79 results about "User knowledge" patented technology

The invention relates to the technical field of test question generation, in particular to an intelligent test question generation method and system based on learning behavior analysis. The method comprises the following steps: acquiring interactive behavior data and score data of learners in a user online learning platform in real time; inputting the interactive behavior data and the score data into a pre-trained knowledge state analysis model to generate a user knowledge state matrix; based on the knowledge state matrix and in combination with a preset teaching target library, identifying a target knowledge point set which needs to be strengthened currently and a corresponding cognitive training type; according to the target knowledge point set needing to be strengthened and the corresponding cognitive training type, a test question element combination algorithm is called, question stems, interference items and question solving path prompts are dynamically assembled, and personalized test questions are generated. The method has the advantages that full-closed-loop intelligent teaching from behavior analysis of the user to targeted training is achieved, and personalized test questions adaptive to individual cognitive vulnerabilities are dynamically generated.

Techniques for creating and updating natural language summaries representing personalized user knowledge (e.g., user interests, user affinities, user preferences, family structure, routines, and other insights) based on conversational interactions with and other natural language content available to an AI system are described. In some embodiments, to provide a more personalized service, a system can use a generative model to summarize learnings about a user and determine helpful nuanced insights about the user such as “the user is learning how to play guitar.” This “user knowledge” can be updated based on further (later) conversations with the user, where updating can involve negating or deleting stored information, adding to or modifying stored information, etc.

The invention discloses an intelligent personalized topic recommendation method based on a knowledge graph, and relates to the technical field of information retrieval, and the method comprises the steps: constructing a multi-dimensional subject knowledge graph which defines knowledge point entities and topic entities through the knowledge graph, and establishes structural relationships and capability dimension attributes between the entities; forming a structured knowledge basis for recommendation; collecting learning behavior data of the user, and generating a user knowledge state model for dynamically evaluating the knowledge state of the user in combination with the multi-dimensional subject knowledge graph; selecting a corresponding recommendation strategy according to an output result of the user knowledge state model, and performing multi-dimensional question matching based on capability dimension matching based on the multi-dimensional subject knowledge graph to generate a personalized question recommendation scheme; and dynamically optimizing the multi-dimensional subject knowledge graph, the recommendation strategy and the matching rule based on the feedback of the user to the recommendation scheme. The problems that a traditional recommendation system is shallow in knowledge association, rough in diagnosis and rigid in strategy are solved.

A mastery level determining method to assess user mastery of educational skills by centralizing and processing data from diverse educational platforms is disclosed. The method involves collecting user educational data from various sources such as online learning platforms, external assessments, and internal quizzes. This data is then normalized to adapt to the educational standards and ingested into a structured mastery framework. The recent and reliable data is evaluated to determine skill mastery states, prioritizing newer and more reliable information. Subsequently, reliability and recency scores are calculated and assigned to each educational data. The method further categorizes user mastery skills into distinct states, providing an overview of the user's knowledge. The simplified mastery states and associated tags are accessible to the user, facilitating personalized learning experiences and assessments within the online learning platforms.

The invention provides a method for joint answering of a user knowledge base and a service system under an AI platform, and belongs to the technical field of AI platform models.According to the method, hierarchical semantic matching is achieved by constructing a three-level knowledge vector cache and a three-level question intention vector cache and adopting vector representation of different dimensions; after user query is received, a semantic similarity algorithm is used for performing parallel retrieval to generate an initial matching degree, multi-dimensional similarity information is fused through a joint matching degree calculation function, and the precision is improved by using an intention recognition optimization model; calculating an optimal sequence length through an adaptive parameter adjustment function according to the long and short memory matching length to obtain real-time data of the service system, fusing the static answer of the knowledge base and the real-time data of the service system to generate a final answer, and updating a vector cache and optimizing algorithm parameters according to user feedback. And high-precision joint answering of the knowledge base and the business system is completed.

The invention discloses a learning assistance method, device and equipment based on a big language model and a storage medium, and the method comprises the steps: collecting historical interaction data of a user and the big language model, after desensitization processing and structured storage, extracting keywords and knowledge points through a natural language processing module, clustering similar problems and knowledge points, and carrying out the clustering of the similar problems and knowledge points; constructing a user knowledge graph containing knowledge point relevance and mastery score; generating a learning priority list based on the map score, and matching a preset knowledge base to generate a personalized learning plan; pushing the plan to a user side, and obtaining a learning and testing result to determine the knowledge mastery degree; and comparing the mastering degree with a preset threshold value, if the mastering degree is lower than the threshold value, regenerating the targeted plan, and if the mastering degree is not lower than the threshold value, marking the knowledge points as mastered and updating the graph. According to the scheme, knowledge blind spots in dialogues are dynamically tracked, conversion from passive question answering to active learning is achieved, and the knowledge mastering ability of a user is systematically improved.

