2444 results about "User group" patented technology

The invention provides a multi-dimensional data authority management and privacy protection method for an electric power information network, and the method comprises the steps: dynamically selecting the type of a watermark according to the leakage risk level of a screenshot event, and enabling the watermark type to comprise a simple character watermark, a character and image mixed watermark, an invisible watermark, and a two-dimensional code watermark; user screenshot content factors are added in a screenshot event distribution curve of user historical data to judge the risk level of a user, the risk level of a user group is updated, and when the screenshot frequency, time interval, screenshot mode, distribution mode and curve volatility of the user are all normal and screenshot content only aims at sensitive data screenshot, the risk level is improved; a screen capture auditing and monitoring mechanism is established, full-life-cycle recording and tracking are carried out on screen capture behaviors of a user, and screen capture events, watermark embedding conditions and abnormal behavior information in a system are monitored in real time through a visual instrument panel and a report.

The invention provides a private domain traffic scheduling and content distribution method and system based on group behavior analysis, and relates to the technical field of private domain traffic operation, and the method comprises the steps: constructing a user social network through analyzing the historical behavior data of a user, calculating the influence weight of the user, and generating a user group portrait in combination with the long-term and short-term interest distribution of the user. And performing semantic analysis on the candidate content, constructing a content propagation network, calculating a content propagation coefficient and a matching coefficient of the content and the user group, and generating a target content sorting table. User active time period distribution is calculated according to the user activeness prediction model, a content delivery strategy is generated in combination with the target content sorting table and the matching coefficient, and the delivery strategy is dynamically adjusted according to the delivery effect index, so that accurate content distribution is realized, and the private domain traffic operation efficiency is improved.

The invention provides a multi-private-domain visitor portrait sharing and privacy protection routing method based on federal learning, and relates to the technical field of data sharing and privacy protection, and the method comprises the steps: calculating the feature sensitivity and distributing a differential privacy budget, and adding mixed noise to the original data of a visitor portrait for privacy protection, according to the method, feature vectors are encrypted by adopting fully homomorphic encryption based on ideal lattices, threshold password segmentation is performed by utilizing a Viterbi algorithm, sub-key components are distributed to private domain environments, a hybrid network structure is constructed to extract features, federal optimization is performed based on data quality and historical contribution degree, and a feature extraction network is updated. The method comprises the following steps: carrying out feature dimension reduction by using a dual auto-encoder, extracting key features and generating user feature fingerprints, carrying out user grouping by calculating the similarity of the feature fingerprints, and realizing safe sharing of user similarity information and visitor portrait original data in combination with multi-party safe calculation and a hierarchical data access strategy.

The invention discloses an intelligent advertisement putting processing method and system based on user data, and relates to the technical field of data processing, and the method comprises the steps: putting an advertisement in an advertisement pool based on an edge device, collecting the video information during the advertisement playing period through the edge device, analyzing the stored video information, extracting the user feature information, and storing the user feature information in the advertisement pool; the user feature information is integrated into user feature vectors, the user feature vectors stored in the edge devices are uploaded to the cloud platform, the cloud platform analyzes the user feature vectors uploaded by the edge devices to generate user portrait information, and the user portrait information is displayed on the basis of the user portrait information generated by the cloud platform. And putting corresponding advertisements to the user groups with similar user portrait information, collecting feedback data, and dynamically optimizing the advertisements put by the edge devices and the user groups based on the feedback data. The method has the advantages that the data transmission delay and the cloud computing pressure are reduced through the cloud edge collaboration method.

The invention discloses an advertisement putting real-time optimization method and system based on user behavior prediction, and particularly relates to the technical field of advertisement putting. Real-time behavior data and historical behavior data of a target user group are collected, a dynamic behavior sequence is generated through time window division, the historical behavior data are classified to construct a user behavior feature library, potential behavior prediction features of users are extracted, and a unified prediction feature vector set is generated; comparing and analyzing with a preset advertisement content label library, and outputting a user interest association degree data set in combination with an advertisement inventory state; a dynamic optimization parameter set is generated in combination with putting strategy constraint conditions; finally, the advertisement putting content, the advertisement putting frequency and the display position are adjusted in real time according to the dynamic optimization parameter set, an optimization result is output, and an advertisement display queue is updated, so that accurate capture and intelligent matching of user interests are achieved, and the advertisement putting effect and the user experience are improved.

