35 results about "Semantic technology" patented technology

This invention relates to methods and systems of procuring services in the cloud and specifically procurement where the requirements are defined by the consumer in a machine understandable knowledge representation language such as RDF and OWL using semantic web technology to establish a cloud agent for discovery of a service provider and effectuate the automatic generation of a contract, or service-level agreement, that can be monitored due to the coupling between the machine understandable knowledge representation language and the contract.

The invention relates to the technical field of voice semantics, and discloses an information interaction method and device based on multi-agent collaboration, equipment and a medium, and the method comprises the steps: generating a target workflow through a large language model and a current user demand; determining a target AP I according to the target workflow, and generating initial interaction information; and generating current reply evaluation information based on the initial interaction information and the criticizing agent, and determining the initial interaction information as target interaction information under the condition that the current matching degree is greater than or equal to a matching degree threshold value. Through the above mode, the user demand is split through the routing agent and the built-in large language model, the target workflow is generated, and the method adapts to complex and changeable task scenes. According to the method, the target AP I is determined through the induction agent, and the initial interaction information is generated, so that the efficiency and accuracy of calling the AP I are improved, and the performance of an automatic business process system for processing complex interaction information in the fields of financial science and technology, medical treatment, health, old-age care and the like is improved.

The invention relates to the technical field of voice semantics, can be applied to business system platforms of financial science and technology, medical health and the like, and discloses an intelligent shopping decision-making method, device, equipment and medium based on voice recognition. Obtaining target voice data; performing voiceprint feature extraction on the target voice data to obtain a target voiceprint feature vector; performing phoneme topology decoding on the target voice data to obtain a target phoneme decoding vector; performing feature fusion according to the target voiceprint feature vector and the target phoneme decoding vector to obtain a comprehensive semantic vector; and constructing a consumption intention matrix of the target user according to the comprehensive semantic vector, and performing consumption decision according to the consumption intention matrix to obtain an optimal consumption scheme. According to the invention, the language recognition efficiency can be improved and full-process voice driving can be realized.

The invention relates to the technical field of voice semantics, can be applied to business system platforms of financial science and technology, medical health and the like, and discloses a business complaint report generation method, device, equipment and medium, and the method comprises the following steps: obtaining business data and customer complaint voice, carrying out text conversion on the customer complaint voice to obtain a customer complaint text, and sending the customer complaint text to a server; performing character recognition on the business data and the customer complaint text to obtain business data fields and text data fields; performing template filling on the customer complaint report template according to the business data field and the text data field to obtain an initial customer complaint report; performing voice coding on the customer complaint voice to obtain coding features, and performing emotion node recognition on the coding features to obtain emotion fluctuation nodes; performing emotion intensity analysis on the emotion fluctuation node to obtain an emotion intensity score; and performing content optimization on the initial customer complaint report according to the emotion fluctuation node and the emotion intensity score to obtain a target customer complaint report. The report generation accuracy and the report generation efficiency can be improved.

The invention relates to the technical field of voice semantics, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a sign language animation generation method, device, equipment and medium based on semantic parse. The sign language animation generation method comprises the steps that voice input is received and recognized as text content, field semantic parse is conducted on the text content to generate a field semantic template, and the field semantic template is used for generating a sign language animation; and converting the domain semantic template into a sign language intermediate representation sequence, generating a three-dimensional sign language action sequence based on the sign language intermediate representation sequence, rendering the three-dimensional sign language action sequence into a virtual image sign language animation, and displaying the virtual image sign language animation. According to the invention, by fusing speech recognition, semantic analysis and three-dimensional action rendering, direct conversion from spoken language content to sign language animation is realized, and a complete visual expression link from speech to sign language is formed, so that a user can intuitively understand the speech content in a sign language form through a virtual image, and the user experience is improved. Therefore, the barrier-free performance of human-computer interaction and the accuracy of information transmission are improved.

