35 results about "Automatic inference" patented technology

In one example, a method performed by a processing system including at least one processor includes automatically inferring metadata about a structured query language database, constructing, based on the metadata, a prompt for generating a new structured query language query to be executed against the structured query language database, and providing the prompt to a language model for use in generating the new structured query language query.

The invention belongs to the technical field of artificial intelligence, and particularly relates to a GUI-Agent trajectory data generation method and system based on multi-agent collaborative reasoning. The method comprises the following steps: S1, capturing and analyzing a page state and a structure, and constructing an initial graph; s2, analyzing semantics of interactive elements based on VLM and generating an initial action instruction set; s3, executing the instruction, recording state change, automatically deducing a target intention, forming an initial track, and storing the initial track in a track pool; s4, for the current track, predicting and executing the next action according to the target and the page state of the current track, and updating the track; s5, unexplored elements are recognized, new actions and intentions are generated in combination with the VLM, and a new track is created and added into a track pool; s6, evaluating whether the action result achieves a target or not, and deciding to terminate, adjust or continue to explore according to the target; and S7, circularly executing the steps S4 to S6, performing parallel iteration processing on the trajectory pool until a termination condition is met, and outputting a trajectory data set.

The invention relates to the technical field of data analysis and processing, in particular to an automatic data standardization management method based on a large language model, a medium and equipment, and the method comprises the following steps: a data receiving step: receiving data from various data sources; a data source analysis step: identifying field semantics and standardization requirements; a standardized rule generation step: based on the semantic understanding result of the large language model, automatically generating a standardized rule suitable for a corresponding data source; a standardization rule application and optimization step: performing application and dynamic optimization; an intelligent monitoring and verification step of data quality: performing real-time quality detection of the data by using a large language model; and a data restoration and suggestion step: automatically deducing a correct value or giving a restoration suggestion when the data does not meet the standardization requirement. According to the method, the problems of non-uniform standards, high manual rule maintenance cost and lack of dynamic adaptivity caused by inconsistent formats and semantics of the multi-source data are solved.

Herein is software dependency reporting with an innovative framework to analytically generate a software bill of materials (SBOM) that is a list of dependencies of a software application that was built in an opaque (i.e. black-box) way. This approach makes minimal assumptions about the build framework(s) and language ecosystem(s) involved with building a software application. For building a deliverable based on source files defined in separate programing languages, source files are read and deliverable files are generated and copied. Unique identifiers of accessed files are recorded by novel probes into a probe log having unprecedented accuracy. The probe log is analyzed to generate a provenance graph that contains a vertex for each file accessed by the build. By graph analytics, a dependency report having unprecedented accuracy is generated for the deliverable from the provenance graph.

The invention belongs to the field of software engineering, and particularly relates to a deep learning compiler test case generation method based on automatic reasoning of a computational graph structure, which can be used for generating a deep learning compiler test case so as to improve the test efficiency of a deep learning compiler. The method is divided into two stages: in a computational graph structure learning stage, a text generation model is adopted to learn structure information of a computational graph; the relationship between operators in the calculation graph is the same as the relationship between words in a natural language, and each calculation path is similar to a sentence; and then all calculation paths in the calculation graph are extracted, so that the existing calculation graph structure information can be learned by utilizing an efficient text generation model, and the method is applied to generation of a new calculation graph. In the calculation graph reasoning generation stage, the calculation graph structure reasoning model obtained in the calculation graph structure learning stage is utilized, so that the next node is automatically reasoned according to the information of the current node, and a complex and diversified deep neural network model is formed.

The invention provides a ship structure assembly process reasoning method and system based on a knowledge graph. The method comprises the following steps: constructing an assembly process knowledge graph library; the assembly process knowledge graph database comprises assembly element data, assembly process data and an association relationship established between the assembly element data and the assembly process data; establishing an assembly process reasoning model according to the incidence relation between the assembly element data and the assembly process data; acquiring and determining assembly element data; based on the assembly element data, establishing and sending an assembly process reasoning request; and in response to an assembly process reasoning request, receiving and extracting assembly element data, and reasoning based on the assembly process reasoning model and the assembly process knowledge graph database to obtain corresponding assembly process data. According to the method, tight coupling of the assembly element data and the assembly process data is achieved by constructing the assembly process knowledge graph database, the assembly process data is obtained through automatic reasoning based on the assembly element data, and the design standardization degree and design efficiency of the assembly process are improved.

