388 results about "Preference data" patented technology

The invention relates to the technical field of information, and discloses an enterprise employee welfare gift bag automatic generation method, and the method comprises the following steps: S1, firstly providing a welfare management system for employees, and enabling the employees to log in the system to browse and autonomously purchase welfare products; s2, processing the collected employee preference data by using a data analysis algorithm; s3, an enterprise administrator sets welfare gift bag generation rules through a system interface; s4, according to the preference model of the employee and the rule set by the enterprise, screening out the commodity meeting the condition from the commodity library; s5, notification reminding is sent to the employees through the enterprise internal platform; and S6, the employee can adjust the commodity in the rule range, and evaluation and feedback are carried out on the gift bag. By collecting the preference data of the employees and analyzing and processing the data, the requirements of the employees are accurately judged, personalized customization of welfare gift bags is achieved, and the satisfaction degree of the employees to welfare is improved.

The invention provides a large model preference alignment method improved by using an online synchronization strategy, a new preference alignment process is provided based on a synchronization strategy optimization and online learning method, transformation is carried out from a training process, links such as synchronous sampling and online parameter updating are added, and the optimization of the large model preference alignment is realized. Reward model updating and data distribution alignment in the model training process are achieved, and finally the financial question and answer ability is effectively improved. On the basis of keeping the high efficiency of the original method, the distribution difference between the strategies can be effectively reduced, the optimization direction of the optimal strategy is ensured, meanwhile, the supervision information of preference data is updated approximately in real time, the reliability of the reward model in the high reward system is enhanced, the human preferences are better aligned, and the method is suitable for popularization and application. Therefore, the reliability and generalization in the financial service field are ensured.

The invention relates to the technical field of data recommendation, in particular to an AI-based multi-platform media content optimization recommendation method and system. The method comprises the following steps: acquiring user equipment parameters and user platform behavior data; user preferences are confirmed based on the user platform behavior data, and user platform preference data are obtained; analyzing the hardware performance of the equipment used by the user according to the parameters of the user equipment, grading, and generating an equipment suitability matrix according to a grading result; performing user active period extraction on the user platform preference data to obtain user active period feature data; performing content loading time consumption analysis on the equipment suitability matrix to generate equipment time consumption data; and extracting format adaptation parameters of the to-be-recommended content based on a preset cross-platform content feature library. According to the method, the compatibility and the response speed of cross-platform media content recommendation are improved by comprehensively considering the user preference, the equipment performance, the time period activeness, the content adaptability and the network fluctuation.

The invention discloses an advertisement putting strategy optimization method and system based on preference data collaboration, and relates to the technical field of advertisement putting, and the method comprises the steps: collecting the internal user data of a local advertisement putting platform, obtaining the external user data of a third-party platform through a safety data interface, carrying out the integration and preprocessing of the data, and obtaining an advertisement putting strategy; extracting explicit preference data and implicit preference data; a user-advertisement scoring matrix is constructed based on the preference data, and user preference vectors are generated after decomposition; acquiring copywriting text, image and category information of an advertisement to be put, constructing an advertisement feature expression model and generating an advertisement feature vector; calculating a matching degree score based on the user preference vector and the advertisement characteristic vector, and dynamically optimizing an advertisement putting strategy according to the score; according to the method, through comprehensive utilization of explicit and implicit preferences of the user, more accurate user interest modeling and advertisement matching are realized, and the advertisement putting effect and putting efficiency are effectively improved.

