1161 results about "User group" patented technology

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 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 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.

A processor may gather raw data comprising a plurality of characteristic data samples of a target user group. The processor may categorize the characteristic data samples into a plurality of user-related classes and triggers. The processor may build an input property graph for each characteristic data sample. The processor may augment the input property graph by a concept of hierarchies. The processor may determine a modification vector from the augmented input property graph. The processor may train an encoder / decoder combination machine-learning system. An embedding vector and a modification vector are used as input for the decoder to build a trained machine-learning generative model.

The invention provides an intelligent message pushing method and system, and the method comprises the steps: collecting the social behavior data and personal attribute data of a user in a social network; dividing the users into a plurality of groups by using the social behavior data and the personal attribute data based on an ant colony algorithm; analyzing a social relation and an interaction mode among users in the group; collecting message resources in the social network, and classifying and labeling messages; performing collaborative filtering processing on the to-be-pushed message, determining a target user group, and generating a message recommendation list; and pushing the recommended message to users in the target user group according to a preset pushing strategy. The user social behavior data and the personal attribute data are converted into the ant feature vectors based on the ant colony algorithm, similar feature vector ants are gathered through pheromone updating and path selection mechanisms, different user groups are formed, the user group division accuracy is improved, and user requirements are more accurately grasped.

The invention relates to the technical field of machine learning, and discloses a user recharging prediction method and device, equipment and a storage medium, and the method comprises the steps: associating behavior data of multiple platforms of a user through an equipment fingerprint algorithm, obtaining a user multi-dimensional feature set, determining a clustering number based on an elbow rule, and obtaining a user recharging prediction result; and performing clustering analysis on the user multi-dimensional feature set according to the clustering number, generating a user value grouping label, and inputting the user value grouping label into a random forest model to obtain recharging prediction results of different user groups. According to the method, multi-platform user behavior information is comprehensively integrated through an equipment fingerprint algorithm, data islands are broken, user value grouping labels are generated through elbow rule clustering, then the user value grouping labels are input into a random forest model to predict a recharging result, user basic features are considered, value grouping information is integrated, feature dimensions are enriched, and the recharging efficiency is improved. And users with different values can be described more accurately, so that the accuracy of recharging prediction of user groups with different values is improved.

An ecommerce messaging system described herein comprises one or more ecommerce extension apps that interact with a messaging app. These embodiments leverage the extension core to manage session apps and smart services for using tap-to-message and tap-to-update processes to generate, update, and manage order workflows and in-app stores through branded messages communicated between customer and seller session apps to share message transcripts on devices of the same user groups via the messaging host, empower ecommerce with action-key-based communication, serialize-deserialize processes, and dynamic update propagation, manage return-refund workflows with temporary tables until one-time entity data model updates can be performed for session apps, and configure multi-store shopping systems on sellers' multiple devices using a store-as-a-service model to enable distributors to distribute production copies of assigned stores to authorized publishers to add custom promotions, which will be published together as production copies to their subscribed user groups for multi-store shopping and tracking.

Techniques for providing explicit proxy solutions for 5G Service Access Service Edge (SASE) with service provider network attach are disclosed. In some embodiments, a system, a process, and / or a computer program product for providing explicit proxy solutions for 5G SASE with service provider network attach includes receiving data plane traffic associated with a User Equipment (UE) from a mobile core network at a Secure Access Service Edge (SASE) cloud network via a service provider network attach using an interconnect between the mobile core network and the SASE cloud network; enforcing a security policy on data plane traffic associated with the UE based on contextual information associated with the UE to provide secured data plane traffic using the security policy configured per user group and / or per user; and forwarding the secured data plane traffic from the SASE cloud network to its original destination if allowed by the security policy, and blocking or dropping the data plane traffic from the SASE cloud network if not allowed by the security policy.

The invention relates to the technical field of online sales, and discloses a healthy retail supply chain optimization method and device and computer device.The method comprises the steps that multi-level semantic analysis is conducted on obtained text data through a natural language processing technology, and potential demand keywords of a user are extracted; constructing a user portrait based on the user potential demand keyword and the user behavior data; grouping the users based on a preset grouping standard and the user portraits in the health scene, screening corresponding required health products for different user groups, and optimizing and adjusting the required health products in combination with market trend data in the user behavior data to obtain an adjusted product selection pool; and calculating a matching degree between the user and a preset candidate social platform based on the user portrait and the product selection pool, and generating a social platform recommendation list based on the matching degree. According to the method, multi-source heterogeneous data are integrated, potential demands of users are mined by using a large model, a product selection pool is optimized, and accurate recommendation and personalized marketing are realized in combination with user portrait analysis.

