CN102819576A - Data mining method and system based on microblog - Google Patents

Abstract

The invention provides a data mining method and a data mining system based on a microblog, relating to food service industries. The method comprises the following courses: a training course and a judgment course, wherein the training course comprises the following steps: performing text preprocessing including word segmentation, feature extraction and the like on microblog sample data as input of a machine learning algorithm depending on a knowledge base system, and creating a classifier in accordance with the machine learning algorithm and informing the classifier of classification judgment standards; and the judgment course comprises the following steps: performing text preprocessing on the microblog data and performing preprocessing including word segmentation and feature extraction, etc. on the microblog data depending on the knowledge base system, and sending the preprocessed microblog data to the classifier and receiving good or bad assessment results returned by the classifier. The invention also provides the data mining system based on the microblog.

Description

A kind of data digging method and system based on microblogging

Technical field

The present invention relates to the data mining technology field, relate in particular to a kind of data digging method and system based on microblogging.

Background technology

At catering industry, at present not based on the microblogging data mining, the product that provides data to support for enterprise management decision-making or consumer spending decision-making.

Summary of the invention

The technical matters that the present invention solves is how to provide the evaluation information of product or service.

In order to overcome the above problems, the embodiment of the invention provides a kind of data digging method based on microblogging, comprises following process:

Training process: rely on the knowledge base system, the microblogging sample data is done text pre-service work such as participle, feature extraction, as the input of machine learning algorithm,, create sorter then, and tell the sorter standard that classification is judged through machine learning algorithm;

Deterministic process: rely on the knowledge base system, the microblogging data are carried out the text pre-service, the microblogging data are done pre-service work such as participle, feature extraction, pretreated microblogging data are issued sorter, and receive favorable comment or the poor result that comments that sorter returns.

Further, as preferred version, knowledge body storehouse system is multi-level tree-like knowledge base system.

Further, as preferred version, machine learning algorithm is the expansion bayesian algorithm.

The embodiment of the invention also provides a kind of data digging system based on microblogging; Comprise: training module: rely on knowledge base system module,, the microblogging sample data is done text pre-service work such as participle, feature extraction earlier through the first text pre-processing module; Then as the input of machine learning module; Through machine learning algorithm, create classifier modules, and tell the standard that the sorter sort module is judged;

Judge module: rely on the knowledge base system; Earlier through the second text pre-processing module; The microblogging data are carried out the text pre-service; The microblogging data are done pre-service work such as participle, feature extraction, pretreated microblogging data are issued classifier modules, and favorable comment or difference that the reception classifier modules is returned comment the result to show at display terminal;

Knowledge base system module: be that the first text pre-processing module, the second text pre-processing module and machine learning module provide data.

Owing to adopted the microblogging data mining technology, the evaluation information of product or service is provided, help the relative merits of food and beverage enterprise's discovery self product or service, for enterprise management decision-making provides the data support.

Description of drawings

When combining accompanying drawing to consider; Through with reference to following detailed, can more completely understand the present invention better and learn wherein many attendant advantages easily, but accompanying drawing described herein is used to provide further understanding of the present invention; Constitute a part of the present invention; Illustrative examples of the present invention and explanation thereof are used to explain the present invention, do not constitute to improper qualification of the present invention, wherein:

Fig. 1 is a method for digging embodiment process flow diagram of the present invention;

Fig. 2 is a digging system embodiment block diagram of the present invention.

Embodiment

Followingly embodiments of the invention are described with reference to Fig. 1-2.

As shown in Figure 1, a kind of data digging method based on microblogging comprises following process:

S1, training process: rely on the knowledge base system, the microblogging sample data is done text pre-service work such as participle, feature extraction, as the input of machine learning algorithm,, create sorter then, and tell the sorter standard that classification is judged through machine learning algorithm;

S2, deterministic process: rely on the knowledge base system, the microblogging data are carried out the text pre-service, the microblogging data are done pre-service work such as participle, feature extraction, pretreated microblogging data are issued sorter, and receive favorable comment or the poor result that comments that sorter returns.

Knowledge body storehouse system is multi-level tree-like knowledge base system.Machine learning algorithm is the expansion bayesian algorithm.

As shown in Figure 2, a kind of data digging system based on microblogging comprises:

Training module 1: rely on knowledge base system module; Earlier through the first text pre-processing module 11; The microblogging sample data is done text pre-service work such as participle, feature extraction, then as the input of machine learning module 12, through machine learning algorithm; Create classifier modules 13, and tell the standard that sorter sort module 13 is judged;

Judge module 2: rely on the knowledge base system; Earlier through the second text pre-processing module 21; The microblogging data are carried out the text pre-service; The microblogging data are done pre-service work such as participle, feature extraction, pretreated microblogging data are issued classifier modules 13, and favorable comment or difference that reception classifier modules 13 is returned comment the result to show at display terminal 22;

Knowledge base system module 3: be that the first text pre-processing module 11, the second text pre-processing module 21 and machine learning module 12 provide data.

As stated, embodiments of the invention have been carried out explanation at length, but as long as not breaking away from inventive point of the present invention and effect in fact can have a lot of distortion, this will be readily apparent to persons skilled in the art.Therefore, such variation also all is included within protection scope of the present invention.

Claims (4)

1. data digging method based on microblogging; It is characterized in that, comprise following process: training process: rely on the knowledge base system, the microblogging sample data is done text pre-service work such as participle, feature extraction; Then as the input of machine learning algorithm; Through machine learning algorithm, create sorter, and tell the sorter standard that classification is judged;

Deterministic process: rely on the knowledge base system, the microblogging data are carried out the text pre-service, the microblogging data are done pre-service work such as participle, feature extraction, pretreated microblogging data are issued sorter, and receive favorable comment or the poor result that comments that sorter returns.

2. according to claim 1 based on the data digging method of microblogging, it is characterized in that said knowledge body storehouse system is multi-level tree-like knowledge base system.

3. according to claim 1 based on the data digging method of microblogging, it is characterized in that said machine learning algorithm is the expansion bayesian algorithm.

4. the data digging system based on microblogging is characterized in that, comprising:

Training module: rely on knowledge base system module; Earlier through the first text pre-processing module; The microblogging sample data is done text pre-service work such as participle, feature extraction, then as the input of machine learning module, through machine learning algorithm; Create classifier modules, and tell the standard that the sorter sort module is judged;

Judge module: rely on the knowledge base system; Earlier through the second text pre-processing module; The microblogging data are carried out the text pre-service; The microblogging data are done pre-service work such as participle, feature extraction, pretreated microblogging data are issued classifier modules, and favorable comment or difference that the reception classifier modules is returned comment the result to show at display terminal;

Knowledge base system module: be that the first text pre-processing module, the second text pre-processing module and machine learning module provide data.

Images