298 results about "Click-through rate" patented technology

The invention belongs to the technical field of catering informatization service, and provides an automatic matching catering menu pushing system, which comprises a user data acquisition module, a catering menu pushing module and a catering menu pushing module, the menu data management module stores and manages menu classification, labels and states, and obtains content feature data; the user portrait construction module generates a multi-dimensional portrait according to the multi-aspect information of the user; the menu matching module combines collaborative filtering and a content recommendation algorithm, and generates a recommendation menu based on the user portrait; the intelligent pushing module pushes dishes of nearby merchants according to the portraits, and the pushing effect is evaluated through the click rate and the conversion rate; according to the method, personalized and accurate catering menu recommendation is realized, and real-time updating and optimization are carried out in combination with geographic positions and time period factors, so that personalized pushing which better fits user preferences and dining environments is provided.

The invention discloses an advertisement creative real-time optimization and putting control method and system based on artificial intelligence, electronic equipment and a computer readable medium, and the method achieves the precise matching, effect prediction and dynamic regulation and control of the advertisement creative through an intelligent technology, thereby improving the efficiency and effect of advertisement putting. The core process of the method comprises the following steps: firstly, carrying out fusion and joint modeling on multi-source features such as user portraits, advertisement creative contents and real-time context environments so as to realize high-matching-degree real-time optimization of creativity, users and scenes; and secondly, a deep cross network (DCN) model is adopted to capture a complex high-order interaction relationship among the user, the creativity and the environment, so that key indexes such as a click rate (CTR) and a conversion rate (CVR) are predicted with high precision. Besides, the system establishes a real-time monitoring mechanism based on a sliding time window and a change slope, creative fatigue is actively identified through the change trend of data such as exposure, clicking and conversion, and intervention and adjustment are carried out in time.

The invention provides a power grid standard intelligent recommendation method based on reinforcement learning and post system management. The power grid standard intelligent recommendation method comprises the following steps of 1, collecting and cleaning power grid standard data; step 2, post-standard system knowledge graph construction; 3, designing a reward function for the power grid standard recommendation system, and realizing a personalized recommendation strategy by taking post responsibilities and skill levels as dynamic weight parameters; and step 4, post-driven online incremental training is carried out. According to the method, a reinforcement learning dynamic optimization engine is adopted to learn user behaviors (click rate and task completion score) in real time, and a standard recommendation strategy is adjusted; and when the standard is updated, the post capability weight is automatically adjusted, closed-loop feedback optimization is realized, and the problem of updating delay of a traditional system is solved.

The invention discloses an e-commerce advertisement accurate recommendation system based on deep learning, and relates to the technical field of e-commerce, and the system comprises the following modules: an entity index module used for constructing a node registry; the hypergraph construction module is used for continuously monitoring an event stream and constructing a dynamic hypergraph; the initial embedding module is used for extracting a node embedding tensor and a hyperedge embedding tensor; the graph representation learning module is used for extracting a final node embedding representation tensor and a final hyperedge embedding representation tensor by improving a GraphTransform model; the click rate estimation module is used for outputting the predicted click rate of each candidate advertisement; and the sorting decision module is used for screening a candidate advertisement list. According to the method, the limitation that a traditional recommendation method depends on simple characteristics and neglects high-order association and dynamic evolution information is overcome, and a powerful solution is provided for realizing efficient, accurate and personalized e-commerce advertisement recommendation.

The invention discloses a global intelligent marketing method based on multi-modal information fusion. The method comprises the following steps: firstly, collecting multi-source heterogeneous data, extracting text, vision and behavior characteristics by using deep learning, and mapping the text, vision and behavior characteristics to a public semantic space for fusion through an attention mechanism; and then, constructing a dynamic user portrait based on the fusion features and identifying a user intention stage. On the basis, the click rate is estimated by using a double-tower network, and a dynamic bidding strategy is generated in combination with a reinforcement learning DQN model and PID control. And finally, aiming at customer inquiry, generating a quoted price in combination with a cost model or performing automatic negotiation by using a time-dependent game strategy, and updating model parameters in real time through online incremental learning. Through full-link intelligent closed-loop control, accurate user intention recognition, efficient advertisement putting and automatic business negotiation are realized, the marketing conversion rate is effectively improved, and the operation cost is reduced.