The invention relates to the technical field of video generation, in particular to an intelligent commodity video generation method based on multi-modal analysis and a dynamic narrative architecture, which comprises the following steps: inputting original commodity data and a user behavior log, and outputting a dynamic selling point weight vector through a selling point value evaluation engine; s2, inputting the dynamic selling point weight vector output in S1 into a narrative flow generator, and executing the following steps: intercepting first K core selling points according to the weight vector to form a narrative trunk chain; based on the historical preference data of the user, inserting an emotion enhancement node to generate a branch enhancement narrative flow; generating a multi-version narrative flow instruction set in combination with the real-time network bandwidth data; retrieving a preset video clip library according to the instruction set to generate an initial video sequence; detecting semantic fault regions between adjacent segments to generate compensation animation parameters; and injecting compensation animation parameters and outputting a continuous narrative video stream. According to the invention, the jamming feeling and the frame skipping phenomenon caused by the change of a narrative structure or different sources of video clips are reduced, and the overall watching experience of a user is improved.

Apparatuses, systems, and methods to provider personalized online product fitting are disclosed. In a variety of embodiments, personalized shopping systems include an automated shopping assistant accessing product data, a matchmaking system accessing history data, preference data, and / or anatomical data measured using an automated shopping assistant apparatus, where the personalized shopping system can generate a personalized match based on the history data, preference data, and / or anatomical data. The automated shopping assistant apparatus may include depth sensors and / or image scanners which can capture a variety of 2D and / or 3D models. These models can be utilized to generate anatomical data. The anatomical data can be used to virtually try on a variety of items. Products may be personalized based on the history data, preference data, and / or anatomical data.

The invention discloses an intelligent parking method and device based on multi-source data fusion and a medium, and relates to the technical field of big data technologies. The method comprises the following steps: collecting multi-source parking data, and analyzing the multi-source parking data to generate a parking lot label library; generating a user tag based on historical search records and residence time preferences of the user, and constructing a user information database; when it is detected that a user triggers a parking request, performing multi-dimensional matching calculation on a user tag and a parking lot tag library to obtain a recommended parking space sequence; and optimizing the recommended parking space sequence based on the real-time traffic state and the user credit score to generate a final navigation path. According to the method, a dynamic parking recommendation mechanism is constructed by collecting and analyzing the multi-source parking data and the user preference data.

The invention relates to a costume design system and method based on multi-modal AIGC and a storage medium thereof. Comprising a multi-source input processing module used for receiving and processing multiple modal inputs including costume design text description, a costume style drawing, a fabric sample image and user preference data; the clothing feature extraction module is used for extracting clothing structure features and visual style features from the multi-source input; the semantic understanding module is used for carrying out semantic understanding and style analysis on the clothing features; the multi-modal fusion module is used for mapping the clothing feature representations of different modals to a unified semantic space and generating a fusion feature vector; and the style migration module is used for realizing design generation of a specific style based on a small number of garment samples through a LoRA low-rank adaptation technology, and is used for generating a garment design drawing through a multi-stage conditional diffusion model based on the fusion feature vector.

The invention relates to the technical field of artificial intelligence, in particular to an intelligent content evaluation and optimization method and system based on multi-standard preference learning, and the method comprises the steps: constructing target user preference data, and generating an evaluation track containing evaluation rules and judgment results; based on the evaluation trajectory, screening samples and distributing credits through sorting and consistency rules to obtain preference pair training data; jointly training a generative reward model by adopting response supervision fine tuning and a direct preference optimization strategy; recombining the original evaluation trajectory into alternate accepting and rejecting samples, forming long thinking chain training data, and further training to obtain a final model; and evaluating and optimizing the alignment degree of the generated text and the user preference through the final model. According to the method, through multi-stage optimization and process supervision, the alignment degree and the overall performance of the language model and human preference are improved, the problems of composite errors, data sparseness and the like of a traditional reward model are solved, and the method is excellent in performance in out-of-distribution evaluation.

The invention provides a preference learning method which can be applied to the technical field of artificial intelligence. The preference learning method comprises the steps that sample questions matched with preset standards are determined from a text document pre-trained by a large model, the preset standards comprise a forward standard and a reverse standard, and the sample questions are used for representing questions generated when a user interacts with the large model; inputting the plurality of sample questions into a large model to generate a plurality of question and answer pairs according to answers corresponding to the sample questions output by the large model; evaluating answers in each question and answer pair based on a forward standard by using a plurality of evaluation models to obtain an evaluation label corresponding to each question and answer pair; and training the large model by using preference data generated based on the evaluation label to obtain a target model aligned with the forward standard. The invention further provides a model application method, a preference learning device, equipment, a storage medium and a program product.

