73 results about "Ranking" patented technology

Disclosed is a chat group management method, including: detecting a message receiving mode corresponding to a chat group; obtaining a degree of interest of a user for chat group messages and an activity degree of the user in the chat group in accordance with a determination that the message receiving mode corresponding to the chat group is a mute-notification receiving mode; determining an importance ranking for the chat group according to the degree of interest and the activity degree; and updating the chat group's position among a plurality of chat groups in accordance with the importance ranking.

The invention discloses a model-based task instruction management method and device, a storage medium and equipment, and belongs to the technical field of deep learning. Obtaining text data of each task to be executed, wherein the text data comprises description information, demand information and supplementary information of the tasks and log information of historical tasks; extracting key information of each task from the text data by utilizing a large language model, wherein the key information comprises an emergency parameter, a target parameter, a resource demand parameter and a time limit parameter of the task; generating a corresponding task instruction based on the key information of each task by utilizing a generative model; combining similar task instructions in the plurality of task instructions; and performing priority ranking on the combined task instructions, and performing execution scheduling on the ranked task instructions. According to the method, the generation requirement of the high-complexity task instruction can be met, the execution efficiency of the instruction and the resource utilization rate are improved, and execution scheduling of the task instruction is adjusted in real time according to resources.

A system and method for extracting data from large language model (LLM) outputs, including: training a model using labeled data items to assign rankings to LLMs; selecting, by the trained model, one or more of the LLMs based on the rankings; sending an LLM prompt to selected models; and outputting, by the model, a refined response to the prompt based on responses to the prompt by the LLMs. Some LLM prompts according to some embodiments may include different sets input parameters of different types-such as, e.g., a set of block parameters and a set of editorial parameters. In some embodiments, a model or LLM may be updated or retrained using a reinforcement learning approach and based output items or refined responses generated by that model or LLM-which may for example be scored or ranked and used in combination with reward or cost functions to update model parameters.

A system and method for extracting data from large language model (LLM) outputs, including: training a model using labeled data items to assign rankings to LLMs; selecting, by the trained model, one or more of the LLMs based on the rankings; sending an LLM prompt to selected models; and outputting, by the model, a refined response to the prompt based on responses to the prompt by the LLMs. Some LLM prompts according to some embodiments may include different sets input parameters of different types—such as, e.g., a set of block parameters and a set of editorial parameters. In some embodiments, a model or LLM may be updated or retrained using a reinforcement learning approach and based output items or refined responses generated by that model or LLM-which may for example be scored or ranked and used in combination with reward or cost functions to update model parameters.

The invention discloses a ranking list determination method and device which can be applied to the field of data processing, and the method comprises the steps that ranking list data are efficiently stored and ranked through an ordered set of Redis, each user serves as an element, and the invitation amount of each user serves as a score. When each preset updating time is satisfied, whether the invitation amount information of the target user is changed or not is checked. If the current ranking information changes, the ranking of the target user is recalculated according to the new invitation quantity information, and the offline ranking list is dynamically updated to ensure that the updated ranking list can accurately reflect the current ranking information of the user. Namely, the ranking list is stored through redis, and before the next timed task is executed, the ranking list is kept unchanged, so that the write-in frequency of the database can be reduced, the storage cost caused by frequent write-in is reduced, and resource waste is avoided.

This invention discloses a method for ranking reserve projects for new power grid infrastructure, comprising: constructing a ranking indicator system from five dimensions: power grid development, security and supply, service quality, efficiency and effectiveness, and green and low-carbon development; collecting raw indicator data and distinguishing indicator types; obtaining objective weights for the indicators through a combination of two objective weighting methods; constructing a matrix by standardization transformation and weight combination; calculating relative proximity to form an objective ranking; subsequently integrating expert rankings; obtaining a subjective consensus ranking by constructing a pairwise preference matrix and an integer programming model; and finally, calculating standardized scores and weighted fusion of the subjective and objective ranking results using a weighted aggregation method to determine the ranking position of the reserve projects. This method balances data objectivity and expert experience, covers the core requirements of projects from multiple dimensions, has a rigorous ranking logic, and effectively improves the scientificity and accuracy of ranking reserve projects for new power grid infrastructure.