The invention provides a title generation model training method and device, a title generation method and device, electronic equipment, a medium and a program product, and relates to the technical field of artificial intelligence, in particular to the fields of model training, reinforcement learning, large language models, generative artificial intelligence and the like. According to the implementation scheme, a title generation model is trained; training a first reward model associated with the click rate for making a first score for each candidate title in the plurality of candidate titles; training a second reward model associated with the content quality of the title for making a second score for each candidate title; fusing the first score and the second score of each candidate title in the plurality of candidate titles to obtain a reward score; and based on the reward score corresponding to each candidate title, training a title generation model to increase the generation probability of the candidate title with the higher score in the plurality of candidate titles and reduce the generation probability of the candidate title with the lower score at the same time.

The invention provides a big data advertisement putting method and system based on a cloud platform. The method comprises the following steps of performing multi-source data collection and preprocessing; dynamically constructing a user portrait; performing multi-dimensional analysis on the behavior pattern; target audience subdivision is based on a Gaussian mixture model; dynamically generating personalized advertisement creativity; a step of optimizing a multi-target delivery strategy; a step of real-time bidding and bidding optimization; a step of putting execution and real-time monitoring; a step of effect evaluation and multi-dimensional feedback; and carrying out adaptive system adjustment and iterative optimization. The big data advertisement putting method based on the cloud platform has the advantages that putting precision and efficiency are improved, audiences are subdivided through complex statistics, dynamic creativity is generated, advertisement correlation is enhanced, the predicted click rate is increased by 15-20%, and budget waste is reduced. And the cloud platform supports stream processing and automatic adjustment, so that the system can quickly respond to market changes, and the delay is reduced to a millisecond level.

Aspects of the disclosure are directed to text to image generative models fine-tuned to generate images that account for performance in addition to quality. For example, in a digital content domain, the generated images can be not only visually appealing but perform well as advertising assets, e.g., result in improved click through rate and / or conversion rate. Accounting for performance and quality can reduce processing cost and memory usage when generating images from text prompts, as the resolution of the image can be balanced with its function, allowing for reduced quality images that can still perform well.

The invention relates to an intelligent advertisement putting optimization method based on a novel consumption scene, and the method comprises the following steps: S1, fusing the multi-dimensional behavior data of a user, and carrying out the precise user portrait modeling; s2, dynamically evaluating the mood state and preference change of the user based on semantic and emotion analysis of the staying chapters of the user; s3, automatically labeling an advertisement insertion point through an NLP technology, and dynamically generating a putting strategy; s4: according to the user portrait, the user mood state and the preference change, automatically designing the advertisement content and the emotion adaptive copywriting by using the generative AI; and S5, constructing a stream processing architecture, monitoring and dynamically analyzing the advertisement effect in real time, and automatically triggering pause and adjustment of an advertisement strategy if the user behavior index is abnormal. According to the invention, the click rate and conversion rate of the user can be effectively improved, and the dislike emotion of the user to the advertisement is reduced.

The invention discloses an intelligent short message anti-interception method and device based on AI deep learning, and a storage medium, and the method comprises the steps: setting a short message sending demand obtaining module which is used for obtaining the short message content which needs to be sent by each client; an information classification module is arranged to detect and automatically classify short message content information needing to be sent; an intelligent short message reconstruction module is arranged, and an intelligent short message and a short message sending scheme are regenerated by using short message content information provided by a client; a short message interception simulation module is arranged and used for simulating short message interception and evaluating a short message sending success rate and a click rate; when the sending success rate is lower than a threshold value, the short message interception simulation module feeds back a reason possibly causing interception to the intelligent short message generation module, and the intelligent short message generation module improves short message content in a targeted manner and regenerates an intelligent short message and a short message sending scheme until the sending success rate is evaluated to be higher than the threshold value; a user confirmation module is arranged, and when the sending success rate is higher than a threshold value, the intelligent short message and a sending scheme thereof can be fed back to a client.

