171 results about "Preference data" patented technology

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 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 relates to the technical field of internet advertisement marketing, in particular to an internet advertisement marketing method and system based on artificial intelligence, and the method comprises the steps: integrating the browsing history, demographic information and behavior preference data of a user, generating a dynamic user portrait, and predicting a user demand; generating personalized advertisement creative content based on the user portrait and the predicted user demand; performing multi-dimensional automatic violation review on the advertisement creative content, and performing originality verification on the advertisement creative content passing the violation review; based on the dynamic user portraits and the advertisement putting targets, advertisement creative contents passing violation review and originality verification are accurately pushed; according to the method, the advertisement can be automatically examined before the advertisement is put, so that the examination efficiency is improved, the compliance risk caused by omission due to manual detection and the brand reputation loss caused by the compliance risk are reduced, and the advertisement marketing effect can be improved.

The invention discloses a cross-language migration-based low-resource programming language corpus enhancement method, which comprises the following steps of: receiving a source language code, and driving a large language model to generate an initial target language code through a two-way retrieval mechanism fusing example guidance and knowledge constraint; secondly, constructing an automatic iterative repair closed loop by utilizing the feedback of a compiler, and carrying out self-correction on codes which fail to be compiled; thirdly, high-quality codes are screened out through automatic quality gating and fed back to a corpus and a knowledge base, and self-enhancement circulation of data and knowledge is formed; finally, the method further comprises an offline model evolution step based on grammar and semantic alignment driven by a compiler, a big language model is trained by collecting preference data generated by an online process, and the ability of the big language model to understand a target language is improved fundamentally. According to the method, the core problems of low quality, poor efficiency and lack of self-evolution ability of a low-resource programming language in code migration are solved.

The invention relates to an intelligent decision-making method and system for server customization demand matching. The method comprises the steps of obtaining a server customization demand input by a user; constructing a multi-dimensional demand portrait based on the server customization demand, wherein the demand portrait comprises a quantitative index and a configuration constraint condition; according to the demand portrait, executing configuration compatibility check, and identifying whether a compatibility problem exists or not; when the compatibility check is passed, a candidate configuration scheme is generated by adopting a multi-target genetic algorithm based on the demand portrait passing the compatibility check; and sorting and screening the candidate configuration schemes based on user preference data in the demand portraits passing the compatibility check to obtain a recommended scheme list, and transmitting the recommended scheme list to a display interface for a user to select and confirm, the recommended scheme comprising a component list, a price, a performance index and a recommendation reason. The method has the effect of improving the accuracy of server customization recommendation.

The invention provides a data generation 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: constructing a preference data pair which comprises an initial question and answer pair and an optimized question and answer pair; inputting the preference data pair into a to-be-trained large language model, and obtaining an enhanced question and answer pair output by the to-be-trained large language model; updating the preference data pair to obtain an updated preference data pair, including: setting the enhanced question and answer pair as an optimized question and answer pair in the updated preference data pair; and iteratively executing the steps of constructing the preference data pair and updating the preference data pair until a preset termination condition is met, and obtaining a trained large language model. According to the method, the question and answer pair data is optimized by utilizing the ability of the large language model, and the large language model is trained by using the preference data pairs subjected to iterative updating, so that high-quality question and answer pair data can be generated efficiently at low cost.

The invention discloses a human preference alignment method based on a self-improvement large visual language model. The method comprises the following steps: automatically constructing a preference data set; acquiring an image-question pair from the visual question and answer data set; applying various visual enhancements to the image, and driving a reference model to generate a group of candidate answers in combination with a question; the group of candidate answers are summarized and extracted into a more comprehensive'win 'text, and meanwhile, the text answers of the reference model to the original picture and the question are taken as'fall-fail' texts, so that preference data in an'image-inquiry-'win 'text-'fall-fail' text 'format are formed; secondly, based on the preference data set constructed in the first step, a direct preference optimization algorithm is applied to conduct alignment fine adjustment on a target visual language model, in the fine adjustment process, parameters of a visual encoder are kept frozen, and a low-rank adaptation layer (LoRA) is only introduced into an extended mode alignment module and a language decoder for training; carrying out iterative self-improvement on the model; after fine tuning is completed, taking the optimized model as a new reference model, and repeating the data construction process in the step 1 to generate preference data with higher quality for the next round of optimization; and the circulation is repeated, so that the continuous self-improvement of the model alignment capability is realized. According to the method, self-supervised preference alignment without manual annotation is realized, and a more comprehensive and high-quality'win 'text is generated.

