摘要
提出一种基于家庭本体知识库的服务决策机制的设计方法.首先,围绕网络中存储的与家庭服务相关的半结构化文本信息初步构建训练数据集.其次,基于与家庭服务相关的本体知识库构建信息提取机制,针对初步数据集包含的物品信息提取知识库中对应的服务物品属性信息;基于长短时记忆网络(LSTM)设计一种学习模型并命名为服务决策机制,该机制利用知识库作为常识部分进行辅助推理,生成与服务请求对应的决策信息.最后,针对决策信息进行对比实验.实验结果表明:将本体知识库作为常识部分辅助推理,能够提高决策信息的准确性.
A method was proposed to design service decision mechanism based on ontology knowledge base.Firstly,an initial training data set about family service was built around the semi-structured text information stored in the network.Then,a mechanism for data extraction based on ontology knowledge base oriented to household service was constructed,focusing on obtaining feature information of objects involved in the knowledge base according to the information in initial data set.After that,a learning model,service decision mechanism,was designed with the structure of LSTM(long shortterm memory)networks,using the knowledge base as a common sense for supplementary reasoning and generated decision information according to service request.Finally,a comparative experiment was made for decision information.The result shows that taking ontology knowledge base as common sense for supplementary reasoning is able to improve the accuracy of decision information.
引文
[1]骆家伟,牟琳,靳泰戈.智能家庭服务机器人语音系统实现[J].计算机应用,2010(12):322-325.
[2]Hemachandra S,Duvallet F,Howard T M,et al.Learning models for following natural language directions in unknown environments[C]∥Proc of IEEE International Conference on Robotics&Automation.Seattle:IEEE,2015:5608-5615.
[3]王文,赵群飞,朱特浩.人-服务机器人交互中自然语言理解研究[J].微型电脑应用,2015(3):45-49.
[4]杜广龙.面向多自由度机器人的非受限智能人机交互的研究[D].广州:华南理工大学图书馆,2013.
[5]Hameed I A.Using natural language processing for designing socially intelligent robots[C]∥Proc of Conference on Development and Learning and Epigenetic Robotics.Paris:IEEE,2016:268-269.
[6]Tenorth M,Nyga D,Beetz M.Understanding and executing instructions for everyday manipulation tasks from the world wide web[C]∥Proc of IEEE International Conference on Robotics&Automation.Anchorage:IEEE,2010:1486-1491.
[7]Tenorth M,Klank U,Pangercic D,et al.Web-enabled robots[J].IEEE Robotics&Automation Magazine,2011,18(2):58-68.
[8]Misu T,Georgila K,Leuski A,et al.Reinforcement learning of question-answering dialogue policies for virtual museum guides[C]∥Proc of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue.Seoul:Association for Computational Linguistics,2012:84-93.
[9]Shang L,Lu Z,Li H.Neural responding machine for short-text conversation[C]∥Proc of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.Beijing:ACL,2015:1577-1586.
[10]Weston J,Chopra S,Bordes A.Memory networks[C]∥Proc of International Conference on Learning Representations.San Diego:IEEE,2015:761-776.
[11]贾松敏,高立文,樊劲辉,等.模糊神经网络在智能轮椅避障中的应用[J].华中科技大学学报:自然科学版,2013,41(5):77-81.