The invention relates to the technical field of internet advertisements, and discloses a multi-channel advertisement flow dynamic scheduling and income optimization method, which comprises the following steps of: 1, acquiring multi-dimensional behavior data at an advertisement playing node and a user browsing page of an e-commerce platform, and sending the multi-dimensional behavior data to an edge computing node, the multi-dimensional behavior data comprises click rate, browsing duration, advertisement interaction data, commodity browsing frequency, advertisement exposure condition and user feedback data; and step 2, the edge computing node receives the multi-dimensional behavior data. According to the technical scheme, algorithm analysis is executed locally at an edge computing node, and real-time fine adjustment of advertisement flow is executed according to a preliminary analysis result, so that the technical effect that an advertisement strategy immediately responds to dynamic change behaviors of a user is achieved. The defect that advertisement strategy adjustment is obviously delayed is overcome.

Aspects of the disclosure are directed to text to image generative models fine-tuned to generate images that account for performance in addition to quality. For example, in a digital content domain, the generated images can be not only visually appealing but perform well as advertising assets, e.g., result in improved click through rate and / or conversion rate. Accounting for performance and quality can reduce processing cost and memory usage when generating images from text prompts, as the resolution of the image can be balanced with its function, allowing for reduced quality images that can still perform well.

The invention provides a graph embedding feature construction method and system based on RTA and a training method of an advertisement click-through rate estimation model.The construction method comprises the steps that interaction related information of a user and equipment is obtained, and the interaction related information comprises advertisement feature information, user equipment information and user advertisement interaction behavior information; constructing an equipment advertisement heterogeneous graph according to the advertisement feature information, the user equipment information and the user advertisement interaction behavior information, wherein the equipment advertisement heterogeneous graph comprises equipment nodes and advertisement nodes; processing the equipment advertisement heterogeneous graph through hierarchical aggregation to dynamically generate graph embedding features; according to the invention, the accuracy of the advertisement click rate prediction result can be effectively improved, and cold start of the new user and the new advertisement is realized.

The invention relates to the technical field of adjustment of cross-platform advertisement material putting, and discloses an adjustment method and device for cross-platform advertisement material putting, electronic equipment and a medium, and the method comprises the steps: generating creative variants in batches by using a multi-modal large language model, shortening the material creation time, greatly improving the production efficiency and diversity, and reducing the production cost. Cultural compliance filtering is automatically completed through a preset rule base, the over-auditing rate is greatly improved, the compliance risk is reduced, an innovative cross-platform adaptation mechanism can intelligently convert core creativity into a form conforming to different platform preferences, efficient reuse of materials is achieved, a large amount of repeated manufacturing cost is saved, and finally, the method is suitable for popularization and application. And performing dynamic strategy adjustment on the real-time feedback data based on the reinforcement learning model. The method has the beneficial effects that the continuous autonomous optimization of the putting effect is realized, the advertisement click rate, the conversion rate and the overall return on investment are remarkably improved, and the end-to-end intelligent advertisement operation capability is formed.

The invention discloses a video advertisement intelligent insertion method and system based on semantic segmentation and multi-modal context fusion. Through pixel-level semantic mask and multi-frame time sequence analysis, a space neutral area which can be used for advertisement embedding in a video is automatically identified, and background stability judgment is carried out in combination with indexes such as structural similarity and brightness change; and constructing a multi-modal context modeler, fusing a character emotion vector, a video rhythm vector and a scene structure vector, generating a context situation vector through a cross attention mechanism, and outputting an insertion suitability score. And when the score reaches a set threshold value and the neutral area meets the condition, the system executes advertisement generation and visual fusion operation to realize natural advertisement insertion consistent with the original video content style. The method is suitable for various content platforms such as short video and live broadcast, and experiments show that the click rate and the complete broadcast rate can be remarkably improved, and the jump-out rate is reduced.