A data processing system implements a framework that utilizes in-situ user interactions as a source of feedback for improving the training of LLMs to generate outputs that align with user preferences. The framework includes a user preference evaluation pipeline analyzes in-situ user interactions with the LLMs and generates preference information that can be used to improve the training of the LLM to improve the alignment of the LLM with user preferences. The user preference evaluation pipeline includes a feedback signal identification unit that identifies explicit and / or implicit feedback provided by the users in response to content output by the LLM in response to a user prompt. The feedback signal identification unit estimates user satisfaction with a set of satisfaction rubrics and user dissatisfaction with a set of user dissatisfaction rubrics to generate user preference data that can be used to align an LLM with these user preferences.

The invention provides a hotel environment adaptive regulation and control system based on the Internet of Things, and belongs to the field of hotel regulation and control management. Comprising a privacy enhanced environment perception and preference acquisition module, a hotel operation data security fusion engine, a dynamic room state and authority regulation and control decision module and a security execution and auditing module which perform data interaction to enhance user data confidentiality and deeply align with hotel operation information; the privacy enhanced environment perception and preference acquisition module is deployed in a guest room and a public area and comprises an environment sensor and a user interaction terminal; a preference acquisition mechanism based on a temporary anonymous identifier is adopted, a user activates an interactive terminal through a check-in voucher and establishes an encrypted anonymous identifier uniquely corresponding to a physical room number, and acquired environment setting preference data is only bound with the anonymous identifier and is stored in an encrypted storage area of a local edge computing node of a guest room.

The invention discloses an interactive advertisement engine implementation method and device, a server and a storage medium, and belongs to the technical field of advertisement technology and intelligent interaction, and the method comprises the steps: generating advertisement content containing interaction elements based on advertisement materials and pre-collected user preference data; in the playing process of the advertisement content containing the interaction elements, a voice instruction of a user is received and analyzed, and corresponding voice interaction response is controlled to be carried out on the interaction elements in the advertisement content according to a voice instruction analysis result; in the playing process of the advertisement content containing the interaction elements, analyzing a gesture interaction instruction of a user when the gesture interaction instruction is received, and controlling the interaction elements in the advertisement content to perform corresponding gesture interaction response according to the analysis result of the gesture interaction instruction; and optimizing an advertisement generation strategy based on the analyzed interaction data of the user. According to the invention, interaction between the user and the advertisement content through voice or gestures is supported, so that the attraction and effect of the advertisement are improved.

The invention discloses a multi-agent collaboration system for constructing a data set for vertical field large language model training. The system integrates four levels of data acquisition, data processing, data generation and data optimization, and can automatically complete full-process processing from multi-source corpus acquisition, structured analysis to instruction and preference data construction after receiving a field demand and a retrieval intention proposed by a user. Through the cooperative effect of picking, structured reconstruction, co-citation analysis, expert generation and screening optimization intelligent agents, automatic construction of a pre-training data set, an instruction fine tuning data set and human feedback reinforcement learning RLHF data is realized, and the consistency, traceability and high quality of the data are ensured; therefore, the training effect and the application performance of the vertical field large language model are effectively improved.

The application discloses a KTV system rear surround setting method and device, a terminal and a medium. The method comprises the following steps: acquiring rear surround device static parameters, box environment data, box acoustic data and customer preference data; determining a target position of the rear surround device in the box based on the rear surround device static parameters, the box environment data and the box acoustic data; determining a target adjustment parameter combination corresponding to the rear surround device based on the rear surround device static parameters, the box acoustic data and the customer preference data; processing the rear surround device based on the target adjustment parameter combination, and placing the rear surround device at the target position. The application aims to achieve the optimal acoustic effect of the rear surround device of the KTV system in the box, and ensure that the acoustic effect of the rear surround device meets the preferences of customers in the box.