The invention relates to a multi-dimensional user grouping matching method and device, equipment and a medium. The method comprises the following steps: firstly, acquiring real-time behavior data, consumption data, interest data, historical conversion data and social media data of a user group, and integrating to form a user feature data set; performing multi-dimensional data fusion and cross-dimensional correlation analysis on the data set to generate a user group feature set; the value weight of the user group is updated based on the feature set, grouping levels are divided in combination with service accuracy requirements, and a dynamic grouping mechanism is constructed; and finally, receiving bidding requests of the service providers, constructing a dynamic bidding model in combination with a dynamic grouping mechanism to calculate bidding scores of the service providers, sorting the service providers according to the scores, and generating an accurate matching result with the target user group. According to the method, the limitation of single-dimensional grouping is overcome, the timeliness and flexibility of grouping are improved, and the accuracy and efficiency of matching between the service provider and the target user group are effectively improved.

The invention discloses an anomaly detection method and system for transaction flow data, and relates to the technical field of big data analysis. The method comprises the following steps: based on transaction flow data, acquiring operation behavior data of a target user in a transaction process and interaction behavior data after the transaction is completed, and sorting according to timestamps to form a user operation behavior sequence and a user interaction behavior sequence; inputting the sequence into a pre-trained abnormal risk prediction model, and outputting an initial risk coefficient, wherein the model integrates an individual behavior baseline and an adaptive weight module; acquiring a group behavior baseline of the similar user group, and correcting the initial risk coefficient in combination with a matching result of the sequence and the group baseline to obtain a final risk coefficient; and performing classification abnormity early warning operation on the final risk coefficient based on a preset risk threshold. According to the method, through whole-process behavior sequence analysis, individual and group baseline dual calibration and dynamic weight adjustment, the accuracy and timeliness of transaction flow data anomaly detection are effectively improved.

An administrator of an organization may create access policies within an access request management system which define relationships between resources and request-and-approval flows. For example, the administrator may create an access policy, and the access policy may be applied across multiple resources of the organization. The access policy may indicate rules that indicate characteristics of a request-and-approval flow for granting access to the corresponding resources. For example, the rules may indicate a duration to grant access to the users, a group of users that are eligible to request the resource, approving users that provide approval to the requesting user, and information to collect from the requesting users, among other examples.

The invention provides a multi-modal emotion recognition fusion method based on a multi-head attention mechanism, and the method comprises the steps: carrying out the feature extraction and fusion of various data, capturing the internal relation of a modal through the multi-head attention mechanism, achieving the information complementation between modals through cross-modal interaction, and dynamically adjusting the weight according to the quality of the modals. And a self-built database containing a large amount of Chinese data is constructed, and a culture adaptation optimization strategy is combined, so that the generalization performance and culture adaptability of the model in Chinese user groups are improved. The system is deployed on a cloud server, optimized hardware and software configuration is adopted, efficient model reasoning and multi-user concurrent processing are achieved, and the large-scale real-time application requirement is met. The emotion of the user can be monitored in real time and early warning can be provided in scenes such as psychological counseling and group emotion monitoring, professionals are assisted in better understanding the emotion state of the user, and the service effect is improved.

The invention relates to the field of advertisement putting, and provides an advertisement putting management platform and a management terminal thereof, and the platform comprises an account management module which provides account registration and login for a user; the advertisement putting management module is used for providing advertisement putting setting for an advertiser; the advertisement creativity management module provides advertisement creativity for an advertiser and supports the user to upload or create the advertisement creativity; the audience orientation and marketing module collects and arranges user data, constructs a user portrait, and helps an advertiser to carry out audience orientation and accurately put an advertisement to a target user group according to the user portrait; and the data monitoring and effect evaluation module is used for collecting advertisement putting data for the put advertisement, creating a data report according to the advertisement putting data, and analyzing and evaluating the advertisement data. According to the technical scheme, the problem that the advertisement effect is difficult to improve due to the fact that an advertisement putting management platform cannot accurately position audiences in the prior art is solved.

