method, multi-channel recursive combination and a hierarchical recursive expansion mechanism are combined with self-supervised pre-training, so that accurate generation and performability improvement of cross-language codes are realized.

The invention relates to the technical field of artificial intelligence, provides a multi-language task execution method, device and equipment and a medium, is applied to financial and medical health care service scenes, and can acquire text data and visual action data of multiple languages according to an execution instruction and perform preprocessing to realize standardized processing of multi-modal data; constructing a cross-language word vector semantic space based on adversarial training according to the multi-language features to realize preliminary word vector alignment; performing multi-language semantic alignment on the multi-language features according to a cross-language word vector semantic space, further breaking language barriers, and realizing depth mapping and alignment among different language semantics; a multi-language culture knowledge graph is constructed, so that culture knowledge is introduced, and the culture perception ability is improved; fusion is carried out through a gating fusion mechanism, fusion features with language attributes and cultural attributes can be obtained, and therefore multi-language tasks can be executed more accurately by integrating multi-language information and cultural knowledge.

The invention relates to a speech translation method, device and equipment of an end cloud translation system and a medium, and relates to the technical field of intelligent speech translations, the end cloud translation system comprises an audio receiving end and a cloud, the method is applied to the audio receiving end, and the method comprises the following steps: obtaining a first language audio of the audio receiving end; sending the first language audio to a cloud; and receiving and playing a second language audio, wherein the second language audio is translated by the cloud according to the first language audio and then is sent out. The method can be widely applied to cross-border conference scenes, and the cross-language communication efficiency and experience are improved.

The invention provides a minority language threat intelligence clue expansion method, system and device and a medium, and belongs to the technical field of network security. The method comprises the steps of obtaining minority language threat intelligence, performing data cleaning, format conversion and semantic index establishment on intelligence information, and constructing a vector knowledge base by utilizing a vectorization model based on the processed intelligence information to serve as an initial threat intelligence base; acquiring tactics, technologies and associated information related to the attack from the initial threat intelligence library by using a preset agent, and outputting semi-structured attack process description information; and based on the attack process description information, obtaining extension information and context promotion information, obtaining depth information related to an attack technology through analysis and retrieval, and generating a structured or reported threat intelligence clue extension result. According to the method, the multi-agent with domain knowledge and scene memory is utilized, and analysis and understanding of cross-language threat intelligence, intelligence key point extraction and semi-structured representation output are achieved.

The invention discloses a static vulnerability detection method and system based on a unified cross-language program structure diagram, and the method comprises the following steps: constructing the unified cross-language program structure diagram according to a to-be-detected source code and compiling metadata thereof, and building an interface semantic mapping relation on a cross-language interface edge; a cross-language path from a program entry to a sensitive operation point is extracted on the unified cross-language program structure chart, uncertain elements in the cross-language path are labeled, and the confidence coefficient of the path is calculated; performing semantic alignment on heterogeneous language states on a cross-language path based on a cross-language abstract domain, and converting a path condition and a vulnerability establishment condition into logic constraints; and carrying out satisfiability judgment on the logic constraint, outputting a vulnerability detection result according to a judgment result, and generating a structured evidence chain. According to the method, the cross-language evidence chain can be output, vulnerability paths, witness information of trigger conditions and cross-language conversion details can be clearly displayed, and work such as manual recheck and vulnerability repair is powerfully supported.

The invention discloses a cross-border e-commerce service data management method, and relates to the technical field of service data management, and the method comprises the steps: obtaining commodity service data from a plurality of overseas e-commerce platforms, and caching the commodity service data to an edge data pool according to the attributes of a data source; based on source attributes, updating time and historical accuracy of the data sources and supervision rating of judicial jurisdictions, comprehensive credible weight values of the data sources are calculated, and main data channels are screened out according to the weight values; inputting commodity service data in the main data channel into a multi-language semantic encoder, generating semantic vectors, calculating cross-language semantic alignment, and comparing logic consistency of key structured fields; generating a consistency score according to a comparison result of the semantic alignment degree and the structured field, when the score is lower than a preset threshold value, marking as abnormal and entering a rechecking process, and otherwise, entering a compliance review stage; and calling the regional compliance rule base to carry out regulation matching on the data passing the consistency verification.