Various embodiments of the present disclosure provide computer forecasting techniques for initiating presentation of an interactive user interface. The techniques may include receiving one or more candidate prediction-based actions and generating a plurality of causal risk-based impact scores with respect to a candidate prediction-based action. The techniques include generating a plurality of causal quality-based impact scores and an action sequence for a plurality of evaluation entities and generating a causal net impact score based on (i) an aggregation of the plurality of causal risk-based impact scores and the plurality of causal quality-based impact scores and (ii) a sequence impact metric corresponding to the action sequence. The techniques include generating a sequence ranking for the action sequence and initiating a presentation of an interactive user interface reflective of the action sequence and the sequence ranking.

An example may train a cross encoder embedding model using a ranking instruction, a combined input, a pseudo label, and a combined loss. The combined loss includes a ranking loss and a first retrieval loss. A first entity embedding of an entity and a first item embedding of an item may be obtained from the trained cross encoder embedding model. A first input including the first entity embedding obtained from the trained cross encoder embedding model, a second input including the first item embedding obtained from the trained cross encoder embedding model, and a second retrieval loss, may be used to train a dual encoder retrieval model to produce a trained dual encoder retrieval model. A system may use output of the trained dual encoder retrieval model to include or exclude items from a presentation of digital content items to the entity via a device.

The invention relates to an industrial and commercial enterprise management method and system based on the Internet of Things, and the method comprises the steps: obtaining production operation data and equipment asset data through Internet of Things equipment, and generating a structured data set according to the classification of preset service labels; based on the production operation data set, optimizing a production plan and productivity matching through a constrained programming algorithm, and generating a production scheduling scheme in combination with an equipment state; based on the equipment asset data set, utilizing a machine learning model to predict an equipment fault and calculate a maintenance period, and combining a maintenance standard to generate an equipment asset maintenance plan; and performing time conflict detection and resource allocation optimization on the production scheduling scheme and the equipment asset maintenance plan, and generating a comprehensive management scheme through a multi-target priority ranking algorithm. According to the method, by dynamically coordinating production resources and equipment maintenance tasks, the productivity utilization rate and the equipment reliability are improved, the non-planned shutdown loss is reduced, and collaborative optimization of enterprise operation efficiency and cost control is achieved.

The invention relates to the technical field of information security, in particular to a sequential cipher security analysis method for a composite structure, which comprises the following steps of: acquiring round function parameters of a target cipher algorithm, nonlinear component definition and a key scheduling rule, and generating a standardized configuration data set; dividing the complete algorithm into a plurality of independent low wheel structures along the boundary of the nonlinear component according to the wheel function parameters, and constructing a directed graph data model containing state transition constraints to compress a state space; calling a password component vulnerability feature library to quantify a sub-structure active S box distribution abnormal value and a linear diffusion layer vulnerability path, and generating a risk weight priority ranking list; and inputting the state sequence data into the target application environment simulation platform, and generating a reproducible vulnerability report when the output deviation exceeds a security threshold. Through hierarchical compression, risk guidance and multi-environment verification, the technical defect of insufficient path coverage of a high-round-number lightweight algorithm in a resource-limited scene is solved.

The invention relates to the technical field of deep learning, and discloses a two-stage text classification method, which comprises the following steps of: inputting a target text and a label description text of a classification label into a first text encoder to obtain K alternative labels with the highest similarity with the target text; respectively constructing the target text and the label description text of each alternative label to obtain K combined texts; inputting each combined text into a second text encoder to obtain a matching probability of the target text and each alternative label; and selecting the alternative label with the maximum matching probability as the classification category of the target text. According to the method, the alternative labels with relatively high similarity with the target text are screened out from the classification labels through the first text encoder, and then the target text and each alternative label are finely arranged through the second encoder, so that the matching probability of the target text and each alternative label is obtained; and selecting the alternative label with the highest matching probability as the classification category of the target text, so that the classification precision of the limit label text classification task can be improved.

The application is suitable for the computer field, and provides an article recommendation sorting method and device, computer equipment and a storage medium, which comprises the following steps: obtaining log information of a target user and to-be-recommended articles, wherein the log information comprises user information and a user click sequence; pre-processing the obtained user information and the user click sequence to generate first-order features, and processing part of the first-order features to obtain second-order features; determining one-hot coding of the to-be-recommended articles, and mapping the one-hot coding of a plurality of to-be-recommended articles into distinguishable low-dimensional vectors; constructing a training set according to the first-order features, the second-order features and the low-dimensional vectors of the to-be-recommended articles, and training a LightGBM model; generating a similarity result of the user click sequence and the to-be-recommended articles according to the LightGBM model, and recommending articles in the to-be-recommended articles to the target user according to the similarity result. The article recommendation sorting method can reduce the storage space of the model, improve the updating and iteration speed of the model, and further improve the efficiency of article recommendation sorting.

