-
公开(公告)号：US11954522B2
公开(公告)日：2024-04-09
申请号：US17076346
申请日：2020-10-21
Inventor： Daxiang Dong , Haifeng Wang , Dianhai Yu , Yanjun Ma
CPC classification number: G06F9/4881 , G06F9/52 , G06N20/00
Abstract: Embodiments of the present disclosure disclose a method for processing tasks in parallel, a device and a storage medium, and relate to a field of artificial intelligent technologies. The method includes: determining at least one parallel computing graph of a target task; determining a parallel computing graph and an operator scheduling scheme based on a hardware execution cost of each operator task of each of the at least one parallel computing graph in a cluster, in which the cluster includes a plurality of nodes for executing the plurality of operator tasks, and each parallel computing graph corresponds to at least one operator scheduling scheme; and scheduling and executing the plurality of operator tasks of the determined parallel computing graph in the cluster based on the determined parallel computing graph and the determined operator scheduling scheme.
-
公开(公告)号：US11651002B2
公开(公告)日：2023-05-16
申请号：US16193454
申请日：2018-11-16
Inventor： Daxiang Dong , Jun Zhang , Dianhai Yu
IPC: G06F16/248 , G06F16/33 , G06F16/332 , G06F16/2457 , G06F7/16 , G06N3/04 , G06N3/08
CPC classification number: G06F16/248 , G06F7/16 , G06F16/24578 , G06F16/3326 , G06F16/3334 , G06N3/04 , G06N3/08
Abstract: A method for providing an intelligent service, an intelligent service system and an intelligent terminal based on artificial intelligence. The method comprises: receiving a first service request from a user (102); determining a search term and the weight thereof for the first service request (104); providing a first service result according to the search term and the weight thereof (106); and collecting feedback information for the first service result from the user, and adjusting, in real time, the search term and/or the weight thereof for the first service request, according to evaluation information in the feedback information (108).
-
公开(公告)号：US11481419B2
公开(公告)日：2022-10-25
申请号：US15981334
申请日：2018-05-16
Inventor： Shengxian Wan , Yu Sun , Dianhai Yu
IPC: G06N3/04 , G06F16/33 , G06N5/04 , G06K9/62 , G06F40/258 , G06V30/262
Abstract: The present disclosure provides a method and apparatus for evaluating a matching degree based on artificial intelligence, a device and a storage medium, wherein the method comprises: respectively obtaining word expressions of words in a query and word expressions of words in a title; respectively obtaining context-based word expressions of words in the query and context-based word expressions of words in the title according to the word expressions; generating matching features according to obtained information; determining a matching degree score between the query and the title according to the matching features. The solution of the present disclosure may be applied to improve the accuracy of the evaluation result.
-
14.发明授权公开(公告)号：US11238097B2
公开(公告)日：2022-02-01
申请号：US16000160
申请日：2018-06-05
Inventor： Zhiliang Tian , Daxiang Dong , Dianhai Yu
IPC: G06N3/00 , G06F16/901 , G06N5/02 , G06N3/04 , G06F40/30
Abstract: A method and apparatus for recalling news based on artificial intelligence, a device and a storage medium. The method comprises: building an index repository according to candidate news, the index repository including M search trees, each search tree being a complete binary tree including at least two layers, each non-leaf node in each search tree corresponding to a semantic index vector, each piece of candidate news corresponding to a leaf node in each search tree; when news needs to be recommended to the user, generating a user's semantic index vector according to the user's interest tag; with respect to each search tree, respectively according to semantic index vectors corresponding to non-leaf nodes therein and the user's semantic index vector, determining a path from a first layer of non-leaf nodes to a leaf node, and regarding candidate news corresponding to the leaf node on the path as a recall result.
-
公开(公告)号：US20180336266A1
公开(公告)日：2018-11-22
申请号：US15891258
申请日：2018-02-07
Inventor： Liwei Chen , Xiao Zhou , Dianhai Yu , Shiqi Zhao
CPC classification number: G06F16/3325 , G06F16/3329 , G06F16/951 , G06N3/02 , G06N3/0445 , G06N5/022 , H04L51/02
Abstract: The present disclosure discloses an interaction method and apparatus based on artificial intelligence. A specific embodiment of the method comprises: receiving a current interactive statement entered by a user through a terminal; extracting at least one type of characteristic based on the current interactive statement and a previous interactive statement entered by the user; processing the at least one type of characteristic using a pretrained neural network model to determine whether an intent maintaining relationship exists between the current interactive statement and the previous interactive statement; and if the intent maintaining relationship exists, updating a limitation condition for the previous interactive statement using the current interactive statement, performing information retrieval using the previous interactive statement with the updated limitation condition, and pushing a retrieved retrieval result to the terminal. This embodiment reduces time spent in user entry.