The invention provides an intelligent customer service dialogue method and system for intellectual property legal consultation, and the method comprises the steps: firstly receiving an intellectual property legal consultation request of a user, and obtaining a consultation text sequence which comprises a plurality of legal question expressions and logic association information; performing intention analysis on the consultation text sequence, and extracting surface and deep appeal elements to form an appeal element set; calling an AI legal reasoning model to perform scene element matching based on the appeal element set, and generating a legal reasoning scene anchoring result; constructing a multi-round legal reasoning chain with the appeal element set as a starting node and the legal conclusion derivation as a termination node, and generating a multi-round reasoning process record; and the content of the reasoning node is dynamically associated with the provisions of the preset intellectual property legal basis library to generate a consultation response sequence containing the reasoning logic and the legal basis, and the consultation response sequence is fed back to the user, so that the efficiency, the accuracy and the comprehensiveness of intellectual property legal consultation are improved.

The invention relates to a method for realizing semantic chain retrieval enhanced generation processing for knowledge questions and answers of long documents. The method mainly comprises two parts of knowledge base construction and user knowledge questions and answers. User knowledge questions and answers are constructed based on a knowledge base, and knowledge base construction relates to long document preprocessing, semantic chain type storage, information compression and knowledge extraction and storage. When a user performs knowledge questions and answers, a retrieval vector is formed through fine-grained semantic coding, and then related document vectors and knowledge maps are matched in a knowledge base through vector similarity calculation. If the length of the document exceeds the context scale of the model, document information after static information compression is indexed through information compression, whether dynamic compression is carried out or not is evaluated, and document fragments related to tasks are returned through dynamic compression. Otherwise, directly returning the related original document as the background knowledge of the generator. And the model generator generates an answer based on the related document information / information after information compression, the knowledge graph information, the user question and a model prompt.

The invention relates to the technical field of artificial intelligence, in particular to an online state grid potential lost user identification method based on a knowledge graph. The identification method comprises the following steps: constructing a user knowledge graph; based on the user knowledge graph, constructing a relational graph convolutional neural network to deeply mine and analyze graph structure data, learning low-dimensional vector representation of entities and relationships in the knowledge graph, and capturing complex relationships between the entities and deep features of the graph structure data; two classifiers are constructed based on the extracted user features by reference to a multi-task learning network, an independent output layer is designed for each classification task, one is used for identifying whether the user has a loss risk, and the other is used for predicting the level of the user loss risk. According to the invention, the problem of how to improve the identification accuracy of the state grid user loss risk in the big data environment is solved; and the power consumer groups with potential loss risks are effectively identified, risk level subdivision of the users is realized, and then differentiated recall strategies are formulated.

The present disclosure provides a knowledge processing method, system, storage medium and program product, and relates to the field of artificial intelligence. The method comprises: constructing a user knowledge graph according to historical operations of each user on knowledge in a public knowledge base; processing the user knowledge graph to obtain a user feature vector and a knowledge feature vector; obtaining an embedding vector matrix of a plurality of candidate knowledge based on the user feature vector and the knowledge feature vector; and performing knowledge recommendation for a target user based on historical operations of the target user on knowledge and the embedding vector matrix of the plurality of candidate knowledge.

A system is capable of reducing effects of how much knowledge / experience a user has and making it easy for the user to decide a plan for work by a crane. It is possible to cause a user who has specified first carriage points through a terminal input interface to grasp an arrangement aspect and specifications of a crane for carrying materials to the first carriage points (or from the first carriage points) by the crane while avoiding interference of the crane and the materials with a building, through a secondary work situation image output to a terminal output interface of an information terminal.

This invention discloses an intelligent knowledge extraction system based on natural language processing, comprising: a text data acquisition module that acquires unstructured text and forms raw data; a text data preprocessing module that removes noise and standardizes the format of the raw data, outputting standardized text data; a text feature encoding module that converts the standardized text data into feature vectors that satisfy the input of an improved W2NER model; a knowledge extraction module that processes the feature vectors based on the improved W2NER model to obtain entity extraction results; an entity normalization module that performs ontology mapping and normalization on the entity extraction results; a knowledge fusion module that performs deduplication and fusion on the entity knowledge set; a knowledge storage module that stores the fused knowledge data in a structured manner; and a knowledge application service module that provides user knowledge query and reasoning services. This invention improves the accuracy of knowledge extraction and the efficiency of data application.