The invention discloses a customer relationship intelligent management and analysis system based on CRM, and relates to the technical field of intelligent analysis, a business logic layer comprises a customer information management unit, a sales opportunity tracking unit and a marketing activity management unit, the customer information management unit is used for extracting basic attributes, consumption habits and preference characteristics of customers from customer data by using a data analysis technology so as to construct a comprehensive and three-dimensional customer portrait; and the customer information management unit further divides the constructed customer portraits into subdivided groups with common demands, preferences and behavior patterns through in-depth market research. According to the method, the wide customer groups are divided into the subdivided groups with common requirements, preferences and behavior patterns, so that an enterprise can more accurately understand each user group, a more targeted marketing strategy is formulated, resource allocation can be optimized to a certain extent, and the market response speed is increased.

The invention belongs to the technical field of artificial intelligence, and discloses a government information consultation system based on a large language model, which comprises a user interaction module, a large language model core engine, a knowledge base integration module, a multi-level authority management module, a feedback optimization mechanism and a risk control module. The comprehensive intelligent government affair service system is constructed through the six core modules, remarkable advantages are shown in government affair service digital transformation, the system innovatively adopts multi-mode interactive design, multiple input and output modes of voice, text and images are supported, an intelligent authority management mechanism is matched, and the intelligent authority management mechanism is matched with the intelligent authority management mechanism. According to the technical scheme, the accessibility and convenience of government affair services are greatly improved, precise services for different user groups are achieved, it is guaranteed that sensitive data are safe and controllable while wide spreading of government affair information is guaranteed, and a large language model of a system core is subjected to professional government affair scene optimization training and is combined with a dynamically-updated knowledge graph technology.

The invention discloses a creation content generation method and system based on AIGC, a medium and a program product, and relates to the technical field of artificial intelligence, and the method comprises the steps: determining the theme and style of creation content, carrying out preliminary content creation in combination with target audience information, and generating a preliminary creation content frame; performing emotional enrichment and creative enhancement processing on the preliminary creation content framework, and obtaining a processed creation content framework and a corresponding creation element set; based on historical combination data of different creation elements in the creation element set, determining an optimal creation content generation strategy according to innovation factor correlation coefficients of the creation elements and corresponding creation optimization strategies in a content generation model for creation effect-oriented optimization; according to the optimal creation content generation strategy, utilizing the optimized content generation model to intelligently generate final creation content; while the content generation efficiency is ensured, the personalized level of the generated content is improved, and the diversified requirements of different user groups are met.

The invention relates to the technical field of brand promotion, in particular to a brand promotion method and system based on user positioning, and the method comprises the following steps: collecting user browsing history, purchase records and social media interaction data, carrying out the statistical analysis of the data, recognizing the field in which a user is interested, and constructing and generating a user interest recognition result. In the invention, through detailed analysis and real-time updating of user data, a dynamic user portrait can be constructed, promotion content can be accurately customized, advertisement content is ensured to be highly related to current interest of a user, a user behavior mode is revealed through clustering analysis, key features are extracted, an advertisement system is allowed to adaptively adjust content and putting time, and user experience is improved. According to the method, the personalized degree and effect of advertisements are remarkably improved, dynamic advertisement configuration is automatically optimized according to real-time changes of user behaviors, promotion activities can accurately aim at potential key user groups, the conversion rate and the user interaction rate are increased, and finally more effective market penetration is achieved.

A computerized system receives an original prompt that a querying user sends to a Large Language Model (LLM) that is operably connected to organizational data sources of an organization. Instead of executing the original prompt by the LLM, the system obtains user-related organizational context that pertains to characteristics of the querying user, obtains data-related organizational context that pertains to data from which the LLM is expected to obtain information for responding to the original query, and obtains pre-defined organizational policy rules, that indicate which type of users are authorized to access which type of organizational data. Based on the obtained data, the system modifies the original prompt into an adapted prompt. The system sends the adapted prompt, and not the original prompt, to the LLM for processing. The system obtains LLM-generated output from the LLM in response to the adapted prompt, and provides that LLM-generated output to the querying user.