The invention discloses a footprint image human body attribute automatic inference method based on a multi-modal large model, and relates to the technical field of mode recognition. The inference method comprises the following steps: constructing a CLIP-based footprint image and text analysis multi-modal large model: the model adopts a double-flow network structure, a graphic encoder processes image features, a text encoder processes text features, and cross-modal feature fusion is realized through a feature fusion layer; and constructing a Grad-CAM interpretable visualization model, wherein Grad-CAM is a gradient-based feature visualization technology in deep learning. The gradient of the feature map is output through the calculation model, an attention map is generated, and key areas concerned by the convolutional neural network model during decision making are displayed; the correlation between the footprint image and the human body attribute is deeply discussed, a new multi-modal feature fusion method and model architecture are provided, and the algorithm, the model and the application method thereof formed in the research process also promote the industrial application of the technology.

The application discloses a method for automatically inferring semantics of a data cleaning script, comprising loading an original table to the data cleaning script and obtaining an input table and an output table; constructing a table change space, obtaining a table change characteristic set based on comparison between the input / output table and the table change space; taking data conversion operation types that all satisfy inevitable occurrence, impossible occurrence and possible occurrence as candidate data conversion operation types; converting and splicing multiple descriptive texts corresponding to function names, function parameters and table change characteristics to obtain a semantic vector, inputting the semantic vector into a twin convolutional neural network model to obtain candidate data conversion operation type ranking; constructing a parameter slot of each data conversion operation type, inferring the parameter slot of the candidate data conversion operation type by using data cleaning code, table content and table change information of a corresponding row, and obtaining the type and parameters of the data conversion operation based on the inference result. The method can simply and conveniently infer the type and parameters of the data conversion operation in the cleaning code.

We provide the system. [Solution] A means of acquiring a large dataset including location data from multiple external data sources, A means of performing format standardization and data cleaning on acquired data, A means for automatically inferring potential causal relationships from the dataset using generative artificial intelligence, A means for generating an analysis report based on inferred causal relationships, A means of delivering and displaying the generated analysis report on a terminal, A system that includes this.

The invention provides a welding process reasoning method and system based on a knowledge graph. The method comprises the steps that a welding process knowledge graph library is constructed; the welding process knowledge graph database at least comprises a welding process reasoning relation graph model, and the welding process reasoning relation graph model comprises a welding process incidence relation between the welding seam feature data and the welding process data and an internal incidence relation between internal data of the welding process data; weld joint characteristic data are obtained and determined; based on the determined weld joint feature data, a welding process reasoning request is established and sent out; and in response to a welding process reasoning request, inputting welding seam feature data based on the welding process reasoning relation map model, and reasoning to obtain welding process data. According to the method, the information island problem between the design content and the design object is solved by constructing the welding process knowledge graph database, tight coupling of the welding seam feature data and the welding process data is achieved, and automatic reasoning of the welding process data can be achieved.

The invention relates to the technical field of databases and artificial intelligence, and discloses a data lake table association relationship automatic discovery method and system, and the method comprises the steps: generating a table description and a column description of a new table through automatic reasoning based on a knowledge base and a language model; calculating a semantic similarity and a value overlapping distance between the query column and a target column of any table in the data lake; screening out a candidate column associated with the query column based on the semantic similarity and the value overlapping distance, and considering that an association relationship exists between the candidate column and the query column; and constructing a metadata graph based on the table description, the column description, the affiliation relationship between the table and the column and the discovered association relationship between the columns, and performing multi-hop reasoning by calculating a pass closure to derive the potential association relationship between the columns. According to the method, through knowledge-enhanced metadata construction, fusion of semantic features and value overlapping features, and a mapping metadata organization and graph reasoning technology, automatic inference of the connection relation between tables in a data lake is achieved.

The application relates to the technical field of relationship graph data clustering, and provides a relationship graph data clustering method and system based on a non-parametric Bayesian method, which comprises the following steps: obtaining relationship graph data; initializing model parameters according to a probabilistic graph model; using multiple sampling algorithms to iteratively sample samples of the model parameters based on the relationship graph data; selecting a cluster division sample according to a maximum likelihood function mode based on the model parameters obtained through sampling, so as to obtain a clustering result; and the prior probability of the cluster division sample is a non-parametric Bayesian prior. The number of clusters can be automatically inferred in the parameter inference process, and manual setting is not needed.