The invention provides a reward model training method and device, a strategy model training method and device, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence, and the method comprises the steps: obtaining a preference data pair which comprises a preferred response and a non-preferred response generated for the same prompt word, and each of the preferred response and the non-preferred response is composed of a plurality of text unit sequences; inputting each text unit sequence into a to-be-trained reward model to obtain a predicted reward value; and calculating the total training loss according to the predicted reward value, and updating the model parameters of the to-be-trained reward model. According to the method, the response text is subjected to serialized splitting, and the preference data composed of the preferred response and the non-preferred response is introduced for comparative learning, so that the target of model training is no longer to evaluate the absolute quality of a single response, but to identify a key text unit which causes one response to be superior to the other response; the fine-grained evaluation of the response content is realized, and the evaluation accuracy of the reward model and the identification capability of complex user preferences are effectively improved.

The invention relates to the technical field of business propaganda and pushing, in particular to a telecommunication business propaganda and pushing method based on artificial intelligence. Comprising the following steps: S1, collecting behavior data, preference data and telecommunication service data of a user, and sending the collected data to a database for storage; s2, obtaining a push value of a telecommunication service product through multi-dimensional analysis of the user information and the telecommunication service product information; s3, performing comprehensive analysis on the user active time, the login frequency and the response behavior to realize accurate pushing of related telecommunication services; s4, obtaining real-time feedback of the user to the pushed content by providing a user feedback entrance; through analysis of the time period and the activity degree, pushing is carried out at the active time of the user, the opening rate and the click rate of pushing are improved, the pushing frequency and the pushing interval are adjusted, and excessive interference to the user is avoided; the invalid pushing frequency is reduced, pushing in a low-response-rate channel and an inactive time period is avoided, and resource use is optimized.

The invention discloses a healthy drink recommendation system based on artificial intelligence, and relates to the technical field of health preservation and health, and the healthy drink recommendation system based on artificial intelligence comprises a central control module, a data acquisition module, a data processing module, a recommendation generation module and a user feedback module. According to the system, the body data, the beverage preference data and the environment data of the user are obtained through the data acquisition module, the extracted data are processed through the data processing module, the beverage features are matched with the user requirements through the recommendation generation module, the recommendation list is generated, the recommendation result is displayed through an interaction interface in the user feedback module, and the user experience is improved. According to the method, the user can conveniently select proper beverage supplies according to the body health condition of the user, the problems that in the prior art, functional component analysis in a beverage recommendation scene is insufficient, and drinking time and drinking frequency are not fully considered are solved, and the accuracy and adaptability of a recommendation result are enhanced.

The invention discloses an AI system for generating customized contents based on user preferences, which belongs to the technical field of artificial intelligence, and comprises a user preference modeling module for constructing and continuously updating a user feature vector library and realizing personalized demand modeling and classification; the interactive input and early warning module is used for receiving user input, implementing risk control and providing a visual interactive correction tool; an intelligent parameter conversion module; a video preprocessing and enhancing module; a cross-modal semantic generation module; the dynamic training and optimizing module is used for controlling a model training process and balancing repair quality and style migration; the multi-version generation and evaluation module is used for outputting a differentiated repair result and quantitatively evaluating the performance; the feedback learning and iteration module is used for collecting user preference data and driving the system to continuously optimize; and a distributed task scheduling module. According to the method, the real-time performance and accuracy of the user portrait are ensured through the layered modeling mode, accurate matching of personalized content generation is supported, and user experience and content recommendation are effectively improved.