Embodiments of the present application disclose a kind of object processing method, device, equipment, storage medium and program product, at least involve blockchain technology, for reducing the complexity of calculation and gas consumption, quickly and efficiently calculate object ranking.The method comprises: obtaining the target index value of target object and the first identification of the request to be processed, target tree data structure, target tree data structure includes N level first search node of cascade, the first search node of each level includes index value sequence and object quantity;Target tree data structure is traversed, and target index value is determined from N level first search node of cascade based on target index value Target search node;First object quantity is determined based on target index value, the index value sequence of target search node and object quantity, and second object quantity is determined based on target index value, the first identification, the index value sequence of target search node and object quantity;First object quantity and second object quantity are determined based on target index value, and the target ranking of target object is determined.

The present disclosure provides a method, apparatus, device and storage medium for determining a ranking model. It relates to the field of computer technology, and in particular to the fields of data processing, machine learning, intelligent search, and intelligent recommendation. The specific implementation scheme is: obtaining a sample set and a feature set of a target product; determining a candidate ranking model for the target product from a model library; determining a target feature set for the target product based on the feature set, where the target feature set is a set of features used for model parameter adjustment; adjusting the parameters of the candidate ranking model based on the sample set and the target feature set to obtain a target ranking model for the target product, which is used to predict the click-through rate of the target product's resources. According to the technical solution of the present disclosure, a target ranking model that is suitable for each product can be provided, thereby improving the recommendation performance of each product.

A multi-label ranking method includes receiving, at a processor and from a first set of artificial neural networks (ANNs), multiple signals representing a first set of ANN output pairs for a first label. A signal representing a second set of ANN output pairs for a second label different from the first label is received at the processor from a second set of ANNs different from the first set of ANNs, substantially concurrently with the first set of ANN output pairs. A first activation function is solved based on the first set of ANN output pairs, and a second activation function is solved based on the second set of ANN output pairs. Loss values are calculated based on the solved activations, and a mask is generated based on at least one ground truth label. A signal, including a representation of the mask, is sent from the processor to each of the sets of ANNs.

This invention discloses a sequence recommendation method based on the fusion of positive and negative feedback and logical rules, comprising: dividing user behavior into positive and negative feedback; constructing a feedback sequence, including positive and negative feedback sequences, based on user behavior and time sequence; processing the features of the user behavior sequence and the feedback sequence to obtain corresponding embedded features; using the self-attention mechanism of a deep learning model to process the input embedded features, capturing the internal dependency features of the original user behavior sequence; and using a cross-attention mechanism to cross-associate the feedback sequence and the input user behavior sequence to capture the dynamic relationship between user behavior and feedback; and through an output layer, mapping the model's intermediate features to user preference ratings for target items, outputting a rating list for recommendation ranking. This invention significantly improves the performance, interpretability, and adaptability of recommendation systems by combining positive and negative feedback information from user behavior with logical rules.

The invention discloses a recommendation method based on interpretable generalized logic transformation matrix decomposition. The recommendation method comprises the following steps: converting an original scoring matrix into normal distribution data through a generalized logic transformation function; constructing indexes based on similarity and indexes based on ranking; calculating probability distribution and expected scores of scores of the recommended items by the similar users, and generating interpretability indexes in combination with the similarity indexes; integrating the interpretability index into a matrix decomposition objective function for optimization; solving a user feature matrix and a project feature matrix through an alternating least square method or stochastic gradient descent; calculating a prediction score and mapping the prediction score back to an original score interval through generalized logic inverse transformation; generating a recommendation list; the method provided by the invention has wider applicability and higher performance in practical application.

Approximating a more complex multi-objective feed item scoring model using a less complex single objective feed item scoring model in a multistage feed ranking system of an online service. The disclosed techniques can facilitate multi-objective optimization for personalizing and ranking feeds including balancing personalizing a feed for viewer experience, downstream professional or social network effects, and upstream effects on content creators. The techniques can approximate the multi-objective model-that uses a rich set of machine learning features for scoring feed items at a second pass ranker in the ranking system-with the more lightweight, single objective model-that uses fewer machine learning features at a first pass ranker in the ranking system. The single objective model can more efficiently score a large set of feed items while maintaining much of the multi-objective model's richness and complexity and with high recall at the second pass ranking stage.