This invention belongs to the field of antenna testing technology. It discloses an automated testing method and system for multi-channel antenna line sources. The method includes: before starting the multi-channel line source test, constructing a phase closed-loop matrix between channels using a full-channel mutual excitation sequence; during acquisition, using a real-time phase deviation drift prediction algorithm to compensate for phase deviations in real time, outputting phase-locked multi-channel amplitude and phase data; performing dual-time-scale decomposition on the multi-channel amplitude and phase data to separate short-period structural difference components and long-period environmental drift components; using an online environmental drift tracking factor to remove drift, retaining only the structural difference components as multi-dimensional difference vectors; mapping the multi-dimensional difference vectors to a channel-difference parameter bipartite graph, analyzing the connected component distribution pattern of abnormal parameters, and automatically inferring the location of abnormal sources by combining the channel physical topology mapping table, outputting a set of abnormal channels with spatial pattern labels; this facilitates reliable verification of test results and improves testing efficiency.

The invention provides an advanced instruction understanding and long-range navigation method based on a visual language model, and the method comprises the steps: carrying out the semantic object reasoning and spatial position prediction based on an advanced instruction and a global three-dimensional scene with annotations through a visual language model, and obtaining a target region; determining a target waypoint in the local boundary of the target area through a random sampling mode; and based on the panoramic view of the target waypoint, through the intelligent model with the body, carrying out detection and positioning to obtain the position information of the target object. Compared with the large difference between a navigation task and a real world demand in the prior art, the method comprises the following steps: performing semantic object reasoning and spatial position prediction through a visual language model, and determining the position of a target object; based on the panoramic view of the target waypoint, through the intelligent model with the body, detection and positioning are carried out, and a target object is determined; understanding of a high-level abstract instruction is realized, and a target object and a possible position are automatically reasoned; and the navigation capability of the robot in a complex real environment is obviously improved.

The invention provides a multi-source document automatic abstracting method and device, equipment and a storage medium, and the method comprises the steps: extracting information from a multi-source document, and constructing an initial knowledge graph; obtaining an inference rule based on the initial knowledge graph, performing automatic inference according to the inference rule, and adding or labeling an inference result in the initial knowledge graph to obtain a first knowledge graph; taking an entity needing to generate an automatic abstract as a key entity, extracting an event corresponding to the key entity from the multi-source document, constructing a relationship between the extracted event and the key entity, and adding the constructed relationship into the first knowledge graph to obtain a second knowledge graph; traversing all events associated with the key entity in the second knowledge graph, calculating importance scores of all the events, and screening part of the events as initial abstracts according to the importance scores; and inputting the initial abstract into a pre-trained editing network to obtain a final abstract.

The invention belongs to the technical field of network security, and particularly discloses a fuzzy testing method and system based on network protocol format inference and a program product. Based on the deduced protocol format characteristics, the final fuzzy test data is generated in the mode that a fixed value field, a control value field and a separator field in sample data are kept unchanged, and a variable-length field and a fixed-length field use multiple variation strategy dynamic combinations. According to the fuzzy test method based on the protocol format feature inference and the dynamic combination sample variation strategy, the difficulty of manually and reversely analyzing the protocol format and the fuzzy test data validity of an undisclosed and normative network protocol in the fuzzy test process is solved to a certain extent; a methodology and a basis of a protocol format automatic inference tool are formed, and the purpose of performing effective fuzzy testing on specific network protocol implementation is achieved.

The application discloses a low-code platform variable type automatic inference method and device. The method comprises the following steps: screening a variable with an automatic type identifier in a low-code platform to obtain a target variable; obtaining a default value inference result based on a type inference rule; traversing a structured model corresponding to a business logic and declaration information to obtain a node assignment inference result; obtaining a dependency relationship inference result through a multi-round iteration strategy recursive derivation; integrating the default value inference result, the node assignment inference result and the dependency relationship inference result to determine an initial type of the target variable; storing the initial type based on inference trace information and realizing change notification to finally obtain a target type. Through multi-stage inference, expression type calculation, chain dependency processing and other designs, the application does not need to manually specify the type, supports complex scene inference, maintains type safety, reduces use and maintenance costs, and improves the development efficiency and ease of use of the low-code platform.

