Workflow
模型训练方法
icon
Search documents
腾讯申请模型训练及推荐相关专利,提高推荐模型的训练效率
Jin Rong Jie· 2025-08-23 01:24
Group 1 - Tencent Technology (Shenzhen) Co., Ltd. has applied for a patent titled "Model Training Method, Recommendation Method, Device, Electronic Equipment, Computer Program Product, and Computer-Readable Storage Medium" with publication number CN120524221A, filed on February 2024 [1] - The patent application describes a method that includes obtaining a recommendation model to be trained, multiple training samples, and their label information, followed by feature mapping of each training sample to obtain embedding vectors [1] - The method involves feature fusion mapping of first and second click message sequences using a shared dynamic embedding table to derive fused embedding vectors, which are then used to train the recommendation model [1] Group 2 - Tencent Technology (Shenzhen) Co., Ltd. was established in 2000 and is primarily engaged in software and information technology services, with a registered capital of 2 million USD [2] - The company has invested in 15 enterprises, participated in 264 bidding projects, and holds 5000 trademark and patent information records, along with 535 administrative licenses [2]
小米取得用户行为预测相关专利
Jin Rong Jie· 2025-08-22 01:40
Group 1 - The State Intellectual Property Office of China has granted a patent to Beijing Xiaomi Mobile Software Co., Ltd. and Beijing Xiaomi Pinecone Electronics Co., Ltd. for a technology related to "user behavior prediction methods, model training methods, electronic devices, and storage media" [1] - Beijing Xiaomi Mobile Software Co., Ltd. was established in 2012, has a registered capital of 148.8 million RMB, and has participated in 139 bidding projects, with a total of 5000 patent records [1] - Beijing Xiaomi Pinecone Electronics Co., Ltd. was founded in 2014, has a registered capital of 25 million RMB, and holds 15 trademark records and 1046 patent records [1]
腾讯取得推广数据处理相关专利
Jin Rong Jie· 2025-08-22 01:33
Group 1 - The core point of the article is that Tencent Technology (Shenzhen) Co., Ltd. has obtained a patent for a data processing method, model training method, system, and storage medium, with the patent number CN113570398B, applied for on February 2021 [1] - Tencent Technology was established in 2000 and is primarily engaged in software and information technology services, with a registered capital of 2 million USD [1] - The company has invested in 15 enterprises and participated in 264 bidding projects, holding 5000 trademark records and 5000 patent records, along with 537 administrative licenses [1]
腾讯申请模型训练及信息投放相关专利,提高投放预测模型的准确性
Jin Rong Jie· 2025-08-07 03:21
Core Insights - Tencent Technology (Shenzhen) Co., Ltd. has applied for a patent titled "Model Training Method, Information Delivery Method, Device, Equipment, and Medium," with publication number CN120430833A, filed on February 2024 [1] - The patent describes a method that involves obtaining positive samples, negative samples, and unlabeled samples, which are used to train a label prediction model and a delivery prediction model [1] Company Overview - Tencent Technology (Shenzhen) Co., Ltd. was established in 2000 and is located in Shenzhen, primarily engaged in software and information technology services [1] - The company has a registered capital of 2 million USD and has invested in 15 enterprises, participated in 263 bidding projects, and holds 5000 trademark records and 5000 patent records [1] - Additionally, the company possesses 527 administrative licenses [1]
腾讯申请模型训练方法、装置、电子设备及存储介质专利,提升相关程度预测模型的语义理解能力以及泛化能力
Jin Rong Jie· 2025-08-07 02:54
Group 1 - Tencent Technology (Beijing) Co., Ltd. has applied for a patent titled "Model Training Method, Device, Electronic Equipment, and Storage Medium" with publication number CN120430298A, filed on April 2025 [1] - The patent describes a method that includes obtaining sample text pairs and labeling their relevance categories, constructing a first prompt text for predicting text relevance, and training a large language model based on predicted probabilities [1] - The implementation aims to enhance the semantic understanding and generalization ability of the relevance prediction model [1] Group 2 - Tencent Technology (Beijing) Co., Ltd. was established in 2005 and is primarily engaged in software and information technology services, with a registered capital of 1.6 million USD [2] - The company has made investments in 9 enterprises, participated in 47 bidding projects, and holds 1,426 patent records, along with 159 administrative licenses [2]
腾讯申请模型训练方法、装置、电子设备及存储介质专利,提升模型推理准确性
Jin Rong Jie· 2025-08-05 13:22