The present invention relates to the technical field of electricity applications. Disclosed are a supply-demand interaction game method based on electricity consumption behaviors of user groups, and a system. The method comprises: collecting and preprocessing historical electricity consumption data of smart terminals of user groups; using a clustering analysis method to perform classification on the types of electricity users; by means of the central-limit theorem and Monte-Carlo method, constructing a user electricity consumption behavior analysis model; creating an electricity user group evolutionary game model, so as to analyze long-term evolution patterns of electricity consumption strategies of the user groups; and power supply entities adjusting and formulating, on the basis of the analysis result, an electricity price incentive plan that maximizes benefits, and transmitting, via power lines, the updated plan to smart electricity consumption terminals of the users. By means of using electricity consumption data of user groups collected by a large number of smart terminal devices and combining the data with the evolutionary game theory, the present invention successfully performs mathematical modeling and analysis on electricity consumption behaviors of user groups, thus achieving mutual benefit, win-win outcomes and stable equilibrium between supply-demand parties in long-term supply-demand interaction.

The invention relates to the technical field of data processing, and provides a trade big data processing and user behavior prediction method and system.The trade big data processing and user behavior prediction method comprises the steps that transaction data, browsing behavior data and feedback evaluation data of a user on a cross-border e-commerce platform are obtained to generate a user behavior pattern sequence, and then a user interaction graph is constructed; and carrying out edge weight updating and node label classification to obtain a high-dimensional relation graph, carrying out similarity partition processing to obtain a predicted popularity index graph, and predicting the future cross-border commodity interaction behavior of the target user group by using the predicted popularity index graph. By acquiring transaction data, browsing behavior data and feedback evaluation data of users and generating a prediction popularity index graph, multi-dimensional data are effectively and comprehensively processed, accurate prediction of cross-border commodity interaction behaviors of a target user group is realized, and the user experience is improved when a user intention deep relationship is processed and cross-time-period behavior evolution analysis is performed. The problems of low model dimension and insufficient prediction precision exist.

The invention relates to the technical field of data security and the field of financial science and technology, and discloses a permission-based interface flow limiting method, which solves the problem of low efficiency caused by unified processing of all requests by obtaining accessed service interface information and screening out key access requests according to a preset interface path rule. Permission classification is performed based on service roles, account identifiers or user group information of the users, flow limiting management is further refined, and personalized flow limiting conditions are set for the users in different permission ranges. According to the flow limiting conditions, the system dynamically selects a proper flow control strategy, such as request frequency limitation and concurrent request number control, so that system resources are reasonably distributed. According to the method, the flow limiting strategy can be dynamically adjusted according to different permissions of the user, it is guaranteed that the high-permission user is not limited too much, meanwhile, the situation that malicious users cause too large pressure on the system through frequent requests is prevented, and the overall safety and stability of the system are improved.

The invention discloses a low-orbit satellite beam scheduling and resource allocation method and device, equipment and a storage medium, and relates to the technical field of communication, and the method comprises the steps: determining the time slot priority of a to-be-scheduled user; dividing to-be-scheduled users into different user groups, and determining a wave potential interference matrix between the user groups; time slot allocation is carried out based on the time slot priorities of the to-be-scheduled users and the beam position interference matrix between the user groups, and a hopping beam spectrum is generated; determining a target to-be-scheduled user corresponding to an available beam in each time slot in an updating period of the hopping beam atlas; and performing resource allocation on each time slot based on the service priority of the target to-be-scheduled user of the available beam in each time slot. Through the above mode, interference isolation and time slot allocation calculation are completed based on user priorities and user grouping, multi-user resource allocation scheduling is carried out under a single time slot, air interface resource information is fully utilized, and the spectrum utilization rate and the system throughput rate are improved to the maximum degree.

The invention discloses an international propagation effect accurate evaluation method and system based on a large language model, and relates to the field of international propagation effect evaluation, and the method comprises the steps: obtaining a behavior log data set of a user, and dividing the user to a preset life cycle stage; extracting an interest label set of the user in a continuous time window, calculating a weight change rate of the same semantic keyword, and generating a user interest drift trend feature; extracting a propagation content feature vector of the to-be-evaluated propagation content, and calculating a basic matching degree with the interest label set; dynamically correcting the basic matching degree in combination with the life cycle stage and interest drift trend characteristics to obtain a final matching degree; extracting a path mode feature vector of the user, performing parameter matching with a propagation path mode library, and determining a propagation effect evaluation level; dividing the users into user groups according to the propagation effect evaluation levels, and implementing an intervention strategy on the user groups; according to the invention, refined grading evaluation of the propagation effect can be realized.