The invention discloses a large language model alignment method based on multi-user preference dynamic balance, and the method comprises the steps: collecting user interaction data, preference comparison data and public policy question and answer data in a livelihood consultation scene, and dividing the data into structured preference data and unstructured data; preprocessing the divided data to generate a user feature vector and a response feature vector; constructing a user-response bipartite graph, performing multi-hop preference propagation through a graph neural network, capturing potential association among users, and outputting a user preference embedding vector; embedding a vector selection expert path according to user preference through a dynamic gating function, and generating a personalized response; and through an optimization-free embedding aggregation strategy, similar users are retrieved based on a graph structure, and the embedding of the similar users is weighted and aggregated, so that rapid cold start of new users is realized. The precision and efficiency of livelihood consultation can be remarkably improved, and the method is particularly suitable for smart city scenes with high-frequency policy updating and frequent user flow.

The invention discloses a dynamic model pruning method and device, and electronic equipment, and the method comprises the steps: firstly obtaining a dynamic model, then carrying out the partitioning calculation of the dynamic model, obtaining a first activation matrix block, obtaining first preference data based on the dynamic model, and enabling the first preference data to correspond to the first activation matrix block, obtaining a first inevitable effect on the basis of the first activation matrix block and the first preference data, obtaining a first value conduction chain on the basis of the first inevitable effect, obtaining a first quantization efficiency-value ratio on the basis of the first value conduction chain, and trimming the dynamic model on the basis of the first quantization efficiency-value ratio. In other words, after block calculation is carried out, a first inevitable effect is generated according to the first preference data and the first activation matrix block, then a first value conduction chain is obtained, and finally a first quantization efficiency value ratio is obtained to trim the dynamic model, so that when different data distributions are faced, the output quality is uniform, and the stability is high.

The embodiment of the invention provides a data preprocessing and optimizing method and device for a generative model in a question and answer scene. In an intelligent question and answer service scene, on the basis of answering the user question, another tag question can be provided for the user to select. Tag questions may be determined based on questions generated by the generative model. The generative model herein may be a natural language processing model such as a large language model. In order to optimize the generative model, sample data for training can be determined according to the operation performed by the user on the pushed label problem in the online use process. A plurality of preference data pairs are automatically extracted from a single operation of a user through data screening and processing to serve as training samples. Therefore, the generated model is optimized by using the extracted training sample, and the generation result of the generated model can be guided, so that the generated model generates a tag problem which better conforms to human preference.

Provide a system. 【Solution means】 Means for generating optimal visit candidates based on the preference data of participants, Means for presenting the list of generated visit candidates and automatically making a reservation to the selected location, Means for sending event participation confirmation to members via a communication network, Means for selecting the date on which the most members can participate based on the response to the participation confirmation, Means for automatically calculating the expenditure amount for each member and notifying the member, Means for generating location candidates according to preferences using prompts, Means for making a settlement through the platform after selection, A system including the above.

A method for providing personalized non-profit venue visit recommendations to a visitor at a non-profit venue, comprising: providing a management interface for management of a set of multimedia assets; receiving a mapping of multimedia assets to a display in at least one site plan; receiving metadata for the set of multimedia assets; providing an interface for receiving data indicating personal interests of a visitor, including visitor-provided preference data and passively-collected visitor interaction data; receiving personal interest data for a plurality of non-profit venue visitors; receiving preference data relating to a prospective visitor; applying a machine learning system to analyze the metadata, the data indicating personal interests of the visitor, the personal interest data for the plurality of non-profit venue visitors, and the preference data relating to the prospective visitor; and generating a selection or sequence of non-profit venue location recommendations for the prospective visitor.

The invention discloses an artificial intelligence aided design color matching decision-making system and method, and relates to the technical field of computer aided design. Comprising the steps of obtaining a design semantic text, user visual preference and scene illumination parameters; converting the text data into emotion vectors through machine learning; mapping the emotion vectors into a color base vector set by using a pre-trained emotion color mapping model; carrying out personalized parameter adjustment on the color basis vector based on the visual preference data of the user; environment self-adaptive correction is carried out in combination with scene illumination parameters; performing multi-dimensional intelligent evaluation on the corrected color set to generate a comprehensive confidence score and a color matching scheme; when the score is lower than a preset threshold value, iterative optimization is carried out, and finally an optimized color matching scheme is output. The problem that a traditional color matching tool is difficult to consider design intentions, user preferences and physical scenes is effectively solved, and the quality, personalization and practicability of a color design scheme are improved.