The invention discloses an automatic inference method and device for low-code platform variable types. The method comprises the following steps: screening and matching variables with automatic type identifiers in a low-code platform to obtain target variables; obtaining a default value inference result based on the type inference rule; traversing the structured model and the declaration information corresponding to the service logic to obtain a node assignment inference result; recursive derivation is carried out through a multi-round iteration strategy to obtain a dependency relationship inference result; integrating the default inference result, the node assignment inference result and the dependency inference result, and determining the initial type of the target variable; and storing the initial type based on the deduced traceability information and realizing change notification, and finally obtaining a target type. Through multi-stage inference, expression type calculation, chain dependency processing and other designs, a user does not need to manually specify a type, complex scene inference is supported, type safety is kept, the use and maintenance cost is reduced, and the development efficiency and usability of a low-code platform are improved.

Methods, systems and computer-readable media enable various techniques related to semantic navigation. One aspect is a technique for displaying semantically derived facets in the search engine interface. Each of the facets comprises faceted search results. Each of the faceted search results is displayed in association with user interface elements for including or excluding the faceted search result as additional search terms to subsequently refine the search query. Another aspect automatically infers new metadata from the content and from existing metadata and then automatically annotates the content with the new metadata to improve recall and navigation. Another aspect identifies semantic annotations by determining semantic connections between the semantic annotations and then dynamically generating a topic page based on the semantic connections.

The application relates to a sonar echo image background suppression method based on a non-parametric Bayesian model, and mainly aims at the background suppression problem of sonar echo image target detection in a port environment. Machine learning is applied to the sonar echo image background suppression problem, a non-parametric Bayesian model is used for background modeling of the sonar echo image, and statistical characteristics and a threshold method are used for suppressing the background reverberation of the image. Compared with a parameter method, the non-parametric Bayesian model can automatically select the optimal component number required for establishing a mixed model according to the actual distribution of data samples, and solves the overfitting or underfitting problem caused by unknown mixed components of a traditional parameter model. Meanwhile, since the non-parametric Bayesian method can automatically infer the statistics required for establishing a mixed model from data, the dependence on prior information of actual data before modeling is further reduced, and the interference of background reverberation in the sonar echo image on target detection is significantly reduced in the suppression effect.

The invention discloses a workflow automatic production system and method based on natural language analysis, and the system and method enable a workflow building process not to depend on manual node dragging and tedious configuration through the automatic analysis of the natural language input of a user and the intelligent generation of a flow structure. The capability of constructing a complete process without a professional technical background is realized, so that the learning cost is effectively reduced. By means of automatic inference of a deep learning model on a process structure, a process generation process is completed by an automatic model. The system combines preset process knowledge and rules when generating the process, so that standardization of node selection and a connection relationship is realized, structural errors which are easy to occur in manual construction are reduced, and consistency and integrity of process construction are ensured. Besides, through an automatic process conversion and execution monitoring mechanism, the generated process can be rapidly deployed and error analysis and correction can be carried out in the operation process, so that the response capability of the system to the business demand change is improved and the execution maintenance cost is reduced.

This invention belongs to the field of indoor positioning technology and discloses a method and system for constructing and maintaining a long-term WiFi fingerprint map. The method includes: deploying reference points at intervals indoors and collecting WiFi signal strength (RSS) data, coordinates, and timestamps; automatically inferring access point (AP) coordinates based on signal backpropagation and maximum a posteriori probability (MAP) estimation, combined with a path loss model; decomposing the RSS into the mean path loss and residual terms, and modeling the residuals using spatiotemporal Gaussian process regression (GPR); incrementally updating the fingerprint map using an induced point set based on a sparse variational Gaussian process (SVGP); and performing terminal positioning based on the updated map. The system includes five functional units. This invention achieves automatic AP location inference, resistance to dynamic environmental interference, and low-cost long-term map maintenance, improving positioning accuracy and stability.

Techniques are described for providing a SAT-based solver for a quantifier string and bit vector theory. The solver may be used by an automatic inference service of a cloud provider network to analyze policies and results of policies. The solver simplifies an input formula to a Boolean satisfiability problem by encoding the input formula as an equivalently satisfiable propositional formula, where the satisfiability of the equivalently satisfiable propositional formula is determined by an SAT solver. The solver described herein does not use a conventional DPLL (T) type algorithm, but limits the length of variables in the input formula and simplifies the problem to a single formula, which may then be solved using an incremental SAT solution. The solvers may be used independently, or as part of a solver combination, for determining the satisfiability or non-satisfiability of certain formulas, e.g., corresponding to problems about user policies within a cloud provider network.

