-
公开(公告)号：EP4116839A1
公开(公告)日：2023-01-11
申请号：EP21774325.1
申请日：2021-02-23
发明人： LI, Weiguo , QIAN, Li , JIANG, Xin
IPC分类号： G06F16/33
摘要： Embodiments of this application provide a voice interaction method and an electronic device, and relate to the field of artificial intelligence AI technologies and the field of voice processing technologies, to improve performance of the electronic device in interaction with a user, thereby providing the user with individualized voice interaction experience. A specific solution includes: An electronic device may receive first voice information sent by a second user, and the electronic device recognizes the first voice information in response to the first voice information. The first voice information is used to request a voice conversation with a first user. The electronic device may have, on a basis that the electronic device recognizes that the first voice information is voice information of the second user, a voice conversation with the second user by imitating a voice of the first user and in a mode in which the first user has a voice conversation with the second user. The method may be applied to a scenario in which an intelligent robot accompanies and educates a child in place of parents.
-
公开(公告)号：EP4089587A1
公开(公告)日：2022-11-16
申请号：EP20919261.6
申请日：2020-09-25
发明人： HOU, Lu , SHANG, Lifeng , JIANG, Xin
摘要： This application relates to the field of artificial intelligence, and discloses a data processing method, including: obtaining a first neural network model and an available resource state of a terminal device; and determining a second neural network model based on the available resource state. In this application, an appropriate model size may be determined based on the available resource state, and a part of the first neural network model is selected, based on the determined model size, as the second neural network model on which data processing is to be performed, thereby reducing a size of the model.
-
公开(公告)号：EP4131020A1
公开(公告)日：2023-02-08
申请号：EP21789181.1
申请日：2021-03-01
发明人： LIAO, Yi , LI, Bowen , ZHENG, Hao , JIANG, Xin , LIU, Qun
IPC分类号： G06F16/33
摘要： This application provides a data processing method and apparatus. This application relates to the field of artificial intelligence, and specifically relates to the field of natural language processing. The method includes: determining original text samples, where masking processing is not performed on the original text samples; and performing mask processing on the original text samples to obtain mask training samples, where the mask processing makes mask proportions of the mask training samples unfixed, and the mask training samples each are used to train a pretrained language model PLM. Training the PLM by using the mask training samples whose mask proportions are unfixed can enhance mode diversity of the training samples of the PLM. Therefore, features learned by the PLM are also diversified, a generalization capability of the PLM can be improved, and a natural language understanding capability of the PLM obtained through training can be improved.
-
公开(公告)号：EP3964998A1
公开(公告)日：2022-03-09
申请号：EP20804954.4
申请日：2020-01-17
发明人： WANG, Yasheng , JIANG, Xin , CHEN, Xiao , LIU, Qun , ZHANG, Zhengyan , QI, Fanchao , LIU, Zhiyuan
IPC分类号： G06F40/00
摘要： This application relates to the field of artificial intelligence, and provides a text processing method, a model training method, and an apparatus. The method includes: obtaining target knowledge data, where the target knowledge data includes a first named entity, a second named entity, and an association between the first named entity and the second named entity; processing the target knowledge data to obtain a target knowledge vector; processing to-be-processed text to obtain a target text vector, where the to-be-processed text includes the first named entity; fusing the target text vector and the target knowledge vector based on a target fusion model, to obtain a fused target text vector and a fused target knowledge vector; and processing the fused target text vector and/or the fused target knowledge vector based on a target processing model, to obtain a processing result corresponding to a target task. The foregoing technical solution can improve accuracy of a result of processing a target task by the target processing model.
-
15.发明公开
公开(公告)号：EP3816797A1
公开(公告)日：2021-05-05
申请号：EP19893527.2
申请日：2019-12-03
发明人： LI, Yingtao , JIANG, Xin , CHEN, Xiao , ZHANG, Baofeng , QIAN, Li
IPC分类号： G06F9/451
摘要： The present invention relates to the field of man-machine interaction in artificial intelligence. Embodiments of the present invention provide a multi-task processing method. The method includes the following steps: determining a first task based on request information entered by a user; obtaining key information corresponding to the first task and executing the first task, where the key information includes one or more slots and values of the one or more slots; storing task status information of the first task, where the task status information includes the key information; and predicting and initiating a second task based on the task status information of the first task.
In the method provided in the embodiments of the present invention, status information of each task can be shared and used. A man-machine interaction system may predict a next task based on the stored task status information, and actively initiate the predicted task. This improves intelligence and efficiency of multi-task processing by the man-machine interaction system.-
公开(公告)号：EP3567498A1
公开(公告)日：2019-11-13
申请号：EP18760453.3
申请日：2018-02-28
发明人： JIANG, Xin , LI, Hang
摘要： Embodiments of the present invention disclose a question answering method, including: obtaining target question information; determining a candidate question and answer pair based on the target question information; calculating a confidence of answer information in the candidate question and answer pair, where the confidence is used to indicate a probability that question information in the candidate question and answer pair belongs to an answer database or an adversarial database, and the confidence is positively correlated to the probability that the question information in the candidate question and answer pair belongs to the answer database; determining whether the confidence is less than a first preset threshold; and when the confidence is less than the first preset threshold, outputting "incapable of answering". In this way, the candidate question and answer pair is determined in a knowledge base based on a matching degree, and then a confidence of each piece of answer information is calculated. If the confidence is relatively high, the answer information can be output, or if the confidence is relatively low, "incapable of answering" can be output, so as to avoid misleading a user, thereby improving answering accuracy.
-
-
-
-
-
搜索结果
16 条记录 (耗时 0.014 秒)