The invention discloses an electric power fault diagnosis method, system and device based on large model retrieval enhancement and a medium, and belongs to the technical field of electric power fault diagnosis, and the method comprises the steps: carrying out the preprocessing of an electric power fault problem, and obtaining a sub-problem; executing vectorization retrieval in the electric power overhaul knowledge base for the sub-problems; performing secondary sorting on the reference data, and performing fine sorting on the retrieval results of the sub-problems by adopting a learning sorting model; performing fusion sorting on the fine sorting results of the sub-questions, distributing scores based on a reciprocal ranking and calculating a combined score, and rejecting reference data with the scores lower than a preset threshold value to obtain an optimized reference set; and inputting the optimized reference set and the power fault problem into the large language model to generate a power fault diagnosis result and a solution. According to the method, the knowledge of the large language model is supplemented by using the external knowledge base, the illusion generation is reduced, the large language model can automatically process the question in the answer generation process, and a more accurate fault diagnosis and solution can be generated.

The application provides a game ranking list updating method and device and electronic equipment, score change data in a current season, a first ranking list of the current season and a second ranking list of a last season of the current season are acquired; the first ranking list and the second ranking list save the same data; based on the score change data and the second ranking list, the first ranking list and a third ranking list of a next season of the current season are updated, to obtain an updated first ranking list and an updated third ranking list; when the current season ends, the updated first ranking list and the updated third ranking list are saved, and the updated first ranking list and the updated third ranking list save the same data. The method writes the current season and the next season at the same time when the ranking list is updated, so that there is a snapshot of the old season when the season is switched, and the ranking list of the new season directly inherits from the old ranking list, there is no off-season, and the original old season ranking list does not need to be blocked and copied.

Technologies for skill taxonomy management are described. Embodiments include extracting an input text from an online system and applying an unsupervised generative text machine learning model to the input text. The text generator generates a set of sentences based on a job title included in the input text. One or more skills are extracted from the set of sentences. The extracted one or more skills correspond to one or more skills in a skill taxonomy. A frequency distribution is generated over the extracted one or more skills. The one or more skills are ranked based on the frequency distribution. Based on the ranking, a subset of the extracted one or more skills is generated. The subset of the extracted one or more skills is provided to a downstream operation, process, or service of the online system.

Embodiments of the present disclosure provide a ranking optimization method and device, equipment and a storage medium. The method comprises: obtaining predicted scores and real scores of a recommendation object on each target; determining abnormal vertical categories and corresponding abnormal targets according to the predicted scores and real scores of the recommendation object on each target, to form abnormal combination items; generating weight optimization items matched with each abnormal combination item, correcting a multi-target fusion formula according to the weight optimization items; calculating final scores of each recommendation object using the corrected multi-target fusion formula, and ranking each recommendation object according to the final scores. Through the above technical solution, the accuracy of ranking is improved by adding weight optimization items to the multi-target fusion formula to optimize the abnormal vertical categories and corresponding targets of the prediction results.

The disclosed embodiments provide a system for simplifying machine learning. During operation, the system determines the resource overhead for a baseline version of a machine learning model that uses a set of features to generate entity rankings; and determines the number of features to be removed to reduce the resource overhead to a target resource overhead. Next, the system calculates importance scores for the features, where each importance score represents the impact of the corresponding feature on the entity ranking. The system then identifies a first subset of features to be removed as a plurality of features with the lowest importance scores; and trains a simplified version of the machine learning model using a second subset of features excluding the first subset of features. Finally, the system executes the simplified version to generate a new entity ranking.

The invention relates to the technical field of education and teaching management, in particular to a ranking increment-based teaching assessment method and analysis system. The total data comprises class ranking of the to-be-analyzed object, class average score of the to-be-analyzed object, class level of the to-be-analyzed object, class average score of all classes of the same level, end-of-period ranking of the to-be-analyzed object, end-of-period average score of the to-be-analyzed object, and end-of-period average score of all classes of the same level. According to the method, total data including class levels and test question difficulty coefficients are collected, and level feature factors are calculated according to historical score distribution of classes of all levels so as to distinguish ranking fluctuation sensitivity of classes of different levels, so that the problem of'one-cut 'of a unified regression equation of an existing method is avoided; and carrying out two-dimensional calibration of the level characteristic factor and the test question difficulty coefficient on the basic ranking difference, and correcting the interference of the level characteristic and the test difficulty on the ranking.