An operating system state root cause inference method, device, equipment, medium and product are provided. The operating system state root cause inference method comprises: obtaining a structured event with a predefined format in an operating system kernel; determining whether the operating system is abnormally stopped; in response to determining that the operating system is abnormally stopped, obtaining, by a user state service, state information of the operating system based on the structured event obtained in an operating system running cycle before abnormal stop through a predetermined state machine; and obtaining, by the user state service, an abnormal stop root cause based on the state information of the operating system through the predetermined state machine. Through the present disclosure, the structured degree and machine analyzability of operating system abnormal stop analysis can be significantly improved, different fault types can be more accurately distinguished, kernel invasiveness and maintenance costs can be reduced, the implementability of rule iteration and product deployment can be improved, and automatic inference and large-scale review can be realized.

The invention discloses an inference code automatic generation method and system in a model deployment process, and belongs to the technical field of model deployment, and the method comprises the following steps: extracting model information from an intermediate file of a model to be deployed, defining variables of each operator, and generating an output variable name index table and a weight variable name index table; determining an input variable name of each operator, and generating an input variable name index table according to the sequence of the operators; generating a pad value index table, an input size index table and an output size index table during actual reasoning; for each operator, extracting a corresponding API from an API library, filling parameters of the API according to an output variable name index table, a weight variable name index table, an input size index table, an output size index table, an input variable name index table and a pad value index table, and generating API calling of the corresponding operator; and combining the API calls of the operators to obtain the required reasoning code. According to the scheme, an automatic reasoning code generation method is provided for the AI chip, and the model deployment process is simplified.

According to the method and device for deducing the loop boundary, the target code comprising the loop unit is obtained, and the loop unit is subjected to expansion inspection according to the preset first expansion number of times by means of the bounded model inspection tool so as to determine whether the loop unit can be completely expanded under the first expansion number of times or not. Under the condition that complete expansion cannot be achieved, a counter example generated by a bounded model inspection tool is obtained, the first expansion number and the counter example are provided for the large model, so that the circulation boundary of the circulation unit is automatically inferred through the large model, and the counter example represents an execution path from an execution inlet of the target code to the circulation unit; therefore, automation of circulation limit deduction is achieved, and the requirement for manual intervention is reduced. Moreover, the counter example is utilized to guide the large model to deduce the circulation boundary, and the large model can extract a lot of key information from the counter example, so that the accuracy of deducing the circulation boundary can be improved.

The invention provides an API automatic inference and test method and device, and the method comprises the steps: generating a plurality of first API specifications according to a basic URL address based on a large language model, the basic URL address comprises a protocol and a domain name, and the first API specifications comprise an API path and a request parameter; adjusting the API path and the request parameter of each first API specification to obtain a plurality of second API specifications; splicing the basic URL address with each first API specification and each second API specification to obtain a test request; and sending the test request to the test server, and determining the validity of the test request according to the response state code of the test server. According to the method, the problem of low test coverage rate caused by incomplete test documents in the prior art is solved.

Embodiments of the invention disclose a data processing method and apparatus, a device, a storage medium and a program product. The method comprises the steps of obtaining first behavior sequence data of a target object in a first time period; performing causal relationship learning on the first behavior sequence data through a causal attention mechanism to obtain a behavior causal relationship and a behavior demand relationship of the target object; acquiring second behavior sequence data of the target object in a second time period, and performing reverse causal reasoning on the target object based on the second behavior sequence data and the behavior causal relationship to obtain predicted demand probability distribution of the target object; the first time period is earlier than the second time period; and performing reverse demand reasoning on the target object based on the prediction demand probability distribution and the behavior demand relationship to obtain a prediction behavior of the target object. By adopting the embodiment of the invention, the causal relationship and the deep demand can be automatically deduced from the user behavior, and more accurate user understanding and prediction are realized, so that the user guiding capability is effectively improved.

The invention discloses a code completion model member inference method based on antagonism prompts, which comprises the following steps of: firstly, designing and applying a series of antagonism prompts which keep program functions and are specific to codes, and converting an original input code prefix into a group of disturbed input codes; then querying the target model to respectively obtain prediction outputs of the target model for the original input and the group of input after disturbance, and constructing a feature vector by quantifying the similarity and confusion difference between the two prediction outputs and the real completion code; and finally, training a binary classifier by using the feature vector to automatically deduce the member identity of the sample. According to the method, an inference framework for exposing model memory by utilizing'behavior stability difference 'induced by adversarial prompts is proposed for the first time, an expensive shadow model does not need to be trained, a fine memory mode of a code large language model can be captured, and the accuracy, universality and application feasibility of member inference are remarkably improved.