704 results about "Current user" patented technology

The invention discloses a virtual historical character dialogue method and system with role knowledge and context awareness, and relates to the technical field of man-machine interaction, and the method comprises the steps: constructing a multi-level role depth model; when a question of a current user is received, identifying information of a virtual scene where the current user is located, analyzing micro-expressions of the face of the user and voice rhythm characteristics of speech of the user, analyzing an emotional state and an interaction intention of the user based on a multi-modal fusion algorithm, and generating a user state vector; executing a dynamic Prompt construction program, extracting related information from the multi-level role depth model and the user state vector, and generating a structured Prompt; and inputting the structured Prompt into a large language model, generating a reply text conforming to role features based on questions of the current user, and driving a virtual character model. The method solves the problem that in the prior art, virtual historical figures cannot provide real immersion and credible interactive experience with emotional connection.

The invention provides a context compression method based on multi-round dialogue intention graph construction, which comprises the following steps: S1, dialogue data acquisition and preprocessing: carrying out natural language processing on each dialogue unit; s2, intention atlas construction is achieved through node design and edge design, and each node comprises original text content and structured semantic information; s3, carrying out context compression and graph structure cutting, and only retaining sub-graphs forming a core semantic link; s4, dynamic context management and topic jump processing: in a multi-topic dialogue, when a user jumps or switches to a new topic, a system records a sub-graph of a current active topic, and contextual nodes of an inactive topic are frozen; s5, context sequence generation and model input: linearizing node contents in the cut sub-graph according to a dependent link sequence to generate a compressed context sequence, and transmitting the context sequence and current user input to a large language model for reasoning; and S6, continuous updating and feedback optimization are carried out.

Embodiments described herein are directed to systems and methods for modifying issue groups for a graphical user interface of an issue tracking platform. An issue dashboard graphical user interface can include multiple sets of issue tickets, where each set of issue tickets is grouped in accordance with a queue definition. A prompt can be generated and include predetermined prompt text including a recommendation criteria, data extracted from the multiple sets of issue tickets including an issue title and assignee, and data associated with a current user account authenticated with respect to the frontend application. A group modification interface can be displayed and include at least a portion of a generative response. In response to a user input, a new issue ticket group can be created by performing a structured query on issues managed by the issue tracking platform and saving the structured query as a new queue definition.

The invention relates to the technical field of smart home, and discloses a smart home control method and device for realizing user interaction based on a smart mirror, and the method comprises the steps: confirming a plurality of user registration instructions, obtaining a registration voice stream based on the user registration instructions, carrying out the feature extraction of the registration voice stream, obtaining reference voiceprint features, summarizing the reference voiceprint features, and carrying out the collection of the reference voiceprint features. The method comprises the following steps: obtaining a plurality of reference voiceprint features, confirming to receive a pre-confirmed voice wake-up word, carrying out voice collection based on the voice wake-up word to obtain a user voice stream, obtaining a voiceprint label by using the user voice stream and the plurality of reference voiceprint features, carrying out voice analysis on the user voice stream to obtain a control instruction, and sending the control instruction to a server. And performing permission verification by using the voiceprint tag and the control instruction to obtain a permission verification result, and obtaining response feedback based on the permission verification result. According to the invention, the problem that the personalized intelligent service cannot be provided because the current user identity cannot be distinguished and the control authority cannot be verified according to the user identity in the smart home interaction scene can be solved.

The invention discloses a high-precision positioning method and device for a wiring error electric leakage user, and a storage medium, and relates to the technical field of electric leakage detection. The method comprises the following steps: collecting residual current of a tested transformer area and time sequence data of load current of each user in the tested transformer area; based on the time sequence data, calculating the time sequence correlation strength between the load current and the residual current of each user; generating a differentiated penalty coefficient for each user based on the time sequence correlation intensity; constructing a regression model taking the residual current as a dependent variable and the load current of each user as an independent variable, and reconstructing a target loss function of the regression model by taking a penalty coefficient as a coefficient of a regularization term; and through minimizing the target loss function, a weight coefficient corresponding to the load current of each user is estimated, and then the user with a wiring error electric leakage fault is determined. According to the method, the problem of misjudgment caused by normal user interference in a traditional electric leakage user identification method is effectively solved.