The invention relates to the technical field of voice semantics, and discloses a dialogue intention recognition method and device based on a large model, equipment and a medium, and the method comprises the steps: recognizing a target first-level intention label of a target query text through SFT; determining a target knowledge block according to the knowledge base and the target first-level intention label; and determining a dialogue intention according to the RAG and the target knowledge block. Through the above mode, effective preliminary intention recognition is performed on the target query text through the SFT, the target first-level intention label is determined, the target second-level intention label is accurately determined in combination with the preset knowledge base and the RAG model, the intention recognition accuracy and fineness are improved, and the intention recognition efficiency is improved in the second-level intention recognition process. The method can focus on the knowledge content highly related to the target query text, and reduces the burden of processing irrelevant information by the RAG model. The method can be applied to the business fields of financial science and technology, medical health, old-age care and the like, and the user intention recognition accuracy of the intelligent customer service system is improved.

The invention relates to the technical field of voice semantics, can be applied to the fields of medical health, financial science and technology and the like, and discloses a voice conversion method, device and equipment and a storage medium, and the method comprises the steps: obtaining an input voice signal, and converting the input voice signal into a Mel spectrogram; respectively extracting basic content information, global timbre information and rhythm feature information from the Mel spectrogram through a timbre encoder, a content encoder and a rhythm encoder; performing quantization processing on the global timbre information, the basic content information and the rhythm feature information to respectively generate timbre quantization information, content quantization information and rhythm quantization information; inputting the timbre quantization information, the content quantization information and the rhythm quantization information into a neural network model to obtain voice feature information; and inputting the voice feature information into a decoder to obtain a target voice signal. According to the method, the voice signals are decoupled into three independent attributes of timbre, content and rhythm, features are extracted through the special encoders respectively, and the encoding efficiency is improved.

The invention relates to the technical field of voice semantics, is applied to the field of financial science and technology businesses, and discloses an aspect-level emotion triple extraction method, device and equipment and a storage medium. The method comprises the steps that an input text is analyzed through an encoder, and a high-dimensional semantic feature vector is generated; converting each high-dimensional semantic feature vector into an input sequence of a preset neural network model, and combining each input sequence based on the preset neural network model to generate an initial word pair; and determining a target aspect-level emotion triple through a preset decoder and each initial word pair. According to the method, the neural network model is used, so that the long-distance dependency relationship and the relationship between multiple aspects and the sentiment words are better processed. And meanwhile, by utilizing pre-training knowledge of corpora, the feature extraction capability and generalization capability of the model are improved, and the target aspect-level emotion triad is determined more accurately, so that the accuracy of understanding the user emotion is improved.

The invention relates to the technical field of voice semantics, and discloses a cue word generation method and device based on large model optimization, equipment and a medium, and the method comprises the steps: carrying out the fitness evaluation of an initial cue word, and generating all comprehensive fitness scores; performing semantic crossover processing and semantic variation processing on the parent cue word to generate a child cue word; and according to the comprehensive fitness score, the offspring cue word and the initial cue word population, generating a target cue word population. By means of the mode, the cue word variant positioning optimal solution is explored through multi-target fitness evaluation and a population evolution mechanism, and it is ensured that cue words are professional. A large language model is introduced to perform semantic crossover and semantic adjustment on understanding of semantic content of parent cue words, so that child cue words inherit effective information and keep smooth. The method can be applied to the business fields of financial science and technology, medical health, old-age care and the like, and the accuracy of an intelligent customer service system for understanding complex semantics and generating cue words is improved.

The invention relates to the technical field of speech semantics, and discloses a context-based multi-modal data generation method, device and equipment and a medium, and the method comprises the steps: carrying out the semantic segmentation of context text information through a semantic recognition model, and determining a target semantic tag; multimedia materials are obtained, association is carried out according to the multimedia materials and the context text information, and initial multi-modal data are generated; and generating target multi-modal data according to the initial multi-modal data and the multi-modal data template. According to the mode, the target semantic label of the context text is extracted through the preset semantic recognition model, the text subjected to voice transcription is dynamically associated with the multimedia material according to the semantic label, and the multi-modal data integrating the image-text, the audio and the video is generated, so that a user only needs natural dialogue and does not need typewriting or complex operation, and the user experience is improved. In the business fields of financial science and technology, medical health, old-age care and the like, the interaction efficiency between the intelligent voice interaction system and the user is improved.