Group 1 - Tencent Technology (Shenzhen) Co., Ltd. has applied for a patent titled "Model Training Method, Device, Electronic Equipment, and Storage Medium" with publication number CN120431962A, filed on June 2025 [1] - The patent describes a method that includes obtaining sample data sets for multiple training stages, sorted by training difficulty from easy to hard, and training an initial model based on these data sets [1] - The method aims to enhance the accuracy of model inference through a multi-stage training process, which includes optimizing the model based on the correctness of inference results and applying reinforcement learning to achieve a target model [1] Group 2 - Tencent Technology (Shenzhen) Co., Ltd. was established in 2000 and is primarily engaged in software and information technology services, with a registered capital of 2 million USD [2] - The company has invested in 15 enterprises and participated in 263 bidding projects, holding 5000 trademark records and 5000 patent records, along with 527 administrative licenses [2]
腾讯申请模型训练方法相关专利,保证目标模型迭代方向的正确性
Jin Rong Jie· 2025-08-05 07:19
Group 1 - Tencent Technology (Shenzhen) Co., Ltd. applied for a patent titled "Model Training Method, Device, Equipment, Storage Medium, and Computer Program Product" with publication number CN120409606A, filed on April 2025 [1] - The patent application describes a method that includes determining the first preference difference of a target model for training samples and the second preference difference of a reference model for the same samples [1] - The method aims to ensure the correctness of the iteration direction of the target model by calculating total loss values based on preference differences and updating the model parameters accordingly [1] Group 2 - Tencent Technology (Shenzhen) Co., Ltd. was established in 2000 and is primarily engaged in software and information technology services, with a registered capital of 2 million USD [2] - The company has invested in 15 enterprises and participated in 263 bidding projects, holding 5000 trademark records and 5000 patent records [2] - Additionally, the company possesses 527 administrative licenses [2]
网宿科技取得模型训练方法等相关专利
Jin Rong Jie· 2025-08-02 03:16
Group 1 - The core point of the article is that Wangsu Technology Co., Ltd. has obtained a patent for a "model training method, system, electronic device, and storage medium" with the authorization announcement number CN114239848B, applied for on November 2021 [1] - Wangsu Technology Co., Ltd. was established in 2000 and is located in Shanghai, primarily engaged in software and information technology services [1] - The registered capital of Wangsu Technology Co., Ltd. is 2,445.73 million RMB [1] Group 2 - According to data analysis from Tianyancha, Wangsu Technology Co., Ltd. has invested in 39 companies and participated in 1,125 bidding projects [1] - The company has 269 trademark information entries and 1,292 patent information entries, along with 6 administrative licenses [1]
腾讯申请图像分类方法等相关专利,有效提升图像分类的准确性
Jin Rong Jie· 2025-06-27 00:46
Group 1 - Tencent Technology (Shenzhen) Co., Ltd. has applied for a patent titled "Image Classification Method, Model Training Method, Device and Electronic Equipment," with publication number CN120219784A, and the application date is December 2023 [1] - The patent describes a method that improves image classification accuracy by using a target loss to constrain the relationship between confidence scores of sample images and target noise images, which helps avoid misclassification due to noise in the background or semantic areas [1] - The technology has potential applications in various fields, including artificial intelligence, medical detection, and smart transportation [1] Group 2 - Tencent Technology (Shenzhen) Co., Ltd. was established in 2000 and is primarily engaged in software and information technology services, with a registered capital of 2 million USD [2] - The company has invested in 15 enterprises and participated in 259 bidding projects, holding 5000 trademark records and 5000 patent records, along with 469 administrative licenses [2]
三峡集团申请风速区间预测相关专利,提高短期风速区间的预测精度
Jin Rong Jie· 2025-05-24 09:55
Group 1 - China Three Gorges Corporation applied for a patent titled "Wind Speed Interval Prediction Method, Model Training Method, Device, Equipment and Medium" with publication number CN120030096A, filed on December 2024 [1] - The patent involves a method for predicting wind speed intervals using a model training approach that includes inputting raw wind speed data into multiple gated convolutional layers with different window sizes [1] - The outputs from these layers are processed through a fully connected layer to produce upper and lower limits for the predicted wind speed intervals, optimized through a predefined loss function [1] Group 2 - China Three Gorges Corporation, established in 1993 and located in Wuhan, primarily engages in electricity and heat production and supply, with a registered capital of 21,150 million RMB [2] - The company has made investments in 40 enterprises, participated in 5,000 bidding projects, and holds 96 trademark records and 4,786 patent records [2] - China Three Gorges Corporation also possesses 59 administrative licenses [2] Group 3 - Three Gorges Jinsha River Yuncun Hydropower Development Co., Ltd., founded in 2013 and based in Kunming, also focuses on electricity and heat production and supply, with a registered capital of 5,600 million RMB [2] - This subsidiary has participated in 755 bidding projects and holds 923 patent records [2] - The company has 14 administrative licenses [2]