An apparatus for generation of an integrated data file, wherein the apparatus includes at least a processor and a memory communicatively connected to the at least a processor, the memory containing instructions configuring the at least a processor to receive content data from a user, receive preference data from the user as a function of receipt of the content data, create a plurality of templates as a function of the preference data and the content data, receive user feedback associated with the plurality of templates, generate one or more updated templates as function of the user feedback and the plurality of templates, generate an integrated data file as a function of one or more updated templates and transmit the integrated data file to one or more content producers.

The invention relates to the technical field of user personalized content pushing, in particular to a user personalized content pushing system based on big data and a promotion method. The method comprises the following steps: collecting user behavior and preference data through multiple channels; dynamically constructing user portraits, and enriching the user portraits in combination with multi-dimensional data; based on user portraits and content features, a recommendation model is constructed by using a deep neural network, and user preferences are accurately predicted through multiple hidden layers; through a push model and a multi-objective optimization method, the probability of pushed content is calculated in combination with indexes such as a click rate and a conversion rate, the push frequency and content selection are optimized, and the correlation of the pushed content and the user satisfaction are ensured; by monitoring user feedback in real time and adjusting a pushing strategy, intelligent decision and personalized recommendation of content pushing are realized, and long-term accurate pushing and improvement of user experience are ensured. According to the method, the accurate user portrait is constructed through multi-data source collection and processing, so that personalized content pushing is realized.

The invention provides an electronic book data pushing method, device and equipment, belongs to the technical field of computer information processing, and solves the problem that a recommendation result is inaccurate when books are recommended to a user. The method comprises the following steps: acquiring log data and book feature data; processing the log data to obtain user preference data; processing the user preference data and the book feature data to obtain book pushing data; and sending the book pushing data to a client. According to the scheme, dynamic tracking and attenuation processing of user preferences are achieved, and the effect of recommending and displaying books to users in a personalized mode is achieved.

The invention discloses a music intelligent recommendation and music data sharing method and system, and particularly relates to the technical field of music recommendation. Music playing data, search data and user interaction data of a user on a plurality of music platforms are integrated, a global music preference model is constructed, a personalized recommendation list is generated in real time, the recommendation accuracy is dynamically evaluated and optimized, and through a safe and efficient data sharing and migration mechanism, the user experience is improved. Sharing the music preference data of the user among different platforms; meanwhile, the synchronization efficiency and the network stability in the data transmission process are analyzed through fuzzy logic, the safety and the stability of data sharing are ensured, the problems that scattered data are difficult to integrate, recommendation is not accurate and data sharing is not safe are effectively solved, and the accuracy and the user experience of the music recommendation system are remarkably improved.

The invention discloses a biochemical experiment automation script training generation method based on RAG and DPO. The method comprises the steps that biochemical experiment technical documents are collected to serve as an external knowledge base; the BM25 and the Fiss are fused to construct a hybrid retriever; generating experimental process description by using a large language model, determining equipment, protocols and materials, and retrieving related documents from a knowledge base on the basis of the experimental process description, the protocols and the materials; generating an experiment script based on a retrieval result, and performing platform simulation verification, and performing iterative optimization on the script which fails in verification; marking successful and failed scripts as preference data pairs, and constructing a training set; carrying out LoRA fine tuning on a local large language model by adopting direct preference optimization; and according to a target and appliance prompt input by a user, generating a verified experiment script by using the large language model after direct preference optimization training. According to the method, the script generation automation level and the passing rate are remarkably improved, the manual intervention cost is reduced, and an efficient solution is provided for automation of biochemical experiments.

The invention belongs to the technical field of intelligent control, and discloses an energy optimization management system and method for hotel guest rooms, and the system comprises a central data pool unit which constructs a time sequence database cluster, and carries out the uploading and interaction of data between all units through a data bus; the existence sensing unit is used for integrating multiple sensors by adopting a sensing layer architecture to form a sensing network, capturing existence sensing data and generating a room existence state map based on the existence sensing data; the existence sensing data comprises guest room reservation information data, guest room environment data and guest information data; the partition environment control unit is used for obtaining customer preference data by analyzing a room existence state map; based on the guest preference data and the guest room environment data, selectively activating environment control of different guest room areas by adopting an intelligent optimization algorithm; and the hotel energy utilization rate and customer satisfaction are improved.