The invention provides a power equipment-oriented standard semantic knowledge base retrieval method, which comprises the following steps of: acquiring power equipment standard data, analyzing text information of the power equipment standard data, establishing semantic association among standard terms, equipment attributes and key indexes, and forming an equipment-standard-index knowledge graph; standard terms are calculated through a semantic vectorization technology, and matching calculation of the standard and equipment suitability is carried out based on a vector retrieval method; and according to the standard historical data and the deep learning model, carrying out evolution analysis on the standard terms, and providing suitability recommendation of the equipment standard. By establishing the semantic association between the equipment and the standard terms, efficient and accurate standard suitability recommendation and evolution analysis are realized, and efficient and accurate equipment standard suitability recommendation is provided through a semantic technology and a deep learning model.

The invention discloses an industrial technology bottleneck identification method based on science and technology service big data driving, and relates to the technical field of science and technology services, and the method comprises the steps: obtaining to-be-analyzed industrial multi-source heterogeneous data through a data collection interface; respectively extracting a text semantic feature vector, a technical association feature vector and a statistical feature vector; fusing the multi-modal features through an attention fusion mechanism; on the basis of the comprehensive feature representation, probability distribution of the industry on various potential technical bottlenecks is calculated through a bottleneck recognition model; and generating an identification result of the industrial technology bottleneck according to the probability distribution. The method has the advantages that by constructing a multi-modal analysis framework fusing scientific and technical literatures, patent networks and industrial statistical data, comprehensive perception of deep semantics, technical association and macroscopic trends is realized, and the recognition precision and comprehensiveness are remarkably improved; and dynamic, accurate and operable intelligent support is provided for industrial technology layout and research and development decision.

A subject-event method and a workflow engine developed based on it are designed for no-code creation and execution of semantic models of business processes and construction of domain ontologies. The operation of the workflow engine is based on original event semantics using the semantic implementation of a dataflow approach to algorithm execution. The use of a unified event data format made it possible to implement: (1) a specification for describing actions and entities, (2) a semantic workflow engine for executing business processes, (3) a semantic temporal data store. The invention provides a unified platform for enterprise content management, process automation, and knowledge base maintenance, addressing the limitations of traditional workflow engines and semantic technologies.

To provide devices, a data structure and computer-implemented methods for machine learning realizing data-efficient and resource-efficient labeling.SOLUTION: A method for machine learning includes: providing a data structure of a database; predicting a plurality of tuples depending on the data structure; predicting, for the plurality of tuples, an uncertainty about whether each tuple of the plurality of tuples classifies as a member of a set of tuples; selecting a tuple from the plurality of tuples depending on the uncertainties predicted for the respective tuples; acquiring a label that indicates whether the selected tuple classifies as a member of the set of tuples; and, if the label indicates that the selected tuple classifies as a member of the set of tuples, adding the selected tuple to the set of tuples, or otherwise not adding the selected tuple to the set of tuples.SELECTED DRAWING: None

The application provides a medical search recommendation method, system, product and terminal based on a knowledge graph and a semantic vector. The medical search request input by a user is subjected to medical entity recognition and standardized processing to obtain standard medical entity data. On the one hand, based on the standard medical entity data, a pre-constructed medical knowledge graph is used to perform retrieval reasoning to obtain a first retrieval result set. On the other hand, based on the standard medical entity data, a pre-trained semantic vector model and a vector database are used to obtain a second retrieval result set. According to a preset fusion rule, the first retrieval result set and the second retrieval result set are subjected to fusion processing to obtain a recommendation result. The application effectively breaks the limitations of the existing medical retrieval technology, and through double-path collaborative fusion, the defects of the vector semantic technology in lacking explicit medical logic support and the semantic generalization of the knowledge graph being insufficient are compensated for, so that precise, interpretable and safe medical search recommendation is finally achieved.