The invention relates to the technical field of personalized health follow-up visit, in particular to a personalized health follow-up visit method, system and device based on a health portrait and a large language model and a medium, and the method comprises the steps: collecting multi-dimensional health data of a user, carrying out the standardization processing and feature extraction of the health data, and generating a plurality of user feature tags; based on the user feature tag, constructing a dynamically updated user health portrait; inputting the user health portrait into a service classification model, and determining a target follow-up visit service line and a follow-up visit mode corresponding to the current user; on the basis of the target follow-up visit service line, the follow-up visit mode and the user health portrait, a prompt word is constructed and input to a large language model, so that personalized follow-up visit content is generated; and based on the follow-up visit content, executing a follow-up visit task on the user through the intelligent call-out system. The method has the beneficial effects that the follow-up visit efficiency and coverage are remarkably improved, and refined, dynamic and humanized health management of each user is really realized.

The invention relates to the field of man-machine interaction, and discloses a man-machine interaction method and system based on a large language model, and the method comprises the steps: extracting original semantic features from the current input of a user; obtaining a context representation of the current dialogue; extracting a historical emotional state sequence from the multi-round dialogue historical record; generating a current user emotion representation vector based on the context representation of the current dialogue and the historical emotion state sequence; constructing a hierarchical memory structure based on the current user emotion representation vector and the context representation of the current dialogue; adjusting the attention degree of the historical dialogue content stored in the semantic memory component according to the hierarchical memory structure; and generating a response sequence through a large language model based on the adjusted attention degree, the hierarchical memory structure and the context representation of the current conversation, and outputting the response sequence to the user. According to the technical scheme, the problems of stiff switching and dialogue breakage during emotion turning of a traditional dialogue system are solved.

The invention discloses a user ad-hoc query report realization method and device based on a large language model, and relates to the technical field of natural language processing. The method comprises the following steps: constructing an ad hoc query report system based on the large language model, wherein the ad hoc query report system comprises a semantic analysis module, an analysis engine module and a query statistics module; a natural language query statement input by a user is input into a semantic analysis module to be analyzed through a fine-tuned large language model, a structured query condition set and a structured query result index column set are output and input into an analysis engine module, and according to permission information of the current user, through pre-constructed index metadata and SQL semantic analysis rules, the query result index column set is analyzed, and the query result index column set is analyzed. Generating a query SQL statement; and inputting the query SQL statement into a query statistics module, connecting a target database to execute query operation to obtain a query result set, and performing data formatting processing on the query result set to obtain a final query result. By adopting the method, complex query requirements can be met.

Dynamic valuation of virtual spaces in a virtual environment includes receiving telemetry data describing current user interactions with a virtual environment; performing predictive analysis on the telemetry data to predict future user interactions with a plurality of virtual spaces in the virtual environment; and continually adjusting values of the virtual spaces based on the predicted future user interactions without considering virtual objects in the plurality of virtual spaces.

The present application relates to a zero trust-based service system access control method and apparatus, a device, and a medium. The method comprises: triggering, among core network functional network elements of a network, a session management function network element or an AAA server to send a user re-authentication request to a user terminal, so that the user terminal returns current user information to the AAA server; upon the AAA server verifying that current user identity information is consistent with user identity information corresponding to a target user, determining an identity authentication success result; on the basis of the identity authentication success result and the current user identity information, the AAA server initiating a biometric authentication request to the user terminal, so that the AAA server checks whether most recent biometric information of the target user returned by the user terminal matches pre-stored biometric information of the target user, and if so, returns a biometric authentication success result to the user terminal, so as to authorize the target user to continue accessing a target service system. The present application can prevent several security issues, such as unauthorized control over authorized devices.