The invention discloses a user analysis method and device based on a large model, equipment and a medium, and the method comprises the steps: obtaining user data from a plurality of data sources, and carrying out the preprocessing of the user data, so as to form a structured data set; inputting the structured data set into a pre-trained large model based on deep learning, and outputting a current user portrait after performing feature extraction on the user data through the large model; according to the user portrait, analyzing the user by adopting clustering analysis, association rule mining or a classification algorithm, and outputting a user classification result; and according to the user group characteristics corresponding to the user classification result, in combination with the user portrait, performing user behavior prediction so as to push personalized recommendation content to the user. According to the method, the users are analyzed and classified through the user portraits, and the pushing requirements of personalized contents can be accurately and quickly met.

The invention provides an information resource distribution method and system applied to a dynamic network environment, and the method comprises the steps: firstly obtaining a real-time state feature set of a target distribution network, determining a resource distribution constraint condition set in a current network environment based on the real-time state feature set, carrying out the priority analysis of a real-time resource request sequence of a target user group, and obtaining a real-time resource distribution constraint condition set; obtaining resource timeliness grade distribution and a request path optimization feature set, generating a dynamic distribution strategy parameter set matched with a resource distribution constraint condition, triggering a resource redirection operation, and enabling the resource request response rate of the target user group to be improved to a preset threshold interval; and the information resource distribution efficiency and stability in the dynamic network are improved.

The invention discloses an interest point recommendation method based on a knowledge graph, and relates to the technical field of computers, and the method comprises the following steps: obtaining user sign-in data to obtain user information, respectively dividing according to interest points and time to obtain interest areas and a plurality of time slots, calculating user similarity, and performing spectral clustering according to the user similarity to obtain user groups, and according to the user group, the time slot and the region of interest, constructing a multi-level point-of-interest knowledge graph fused with context information. Preliminarily learning an interest point knowledge graph based on a graph translation model to obtain an embedded vector, and using a gating graph neural network introduced with geographic information for a plurality of sign-in sequences to obtain interest point representation with spatio-temporal characteristics; through the graph attention mechanism model, the sign-in relation with user group features and interest area features is fused, user preferences are spread, possible interest point preferences of a single user are mined and predicted, user requirements can be more effectively met, and a more highly personalized recommendation service is provided.

The invention relates to the technical field of network advertisement promotion, in particular to a network advertisement promotion method and system based on the Internet, and the method comprises the following steps: obtaining user behavior data, analyzing a browsing track, a staying duration, a click frequency and an interactive behavior, calculating the activity of a user in real time, and recognizing the interest point of the user. And updating user tags in real time, classifying user groups, and generating a user tag data set. According to the method, the interest point of the user is identified, the user label is updated in real time, it is ensured that personalized recommendation of the advertisement conforms to the real-time behavior of the user, the active time period of the user is analyzed and predicted, resource waste caused by putting in a fixed time period is avoided, budget allocation is dynamically adjusted according to the adaptation degree between the behavior of the user and the platform, and the user experience is improved. The advertisement putting efficiency is improved, user behavior changes before and after advertisement display are compared, the advertisement putting effect is accurately evaluated, data support is provided for adjustment of advertisement strategies, and the advertisement putting effect and resource configuration are optimized.

The invention provides a right content delivery strategy generation method and device based on AI big data, and relates to the technical field of strategy generation, and the right content delivery strategy generation method comprises the steps: obtaining user behavior data corresponding to a content platform type, so as to construct a corresponding target user portrait; dividing the to-be-put right and interest content into corresponding right and interest types according to content platform types; based on the target user portrait, analyzing preference degrees and response rates of user groups of the content platforms to different right and interest types; generating an adaptation relation matrix corresponding to the preference degree and the response rate; and distributing a corresponding right content type to each content platform according to the adaptation relation matrix, and determining a delivery frequency weight corresponding to each content platform. The cross-platform user portrait integration degree is improved, a right and platform dynamic matching mechanism is optimized, and the real-time adjustment capability of the delivery strategy is enhanced by constructing the cross-platform user portrait, dynamically generating the adaptation relation matrix and intelligently distributing the delivery strategy.