A first acquisition unit acquires user information of a target user who is the target of an interaction from a first database in which user information including at least information on a genre of interest and information on knowledge is registered for each user. A second acquisition unit acquires a list of episode data associated with the genre of interest of the target user from a second database in which episode data associated with at least one of a plurality of genres is registered. A generation unit uses the information on the knowledge of the target user acquired from the first database and the list of episode data acquired from the second database to generate a query instructing a language model to select episode data assumed to be of interest to the target user and about which the target user is assumed to have no knowledge.

To facilitate the formation of a shared understanding among stakeholders with different areas of expertise, and to enable work efficiency and cost optimization through optimal evaluation tailored to the characteristics of each component. [Solution] The user interface provider unit 51 provides the user terminal 2 with a user interface having a function to select an operation mode according to multiple user knowledge levels, a function to acquire target building information, and a function to present output information. The classification unit 52 classifies the components of the target building according to their location and arrangement based on the target building information. The evaluation unit 53 compares the evaluations of multiple evaluation methods for each classified component and selects an evaluation result using an appropriate evaluation method based on the comparison results. The output control unit 55 generates output information indicating the selected evaluation result for each classified component and executes control to present it from the user interface.

An auto-login system and process enable maintaining user accounts on a server without a user having to register or create a user name, password, or other authentication method. An account may be created without user knowledge. The server may transmit a content item to a target user, along with a link. A server identifies the target user from use of the auto-login link and collects interaction or “engagement” data while the user is logged in, to assess user interest in products, for example, a mutual fund investment product, which may be characterized by tags and / or categories. The system may quantify a product salience metric for a given product relative to a target user's interest profile to focus marketing efforts and support engagement with interested target users, especially securities funds and financial advisors.

The invention provides a model reasoning method. The method comprises the steps that information input by a user is acquired; a first text related to the information input by the user is output, and the first text comprises at least one sentence of text data; determining at least one piece of non-text data related to the at least one sentence of text data in a target original text segment, the target original text segment being an original text segment referenced by the at least one sentence of text data, and the target original text segment being included in a user knowledge base; determining target non-text data matched with the at least one sentence of text data from the at least one non-text data; and outputting the target non-text data. According to the scheme, the understandability, correctness and diversity of the output content can be improved, and the waiting time of the user is shortened, so that the use experience of the user is improved.

The invention relates to the field of multi-modal modeling, and provides a three-dimensional enterprise knowledge base construction method and system. The method comprises the following steps: classifying and marking knowledge assets to be constructed according to a preset dimension system, and extracting semantic feature information corresponding to multiple dimension knowledge nodes to obtain a multi-dimensional cross knowledge framework; knowledge nodes in the multi-dimensional cross knowledge framework are stored in a graph database, a knowledge association network is established, and a dynamic knowledge graph is obtained; collecting user feature data, and generating a user knowledge demand portrait according to the user feature data; performing matching calculation on the user knowledge demand portrait and knowledge nodes in the dynamic knowledge graph, and screening matching results to obtain a target knowledge push list; and determining an access permission level according to the role permission attribute of the user, performing permission verification on the knowledge nodes in the target knowledge pushing list based on the access permission level, and generating personalized knowledge content. According to the invention, the knowledge management efficiency, the delivery accuracy and the security are improved.

This invention discloses a method, system, and device for recommending learning paths in online communities based on knowledge graphs. First, a knowledge graph model is constructed, consisting of three layers of entities: "course – topic – knowledge point." A multi-level text similarity function based on a corpus and core phrases is then constructed using user posts in the online community. Second, horizontally, the similarity function measures the semantic similarity between posts. Based on the user's knowledge background, a unique user with a similar knowledge level within the user group is identified, and their learning path is obtained. If a path is missing, vertically, the knowledge graph is used to recommend users at a higher level than the current topic's knowledge point. A unique user is identified based on their knowledge background, and their posts are obtained. Finally, the knowledge graph is used to recommend fine-grained and multi-context-aware learning paths for users in the online community. This invention can recommend fine-grained and multi-context-aware learning paths from both horizontal and vertical perspectives, combined with the user's knowledge background.

