Hewlett Packard Enterprise Development LP

Baidu Online Network Technology (beijing) Co., Ltd.

Micro Focus Lcc

Xiaofeng Yu

Jun Qing Xie

Shuai Wang

Qun Yang Lin

You Han

Litao Zheng

JunQing Xie

Xiyao Lin

A method for retrieving a multi-turn dialogue, a storage medium, and an electronic device are provided. The detailed implementation includes: obtaining present question information and context information of the present question information; obtaining a plurality of pieces of candidate reply information of the present question information; generating a context feature based on the context information, and generating a plurality of candidate reply features based on the plurality of pieces of candidate reply information; obtaining consistency information between the context feature and each of the plurality of candidate reply features; selecting a piece of candidate reply information from the plurality of pieces of candidate reply information for replying based on the consistency information between the context feature and each of the plurality of candidate reply features.

Method for retrieving multi-turn dialogue, storage medium, and electronic device

Examples relate to predicting available access points. In one example, a computing device may: obtain a set of training fingerprints, each training fingerprint specifying, for a client device, i) a set of access points, and ii) cellular signal strength measurements for each cellular tower in a set of cellular towers; generate a plurality of classes based on the set of training fingerprints, each class specifying at least one access point, the access points of each class corresponding to the set of access points specified by at least one training fingerprint, and each combination being different from combinations specified by each other class in the plurality of classes; and train a predictive model to receive, as input, an input fingerprint specifying a cellular signal strength measurement for each cellular tower in a set of input cellular towers and produce, as output, at least one of the plurality of classes.

Predicting available access points

Relationship extraction can include applying unsupervised relationship learning to a logic knowledge base and a plurality of entity groups recognized from a document to provide a probabilistic model. Relationship extraction can include performing joint inference on the probabilistic model to make simultaneous statistical judgments about a respective relationship between at least two entities in one of the plurality of entity groups. Relationship extraction can include extracting a relationship between at least two entities in one of the plurality of entity groups based on the joint inference.

Relationship extraction

In an example, a set of training fingerprints may be accessed, in which each of the training fingerprints specifies an access point of a plurality of access points to which a mobile device made a successful connection, a relative signal strength of the connection to the access point, and a cellular signal strength of a cellular tower near the mobile device when the successful connection to the access point was made. Level counts of the relative signal strengths of the connections to the access points corresponding to the cellular signal strengths of the cellular tower may be cumulated from the set of training fingerprints. The cumulated level counts of the relative signal strengths of the access points may be ranked.

Access point availability prediction

A SCI (Split, Compression and Intersection) packet classifier, wherein the SCI packet classifier comprises a construction module to generate rule ID array, h pairs of ISG and three binary search trees, and a lookup engine to look up the binary search trees and ISGs to find the highest priority rule matching the incoming packet and to output a corresponding rule ID.

Memory efficient packet classification method

Examples relate to predicting wireless access point availability. In one example, a computing device may: generate, for a wireless access point, a mapping for predicting availability of the wireless access point, the mapping specifying: one or more in-range cellular towers to which at least one client device has been connected while the at least one client device was also connected to the wireless access point; one or more border cellular towers to which at least one client device has been connected to i) subsequent to being connected to one of the one or more in-range cellular towers, and ii) while not connected to the wireless access point; and one or more out-of-range cellular towers to which at least one client device has been connected to i) subsequent to being connected to one of the one or more border cellular lowers, and ii) while not connected to the wireless access point.

Predicting wireless access point availability

In an example, a set of training fingerprints may be access, in which each of the training fingerprints may specify an access point of a plurality of access points to which a mobile device made a successful connection and a cellular signal strength of a cellular tower near the client device when the successful connection was made. An interim model may be generated from the accessed set of training fingerprints, in which the interim model may contain a subset of the information in the set of training fingerprints to enable a destination device to generate a prediction model to predict an availability of an access point. The generated interim model may be transferred to the destination device.

Growing community of inventors

Beijing, China

Xiaofeng Yu