The invention provides a verbal skill recommendation method based on context and intention prediction, and the method comprises the steps: introducing intention recognition and a potential subsequent intention prediction mechanism based on a affair graph, and fusing the current input information, a business knowledge context and a multi-round dialogue context corresponding to multi-round dialogue historical data; and the current intention of the user is responded, and a more accurate target reply verbal skill is generated. Then, the intention evolution of the potential follow-up intention of the current user is further predicted based on the affair graph, so that the potential demand of the user is pre-judged, and the target guide verbal skill is generated aiming at the potential demand, so that the verbal skill pertinence of the generated verbal skill in a complex dialogue scene is improved through a recommendation mode of combining the reply verbal skill and the guide verbal skill; therefore, the verbal skill generation accuracy is improved, and the user experience and the message reply efficiency are improved. The method can be applied to a seat verbal skill recommendation function in the financial field or the medical field, so that the seat verbal skill generation accuracy is improved.

The invention provides a software jitter elimination method and system, and the method comprises the steps: calculating a triggering time interval based on a current user triggering interaction signal collected in real time; based on the trigger time interval and a preset time judgment threshold interval, obtaining a trigger operation type; if the trigger operation type meets a preset execution requirement, obtaining an operation time sequence based on a preset time sliding window, and obtaining statistical data according to the time sequence; calculating a current operation dynamic threshold based on the statistical data; and responding to user triggering interaction based on the dynamic threshold value so as to carry out jitter elimination on software interaction. The problem that in the prior art, due to the fact that a fixed time threshold value is adopted in a high-frequency-triggered interactive application scene, part of operation needing to be responded is ignored, and the software interaction reliability is poor is solved. According to the method, the triggering interval is adaptively adjusted, the corresponding time threshold value is calculated to serve as a reference to eliminate shake of software triggering, and the software interaction reliability is improved.

The invention relates to the technical field of computer software, provides a visual flow arrangement method for e-commerce marketing, and aims to solve the problem of insufficient system processing performance and expansibility when an existing flow arrangement technology is applied to an e-commerce marketing scene. Generating and storing a state transition rule set; obtaining a user behavior event, obtaining a historical state transition event sequence according to the user behavior event, and then dynamically calculating a current user journey state; acquiring a corresponding state transition rule set, and performing matching query by taking the current user journey state and the user behavior event as input; if matching succeeds, a corresponding marketing action command is executed, and a new state transition event is generated and persisted to an event log so as to update a user journey state, so that efficient and accurate state-driven rule matching and automatic execution are realized, and the processing efficiency, expandability and state traceability of a system in a high-concurrency scene are improved.

Certain aspects of the disclosure provide methods and systems for providing resolution guidance to a help center agent are provided. One method generates a set of intent-resolution pairs based on a historical interactions, including: grouping similar intents extracted from the corpus of historical interactions in a same intent topic group of a plurality of intent topic groups, and grouping resolutions associated with the similar intents in a same resolution topic group of a plurality of resolution topic groups. Additionally, the method determines an intent of the current user utterance as a user intent. The method maps the user intent to one or more intent-resolution pairs from the set of intent-resolution pairs. Moreover, method provides, to the help center agent, one or more suggested resolutions corresponding to the one or more intent-resolution pairs. Also, the method provides, to the customer, a selected resolution from among the one or more suggested resolutions.