The invention provides a cross-language function consistency verification method and device, a storage medium and a program product, and the method comprises the steps: compiling a to-be-verified first language code into a first format file represented in the middle, and carrying out the modeling based on a predetermined formalized verification language, and generating a first formalized specification; compiling the second language code into a second format file represented in the middle, and modeling to generate a second formalized specification; verifying the consistency of the first format file and the first formalized verification language specification and the consistency of the second format file and the second formalized verification language specification through symbolic execution by using a formalized verification tool; and under the condition that the first formalized verification language specification and the second formalized verification language specification are consistent, verifying the equivalence of the first formalized verification language specification and the second formalized verification language specification through a formalized verification tool. According to the method, the problem that a traditional function consistency verification method cannot prove that codes realized by different languages are kept equivalent under all input conditions can be solved, and verification efficiency and completeness can be improved.

This invention relates to the field of speech recognition technology, specifically disclosing a cross-language AI voiceprint cloning method, system, and storage medium. The method includes: a speech collection end gating the raw microphone speech, with qualified samples entering preprocessing; gating, restricted spectrum, and unified conditional signals are integrated across the upstream and downstream processes to significantly improve robustness under noise / echo conditions; a speech processing end using AI adaptive filtering to denoise and obtaining representational data according to restricted parameters; a feature extraction and recognition end extracting voiceprints from the spectrum and embedding them into parallel language recognition, storing the voiceprint-language-quality association; a voiceprint cloning end performing cosine search in a template library to obtain a similarity queue, which is then weighted and aggregated after being rearranged based on quality and language consistency to obtain a target template; small-sample adaptation improves cross-language generalization and scalability; and finally, obtaining the target language and generating cloned speech by combining it with the target template.

The invention discloses a cross-border digital service multi-language real-time interaction and semantic error correction method and system, and belongs to the technical field of text processing.The method specifically comprises the steps that when cross-border interaction begins, voice, text and auxiliary multi-mode information of a user are collected, fused semantic representation is generated, the semantic representation is input into a cross-language prediction model, and the cross-language prediction model is obtained; a target language candidate result is obtained, a reverse mapping channel is established, when semantic errors or ambiguity occurs in the target language candidate result, collaborative correction is conducted in combination with the scene rule base, user historical preferences and real-time feedback, the corrected result is processed through a predefined target context sensitive model, and the target language candidate result is obtained. Automatically adjusting the culture expression, the terminology and the compliance, and outputting to the cross-border service terminal in real time; according to the method, the target context sensitive model is introduced in the output stage, cultural expression, terminologies and law compliance are automatically adjusted, and multi-language seamless communication and high-reliability semantic transfer in cross-border digital services are achieved.

The invention discloses a cross-language voice interaction method and system based on multi-modal semantic understanding and a storage medium, and relates to the technical field of artificial intelligence and natural language processing. The method comprises the following steps: acquiring a source language speech stream, performing parallel double-flow feature extraction, extracting text semantic features through a mixed language code recognition model based on a unified phoneme space, and extracting acoustic features containing rhythm information at the same time; performing alignment fusion on the text and the acoustic features by using a cross-modal attention mechanism to generate multi-modal semantic representation; analyzing the explicit intention and the implicit emotion based on the representation, and generating a reply strategy and an emotion control label of the target language; and finally, synthesizing a target voice with a corresponding emotion color. According to the invention, the bottleneck that the traditional cascade architecture loses side language information is broken through, the precise understanding and strategic feedback of complex contexts such as Chinese-English mixed language codes (Code-mixing), anti-quiescence, hesitation and the like are realized, and the method is particularly suitable for transnational business negotiation and international customer service scenes.

The invention relates to a fusion method and device based on multi-source data, and relates to the technical field of multi-source data fusion, and the method comprises the steps: associating a multi-source enterprise code with a unique DID through a cross-chain identification mapping protocol based on a block chain master-slave chain architecture, and generating an enterprise unique ID to achieve identity normalization; calling a GCN-LLM intelligent unit, splitting a multi-language address and a business scope text into entity nodes, constructing a cross-language association graph, and extracting standardized fields of countries, cities and the like; a Transform model is adopted to extract historical time sequence characteristics to predict the data abnormal probability, and dynamic cleaning is triggered; and finally, the data hash value is subjected to uplink evidence storage, credibility is ensured through consistency verification, and a permission controllable interface is generated to be called by a downstream application. According to the method, unique credible association of cross-source enterprise identities, high-precision structured extraction of multi-language unstructured texts, advanced prediction of data anomalies and credible reuse are realized, and the enterprise data fusion efficiency and credibility are improved.