A digital promotion processing system may include a shopper device associated with a given shopper, and a promotion processing server. The promotion processing server may be configured to determine available digital promotions for a given product for purchase, each available digital promotion having different redemption terms. The promotion processing server may also be configured to cooperate with the shopper device to prompt the shopper to select one of the available digital promotions to apply toward purchase of the given product, store shopper promotion terms preference data based upon the selected digital promotion, and update the shopper promotion terms preference data based upon a plurality of new selections of available digital promotions. The promotion processing server may further be configured to generate and communicate a personalized digital promotion to the shopper device. The personalized digital promotion may have redemption terms based upon the updated shopper promotion terms preference data.

The present disclosure provides a system for generating artist-governed merchandise derivative works, comprising at least one processor and memory storing instructions that, when executed, cause the system to receive a request associated with source content and a transformation theme for creating a merchandise derivative work, evaluate the request against pre-generation preference data associated with a content authority using a knowledge agent maintaining brand guidelines, generate the merchandise derivative work from the source content according to the transformation theme by applying a generative artificial-intelligence model through an action agent, perform post-generation validation against the brand guidelines, generate a digital identifier based on the merchandise derivative work, and enable distribution through a physical merchandise path for tangible products or a virtual merchandise path for digital assets.

The invention provides a remote internet-of-things control system and control method for home equipment, and the method comprises the steps: obtaining the operation data, environment data and user operation data of each piece of home equipment in a home system through a data obtaining module, and carrying out the edge calculation of the data; and online learning is carried out according to the processed data by adopting a deep reinforcement learning method through an instruction generation module, and an equipment control instruction set is constructed. The instruction verification module verifies the feasibility of each instruction in the equipment control instruction set through the preset virtual twin model based on the historical fault data and the user preference data corresponding to the home system, determines the initial control instruction set, and avoids the problem of equipment misoperation. The network state is monitored in real time through the network self-adaptive transmission module, a transmission path is dynamically adjusted according to factors such as network delay and packet loss rate, and it is ensured that a control instruction can be timely and accurately transmitted to home equipment. The instruction transmission delay or loss caused by network problems is avoided, and the user experience is improved.

Devices, systems and process for automated event ticketing are disclosed. A system includes: a user device having a data store and a processor coupled to the data store; a set top box (“STB”), coupled to the user device, having an STB data store and an STB processor; and at least one event server, coupled to the STB providing event data and event ticketing data for a plurality of events. Based on user preference data received from the user device, the STB processor searches the plurality of events for a given event which matches, at least in part, the user preference data, and when instructed by the STB, the event ticketing engine facilitates ticketing of the given user to the given event. When executed, first computer instructions instantiate a content application that performs content monitoring and user preferencing, and based on the foregoing generates user preference data.

The invention relates to the technical field of finance, and provides a time series data prediction method and system based on an auto-reflection mechanism large language model, and the method comprises the steps: firstly collecting structured transaction data and public unstructured text information in a preset historical time window, inputting a first large language model, and generating structured market background information in combination with a preset cue word; inputting the data and preset risk preference data into a second large language model to generate first causal reasoning training data; and inputting a third language model for reflection correction, checking whether the argument can be verified in the background information, and if so, reserving and strengthening to obtain second causal reasoning training data. And constructing a prediction large language model, optimizing parameters by means of a group relative strategy optimization algorithm, and then outputting the parameters. The system and the method depend on an auto-reflection mechanism, the model considers risk preferences in financial time sequence prediction to generate various risk strategies, manual annotation dependence is greatly reduced, the cost is reduced, and the risk preference module is independent and configurable and can be flexibly expanded.