A recommendation system and method based on an e-commerce coupon field knowledge graph, and relate to the technical fields of knowledge graphs and recommendations.The present application is to solve the problem that the existing business coupon recommendation method cannot recommend for new users, and has low reliability and accuracy.The present application comprises: constructing a knowledge graph corresponding to the current e-commerce platform user to obtain a knowledge graph library;obtaining current user information and determining whether the current user is a new user;obtaining the knowledge graph corresponding to the current user, using the knowledge graph corresponding to the current user to obtain a user-coupon list, and thus performing coupon recommendation information;obtaining the old user information input by the new user, and obtaining the knowledge graph corresponding to the old user in the knowledge graph library;using the knowledge graph corresponding to the old user and the scoring situation of the popular goods of the e-commerce platform for the new user to construct a new user knowledge graph, and then obtaining coupon recommendation information.The present application is used for recommending e-commerce coupons.

This invention discloses a method for digital creative content recommendation and user profile construction based on knowledge graphs, belonging to the field of data processing technology. The method includes first collecting multi-source heterogeneous user behavior data to construct a time-series sequence; then, after multimodal feature extraction, building an initial knowledge graph centered on the user, with interests as leaf nodes and timestamps as edge attributes; next, using a time-series graph neural network to achieve dynamic evolution of the graph, generating an evolving user knowledge graph; extracting explicit and implicit subgraphs from it and analyzing temporal changes in emotions, and fusing them to construct a multi-dimensional user profile; simultaneously, building a digital creative content knowledge graph containing multi-dimensional features; optimizing and filtering content for recommendation through multi-objective matching; and then pushing the content to the user after sorting by comprehensive score. This invention, by introducing a dynamic evolution mechanism and multi-objective optimization, achieves accurate capture of changes in user interests and multi-dimensional matching of creative content.

The application discloses a format contract generation method and system based on a knowledge base and a contract template, and relates to the technical field of format contract generation. The application aims to improve contract generation efficiency and solve the problem that users need to manually modify contract templates to meet specific contract requirements. The method comprises the following steps: obtaining user demand text, a user knowledge base and a contract template; analyzing the composition elements, format and blank position of the contract template to reconstruct a format template containing format information; retrieving associated information in the knowledge base based on the composition elements; combining the retrieved associated information, the format template and the demand text to form a prompt word, and submitting the prompt word to a large model; obtaining the text with format information returned by the large model, and analyzing and generating a contract with format. This process aims to constrain the large model output to meet the requirements of the contract template and generate a format contract carrying user knowledge. In this way, the efficiency and quality of contract generation can be effectively improved.

The invention discloses a personalized knowledge graph learning system and method based on a dynamic weight rule, and relates to the technical field of personalized learning, and the system comprises a dynamic question grouping module, a multi-dimensional evaluation analysis module, a knowledge graph lightening module, an Ebbinghaus review reminding module and an automatic question generation module. According to the method, a dynamic question grouping algorithm based on a knowledge label test frequency grade is constructed, scientific distribution of exercises is realized, a multi-dimensional exercise result analysis algorithm model is established, knowledge mastering grades are divided in combination with scores and key conditions, and the knowledge mastering degree is visually presented through a knowledge graph according to a set rule. According to the method, the user can intuitively feel the problem owned by the user at present, defects can be checked and repaired in time, a review reminding mechanism which combines behavior habits and data of a user group and is based on an optimized Ebbinghaus forgetting curve is designed, and the knowledge memory retention rate of the user is increased.

The embodiment of the invention discloses an intelligent central control terminal control method, device and equipment based on a multi-mode large model. A specific embodiment of the method comprises the following steps: performing node fusion processing on an electronic medical record of a user and a thyroid cancer knowledge graph; performing feature node mapping processing on the user electronic medical record to obtain a user knowledge sub-graph; performing node attention aggregation processing on the user knowledge sub-graphs to obtain node feature information of each meta path sub-graph and each sub-graph; performing gating enhancement processing on the user electronic medical record, each meta path sub-graph and each sub-graph node feature information to obtain user feature information; performing scheme matching and adaptive optimization processing on the user feature information to obtain a target follow-up visit scheme; and controlling the intelligent central control terminal to execute the task auxiliary operation. According to the embodiment, interaction steps needing to be executed by the user can be reduced, and the operation convenience when the user controls the intelligent central control terminal to conduct rehabilitation training is improved.

A mobile application is designed to transform the travel experience by integrating artificial intelligence (AI) with global positioning system (GPS) technology to offer a dynamic and interactive tour guide. This mobile application determines a user's geographical location using GPS and responds to natural language queries about the location with synthesized information from various internet sources. The application is capable of maintaining the context of user interactions, allowing for follow-up questions and providing personalized, real-time information based on user preferences and movements. By combining AI capabilities akin to those of conversational platforms like ChatGPT with precise location tracking, the application offers tailored, educative content about surrounding areas, thereby enhancing user knowledge and engagement during travel.