-
Patent Agency Ranking
公开(公告)号：US12229667B2
公开(公告)日：2025-02-18
申请号：US17209576
申请日：2021-03-23
Inventor： Daxiang Dong , Wenhui Zhang , Zhihua Wu , Dianhai Yu , Yanjun Ma , Haifeng Wang
IPC: G06N3/08 , G06F9/50 , G06F18/214
Abstract: A method and an apparatus for generating a shared encoder are provided, which belongs to a field of computer technology and deep learning. The method includes: sending by a master node a shared encoder training instruction to child nodes, so that each child node obtains training samples based on a type of a target shared encoder included in the training instruction; sending an initial parameter set of the target shared encoder to be trained to each child node after obtaining a confirmation message returned by each child node; obtaining an updated parameter set of the target shared encoder returned by each child node; determining a target parameter set corresponding to the target shared encoder based on a first preset rule and the updated parameter set of the target shared encoder returned by each child node.
-
公开(公告)号：US12217150B2
公开(公告)日：2025-02-04
申请号：US17248131
申请日：2021-01-11
Inventor： Huihuang Zheng , Xiang Lan , Yamei Li , Liujie Zhang , Fei Guo , Yanjun Ma , Dianhai Yu
Abstract: A data processing method and apparatus based on a recurrent neural network and a device are provided. The recurrent neural network includes multiple recurrent units, each recurrent unit includes multiple data processing nodes and a start node, at least one recurrent unit includes an end node, and at least one data processing node is included between the start node and the end node. During the processing of the first target processing object in a first recurrent unit, in a case that the first target processing object does not satisfy the first preset condition, the start node in the first recurrent unit is run to add a tag to the data processing nodes subsequent to the start node and stop addition of the tag in response to reaching the end node, and no processing is performed by the data processing nodes with the tag.
-
18.发明申请公开(公告)号：US20210326762A1
公开(公告)日：2021-10-21
申请号：US17351194
申请日：2021-06-17
Inventor： Zhihua Wu , Dianhai Yu , Xuefeng Yao , Wei Tang , Xinxuan Wu , Mo Cheng , Lin Ma , Yanjun Ma , Tian Wu , Haifeng Wang
IPC: G06N20/00
Abstract: The present disclosure discloses an apparatus and method for distributedly training a model, an electronic device, and a computer readable storage medium. The apparatus may include: a distributed reader, a distributed trainer and a distributed parameter server that are mutually independent. A reader in the distributed reader is configured to acquire a training sample, and load the acquired training sample to a corresponding trainer in the distributed trainer; the trainer in the distributed trainer is configured to perform model training based on the loaded training sample to obtain gradient information; and a parameter server in the distributed parameter server is configured to update a parameter of an initial model based on the gradient information of the distributed trainer to obtain a trained target model.
-
公开(公告)号：US20210216875A1
公开(公告)日：2021-07-15
申请号：US17218033
申请日：2021-03-30
Inventor： Tianjian He , Yi Liu , Daxiang Dong , Yanjun Ma , Dianhai Yu
Abstract: A method for training a deep learning model may include: acquiring model description information and configuration information of a deep learning model; segmenting the model description information into at least two sections based on segmentation point variable in the configuration information, and loading the model description information to a corresponding resource to run; inputting a batch of training samples into a resource corresponding to a first section of model description information, then starting training and using obtained context information as an input of a resource corresponding to a subsequent section of model description information; and so on until an operation result of a resource corresponding to a final section of model description information is obtained; if a training completion condition is met, outputting a trained deep learning model; and otherwise, keeping on acquiring a subsequent batch of training samples and performing the above training steps until the condition is met.
-
公开(公告)号：US10977578B2
公开(公告)日：2021-04-13
申请号：US16006213
申请日：2018-06-12
Inventor： Ke Sun , Shiqi Zhao , Dianhai Yu , Haifeng Wang
Abstract: A conversation processing method and apparatus based on artificial intelligence, a device and a computer-readable storage medium. The disclosure embodiments, enable the user feedback information provided by conversation service conducted by the user to model conversation understanding system, then according to the user feedback information, perform adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system so that it is possible to execute the conversation service with the model conversation understanding system, based on the adjustment state. Since a fault-tolerant and fault-correcting mechanism is provided, it is possible to adjust the understanding capability of the model conversation understanding system in real time and thereby effectively improve the reliability of conversation by collecting the user's user feedback information, and then adjusting the service state of the model conversation understanding system in time based on the user feedback information.
-
-
-
-
-
-
-
-
-
Search Results
23
records
(took 0.027 seconds)