The invention provides an optimization method, an interaction method and a system of a large language model. The optimization method comprises the steps that a preference data set is obtained, the preference data set comprises a plurality of preference pairs, one preference pair comprises question samples, preference answer samples and non-preference answer samples, the preference answer samples and the non-preference answer samples correspond to the question samples, and dynamic target reward difference values corresponding to all the preference pairs are determined, the dynamic target reward difference values corresponding to the at least two preference pairs are different, the large language model is optimized according to the dynamic target reward difference values, an optimized large language model is obtained, and the optimized large language model is used for determining a target answer meeting the preference of the target user according to the obtained target question of the target user. The optimized large language model not only can well distinguish preference answers from non-preference answers, but also can be finely adjusted according to different preference intensities, so that the personalized requirements of target users can be better met in practical application.

Devices, systems and process for automated event ticketing are disclosed. A system includes: a user device having a data store and a processor coupled to the data store; a set top box (“STB”), coupled to the user device, having an STB data store and an STB processor; and at least one event server, coupled to the STB providing event data and event ticketing data for a plurality of events. Based on user preference data received from the user device, the STB processor searches the plurality of events for a given event which matches, at least in part, the user preference data, and when instructed by the STB, the event ticketing engine facilitates ticketing of the given user to the given event. When executed, first computer instructions instantiate a content application that performs content monitoring and user preferencing, and based on the foregoing generates user preference data.

The invention discloses a direct preference optimization-based large model post-alignment training method and system. The method comprises the following steps of: (1) constructing a static reference model and a strategy model; (2) optimizing preference data by using an implicit reference model, and (3) adjusting a strategy model by optimizing an objective function so that the strategy model better fits the user preference. According to the method, the limitation of the existing DPO and SimPO methods is solved by introducing a new reference model expression, for example, the method depends on a suboptimal reference model or uses a fixed reward margin. By adjusting the balance between the strategy model and the reference model, personalized reference model setting for each pair of responses is realized, and meanwhile, a theoretical guarantee is provided and the KL divergence is effectively controlled. And the alignment performance and the winning rate of the model are remarkably improved, and the method is a robust LLM fine tuning method.

The invention provides an end-to-end large model fine tuning method and system based on retrieval enhancement generation. The method comprises the steps that text information of historical questions of a user is read; performing deep semantic extraction on the text information by utilizing a semantic extraction module of the word segmentation device model to obtain key semantic output; the encoded semantic vector is obtained from the database, the deep semantic information is encoded by using the BGE retrieval model and the M3E vector model, similar information is recalled, and the two paths of recalled vector semantic information are combined; respectively calculating KL divergences of the deep semantic information vector and the text information vector with a target vector in a semantic space, and selecting and inputting the deep semantic information vector and the text information vector with relatively low cost into an examination module; and training the model according to the preference data by using a DPO algorithm to obtain a model conforming to human preferences. The fine-tuned model obtained through the method does not need to be preprocessed in the reasoning process, and the problems of model illusion, toxicity and the like caused by inaccurate retrieval are solved.

The invention discloses a document travel scene data transaction secure storage method and a medium. The method comprises the following steps: collecting necessary data of a data provider through a client of a document travel transaction platform; encrypting the sensitive data, and uploading the encrypted sensitive data, the privacy preference data of the data provider and the information of the data visitor to a server side of the text travel transaction platform; packaging the encrypted sensitive data, the privacy preference data and the data visitor information into a structured privacy tuple; storing the privacy tuple in a relational database, and storing the hash value of the privacy tuple in a block chain; configuring an access control strategy, and limiting that only authorized users or system nodes can access and operate data stored in the relational database; the access request of the privacy tuple data is verified and authorized through the block chain platform, and all data accesses are ensured to conform to the privacy preference of a data provider. According to the invention, the security of the user sensitive data in the text travel scene data transaction can be effectively improved.