The invention relates to the field of real-time translation, and provides a real-time duplex translation method based on multichannel parallel processing and a corresponding product, and the method comprises the steps: collecting multipath voice signals of at least two user groups in real time through a group of audio collection modules; dynamically adjusting beam forming parameters of each audio acquisition module in one group of audio acquisition modules based on a sound source positioning result, and feeding back the beam forming parameters to the corresponding audio acquisition modules; monitoring the voice activity of each audio acquisition module corresponding to each audio channel; when it is monitored that the voice activity of any audio channel reaches a preset condition, automatically activating the translation processing flow of the audio channel and keeping the monitoring state of the other audio channels; a parallel processing mechanism is adopted for voice signals of the activated audio channels, and meanwhile real-time translation of the currently activated audio channels and voice activity monitoring of the other audio channels are executed; and transmitting a translation result of the current speaking user to other users participating in dialogue in the user group to realize synchronous coordination of multichannel data.

The invention discloses a social group evaluation method and system based on double-space fusion calibration, and the method comprises the steps: firstly, extracting user preference features based on user-news interaction data and news type tags, constructing a fixed user portrait through employing a statistical analysis and maximum preference strategy, and completing the division of the user portrait; then, starting from the matching space, sorting the users in the matching space through joint sorting of the behavior activeness and the behavior coupling degree; meanwhile, starting from a semantic space, generating a portrait semantic expression by utilizing a large language model, generating a semantic center point in combination with user behaviors, and sorting the users in the semantic space based on a vector distance; on this basis, the sorting information of the matching space and the semantic space is fused, the semantic consistency and the behavioral representativeness of the users are balanced, and finally the user groups with comprehensive representativeness under each type of portraits are screened out; further, based on the high-frequency behavior record and portrait features of the representative user, constructing an injection simulation behavior sequence, selecting low-interaction news items, and generating an evaluation sample with interference features; and finally, retraining a recommendation model, evaluating recommendation response change of each portrait group on low-interaction information, and quantifying anti-interference scores of the system under different portrait consistency conditions, thereby revealing robustness difference of the recommendation system, and providing support for security enhancement and portrait recognition. According to the method, the performance difference and the anti-interference capability of different user portrait groups in a recommendation system can be described.

The invention discloses a CNN and Informer fused high-risk user loss early warning and retention method and system, and belongs to the technical field of big data, and the method comprises the steps: obtaining the multi-source data of each user, and constructing the static features, daily dynamic features, and a time sequence feature matrix of a set time period of the user through the multi-source data; constructing a CNN and Informer fused deep learning model, and predicting the loss probability of the user by using the trained deep learning model based on the static features and daily dynamic features of the user and the time sequence feature matrix of the time period set by the user; constructing an RFL model, and obtaining a user value score by using the RFL model and the multi-source data; and in combination with the value scores and loss probabilities of all the users, grouping all the users by using a Kmenas model, outputting user grouping results and grouping portraits, and performing early warning and retention. According to the method, potential high-risk lost users can be accurately identified, and the retention cost is reduced.

The invention relates to the technical field of power consumption behavior analysis and intelligent auditing of power consumers, and discloses an auditing rule threshold dynamic recommendation method, system and device based on feature mapping and a medium, and the method comprises the steps: integrating multi-source data of a user, and generating a comprehensive feature vector through a multi-modal fusion network; then, performing group division on the users according to feature similarity under a federated learning framework; using a time sequence generative adversarial network to generate enhanced power consumption data for each user group so as to improve model robustness; training a threshold dynamic adjustment strategy network in combination with reinforcement learning and causal reasoning, and outputting an initial recommendation threshold; the optimal balance threshold set between the false alarm rate and the missing report rate is searched through multi-target Bayesian optimization, and diversified choices are provided for decision making. According to the method, the leap from automation to intellectualization and from single-point optimization to multi-target collaborative decision making is realized, and the accuracy of auditing efficiency and the scientificity of decision making are remarkably improved.

Automatic detection and handling of security-related anomalies by utilizing machine learning and a large language model (LLM). A computerized method for detecting and handling security threats in an organizational network of an organization includes: (a) collecting event data that pertain to organizational users, organizational devices, and organizational resources of the organizational network; (b) constructing user profiles, device profiles, and resource profiles; (c) constructing Organizational Context information that pertains to organizational users, organizational devices, and organizational resources; (d) constructing a time-series of events, enriched with the Organizational Context information; (e) analyzing the time-series of events using a Machine Learning process that detects an anomalous event, and automatically generating an alert message pertaining to and describing the anomalous event.