The invention provides a POI recommendation method and device at specific time and a storage medium, and relates to the technical field of POI recommendation, and the method comprises the steps: obtaining user embedding according to user preference data, and obtaining POI embedding according to POI influence data; based on a Mamb-Transform hybrid model, respectively performing user embedding and POI embedding processing to obtain user preference information and POI influence information of source time; obtaining user preference characteristics and POI influence characteristics of the target time according to the user preference information, the POI influence information and the target time data; and determining a final recommendation score sequence according to the user preference characteristics and the POI influence characteristics, and screening the final recommendation score sequence to obtain a final next POI recommendation. According to the method, the user sign-in history is collected, deep modeling is performed by using the hybrid model, the target time preference is dynamically adjusted, and the recommendation result is optimized, so that highly personalized and scenarized recommendation is realized.

The invention provides a user character recognition method, electronic equipment and a storage medium, and can obtain current dialogue data of a user, determine short-term character characteristics of the user according to the dialogue data, determine long-term character characteristics of the user based on preference data in different types of preference libraries of the user and attention weights corresponding to the preference libraries, and improve the user character recognition efficiency. Since respective corresponding attention weights can be endowed to different types of preference libraries, the accuracy of the determined long-term character traits is improved, then the current actual character traits of the user are determined through the short-term character traits and the long-term character traits, in the process, recent character changes are concerned by means of the short-term character traits, and the user experience is improved. The stable and lasting character characteristics are reserved through the long-term character characteristics, that is, the current actual character characteristics of the user are determined based on the recent character changes and the stable and lasting character characteristics, the respective advantages of the long-term character characteristics and the short-term character characteristics are fully fused, and the accuracy of user character recognition is improved.

The invention provides a webpage optimization method and device, equipment and a storage medium. Relates to the technical field of big data processing. Acquiring user behavior data of the historical webpage, wherein the user behavior data comprises at least one of click data, interaction data, content preference data and access data of the historical webpage; and for each level of historical webpage after grading, extracting behavior characteristic data from the user behavior data through clustering analysis, determining a webpage optimization model through a machine learning algorithm according to the behavior characteristic data, and optimizing a new webpage according to the webpage optimization model. The behavior characteristic data are extracted from the user behavior data of the webpage of each level through clustering analysis, and the situation that similar data appear many times can be avoided. According to the method, the machine learning algorithm is trained by the behavior characteristic data to obtain the webpage optimization model to optimize the new webpage, the attraction degree of each characteristic of the webpage to the user can be accurately identified, the optimized new webpage can better adapt to the personalized behavior preference of the user, and the user satisfaction and the user viscosity are improved.

The invention relates to a loyalty-driven large model preference optimization method, which comprises the following steps of: S1, acquiring question and answer data pairs containing question cues and reference text blocks; s2, inputting the question cue word into the to-be-optimized large model, and obtaining a model answer; s3, performing fine-grained splitting on the model answer to obtain a plurality of statement unit sets; s4, performing fact reasoning verification on the statement unit set by using a preset discrimination model and taking the reference text block as a basis; s5, calculating an answer loyalty score of the to-be-optimized large model according to a verification result of the statement unit; s6, judging whether the score is lower than a preset threshold value or not; if yes, a preference optimization data item is constructed; and S7, forming a training data set according to the preference optimization data items, and performing training update on the to-be-optimized large model. Through the automatic loyalty evaluation and preference data construction process, the illusion problem of the large model in the professional field is solved, and the reasoning credibility of the model can be improved without manual large-scale labeling.

The application discloses a financial risk control report generation method, device, equipment, storage medium and product, relates to the technical field of artificial intelligence, and the method comprises the following steps: generating a preference data set through a supervised fine-tuning technology, a preset risk control report corpus and a preset large language model; performing iterative preference training on the preset large language model according to the preference data set; and generating a financial risk control report through a large language model after training and an intelligent agent-based retrieval enhancement generation technology. The application uses the risk control report corpus of a user to generate a preference data set through supervised fine-tuning, a corpus and a large language model, thereby reducing the dependence on a large amount of labeled data; the model is trained through the preference data set, a database query mode is provided to improve the report generation efficiency of the model, thereby solving the problem that a large number of high-quality samples are required for training in the prior art, and only a small number of samples and iteration times are required to align the output of the large language model with the expected behavior of the user.

We provide the system. [Solution] A means for inputting the user's basic information, Means for collecting users' past behavioral data, A means of analyzing collected behavioral data to identify user preference patterns, A means for automatically generating customized content based on preference patterns, A means of delivering the generated content to the user, A means of receiving user feedback and updating preference data, A means of generating new customized content based on updated preference data and delivering it to the user again, A system that includes this.