The embodiment of the invention aims to provide a method and equipment for providing personalized health management for a user based on a hypertension prevention and treatment knowledge graph, a computer program storage medium and a computer program product. The method comprises the following steps: acquiring multi-modal data for constructing a hypertension prevention and treatment knowledge graph, including medical data and medical big data, so as to construct a standardized causal triple knowledge unit; according to the causal triple knowledge unit of the medical data, constructing a basic structure of a hypertension prevention and treatment knowledge graph; according to a causal triple knowledge unit of the medical big data, constructing the hypertension prevention and treatment knowledge graph which can be dynamically evolved; collecting personalized health data of the current user; and obtaining a dynamic hypertension health management scheme for the current user. The invention constructs a hypertension prevention and treatment knowledge system which is dynamically updated, highly personalized, comprehensive in data fusion, intelligent and efficient.

Kernel-mode security software detects a trigger event indicative of a specific stage in the lifecycle of a target software entity executing in user mode. In response, the security software identifies a target object residing in memory (e.g., loaded library, chunk of code, etc.) according to a current content of the user-mode call stack, and determines whether the target object is malicious. Various methods described herein detect malicious modifications of a loaded module, such as overload, stomping, and unhooking, among others. Other methods described herein detect dynamically swapped libraries and malicious shellcode, among others.

The invention relates to the technical field of artificial intelligence, in particular to an adaptive context processing method and system for a large language model. The method comprises the following steps: collecting multi-source candidate context segments related to current user query; performing utility evaluation on each candidate fragment, outputting a quantized utility score, and performing multi-granularity compression on each fragment based on the utility score and a preset quality constraint to obtain a compressed fragment set; taking the maximization of the total utility score as a target, taking the condition that the total token cost is less than or equal to the global token budget as a constraint, and carrying out optimization selection to obtain an optimal context combination; and inputting the optimal context combination into a large language model to generate an output result for the current query. By applying the method, the context window management of the large language model can be optimized, the adaptive context processing capability of the information utilization efficiency is improved, and the problems of context window limitation, value judgment and the like are solved.

A method for providing a description of a functionality of a vehicle to a user of the vehicle. The method includes obtaining first data (D1) indicative of a current user behavior and obtaining second data (D2) indicative of a historic user behavior. The historic user behavior is associated with the user located inside the vehicle while the vehicle is in a non-driving mode. Moreover, the method includes determining a likelihood (LH) that the user will stay inside the vehicle while the vehicle is in the non-driving mode based on the first data (D1) and based on the second data (D2). Furthermore, the method includes triggering a provision of the description of the functionality of the vehicle, if the determined likelihood (LH) exceeds a predefined likelihood threshold. The disclosure also relates to a data processing apparatus, a computer program, a computer-readable storage medium, and a vehicle including the data processing apparatus.

The invention relates to the technical field of power retail, in particular to a power retail package recommendation method and system, and the method comprises the steps: obtaining user historical power consumption data through an intelligent electric meter or a power data collection terminal, and constructing user power consumption sample data after denoising and abnormal value processing; and in combination with the user attribute data and the power retail package attribute data, adding a user power consumption feature tag for the sample data. And training a package recommendation model by using the power consumption sample data and the feature tags. And acquiring real-time power consumption data and user attribute data of the current user as model input, calculating a recommendation score of each power retail package through a model, and pushing the package with the highest score to a user terminal as a recommendation result. According to the method, personalized recommendation is realized through data driving, the power retail service precision is improved, and the user experience is optimized.

The invention discloses a charging pile control method, device and system and a storage medium, and relates to the technical field of charging piles. The method comprises the steps that a charging pile obtains multi-modal data of a current user through a sensing module and sends the multi-modal data to a cloud platform; the cloud platform determines a user intention and a user state according to the multi-modal data by using a behavior perception model, and sends an optimal charging strategy to the charging pile according to the user intention and the user state, the user state including a new user or an old user; and the charging pile charges the vehicle of the current user according to the optimal charging strategy. According to the technical scheme provided by the embodiment of the invention, the charging pile can adapt to different user groups and environment scenes, a personalized optimal charging strategy is provided for the user, the intelligent sensing capability of the charging pile is improved, and intelligent operation management and energy scheduling are realized.