The invention provides an e-commerce platform order analysis method and system based on data mining, and relates to the technical field of information, and the method comprises the steps: carrying out the grouping of user groups according to the user size judgment accuracy and user behavior tracks, and recognizing the seasonal size selection rule of each group of user groups through analyzing the purchase preference changes of different seasons; the category preference and the size selection habit of the user are analyzed according to the return frequency and the size jump amplitude, potential size selection preference is determined, and a preliminary recommendation list is generated; obtaining size system comparison information of the current commodity category from the preliminary recommendation list, and determining a personalized size recommendation sequence by comparing historical selection records of a user; and if it is identified that switching frequency characteristics similar to the high-deviation group exist in the personalized size recommendation sequence, generating a final size recommendation result by integrating inventory turnover speed constraint conditions.

The invention relates to the technical field of data management, in particular to a cross-platform advertisement putting and SEO collaborative optimization system which comprises a resource time sequence scheduling module, a keyword screening module, a putting path construction module, a data conflict comparison module and a content archiving and auditing module. According to the invention, through association mining of multi-platform advertisement data and user behaviors, real-time mapping of time sequence distribution of put resources and user group states, and dynamic integration of budget weights and audience portraits in a keyword selection process, a multi-parameter interactive screening mechanism is formed for advertisement paths; text similarity judgment and conflict source tracing are synchronously introduced into channel content, an archiving standard is jointly defined by content change frequency and source credibility, data in each link automatically adjusts an attribution boundary according to a change trend, multi-source data validity is accurately distinguished in an archiving process, and structure-level linkage is realized by advertisement circulation, content integration, path adaptation and conflict detection. And the consistency and uniqueness of data updating and archiving are guaranteed.

The invention provides a personalized image content generation and optimization method and system fusing generative AI, and relates to the technical field of AI. The personalized image content generation and optimization method comprises the steps of analyzing a historical interaction track and a current intention expression of a target user based on a deep perception network, and constructing a multi-dimensional behavior portrait; user groups with similar generation preferences are identified by using a group feature recursive quantization technology, and a group wisdom feature map is constructed; performing multi-level mapping analysis on the user features and the group wisdom feature map, anchoring the group affiliation relationship of the target user and concretizing the guide features; constructing a multi-level guide vector according to current intention expression and guide features, performing accurate mapping on hidden space expression of an image generation model, quantizing deviation in real time and triggering intelligent calibration; and reconstructing a group distribution structure based on the evaluation data of the target user to realize dynamic evolution of the features. According to the invention, personalized demands of users can be accurately grasped, and the accuracy of image generation and the satisfaction degree of the users are improved.

The invention relates to the technical field of marketing data analysis, and discloses a marketing analysis control method and system. The method comprises the steps of collecting multi-dimensional interaction data of a target user group; performing time sequence alignment processing on the multi-dimensional interaction data, eliminating asynchronous interference caused by acquisition time offset, and generating a synchronization behavior matrix; potential mode mining is carried out based on the synchronization behavior matrix, behavior clusters with relevance are recognized, and each behavior cluster corresponds to one user decision mode; constructing a dynamic weight model according to the user decision-making mode, calculating the contribution degree weight of the data of each dimension in the current marketing scene, and updating the model by adopting an incremental learning mechanism in combination with real-time feedback data; establishing a marketing strategy mapping table, and selecting an adaptive strategy group according to a current optimal weight combination output by the model; when the strategy is executed, a responsivity index is monitored synchronously, if the responsivity index is lower than a dynamic threshold value, re-matching is triggered, incremental data is fed back to a potential mode mining link, and a closed-loop optimization mechanism is formed.

The invention discloses an intelligent delivery targeted penetration decision-making method for precision marketing, particularly relates to the technical field of intelligent delivery targeted penetration decision-making, and comprehensively identifies potential anomalies through unified processing of a standardized index set and dynamic association construction of multi-level thresholds; by means of the constraint of a delivery strategy oscillation index on a delivery behavior, dynamic bidding, material optimization and flow distribution can be smoothly adjusted in a fluctuating environment, the controllability of budget consumption and the continuity of a delivery effect are ensured, and a multi-dimensional penetration strategy of competition, scenes, crowds and materials is combined, so that the delivery efficiency is improved. According to the method, high-value user groups are more accurately reached, the material matching degree is improved, the return on investment and the conversion rate are stably kept increased, oscillation and resource waste in the putting process are reduced, and the cross-platform collaborative optimization capability and the risk prevention and control level are improved.

