公开(公告)号：US20180157714A1

公开(公告)日：2018-06-07

申请号：US15372377

申请日：2016-12-07

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Chia-Chi WU ,  Pei-Yu HSIEH ,  Meng-Jung SHIH

IPC: G06F17/30 ,  G06Q30/06 ,  G06F17/22

CPC classification number: G06F17/2211 ,  G06F17/2785 ,  G06Q30/0633

Abstract: A method for matching cross-area products includes steps as follows. First and second local product lists are matched through text similarity and graph similarity, and a corresponding relation of the matched first and second products is built. A first difference of topic probability vector of the first and second products and a second difference of topic probability vector of third and fourth products are calculated. If the first difference of topic probability vector is similar to the second difference of topic probability vector, the third and fourth products that are failed to be matched are built a corresponding relation. A cross-area product list of the first and second local product lists is generated. First and second local electronic commerce product lists are added in the first and second local area lists. The first and second local area lists corresponding to the cross-area product list are displayed on a displaying device.

公开(公告)号：US20160148095A1

公开(公告)日：2016-05-26

申请号：US14558918

申请日：2014-12-03

Applicant: Institute For Information Industry

Inventor： Meng-Jung SHIH ,  Chia-Chi WU ,  Ting-Chia LIN ,  Yi-Chun CHEN ,  Pei-Yu HSIEH ,  Ya-Hui CHAN ,  Grace LIN

IPC: G06N5/02 ,  G06F17/30

CPC classification number: G06N5/022 ,  G06F16/30 ,  G06F16/90332

Abstract: An electronic calculating apparatus, a method and a non-transitory machine-readable medium are provided. The electronic calculating apparatus includes an input/output (I/O) interface, a knowledge tree database and a processor. The I/O interface receives first data of a user, wherein the first data is comprised of a natural language character string. The knowledge tree database stores a context knowledge tree. The processor receives the first data of the user via the I/O interface, analyzes the first data and generates context characteristic information, and substitutes the context characteristic information into the context knowledge tree to generate first context recommend information. The processor then enables a display apparatus to display the first context recommend information.

Abstract translation: 提供电子计算装置，方法和非暂时性机器可读介质。 电子计算装置包括输入/​​输出（I / O）接口，知识树数据库和处理器。 I / O接口接收用户的第一数据，其中第一数据由自然语言字符串组成。 知识树数据库存储上下文知识树。 处理器通过I / O接口接收用户的第一数据，分析第一个数据并生成上下文特征信息，并将上下文特征信息替换到上下文知识树中，以产生第一上下文推荐信息。 然后，处理器使显示装置能够显示第一上下文推荐信息。

公开(公告)号：US20180158078A1

公开(公告)日：2018-06-07

申请号：US15372374

申请日：2016-12-07

Applicant: Institute For Information Industry

Inventor： Pei-Yu HSIEH ,  Hong-Han SHUAI ,  De-Nian YANG ,  Yi-Chun CHEN ,  Meng-Jung SHIH ,  Chieh-Yu LIAO ,  Chen-Yu WANG

IPC: G06Q30/02 ,  G06N99/00

CPC classification number: G06Q30/0202 ,  G06N20/00

Abstract: Embodiments disclosed relate to a computer device and a method for predicting market demand of commodities. The method includes: creating multiple-sources data for each of a plurality of commodities, wherein each of the all multiple-sources data comes from a plurality data sources; storing the all multiple-sources data; extracting a plurality of features from a corresponding one of the all multiple-sources data for each of the commodities to build a feature matrix for each of the data sources; performing a tensor decomposition process on the feature matrices to produce at least one latent feature matrix; and performing a deep learning process on the at least one latent feature matrix to build a prediction model and predicting market demand of each of the commodities according to the prediction model.

公开(公告)号：US20150100575A1

公开(公告)日：2015-04-09

申请号：US14094359

申请日：2013-12-02

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Zonyin SHAE ,  Ko-Yang WANG ,  Meng-Jung SHIH ,  Ting-Chieh TU ,  Ya-Hui CHAN ,  Ping-I CHEN ,  Tai-Chun WANG

IPC: G06F17/30

CPC classification number: G06Q30/02 ,  G06Q30/0282

Abstract: An electronic computing device, a personalized information providing method thereof, and a non-transitory machine-readable medium thereof are provided. The electronic computing device establishes a first and a second tree structure data according to a first data of a first user and a second data of a second user arranged in a period respectively by using an ontology construction algorithm, and calculates a similarity between the first and the second tree structure data by using a similarity evaluating algorithm, and then analyzes the similarity to subsume the first and the second tree structure data into a group by using a clustering algorithm. The electronic computing device determines difference between the first and the second tree structure data according to the group and generates recommending information corresponding to the first user which is arranged in the period according to the difference, and then enables a monitor to display the recommending information.

Abstract translation: 提供电子计算设备，其个性化信息提供方法及其非暂时机器可读介质。 电子计算装置根据第一用户的第一数据和第二用户的第二数据分别通过使用本体构造算法建立第一和第二树结构数据，并且计算第一和第二树结构数据之间的相似度 通过使用相似性评估算法对第二树结构数据进行分析，然后通过使用聚类算法分析相似性以将第一和第二树结构数据包含到一个组中。 电子计算装置根据该组确定第一树结构数据和第二树结构数据之间的差异，并且根据该差异生成在周期中排列的与第一用户对应的推荐信息，然后使监视器能够显示推荐信息。

公开(公告)号：US20150097986A1

公开(公告)日：2015-04-09

申请号：US14086136

申请日：2013-11-21

Applicant: Institute For Information Industry

Inventor： Zonyin SHAE ,  Ko-Yang WANG ,  Grace LIN ,  Arthur WANG ,  Ting-Chieh TU ,  Ya-Hui CHAN ,  Meng-Jung SHIH ,  Ping-I CHEN ,  Tai-Chun WANG

IPC: H04N1/21

CPC classification number: H04N1/32101 ,  H04N2201/3247 ,  H04N2201/3253

Abstract: An itinerary generation apparatus, method, and non-transitory computer readable storage medium thereof are provided. The itinerary generation apparatus includes a storage unit, an interface, and a processing unit, wherein the processing unit is electrically connected to the storage unit and the interface. The storage unit is stored with a piece of information related to a place. The interface is configured to receive a plurality of images, wherein each of the images has a shoot time. The processing unit determines that a portion of the images corresponds to the place according to a piece of schedule information. The processing unit retrieves the piece of information related to the place from the storage unit after determining that the portion corresponds to the place.

Abstract translation: 提供了行程生成装置，方法和非暂时性计算机可读存储介质。 行程生成装置包括存储单元，接口和处理单元，其中处理单元电连接到存储单元和接口。 存储单元存储有与场所相关的一条信息。 该接口被配置为接收多个图像，其中每个图像具有拍摄时间。 处理单元根据一段调度信息确定一部分图像对应于该地点。 处理单元在确定该部分对应于该地点之后从存储单元检索与该地点有关的信息。