It is an object of the present invention to define a single abstract hierarchy data model using semantic techniques to manage different applications and to automate, if necessary, the process of generating interoperability rules. Further, it is desirable to provide an intuitive user interface that develops a natural and intuitive way to explore ontologies for a user, while shielding the user from technical aspects such as performing SPARQL queries. According to the invention, this object is achieved by a method for providing an intuitive user interface in at least one MOM system which controls the manufacturing environment of an autonomous plant, the method comprises the steps of: a) encoding manufacturing domain knowledge for an autonomous plant in an equal weighted co-control network of an extensible and configurable ontology, b) defining the ontology of the MOM domain by semantic conceptualization of the manufacturing domain knowledge; c) providing a web-based framework to create an intuitive user interface for navigating the ontology and associating concepts included in the ontology with logical data structures from existing applications included in the MOM system, wherein: c1) the user interface is capable of enabling a user to select an ontology and search concepts associated with the ontology that the user is interested in using public terms; c2) the user interface can also provide a list of concepts matching the corresponding search; c3) the user interface can also enable the user to select at least one concept from the list of concepts and provide a list of entities relating to the selected concept; c4) the user interface can also enable the user to select at least one entity from the list of entities and provide a visualization of the selected entity; and c5) the user interface can also enable a user to select a plurality of entities in the manufacturing domain that refer to the same concept, thereby generating a transformation rule to process logical data structures across said plant and / or domain with respect to the selected entities in the manufacturing environment of the autonomous plant.

Devices, data structure, and computer-implemented methods for machine learning. A method for machine learning includes providing a data structure of a database, which data structure includes a set of nodes and a set of relations, and a set of tuples. Each respective tuple includes at least two nodes, and at least one relation. The method includes predicting a plurality of tuples depending on the data structure, wherein each respective tuple includes at least two nodes and at least one relation, predicting, whether the respective tuples of the plurality of tuples classifies as a member of the set of tuples, selecting a tuple from the plurality of tuples depending on the uncertainties predicted for the respective tuples, acquiring a label that indicates whether the selected tuple classifies as a member of the set of tuples, and adding the selected tuple to the set of tuples based on the label.

Embodiments of the present disclosure disclose a method and device for querying building data and synthetic data. The specific implementation of the method comprises: extracting a graph embedding vector from input building-related graph data, and storing the graph embedding vector into a vector database and storing the graph data into a graph database; converting a question related to the graph data into a question embedding vector, and searching for a target vector similar to the question embedding vector in the vector database; generating a query instruction in a predetermined language based on the target vector through a first large language model; executing the query instruction in the graph database to determine a query result; and outputting a natural language answer to the question based on the query result through a second large language model. The implementation realizes efficient querying of complex building data and reduces the user's dependence on professional knowledge of semantic technology.

The invention relates to the technical field of voice semantics, and discloses a multi-feature voice identification method based on a large model, and the method comprises the steps: generating a voice fusion feature according to an initial semantic feature and an initial voice feature; and generating a voice identification result of the initial voice information based on a preset voice identification decision model and the voice fusion feature. Through the above mode, the semantic feature and the voice feature are fused to generate the voice fusion feature, and the semantic information and the acoustic information of the voice are comprehensively considered. The voice identification result generated based on the preset voice identification decision model and the voice fusion feature can adapt to voice data of different languages, different speaking styles and different background environments, and the accuracy of identifying the voice information by the voice identification system is improved in the business fields of financial science and technology, medical treatment, health, pension and the like.

Systems and methods for search execution, which can involve generating labels and keywords from a search query with a Named Entity Recognition (NER) model; executing classification logic on the labels and keywords from the search query to determine a corresponding search logic; executing the corresponding search logic to generate search results associated with scores; combining the scores of the search results for each of the labels to generate a ranking of the search results; and providing the ranked search results in response to the search query.

The invention relates to a device and a method for evaluating scientific texts using text tools and machine learning methods. These are characterized in particular by the fact that they enable a qualitative and quantitative analysis and evaluation of scientific texts using methods of machine learning, information retrieval, and semantic technologies. For this purpose, a database is connected via a programming interface and a data distribution device to a training device for adapting the data to at least one model and to an evaluation device.The data distribution device and the evaluation device are connected to a device for text analysis and text quality assessment, which, by applying the model(s) to the test data containing featured data and metadata, determines the quality of the model(s) and identifies key features of the texts, allowing the identification of key components of the texts. Furthermore, the device for text analysis and text quality assessment is connected to the database via the programming interface.