The invention relates to the technical field of artificial intelligence, in particular to a verbal skill confrontation training generation method and device based on a large model, equipment and a storage medium, and the method comprises the steps: generating a simulation inquiry based on a preset user portrait, then obtaining a response of a service large model, and comprehensively evaluating the response quality; and the specific defect type of the service model in logic understanding or verbal skill expression is diagnosed through the cognitive deviation between the response and the user expectation by another evaluation model, so that a targeted optimization strategy is generated, the service model is finally driven to carry out directional reinforcement learning, and the verbal skill ability of the large service model is iteratively improved. According to the method, an adversarial sample is dynamically generated, and deep diagnosis is carried out in combination with cognitive deviation, so that a service model can understand deep intentions and emotion demands of different user groups fundamentally. Therefore, the strain capacity and the communication accuracy of the service model in a real interaction scene are remarkably improved, and the user satisfaction is effectively improved.

The invention discloses a resource recommendation method and device based on an assembly platform in the oil and gas field, and the method comprises the steps: searching a user semantic vector and a scene semantic vector from a vector database after a resource recommendation instruction triggered by a user in a business scene is received, and taking the user semantic vector and the scene semantic vector as query semantic vectors; searching a resource semantic vector of which the correlation degree with each query semantic vector is greater than a correlation threshold value from a vector database; the searched resource semantic vectors are reordered, and a reordering result is filtered; obtaining resources used by similar user groups in the service scene; according to the sorted resource semantic vectors and the resources used by the similar user groups, sorting scores and clustering coverage rates of all the resources are obtained on the basis of a fine sorting large model, the sorting scores of the resources are adjusted on the basis of the clustering coverage rates, and the fine sorting large model is constructed on the basis of a deep neural network; and generating a resource recommendation list according to the sorting scores of all the resources. The method is high in recommendation accuracy and high in practicability.

The invention relates to the technical field of advertisement putting, in particular to an advertisement putting method, system and device based on a retail cabinet and a medium. Behavior data such as user purchase records, residence time and commodity attention are collected through a sensor and a transaction system of a retail cabinet, user consumption ability and shopping preference characteristics are analyzed and extracted by using a deep learning algorithm, and a user portrait model is constructed; the system intelligently matches the user portrait with an advertisement content library, selects the most suitable advertisement content for delivery, and continuously collects effect data such as user watching duration, interaction times and purchase behaviors; based on the feedback data, the system automatically adjusts advertising strategies such as advertisement display time and target user groups. According to the invention, accurate matching between the advertisement content and the user demand is realized, a closed-loop optimization mechanism of advertisement putting is established, and the putting effect is improved.

The invention belongs to the technical field of intelligent household appliances, and particularly relates to a control method and equipment of water purification equipment and a storage medium. The method comprises the steps that human physiological data of a target user is obtained through cloud equipment, the cloud equipment classifies the target user based on the human physiological data, and the cloud equipment determines a water purification scheme for the target user based on the classification of the target user and the human physiological data of the target user, the cloud equipment sends the water purification scheme to water purification equipment, and the water purification equipment adjusts the water purification equipment based on the water purification scheme and a raw water detection result; according to the method, the water quality of the water purification equipment is adjusted according to the intake requirements of different types of user groups on trace elements, the intelligence of the water purification equipment is improved, and the user experience is improved.

The invention discloses an attribute-based access control method for realizing puncture revocation and outsourcing decryption under multiple authorizations, which is characterized in that a certificate issuing mechanism is responsible for initialization of a system and registration of an attribute issuing mechanism and a user, and the attribute issuing mechanism manages part of attributes authorized by the attribute issuing mechanism and generates a conversion key of an agency for outsourcing decryption; the data owner encrypts the data by using attribute-based encryption according to the defined access structure and the label structure; and the proxy server converts the access strategy formulated by the data owner into a puncture strategy and then punctures the conversion key so as to cancel the specified user group. According to the method, puncture revocation and outsourcing decryption attribute-based access control under a multi-authorization mechanism can be realized, and a feasible method is provided for lightweight and fine-grained user revocation under the multi-authorization mechanism.