For the intelligent dialogue system of customer service robots in power supply business halls, a large-scale dataset of power business user intents was constructed. The dataset includes 9 577 user queries and their labeling categories. First, the real voice data collected from the power supply business halls were cleaned, processed and filtered. In order to enable the data to drive the study of deep learning models related to intent classification, the data were labeled and augmented with high quality by the professionals according to the background knowledge of power business. In the labeling process, 35 types of service category labels were defined according to power business. In order to test the practicability and effectiveness of the proposed dataset, several classical models of intent classification were used for experiments, and the obtained intent classification models were put in the dialogue system. The classical Text classification model-Recurrent Convolutional Neural Network (Text-RCNN) was able to achieve 87.1% accuracy on this dataset. Experimental results show that the proposed dataset can effectively drive the research on power business related dialogue systems and improve user satisfaction.

Knowledge graph embedding is to embed symbolic relations and entities of the knowledge graph into low dimensional continuous vector space. Despite the requirement of negative samples for training knowledge graph embedding models, only positive examples are stored in the form of triplets in most knowledge graphs. Moreover, negative samples generated by negative sampling of conventional knowledge graph embedding methods are easy to be discriminated by the model and contribute less and less as the training going on. To address this problem, an Adversarial Negative Generator (ANG) model was proposed. The generator applied the encoder-decoder pipeline, the encoder readed in positive triplets whose head or tail entities were replaced as context information, and then the decoder filled the replaced entity with the triplet using the encoding information provided by the encoder, so as to generate negative samples. Several existing knowledge graph embedding models were used to play an adversarial game with the proposed generator to optimize the knowledge representation vectors. By comparing with existing knowledge graph embedding models, it can be seen that the proposed method has better mean ranking of link prediction and more accurate triple classification result on FB15K237, WN18 and WN18RR datasets.

To meet the low cost and real-time requirements of logistics sorting, a systematic method was proposed to extract complete stereo information of typical objects by using multiple stereo cameras. Combining the cameras with an arm and other hardware, a validation and experiment platform was constructed to test the performance of this method. Two Microsoft Kinect cameras were used to measure the locations of objects in horizontal plane with accuracy of 3 millimeters. The stereo features and models of objects were calculated from the complete stereo information at processing rate of about 1 second per frame. Utilizing these features, the arm continuously picked 100 objects without failure. The experimental results demonstrate that the proposed method can extract the stereo features of objects with various sizes and shapes in real-time without off-line training, and based on which the arm can operate on objects with high accuracy.

A six-dimensional linear interpolation theory was proposed to solve the difficult problem of the inverse kinematics equation of six Degree Of Freedom (DOF) manipulator with general structure. Firstly, seven adjacent non-linear correlation nodes were searched from a large number of empirical data to compose hyper-body. Secondly, these seven nodes were used to obtain a six-dimensional linear predictive function. Finally, the predictive function was used to interpolate and inversely interpolate to predict poses and joint angles. The Matlab simulation was used to generate one million group of empirical data according to the positive kinematics equation, and the target pose was inversely interpolated iteratively to predict six joint angles. The experimental results show that compared with the Radial Basis Function Network (RBFN) and the six-dimensional linear inverse interpolation method, the proposed method can approach the target pose faster and more accuratly. The proposed method is based on data, which avoids complicated theory and can meet the requirements of robot daily applications.