The invention discloses a self-adaptive moving method and a self-adaptive moving accompanying robot. Comprising a camera module used for collecting a color depth image of a surrounding environment; the intelligent base is used for acquiring a color depth image, inputting the color depth image into a preset simultaneous localization and mapping algorithm, outputting an identified bounding box and category, and creating an environment map; the identification module is also used for identifying a to-be-tracked moving target based on the bounding box and the category; planning a moving path of the robot based on the position of the moving target and an environment map; the universal wheel is used for tracking a target based on the planned moving path; the pain recognition module is used for evaluating the pain level of the user. According to the accompanying robot provided by the invention, the semantic technology in the SLAM system is invented, so that the environmental perception precision of the robot is improved, boundary detection is optimized, and the perception processing capability of the robot on dynamic objects in the environment is enhanced. The environment map can be constructed more accurately, and the safety and reliability of path planning are improved.

In order to cope with the challenges of data explosive growth and heterogeneous data integration and utilization in the scientific research field, an innovative device integrating intelligent deep analysis, verification and automatic claiming of heterogeneous data of scientific research achievements is invented. According to the method, knowledge graph, artificial intelligence and semantic technologies are fused, standardization, integration and deep analysis of heterogeneous scientific research data are achieved, the data governance level is improved, and data interoperability is promoted. According to the device, knowledge structured representation is constructed by utilizing a knowledge graph, and achievements of different sources are associated; data is deeply analyzed by means of artificial intelligence, key information is extracted, and accuracy is verified; and a semantic technology is introduced to eliminate semantic differences, and data docking is realized. Through technical collaboration, scientific research achievements can be automatically attributed, and the management efficiency and accuracy are improved. The research and development of the system improve the scientific research data management efficiency, provide a convenient tool for researchers, promote interdisciplinary communication and cooperation, promote scientific research data opening and sharing, follow the FAIR principle, accelerate scientific discovery, and provide new power for scientific research and innovation.

Apparatus, data structure and computer-implemented method of machine learning with semantic technology, the method comprising providing a data structure of a database comprising a set of nodes and a set of relationships, and comprising a set of tuples wherein a respective tuple comprises at least two nodes in the set of nodes and at least one relationship in the set of relationships, in one embodiment, a method includes predicting a plurality of tuples depending on a data structure, where a respective tuple includes at least two nodes in a set of nodes and at least one relationship in a set of relationships, the method includes predicting for the plurality of tuples an uncertainty of whether a respective tuple in the plurality of tuples is classified as a tuple set member, selecting a tuple from the plurality of tuples depending on the uncertainty predicted for the respective tuple, obtaining a flag indicating whether the selected tuple is classified as a tuple set member, adding the selected tuple to the tuple set when the flag indicates that the selected tuple is classified as a tuple set member, otherwise or when the flag indicates that the selected tuple is not classified as a tuple set member, the selected tuple is not added to the tuple set.

The invention relates to the technical field of speech semantics, and discloses a speech synthesis method, device and equipment for hierarchical emotion condition control and a medium, and the method comprises the steps: extracting three layers of acoustic feature vectors through a feature extraction model, and determining three layers of emotion distribution; generating to-be-synthesized text information through the original text information; and synthesizing the three-layer emotion distribution and the to-be-synthesized text information to generate target synthesized voice information. By means of the mode, the hierarchical emotion distribution is constructed by generating the three-level timestamps and extracting the acoustic feature vectors. The quality problem caused by alignment error accumulation is eliminated through a speech synthesis model, three-layer emotion distribution and to-be-synthesized text information are fused through a cross attention mechanism, and intensity values of phonemes, words and sentences are adjusted. The method can be applied to the business fields of financial science and technology, medical health, old-age care and the like, and the voice synthesis accuracy of a voice synthesis system in combination with user emotion is improved.