The invention discloses a medical voice interaction dynamic privacy protection method and related equipment, and the method comprises the steps: carrying out the voiceprint recognition of a current user in response to a session request, determining the role of the current user based on a voiceprint recognition result, and dynamically authorizing the data access authority of the current user according to a predefined access control strategy; retrieving related historical dialogues and medical knowledge within the boundary of the data access permission, and generating personalized answers; voiceprint monitoring is continuously carried out during the session, and when switching of the current user is detected, a dynamic privacy protection mechanism is triggered; the dynamic privacy protection mechanism dynamically calculates privacy protection intensity based on multiple factors of voiceprint confidence, dialogue keyword sensitivity, dialogue intention sensitivity and a time decay factor, adds adaptive noise to the personalized answer according to the privacy protection intensity, and then outputs the personalized answer. The invention aims to improve the privacy protection capability of the intelligent voice assistant in the medical scene, so that the intelligent voice assistant can adapt to the complex multi-role cooperation requirement of the medical scene, and the dynamically changing session scene can be effectively processed.

The embodiment of the invention provides a user session processing method and device, electronic equipment and a storage medium, and relates to the technical field of user session processing. The method comprises the following steps: acquiring a complexity score of a current user request and a current session state; according to the complexity score of the current user request and the current session state, performing state migration processing on the current user request according to a preset state migration rule, and determining a target session state of the current user request; according to the method, the target back-end response model is determined based on the target session state, and the current user request is routed to the target back-end response model for response processing, that is, intelligent routing of the user request is realized by combining the complexity score with a dynamic migration mechanism of the session state, and the service cost is effectively controlled while the response quality is guaranteed.

The invention relates to the technical field of artificial intelligence, in particular to a knowledge base intelligent retrieval and multi-modal processing method for an AI sales scene, which comprises the following steps: receiving and analyzing multi-modal input of a user, the multi-modal input at least comprising text input and / or image input; obtaining dynamic context information associated with the current user, wherein the dynamic context information comprises a user portrait and a historical dialogue; based on multi-modal input and dynamic context information, performing deep semantic understanding and intention analysis by using a large language model to obtain real demand description of a user; generating a structured enhanced retrieval configuration based on the real demand description of the user; and performing retrieval based on the enhanced retrieval configuration to obtain a retrieval result set. According to the method, short and fuzzy surface questions of a user can be penetrated, real and complete requirements of the user can be informed, and structured enhanced retrieval configuration is generated in combination with a dynamic context, so that the correlation and the accuracy of a retrieval result are greatly improved.

This document describes systems and techniques for authenticating a user by matching a trusted identification credential with on-device identity verification in generating an authentication token. For example, a request to verify an identity of a current user of the first communications device is received from a second communications device. A trusted identification credential associated with stored biometric information of a designated user is accessed. A sensor of the first communications device is used to collect captured biometric information of the current user. A verification is performed to determine if the captured biometric information matches the stored biometric information. Responsive to determining that the captured biometric information matches the stored biometric information, an authentication token is generated including a cryptographically signed assertion that includes the nonce received from the second communications device and an assertion confirming the match between the captured biometric information and the stored biometric information.

The invention provides an automatic testing method and device based on artificial intelligence. One specific implementation mode of the method comprises the steps that a test case described by a natural language and input by a tester for a tested system is obtained; according to the type of the tested system, obtaining target domain knowledge corresponding to the type of the tested system from a domain knowledge base; based on the test case and the target domain knowledge, executing the following test steps: acquiring state information of a current user page of the tested system; cue words are constructed based on multi-modal data, a large language model is input, the large language model outputs next operation information, and the multi-modal data comprises a test case, state information, historical operation information and target domain knowledge; executing a next test operation on the current user page based on the next operation information, and storing test records generated in the test steps; and under the condition that the current condition reaches a preset test flow termination condition, generating a test report based on the test records generated in each test step.