The present invention is applicable to the logistics field and provides an order value stratification method, a computer-readable storage medium, and a computer device, including obtaining a historical transaction data sample of an order; modeling based on the historical transaction data sample of the order and selecting relevant features of each order; inputting the relevant features into a machine learning model, and the machine learning model sorts the importance of the relevant features according to the size of the gain value with the completion of the order as the goal; screening important features as the input of a regression model according to the importance ranking of the relevant features, and outputting the weight values corresponding to the important features with the completion of the order as the goal; calculating the feature values of the important features, multiplying the feature values by the weight values corresponding to the important features, and summing the products to obtain an order score; sorting according to the order score and dividing the orders into multiple layers according to the sorting. This makes the order value not affected by the current supply and demand and the driver level.

Certain examples of this disclosure provide a method (100) for determining points of interest (200) along a route (400), the method comprising: determining (101) a first set (300) of points of interest (POIs) that meet one or more first criteria (500) along the route; dividing (102) the route into multiple segments (700); associating each one or more points of interest in the first set of POIs with one of the multiple segments of the route (103); ranking each one or more POIs in the first set of POIs (104), wherein the ranking is at least partially based on one or more second criteria (900); for each segment, selecting (105) a threshold number (N) of the highest-ranked POIs associated with the corresponding segment; and generating a second set of POIs at least partially based on the selected POIs.

The embodiment of the invention discloses a display method and device based on a ranking list, computer equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: displaying a first virtual object of a first account in a hall interface; a second virtual object of a second account in the target ranking list is displayed to enter a hall interface, ranking information of the second account in the target ranking list is further displayed beside the second virtual object, and the second account is any account in the target ranking list; and displaying that the second virtual object moves in the hall interface. According to the method and the device, the player can see the second account in the ranking list without manually clicking to enter the ranking list, so that the account in the target ranking list is actively displayed to the player. Moreover, the player can visually see that the virtual object of the second account appears in the hall interface of the player, so that the interestingness of the ranking list display mode is improved, and the game experience of the player is improved.

The invention provides a multi-target task determination method and device based on Pareto optimum and a storage medium, and belongs to the technical field of multi-target optimization. The determination method comprises the following steps: for a multi-target task solved by a multi-target optimization algorithm, selecting a plurality of performance indexes for measuring the multi-target task; calculating the performance of each multi-objective optimization algorithm in each performance index to form a multi-level Pareto leading edge; based on the multi-level Pareto leading edge, adopting at least one preset ranking algorithm to calculate the ranking of each multi-objective optimization algorithm; and determining a corresponding multi-target task according to the calculated ranking of each multi-target optimization algorithm. A plurality of performance indexes are considered, prejudice caused by introduction of a single performance index is reduced, and a multi-target task is solved more comprehensively; fairly and reasonably selecting the algorithm by using a non-dominated sorting algorithm; multiple ranking methods are configured for the algorithm; and the user can understand a plurality of algorithms for solving the multi-target task visually.

The application discloses a target attack priority ranking method and device based on intelligent evaluation, equipment and a medium, and relates to the technical field of data processing.The method comprises the following steps: a target attack priority ranking evaluation index system is constructed; the evaluation index system comprises first-layer indexes and second-layer indexes; the first-layer indexes at least comprise category-type indexes, and the second-layer indexes are used for predicting and evaluating the category-type indexes in the first-layer indexes; a target evaluation decision matrix is constructed based on the first-layer indexes, wherein the values of the category-type indexes in the first-layer indexes are calculated by using an intelligent evaluation method based on a neural network; the weights of the first-layer indexes are calculated by using an entropy weight method; the closeness degrees of the targets are calculated by using a TOPSIS method; the comprehensive correlation degrees of the targets are calculated by using a grey correlation analysis method; the comprehensive evaluation values of the targets are weighted and calculated based on the closeness degrees and the comprehensive correlation degrees; and the targets are ranked according to the comprehensive evaluation values. The application greatly improves the scientificity, objectivity and reliability of the target ranking result.

The invention belongs to the technical field of computer-aided systems, and discloses a volunteer filling system and method based on dynamic ranking, and the method comprises the steps: collecting the score data of an examinee through an examinee score collection module; the enrollment plan acquisition module acquires enrollment plan data; the volunteer filling module receives volunteer filling data input by the examinee; the admission rule definition module generates a file-filling template based on the file-filling main template and a plurality of sub-templates; the ranking operation module is combined with the examinee score data, the enrollment plan data and the volunteer filling data and generates a ranking operation result based on the file filling template; and the ranking display module dynamically displays the volunteer ranking of the examinee and the corresponding admission result based on the ranking operation result. Through the above mode, the method achieves the dynamic ranking of volunteer filling and the dynamic announcement of an admission score line.