The invention relates to the technical field of artificial intelligence, in particular to a software component analysis system based on artificial intelligence, which comprises a data acquisition and preprocessing unit, an AI-driven component identification and analysis unit, a risk detection and evaluation unit, a knowledge base and dynamic updating unit and a result visualization and disposal suggestion unit. According to the method, through a collaborative mechanism of multi-modal semantic fingerprint generation, cross-language component matching and dynamic and static feature dual verification, the bottleneck that traditional software component analysis is insufficient in recognition precision of high-confusion, cross-language and secondary packaging components is effectively broken through, and precise recognition and analysis of the components and key attributes thereof are achieved; therefore, a more reliable technical support which better meets actual business requirements is provided for software component security analysis.

A system includes a hardware processor and a memory storing a cross-language voice similarity analyzer (analyzer). The hardware processor executes the analyzer to generate an embedding vector representation of an audio sample of a human voice in a feature space including existing embedding vectors corresponding respectively to different reference voices, decompose the embedding vector representation to identify a linear or non-linear combination of vocal component vectors corresponding to the human voice, each vocal component vector representing a respective predetermined voice characteristic descriptor, increase the dimensionality of the linear or non-linear combination of the vocal component vectors to match the dimensionality of the embedding vector representation to provide a reconstructed embedding vector representation of the human voice, and identify, by comparing the reconstructed embedding vector representation with one or more of the existing embedding vectors, one of the reference voices as a match for the audio sample of the human voice.

The invention discloses a cross-language migration-based low-resource programming language corpus enhancement method, which comprises the following steps of: receiving a source language code, and driving a large language model to generate an initial target language code through a two-way retrieval mechanism fusing example guidance and knowledge constraint; secondly, constructing an automatic iterative repair closed loop by utilizing the feedback of a compiler, and carrying out self-correction on codes which fail to be compiled; thirdly, high-quality codes are screened out through automatic quality gating and fed back to a corpus and a knowledge base, and self-enhancement circulation of data and knowledge is formed; finally, the method further comprises an offline model evolution step based on grammar and semantic alignment driven by a compiler, a big language model is trained by collecting preference data generated by an online process, and the ability of the big language model to understand a target language is improved fundamentally. According to the method, the core problems of low quality, poor efficiency and lack of self-evolution ability of a low-resource programming language in code migration are solved.

The invention relates to the technical field of translation, and discloses a translation calibration method based on big data, which can accurately identify semantic deviation in a multi-meaning scene, for example, accurately judge that'cell 'should be translated into'cell' instead of'house 'in a biological text. The system can detect the language field mismatching problem of spoken expression in the official file, and provides term correction suggestions conforming to industry standards. Aiming at technical terms with multiple meanings in legal clauses, the calibration process can be combined with context window analysis to select an optimal translation scheme, the omission ratio of manual review is remarkably reduced, continuous optimization and cross-language knowledge sharing of a translation calibration model are realized, and the accuracy of translation calibration is improved. The problems that a traditional system is lagged in updating and low-resource language performance is insufficient are solved.

The invention provides a knowledge editing method based on multilingual semantic retrieval, and belongs to the technical field of natural language process.The method achieves cross-lingual knowledge updating through the two stages of multilingual knowledge retrieval and context editing and comprises the steps that firstly, a multilingual retrieval model based on XLM-R is used for mapping queries and knowledge base entries to a shared semantic space, and then the shared semantic space is used for conducting context editing; semantic correlation is judged through a classifier, and target language knowledge is retrieved; and splicing the retrieval result and the query in a zero sample or small sample mode to generate a prompt template, and inputting the prompt template into a large language model to complete editing. The method is characterized in that monolingual limitation is broken through, collaborative updating of 12 languages is supported, a retrieval-editing decoupling architecture is adopted to achieve model irrelevant adaptation, and retrieval and context learning are fused to improve editing accuracy. The method can efficiently correct multi-language large model fact errors, is suitable for scenes such as search engines and intelligent customer services, avoids the cost of full-model retraining, and remarkably improves the efficiency and accuracy of cross-language knowledge updating.

The invention discloses a knowledge graph alignment method and system based on a large language model and an agent and oriented to the field of the manufacturing industry. The method comprises the following steps: enhancing a key relation weight by adopting a relation perception graph network, fusing a semantic vector of the large language model and a vector of a domain term library to correct a name conflict, and dynamically adjusting learning parameters; implementing a dynamic bucket dividing strategy, high-confidence scene simplification candidates, low-confidence scene fusion term retrieval and a big language model virtual name generation mechanism according to the embedding quality; based on an agent and large language model hierarchical interaction architecture, precise prediction is realized through coarse-grained screening and domain knowledge enhanced fine-grained matching, and an intelligent iteration termination condition is set; and executing lightweight incremental training to update the embedded representation, combining reinforcement learning to dynamically adjust and optimize the strategy library, and synchronizing and automatically expanding the term library. According to the method, cross-language alignment precision jump, data noise interference suppression, efficiency and accuracy optimization balance and system continuous autonomous evolution capability enhancement are realized.