The invention provides a sleep music generation method and device and terminal equipment, and is suitable for the technical field of data processing, and the method comprises the steps: obtaining a sleep music generation result according to user age information, user gender information, current user physiological state information, current user behavior state information, historical user physiological state information and historical user behavior state information; obtaining current user rhythm information and current user sleep state characterization information; generating current user sleep state confirmation information according to the current user rhythm information and the current user sleep state representation information; and in response to the generation of the current user sleep state confirmation information, generating sleep music information according to the current user physiological state information, the sleep music generation model and a preset sleep music set. According to the method and the device, the individual difference of the user and the sleep state of dynamic change are accurately adapted, the accuracy and adaptability of sleep music generation are improved, and personalized sleep adjustment is effectively realized.

The invention relates to the technical field of computers, and discloses a risk prediction method and device based on a user authentication behavior, equipment and a medium, and the method comprises the steps: obtaining the sample data of a target user based on the authentication behavior; performing multi-dimensional processing on the sample data to determine target features; performing anomaly detection based on the target features to obtain a detection result; and performing risk prediction on the detection result by using a plurality of preset models to obtain corresponding prediction results, and integrating all the prediction results to obtain a final risk prediction result of the target user based on the authentication behavior. According to the invention, multi-dimensional processing is carried out based on the user authentication behavior data, and a corresponding result of anomaly detection is predicted by adopting a plurality of risk assessment models to obtain a final risk prediction result for judging whether the current user authentication behavior has a risk, so that the risk prediction accuracy can be improved, and the identity authentication intensity is further improved; meanwhile, the user experience can be ensured, and the user authentication requirement is greatly met.

The invention relates to a session creation method and device, communication equipment, a medium and a product, and relates to the technical field of communication. The method comprises the following steps: receiving a session creation notification sent by an SMF network element; in response to the session creation notification, obtaining a target session number threshold value corresponding to the current user identifier and the number of created sessions; and when the number of created sessions is less than the target session number threshold, returning a session creation permission notification to the SMF network element, so that the SMF network element creates a new session through the NACF network element in response to the session creation permission notification. According to the technology provided by the invention, the session creation process of the NACF network element at this time can be constrained according to the target session number threshold value corresponding to the current user identifier and the number of created sessions, so that a ToB type user can be prevented from abusing satellite resources.

The invention discloses a barrier-free interaction method and equipment for government affair services, and relates to the technical field of barrier-free government affair services. The method comprises the following steps: acquiring identification data for reflecting hearing impairment features; when it is judged that the user is the hearing-impaired user according to the identification data, converting the operation interface into a barrier-free interaction interface matched with user interaction parameters of the hearing-impaired user; pushing a plurality of businesses in the barrier-free interaction interface; performing semantic analysis according to the sign language action of the user in the barrier-free interaction interface to obtain a semantic analysis result; after a target service needing to be handled by the current user is determined according to the semantic analysis result, a service rule of the target service is obtained; and generating and displaying business operation information according to the semantic analysis result and the business rule. According to the method, the hearing-impaired user is actively judged, the user does not need to manually start a sign language mode or switch a function entry, the use threshold of the hearing-impaired user is effectively reduced, and convenience is provided for service handling of the user in a service pushing mode.

This application discloses a method and device, electronic device, and storage medium for processing airline ticket change information, which includes the steps of: obtaining change dates for at least one itinerary of a current target stroke selected by a current user; dividing each date within a preset range based on each change date to obtain target dates corresponding to each change date; constructing each date unit using the target dates corresponding to each change date; generating multiple candidate flight combinations corresponding to each date unit based on flight information for each target date; calculating price differences for each candidate flight combination corresponding to each date unit; selecting the candidate flight combination with the lowest price difference from the candidate flight combinations corresponding to each date unit as a final selected flight combination corresponding to each date unit; and feeding back the price differences and flight information for each date unit and the corresponding final selected flight combination to the current user.