Action and / or process determination and recommendations for Robotic Process Automation (RPA) using semantic action graphs is disclosed. Semantic action graphs are graphs that store individual actions, and potentially graphical elements and / or text associated with the actions, as nodes, as well as the relationships between nodes as edges. Metadata to develop the semantic action graphs may be derived from task mining applications that can monitor the interactions of users with computing systems, workforce intelligence, etc. The semantic action graphs may be for a user, an organization, an industry, product-wide, etc. At their lowest level of granularity, the recommendations may be for mouse clicks, key presses, Application Programming Interface (API) calls, system events, etc. At higher levels of granularity, the recommendations may be for opening an order, creating a lead, approving a work item, etc.

The invention discloses an AI search recommendation method, system and device combined with commodity semantic understanding and a medium, and belongs to the technical field of commodity recommendation. The method comprises the steps that semantic vectors of commodity titles and descriptions are generated; generating a feature vector of the commodity image; fusing the semantic vector of the commodity title and description with the feature vector of the commodity image to generate a comprehensive semantic vector of the commodity; generating a user interest vector; updating the user interest vector by using a recurrent neural network based on the user interest vector; and carrying out joint modeling on the comprehensive semantic vector of the commodity and the updated user interest vector to generate a recommendation result. According to the method, a content semantic driving modeling mode is adopted, recommendation judgment can still be conducted through the deep matching relation between commodity image-text semantics and user behavior preferences even under the condition that user historical behaviors are limited or new commodities are online, good cold start adaptability is achieved, and the method is suitable for popularization and application. And meanwhile, high recommendation difference and content diversity are shown for different user groups.

The invention discloses a dynamic self-adaptive recommendation strategy optimization method for a business handling failure scene, and relates to the technical field of business handling recommendation and intelligent decision making, and the method comprises the steps: firstly collecting various types of data of a whole business handling process, and guaranteeing the integrity and real-time performance at a frequency of 100 milliseconds per time; a decision tree and Bayesian network fusion algorithm is used for attribution, and direct and indirect reasons are clarified; integrating data to construct a user portrait, and mining potential and subsequent demands; generating a recommendation scheme set based on attribution and portraits, and adjusting priorities and forms in combination with scene features; feedback data is introduced, a strategy weight is optimized by using a gradient descent algorithm, and the scheme is updated regularly; a multi-dimensional index weighted evaluation effect is set, and emergency optimization is carried out if the evaluation result does not reach the standard; and establishing a distributed strategy library, and reusing the optimal strategy of the similar scene by using a K-nearest neighbor algorithm. According to the method, failure reason accurate positioning and personalized recommendation are realized, the recommendation effect is continuously optimized along with data accumulation, and the method is adaptive to multiple service types and user groups.

The invention relates to the technical field of digital marketing, in particular to an intelligent marketing data analysis system and method. According to the invention, through deep analysis of the user interaction data, the user behavior offset is accurately identified, so that the marketing strategy can be dynamically adjusted, and the putting accuracy is improved. By means of the change trend of the residence time sequence, the relative change rate is calculated in combination with the access preference, user interest hotspot distribution information is effectively extracted, and the pertinence of content recommendation is improved. Based on access path stability analysis of interest hotspots, a stable mode of user behaviors is extracted, and an advertisement putting interval is optimized, so that user loss caused by frequent putting is reduced. And user groups with fluency decline or obvious jumping behaviors are screened by utilizing change calculation of interaction fluency, so that the advertisement pushing rhythm is reasonably adjusted, and the advertisement experience is improved. The user access data is synthesized to analyze the conversion change of the user behavior after the advertisement is displayed, and the influence of different advertisement intervals on the user behavior is accurately evaluated.