This invention relates to a news recommendation method integrating activation diffusion theory and Ebbinghaus forgetting theory. The method includes the following steps: acquiring a knowledge graph dataset and a news dataset, and preprocessing them respectively; using BERT to obtain vector representations of news words; aggregating word and entity vectors in a convolutional neural network (CNN) using activation diffusion theory to obtain feature vectors for the news; improving the attention mechanism using Ebbinghaus forgetting theory to obtain the user's feature vector based on the user's click history; and predicting click-through rates and recommending news based on the feature vectors of candidate news and the user's feature vector. Compared with existing technologies, this invention can accurately mine the relationship between users and candidate news, thereby improving the accuracy of recommendations.

The invention relates to the technical field of Internet, in particular to a multimedia content display method and device, electronic equipment and a storage medium, and aims to improve the click rate of multimedia content. The method comprises the following steps: presenting a content browsing interface; the content browsing interface is used for displaying the recommended information flow to the target object; in response to a content switching operation for the content browsing interface, presenting exclusive promotion content generated based on the target multimedia content carried by the information stream in the content browsing interface, and skipping to the exclusive promotion content and playing a content segment corresponding to the exclusive key information of the target level; the exclusive promotion content is used for describing different levels of exclusive key information matched with the target object; each piece of exclusive key information is comprehensively generated according to the original key information in the target multimedia content and the content preference information of the target object; the target level is determined according to the interestingness of the target object to the information flow.

The embodiment of the invention provides a method and device for generating a material attribution of an AIGC model through artificial intelligence. In the method, a prediction material corresponding to a first cue word and a prediction click rate of the prediction material are determined through an AIGC model, data processing based on a model interpretable algorithm is executed, and contribution values of a plurality of feature values in the first cue word to the prediction click rate are obtained. Then, a plurality of first feature values with high contribution are determined, first interpretive verbal skills corresponding to the first feature values respectively are inquired from a plurality of pre-constructed triples, any triple comprises the feature values, the field scene and the interpretive verbal skills, and the interpretive verbal skills are used for representing the effect and / or influence of the corresponding feature values in the field scene; the second cue word is input into an attribution report generation model, an attribution report is obtained, the attribution report comprises a contribution description text of a plurality of first feature values to the predicted click rate, and a task instruction contained in the second cue word is combined with the first interpretive verbal skill to generate the contribution description text.

The application discloses a kind of personalized recommendation method based on big data, the present application will elastic search data storage search and based on user's collaborative filtering algorithm and based on item's collaborative filtering recommendation algorithm is combined.For new user, recommend the top 15 data of highest click rate in elastic search database.For old user, the recommendation result of the user-based collaborative filtering algorithm and the item-based recommendation algorithm is linearly weighted fusion, and the top 10 data is selected for recommendation.The application can update the database regularly through the high automation of web crawler.Secondly, by combining TF-IDF algorithm with collaborative filtering algorithm, the sparsity problem of data can be alleviated to a certain extent.

This invention discloses an intelligent advertising design and generation method, specifically including the following steps: S1, Data Collection and Preprocessing: Collecting product data, user behavior data, historical advertising data, and real-time market data, and performing cleaning, labeling, and feature extraction; S2, User Profile Modeling: Constructing a dynamically updated user interest graph based on clustering analysis and deep learning algorithms; This invention relates to the field of artificial intelligence technology. This intelligent advertising design and generation method integrates multi-dimensional data such as product functions, user behavior, and competitor dynamics to improve the accuracy of advertising content, generate targeted advertising copy, support the joint generation and style unification of text, images, and videos, and the system can simultaneously generate advertising slogans such as "Riding the Wind, Unlocking the Acceleration of Youth" and dynamic posters, track click-through rates, conversion rates, and other indicators in real time, automatically adjust content parameters, use blockchain technology to store copyright information, and protect user data through differential privacy algorithms.