The application discloses a data cleaning method based on a Bayesian formula, a terminal and a storage medium, and the method comprises the following steps: acquiring original data and pre-defined prior knowledge; constructing a Bayesian network and an association relationship according to the prior knowledge, performing causal reasoning on the original data according to the Bayesian network, and obtaining a probability score of the Bayesian network; determining an association relationship score of the original data according to the association relationship, and cleaning the original data according to the sum of the probability score and the association relationship score, to obtain a cleaned data version. The application combines the user knowledge prior information which is easy to master, the modeling capability of the Bayesian network on dirty data and the association relationship of mutual information existing in the data, performs scanning and cleaning on the original data, reduces the difficulty of data cleaning, and improves the accuracy and recall rate of data cleaning.

This invention discloses a service recommendation method and system based on knowledge graphs, belonging to the field of knowledge graph service recommendation technology. The method includes: responding to the cold start state of a target new user, acquiring basic attribute data and constructing an initial user knowledge graph; semantically expanding through intent anchor diffusion to mine potential user needs; inputting the expanded graph into a preset service recommendation model to generate a service demand subgraph, and aligning it with the service domain knowledge graph through topology-preserving joint subgraph embedding, calculating joint loss to obtain highly matched recommended services; and optimizing model parameters using an asymmetric update strategy based on real-time user feedback. This invention accurately characterizes and deeply mines the potential needs of new users through user knowledge graphs, effectively solving the problems of low recommendation accuracy and result generalization caused by data scarcity in traditional methods during cold start scenarios, significantly improving the recommendation success rate and user experience for new users.

The application relates to the technical field of computer information processing, in particular to a multi-modal video structured analysis and intelligent playing system and method based on a semantic time axis, aiming at the problems of insufficient video structured analysis capability, separation of playing and knowledge content, low processing efficiency and the like, a distributed asynchronous task architecture is constructed, audio and video preprocessing, speech recognition, time sequence semantic segmentation, subtitle generation and summary extraction are completed through a multi-modal analysis engine, and structured knowledge data accurately bound with a video time axis are generated. After automatic verification and manual review are completed through a quality control module, the structured knowledge base realizes associated storage of original videos and structured data and multi-dimensional index construction, and an intelligent interactive player realizes chapter navigation, subtitle synchronization and knowledge card linkage display in dependence on the semantic time axis. The application realizes standardized and structured conversion of unstructured videos, improves video processing efficiency and resource utilization, and reduces user knowledge acquisition cost.

The present invention relates to a user knowledge tracing method with more improved accuracy, and an operating method for a user knowledge tracing system including a plurality of encoder neural networks and a plurality of decoder neural networks includes: inputting exercise information to a k-th encoder neural network and inputting response information to a k-th decoder neural network; generating query data, which is information on an exercise for which a user is to predict a correct answer probability, by reflecting a weight to the response information and generating attention information to be used as a weight for the query data by reflecting the weight to the exercise information; and training the user knowledge tracing system by using the attention information as the weight for the query data.

The invention relates to a method for creating a user personalized knowledge base, which is applied to a large model knowledge base and comprises the following steps: collecting knowledge input, extracting multilayer semantic features of a text, identifying entities and entity relationships of the text, and mapping the entities and the entity relationships to a vector space; capturing complex associations among entities, and fusing the complex associations with the multilayer semantic features of the text to form vector representations of various entities and entity relationships; recording interaction behaviors of the user and the large model knowledge base, extracting preference characteristics of the user, and dividing knowledge interests of the user into corresponding hierarchies and fields; and extracting correlation vector representation from the large model knowledge base according to the hierarchy and the field to which the knowledge interests of the user belong, and constructing a user personalized knowledge base. Personalized knowledge services can be provided according to use habits and knowledge backgrounds of users, and retrieval precision and recall rate are improved.

The invention provides a task planning strategy searching method and device and a computer readable storage medium. The method comprises the steps of skipping to a first task node; the first task node is a node in a graph structure for performing path planning on a set task of an intelligent agent; a plurality of nodes in the graph structure respectively correspond to set group item state functions; obtaining a first state strategy function of a first item state function in a set group item state function of the first task node, and executing the first item state function by using the first state strategy function to complete path planning calculation of a task step corresponding to the first task node; wherein the first state strategy function comprises a subsequent state jump strategy of the first item state function and first user knowledge corresponding to the first task node and the first item state function thereof.