The invention discloses a Java-to-Cangjie code translation method based on a large model and compilation feedback, and particularly belongs to the technical field of software engineering program language processing, and the method comprises the following steps: step 1, performing structured semantic pre-training by constructing a grammar knowledge base of a target language, and injecting grammar prior knowledge of the target language; step 2, performing semantic enhanced supervision fine tuning training by constructing a high-quality data set containing semantic information, and enhancing semantic alignment and cross-language migration ability of the model; 3, introducing an AST structure perception embedded prompt mechanism in a parallel corpus supervision fine tuning training stage, and guiding the model to perform structure perception translation; and 4, establishing a compiler feedback repair loop, and iteratively correcting output based on error information to form a self-optimized closed-loop system. According to the method, an efficient training path is constructed, dependence on large-scale parallel corpora is effectively reduced, and an extensible and high-reliability technical path is provided for cross-language code translation of low-resource programming languages.

The invention discloses a malicious code detection method and device for a third-party tool, a medium and a product. The method comprises the following steps: acquiring code data of a third-party tool; static analysis is carried out on the code data of the third-party tool to obtain static features, and the static features comprise at least one of cross-language call graph features, multi-version control flow graph difference features and local entropy values; the code data of the third-party tool is dynamically analyzed, dynamic characteristics are obtained, and the dynamic characteristics comprise at least one of an API calling sequence, memory operation information and a taint propagation path; based on a pre-trained detection model, the static features and the dynamic features are detected, a detection result of the code data of the third-party tool is obtained, and the detection result is used for indicating whether the code data of the third-party tool belongs to malicious codes or not. According to the technical scheme, collaborative analysis can be carried out on the code data through the static features and the dynamic features, and the detection accuracy of malicious codes is improved.

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 provides a cross-language text classification and processing method and system based on deep transfer learning, and relates to the technical field of text processing, and the method comprises the steps: extracting feature representations of a source language text and a target language text at different linguistic levels through a multi-level semantic transfer network; and determining an optimal alignment path, performing nonlinear mapping alignment to obtain fusion features, propagating category semantics by using a semantic bridging function, iteratively updating pseudo-tag confidence distribution of the target language text, and completing classification in combination with a multi-task learning model. According to the method, the problem of text classification in a cross-language scene is effectively solved, and the accuracy and efficiency of low-resource language text processing are improved.

Provided is a pseudo parallel translation data generation apparatus for generating pseudo parallel translation data for accurately performing machine translation in an adaptation target domain even when there exists no parallel translation data for the adaptation target domain. Using other-domains parallel translation data D0(L1-L2), other-domains first language data D0(L1), other-domains second language D0(L2), adaptation target domain first language data D0(R1), and adaptation target domain second language data D0(R2), the pseudo parallel translation data generation apparatus 100 performs optimization processing for a cross-lingual language model including an input data embedding unit 2 and an XLM processing unit 3, and performs parameter optimization processing for a pseudo parallel translation data generation NMT model including the input data embedding unit after the optimization processing and a machine translation processing unit 5. Performing processing using the pseudo parallel translation data generation machine translation model obtained by the parameter optimization processing allows for obtaining pseudo parallel translation data for the adaptation target domain for which no parallel translation data sets exist.

The invention discloses a cross-border logistics document multi-language machine translation method based on natural language processing, and relates to the technical field of machine translation, and the method comprises the steps: collecting original data of a cross-border logistics document, and carrying out text extraction and preprocessing through an OCR technology; performing language recognition and format analysis on the preprocessed document text to determine a source language and a target language; using a pre-trained cross-language alignment translation model to translate the document text into a target language text; the translation result is input into a compliance auditing module, and automatic compliance auditing is conducted through a knowledge graph and a double-check algorithm; and generating an output containing a translation result and a compliance audit report, and supporting manual review and revision. According to the method, the translation accuracy of the documents can be effectively improved, the manual auditing burden is reduced, and the globalization requirements of cross-border e-commerce and logistics enterprises are met.