The present disclosure provides a page generation method and device, comprising: obtaining atomic component data and user preference data of a target event, the target event being at least one; in response to identifying a target event of the target event, obtaining a basic weight and an event occurrence time of the target event; and generating a page corresponding to the target event based on the target event, the basic weight, the event occurrence time, the user preference data and the atomic component data. The present scheme realizes the automatic, personalized and emotional generation of the page by fusing real-time event, individual user preference and structured atomic content, significantly improves the user participation and the propagation effect, greatly reduces the operation cost, provides an efficient and scalable technical path for the precise operation of the sports event, and introduces a time decay mechanism by using the event occurrence time, grades the event value in combination with the basic weight, avoids the interference of low-value events to the user, and reduces the invalid exposure.

The invention belongs to the technical field of computers, and discloses an electronic coupon recommendation obtaining method and system based on social network behaviors, and the method comprises the following steps: S1, obtaining multi-dimensional behavior data of a target user and a social associated user from a social network platform, the behavior data comprises consumption preference data, social interaction data and content generation data of the user; s2, performing cleaning and structured processing on the multi-dimensional behavior data, and extracting user social behavior feature vectors; according to the method, consumption preference, social interaction, original content and other multi-source data are fused, the constructed dynamic interest preference graph can deeply and prospectively insight into user interests, the problems of data sparseness and cold start are effectively relieved, the recommendation result is more accurate, and surprise can be brought; by quantifying the social influence index, key opinion leaders or users with high propagation potential can be identified, and coupons which are more attractive or have sharing incentive attributes can be recommended for the key opinion leaders or users with high propagation potential.

The invention provides a dynamic generation and management method of a multi-role humanization knowledge base. The method comprises the following steps: S1, collecting role texts and constructing a knowledge graph; s2, generating a humanization parameter; s3, carrying out multi-modal data acquisition, feature extraction and role matching; s4, local cache verification and cloud resource acquisition; according to the invention, through a role data modeling module, role texts are collected from an IP party database and user preference data, knowledge entities and relationships are extracted by means of an NLP tool, and a dynamically updatable knowledge graph is constructed and stored in a cloud end; cloud centralized management is combined with on-demand requests of terminals, real-time switching of scene knowledge bases such as multiple IPs and family members is supported, preloading static data is not depended on any more, diversified use scenes are adapted, and response timeliness is improved; parameters such as mood, style and knowledge boundary are extracted and bound with the knowledge graph, so that the response has new personalized features, and the problem of insufficient humanization is solved.

One example method includes: obtaining, by an artificial intelligence (AI) system and prior to receiving a query, input data; generating, by the AI system and based on the input data, one or more candidate digital components using a machine learning model; obtaining, by the AI system, user preference data limiting usage of at least one candidate digital component of the one or more candidate digital components; receiving, by the AI system, the query; identifying, by the AI system, one or more digital component regulations associated with the query; identifying, by the AI system based on the one or more digital component regulations and the user preference data, at least one particular candidate digital component of the one or more candidate digital components; and generating, by the AI system and based on the at least one particular candidate digital component, an output digital component.

The invention relates to the technical field of financial marketing, in particular to an integrated financial marketing management method and system based on a marketing data domain, and the method comprises the following steps: collecting customer transaction and preference data, calculating a change amplitude, normalizing the change amplitude into a feature vector, analyzing a group difference degree, calculating a change rate, and generating a judgment result; a personalized marketing plan is generated by combining the life cycle data clustering stage number and the conversion progress matching rhythm parameter, the advertisement space pushing frequency and the consultant service proportion are calculated according to the multi-group requirement to carry out resource optimization distribution, and interaction and transaction data after resource scheduling are collected and input into a regression model to be analyzed to generate a marketing effect evaluation result. According to the method, customer transaction and preference data quantitative changes are collected and normalized into feature vectors, a group difference degree dynamic identification state is analyzed, a life cycle clustering matching rhythm parameter generation strategy is combined, the advertisement space pushing frequency and consultant service proportion is optimized according to group requirements, and regression analysis is carried out to form closed-loop optimization management.

Disclosed herein are methods, apparatuses, systems and computer-elements for generating preference data associated with a product produced from at least one inbound material and for producing at least one product being associated with preference data, where the at least one product is produced by a production from at least one inbound material.