US 11,386,163 B2Granted

Data search method and data search system thereof for generating and comparing strings

AssigneeDelta Electronics, Inc.

InventorsShih-Han Chan, Chao-Hsuan Ko, Guo-Cheng Lan

Life of this patent

Estimating the term…

Loading patent…

Abstract

The present disclosure relates to a data search method and a data search system thereof. The data search method includes steps of: receiving a first learning content data, wherein the first learning content data includes multiple first learning sections; analysing the first learning content data by a way of Natural Language Processing to search multiple first keyword strings corresponding to each of the first learning content data; receiving a search message; analysing the search message by the way of Natural Language Processing to generate a search string; comparing the search string with the first keyword strings; and generating a search list according to the first learning section, which corresponding to the first keyword string that matches the search string.

Claims10

Dependent claims

A data search method, comprising steps of:

receiving, by a first server, a first learning content data, wherein the first learning content data comprises a plurality of first learning sections;
analyzing, by the first server, the first learning content data to generate a plurality of first keyword strings corresponding to the plurality of first learning sections;
receiving, by the first server, a search message;
analyzing, by a second server, the search message to generate a search string;
comparing, by the second server, the search string with the plurality of first keyword strings;
and
generating, by the second server, a search list according to the plurality of first learning sections corresponding to the plurality of first keyword strings matching the search string so as to arrange the corresponding plurality of first learning sections to the search list for an user reference;
receiving, by the first server or the second server, an operation message, wherein the operation message is generated according to a viewing record of an user, corresponds to a second learning section of a second learning content data, and the second learning section comprises a second keyword string;
and
storing, by the second server, the second keyword string corresponding to the operation message to a behavior database and recording as a behavior data;
calculating, by the second server, a plurality of second similarities between the behavior data and the plurality of first keyword strings matching to the search message;
recording a weight value of the behavior data according to a number of times that the second keyword string stored in the behavior database;
adjusting to the plurality of second similarities according to the weight value;
and
adjusting, by the second server, an order of the plurality of first learning sections in the search list according to the plurality of second similarities, wherein the plurality of first learning sections with a higher of the plurality of second similarities is in a front portion of the search list;
wherein the data search method further comprises:
receiving a plurality of training data;
inputting the plurality of training data to an auto-encoder, and creating a semantic network by a data compression processing and a dimension conversion processing;
and
semantic analyzing to the first learning content data and the search message by the semantic network;
wherein the order of the plurality of the first learning sections in the search list is adjusted according to the second similarities, and the second similarities are, in turn, adjusted according to the number of times that the second keyword string is recorded in the behavior database;
wherein the second similarities are calculated by determining how closely the second keyword string matches each of the first keyword strings.

19 more elements

A data search system, comprising:

a data storage device configured to store a first learning content data, wherein the first learning content data comprises a plurality of first learning sections;
an analysis device configured to generate a plurality of first keyword strings corresponding to the plurality of first learning sections according to the first learning content data;
the analysis device further configured to generate a search string according to a search message;
and
an operation device electrically connected to the analysis device, wherein the operation device is configured to compare the search string with the plurality of first keyword strings, and generate a search list according to the plurality of first learning sections corresponding to the plurality of first keyword strings matching the search string so as to arrange the corresponding plurality of first learning sections to the search list for an user reference;
wherein the data storage device further stores a second learning content data, and the second learning content data comprises a second learning section, the second learning section comprises a second keyword string;
wherein after receiving an operation message generated according to a viewing record of an user, the operation device is configured to store the second keyword string corresponding to the operation message to a behavior database and record as a behavior data;
wherein the operation device is configured to calculate a plurality of second similarities between the behavior data and the plurality of first keyword strings matching to the search message;
the behavior database further stores a weight value, the weight value is a number of times that the second keyword string stored in the behavior database;
the operation device is configured to adjust to the plurality of second similarities according to the weight value;
the operation device is further configured to adjust an order of the plurality of first learning sections in the search list according to the plurality of second similarities, and the plurality of first learning sections with a higher of the plurality of second similarities is in a front portion of the search list;
wherein the analysis device further comprises an auto-encoder, the analysis device is configured to input a plurality of training data to the auto-encoder, and create a semantic network by a data compression processing and a dimension conversion processing;
wherein the order of the plurality of the first learning sections in the search list is adjusted according to the second similarities, and the second similarities are, in turn, adjusted according to the number of times that the second keyword string is recorded in the behavior database;
and
wherein the second similarities are calculated by determining how closely the second keyword string matches each of the first keyword strings.

12 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/529,820Filed 2 Aug 2019 · us provisional application
Priority: CN 201910104937.61 Feb 2019
Published: US 2020/0081923 A112 Mar 2020
Granted: 12 Jul 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification12 codes

G06F 16/45
Of multimedia data, e.g. slideshows comprising image and additional audio data: clustering; Classification
G06F 16/90344
Query processing: by using string matching techniques
G06F 16/483
Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually: using metadata automatically…
G06F 16/75
Of video data: clustering; Classification