The invention relates to the technical field of data processing, and provides a social network privacy data protection method and system, and the method comprises the steps: obtaining to-be-encrypted privacy data, and obtaining a keyword popularity coefficient and a sensitivity weight coefficient according to the privacy data; acquiring behavior characteristics and basic information of a user group, and acquiring a group portrait index according to the behavior characteristics and the basic information; acquiring network behavior activeness, equipment characteristics and historical behavior information of the target user, and acquiring personal characteristics of the target user according to the network behavior activeness, the equipment characteristics and the historical behavior information; according to the keyword popularity coefficient, the sensitivity weight coefficient, the group portrait index and the personal characteristics of the target user, obtaining the encryption level of the privacy data; and calling different encryption algorithms to encrypt the privacy data according to the encryption level. According to the method, different encryption algorithms are called for encryption for the privacy data of different encryption levels, and the dynamic adaptability of encryption protection of the privacy data of the social network is improved.

The invention provides a grouping federal recommendation method based on bilateral additive article embedding. A central server constructs a double-layer article embedding characterization structure under a federated learning framework: a client locally maintains user personalized embedding and an article local personalized embedding matrix, and a server generates global group shared article embedding through a dynamic clustering grouping mechanism; superposing global sharing embedding and local personalized embedding by adopting an additive fusion strategy to generate user side personalized article characterization; a progressive course learning scheme is designed, and smooth transition from complete personalization to additive representation is realized by dynamically adjusting a regularization weight coefficient; and a grouping and clustering process is optimized in combination with a knowledge migration strategy, and collaborative knowledge sharing across user groups is promoted. In a client local training stage, a personalized recommendation loss function based on binary cross entropy is constructed, global shared embedding and local embedding parameters are synchronously updated, and a server side updates a global model through grouping federation aggregation. On the premise of protecting user privacy, the problems that in traditional federated recommendation, article characterization is simplified, and personalized perception is insufficient are effectively solved, the accuracy of a recommendation system is remarkably improved, communication overhead is reduced, and the method is suitable for personalized recommendation services of privacy sensitive scenes such as e-commerce and content platforms.

The invention discloses a method and system for independent application of multi-modal data after fusion and archiving, and relates to the technical field of archive management. The technical key points are as follows: establishing a service management platform, including a user group and an archive group, managing the user group and the archive group, defining an archive as a node by adopting a chain network structure, starting archiving management, generating an archiving package, and performing independent application between nodes, so that a user can quickly retrieve and position the archive; effective interaction between data is realized to a certain extent; state data of an archiving packet is processed through a target decision network, an archiving score is calculated, a corresponding archiving interval is matched according to the archiving score, different calling levels are correspondingly set, different users are endowed with corresponding permissions for management, and the whole system judges the management quality by designing evaluation factors, so that the management efficiency is improved. And the management efficiency is further improved.

The invention discloses an information access security system, equipment and medium based on an iterable trust policy, and relates to the technical field of information, and the system comprises the following steps: reading a configuration file and initializing trust thresholds of different user groups according to historical data; collecting multi-dimensional data of a user in real time, and preprocessing the multi-dimensional data; key features of the user are extracted from the preprocessed data, and a multi-factor trust evaluation model is constructed; based on a multi-factor trust evaluation model, the trust degree of the user is calculated, and a trust threshold value is dynamically adjusted; dynamically adjusting the access authority of the user according to the adjusted trust threshold; recording all operations of trust threshold adjustment and access permission change, and performing reexamination through user feedback; the trust degree of a user is calculated based on a multi-factor trust evaluation model, and a trust threshold value is dynamically adjusted. According to the method, the trust degree of the user can be accurately evaluated in real time, the real-time performance and accuracy of trust evaluation are improved, various security threats can be coped with in time, and the security and reliability of the system are improved.

The invention discloses a personalized content recommendation and ROI (Region of Interest) improvement method and system based on a multi-dimensional user portrait, and the method comprises the following steps: collecting user data, and generating the multi-dimensional portrait of a user through feature extraction and weighted fusion; taking the advertisement platform content feature vectors and the multi-dimensional portraits as nodes of a graph structure, taking the interactive behavior data of the users as edges of the graph structure, and constructing an association graph; analyzing the association map and the multi-dimensional portrait by using a causal reasoning model, and identifying invalid correlation variables and key variables which influence a user decision; carrying out recommendation decision making based on a causal reasoning result under a multi-objective optimization framework, and generating a personalized recommendation list of each user; and calculating potential conversion values of different user groups based on a time sequence prediction model, and optimizing an advertisement budget allocation strategy. According to the invention, the personalized degree of advertisement recommendation and the ROI of advertisement putting can be improved.