The application relates to the fields of machine learning and financial technology, and discloses a product display method and device and related products. The method comprises the following steps: in response to a display instruction sent by a client, obtaining product information of a plurality of products to be displayed, user portrait data, user behavior data and product access scene data of a current user; wherein the product access scene data comprises at least one of the following: a client type and an access time; preprocessing the product information of the plurality of products to be displayed, the user portrait data, the user behavior data and the product access scene data of the current user to obtain a processing result; generating a product ranking result by using a pre-trained product ranking model according to the processing result; and displaying the plurality of products to be displayed on a front-end page of the client based on the product ranking result. The application can integrate product information and user multi-dimensional demand data, generate a product ranking result that meets the personalized demand of a user, and effectively improve the click rate and conversion rate of products.

An object of the system according to the embodiment is to efficiently generate an advertisement creative with a high CTR or CVR and display an optimum advertisement for each user.SOLUTION: A system according to an embodiment includes an advertising creative analyzer, a generator, and a user analyzer. The advertising creative analysis unit analyzes an advertising creative with a high CTR or CVR. A generation unit generates a new advertising creative based on the features analyzed by the advertising creative analysis unit. The user analysis unit analyzes the advertising creative generated by the generation unit for each user and displays an optimal advertisement.SELECTED DRAWING: Figure 1

The disclosure provides a click rate estimation model training method and device, and relates to the technical field of artificial intelligence. A specific embodiment of the method comprises: obtaining a preset sample set, the sample set comprising at least one sample; obtaining a click rate estimation network comprising a feature prior module and a model prior module, which is constructed in advance; performing the following training steps: selecting a sample from the sample set; inputting the sample into the click rate estimation network to obtain a click rate estimation value output by the click rate estimation network; calculating a feature loss value of a feature prior layer of the feature prior module and a model loss value common to a feature processing layer of the feature prior module and the model prior module; and in response to the click rate estimation network satisfying a training completion condition, taking the click rate estimation network as a click rate estimation model, which improves the generalization ability of the model.

This invention relates to the field of advertising technology and provides a multi-dimensional advertising effect simulation method for user experience optimization. The method includes: constructing a multi-dimensional evaluation index matrix based on the comprehensive experience utility value, wherein the multi-dimensional evaluation index matrix includes at least commercial revenue indicators, experience loss indicators, attention retention indicators, and brand safety indicators; and using a counterfactual inference method to simulate various advertising strategies in a virtual environment, aiming for Pareto optimality, and determining the strategy combination that maximizes commercial revenue while ensuring that the user experience indicators do not fall below a preset threshold. This invention constructs a multi-dimensional evaluation index matrix including commercial revenue indicators, experience loss indicators, attention retention indicators, and brand safety indicators, breaking through the limitations of traditional methods that rely solely on single commercial indicators such as click-through rate and conversion rate.

The present disclosure provides a search result sorting method and device, computer equipment and a storage medium, wherein the method comprises: obtaining search results matched with a search term, the search results comprising first results of a first genre and at least one second result of a second genre other than the first genre; the second result comprising at least one result document; for any result document in the second result, determining a document feature corresponding to the result document according to text attribute information of the result document, dimension information of the result document in a plurality of preset characteristic dimensions, the search term and source information of the search term; determining a document association feature corresponding to the second result according to the document feature of each result document in the second result; and sorting the first results and the second results according to the document association feature of each second result and a result click rate of each first result.