It is therefore an object of the present invention to define a method of managing a single abstraction layer data model of different applications using semantic techniques and to automate the process of generating interoperability rules among different manufacturing sites. According to the invention, this object is achieved by a method for enabling an MOM system for an autonomous plant by encoding manufacturing domain knowledge in an equal-weighted co-control network of extensible and configurable ontologies, said method comprising the following steps: a) defining an ontology of the MOM domain by semantic conceptualization of manufacturing domain knowledge; b) representing the ontology by at least one mapping knowledge domain; c) implementing the ontology in an owl format; d) providing a web-based framework to provide a set of intuitive user-friendly user interfaces for navigating the ontology and associating concepts included in the ontology with logical data structures from existing applications included in the MOM system; e) mapping the logical data structures by semantic conceptualization semantic matching, f) generating interoperability codes between the data structures of the different applications, thereby mapping the data structures of the different applications within the same MOM system and / or over a plurality of distributed MOM systems of the autonomous plant.

The invention relates to a voice semantic technology, and discloses a universal sql statement execution method, which comprises the following steps of: obtaining a sql statement sent by a user according to a pre-constructed sql universal driving service, and inquiring a service entity of the sql statement by utilizing a pre-trained entity extraction network model to obtain an object entity set and an action entity set; querying whether the object entity set has a query permission conforming to the action entity set; generating error reporting information when the permission conforming to the query does not exist; and when the query permission is met, performing statement analysis on the sql statement by utilizing an sq1view platform to obtain a calculation engine suitable for the sql statement, and importing the sql statement into the calculation engine to obtain an execution result corresponding to the sql statement. The invention further provides a universal sql statement execution device and equipment and a storage medium. The invention aims to identify the sql statement sent by the user and automatically select a proper search engine to search, so that the data search efficiency is improved.

The invention relates to the technical field of voice semantics, and discloses an emotion perception and cross-language dialogue information generation method and device, and the method comprises the steps: extracting a current discrete voice unit sequence and a current emotion feature vector; multi-modal emotion joint representation is generated through an extended vocabulary library and an attention fusion mechanism; and according to the multi-modal emotion joint representation, generating a target voice signal, and based on the context cache pool and the target voice signal, generating interactive dialogue information. By means of the mode, the multi-mode emotion joint representation is generated by extracting the discrete unit sequence and the emotion feature vector, and the emotion state of the user is captured while the semantic content is understood. And multiple rounds of dialogues fusing semantics and emotions are generated by means of an attention mechanism. The method can be applied to the business fields of financial science and technology, medical health, old-age care and the like, and the accuracy of dialogue information generation by an intelligent interaction system in combination with user emotion and cross-language cross-mode is improved.

The invention relates to the technical field of voice semantics, can be applied to the fields of financial services and medical services, and discloses a response performance index determination method and device of a large language model, equipment and a medium, the method comprises the following steps: obtaining a preset number of preset question texts and standard response texts from a preset question and answer text database; according to the LLM question-answering robot and each preset question text, generating a to-be-verified response text; and performing at least one response performance test on each to-be-verified response text through each standard response text, and determining each response performance index of the LLM question and answer robot. Through the mode, the preset question text and the standard response text are acquired from the database, the response text to be verified is automatically generated, and the performance test is performed, so that manual operation is reduced, the performance of a large language model is comprehensively assessed through the multi-dimensional performance test, and the efficiency of the large language model is improved in the financial business field and the medical business field. And the semantic understanding accuracy of the large language model is improved.

The invention relates to the technical field of speech semantics, and discloses a speech generation method and device based on a self-guiding diffusion model, equipment and a medium, and the method comprises the steps: generating a semantic mark sequence; generating a Mel spectrogram according to the coarse-grained diffusion model, the fine-grained diffusion model and the semantic marking sequence; and generating target voice information through a feature conversion technology and the Mel spectrogram. By means of the mode, the weakening semantic guiding model and the main semantic prediction model work cooperatively, self-guiding enhancement is carried out in the semantic mark generation process, and the generation probability of wrong semantic marks is reduced. Through self-guiding optimization of coarse-grained and fine-grained two-stage diffusion models, hierarchical refined generation of speech features is realized, fine noise easily generated by a traditional single diffusion model is avoided, and the method can be applied to the business fields of financial science and technology, medical treatment, health, old-age care and the like, and has a wide application prospect. And the reliability of converting the text information into the voice information by the intelligent customer service system is improved.