The invention discloses an advertisement bidding method, system and device based on behavior cloning and a medium, and the method comprises the steps: obtaining historical advertisement bidding data, carrying out the preprocessing of the historical advertisement bidding data, and obtaining the preprocessed historical advertisement bidding data; generating track data according to the preprocessed historical advertisement bidding data; inputting the track data into a preset advertisement bid model based on a behavior cloning algorithm for training, and obtaining a trained advertisement bid model; and bidding the advertisement in real time according to the trained advertisement bidding model. According to the method, the advertisement bidding model capable of making bidding decisions under the limitation of dynamic budget is trained by using the historical advertisement bidding data and the behavior cloning algorithm. According to the model, an optimal advertisement bidding strategy is learned by simulating advertisement putting behaviors in historical advertisement bidding data, so that the benefits of advertisement putting are improved, and the benefits comprise the click rate, the budget utilization efficiency, the income of an advertiser and the like.

The invention provides a user intelligent recommendation method and system for information flow delivery. The method comprises the following steps: a step of multi-source heterogeneous data acquisition and real-time fusion; a hidden Markov model is used for dynamic user interest modeling; a multi-mode step is used for content deep semantic analysis; a step of user content interaction modeling; a multi-objective optimization recommendation strategy uses a Pareto frontier step; updating the real-time feedback driven model by using online learning; cross-domain knowledge migration uses antagonism domain self-adaption; a step of using a generative adversarial network for robustness training of the resistance sample; the personalized diversity balance mechanism uses information entropy and reinforcement learning; and the end-to-end interpretability evaluation system uses anti-fact reasoning and A / B testing. The intelligent user recommendation method for information flow delivery has the advantages that recommendation accuracy is improved, user interests are matched more accurately through dynamic interest modeling and multi-modal analysis, and the predicted click rate is improved by 15-20%.

The invention belongs to the technical field of business data processing, and particularly discloses an industrial park intelligent investment attraction management system and method based on machine learning, and the method comprises the steps: collecting an enterprise interaction log record, and extracting a feedback response index from the click rate and the stay duration; according to the index quantization professional depth and the initial weight of the data proportion, obtaining an attribute parameter vector; processing the attribute parameter vector by adopting a reinforcement learning algorithm, if a feedback response index exceeds a preset threshold value, improving the association strength of policy preference and case similarity, and obtaining an adjusted parameter vector through iterative updating; analyzing a restriction relationship between abstract description and emotional tendency according to the adjusted parameter vector, if the proportion of the abstract description is higher than a data proportion, reducing the proportion, and fusing chart response elements to determine an optimized content template; the invention aims to solve the problem of poor user interaction feedback and content attraction in the investment attracting content pushing process in the prior art.

This application provides a cold start method, apparatus, electronic device, and storage medium for a recommendation system. The method includes: determining a list of historical clicked content corresponding to user tags based on acquired user tracking data and user tags; calculating feature data of the historical clicked content based on the user tracking data; smoothing the feature data to calculate the click-through rate (CTR) data corresponding to the historical clicked content, and determining a first candidate content list corresponding to the user tags based on the CTR data; determining a second candidate content list based on the first candidate content lists corresponding to multiple user tags under the same user; performing Thompson sampling on the CTR data of the candidate content in the second candidate content list to calculate a random number corresponding to the candidate content; and reordering the candidate content in the second candidate content list based on the random number to determine a user recommendation list. This application can provide users with more differentiated recommended content.

The invention provides a model training method and device, and relates to the technical field of logistics. The method comprises the following steps: acquiring log information and activeness information corresponding to a plurality of initial goods sources respectively, wherein each initial goods source is a driver generating an exposure behavior in a freight platform and a goods source in a goods source pair; according to the log information and the activeness information, primarily screening the plurality of initial goods sources, and determining a plurality of candidate goods sources; obtaining feature information corresponding to the plurality of candidate goods sources; performing fine screening on the plurality of candidate goods sources according to driver behavior characteristics and goods owner behavior characteristics in the characteristic information, and determining a plurality of sample goods sources; and taking the feature information corresponding to the plurality of sample goods sources as training samples, taking the goods source states corresponding to the plurality of sample goods sources as sample labels, training the basic model to obtain a click rate prediction model, so that the model learns a healthy, real and valuable behavior mode, and the click rate prediction efficiency is improved. And the prediction accuracy and rationality of the click rate prediction model obtained by training are improved.