Occupational psychological character analysis method based on social network
A technology of social network and analysis method, applied in the field of psychoanalysis, which can solve the problems of emotional cognition and untargeted research
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0087] The present invention provides such as Figure 1-4 Shown is a social network-based occupational psychological personality analysis method, the specific steps are:
[0088] Step 1: Collect the basic information of the user, and label various usage behavior tags, topic tags, and emotional tendencies according to the content of the basic information, and calculate the usage percentage of each tag respectively, and make statistics on the words used in the basic information, including high-frequency words and their rate of use;
[0089] Step 2: Construct a classifier for the four dimensions of MBTI professional personality, and divide the personality into four dimensions: motivation (extraversion / introversion), information collection (feeling / intuition), decision-making style (reason / emotion), and lifestyle (independence / dependence) A total of 16 combinations, use the training data to train the four classifiers respectively, and optimize the classifier by predicting the acc...
Embodiment 2
[0107] Can know by embodiment one:
[0108] In step 2, the classifiers are trained separately, including the Logistic regression algorithm, which is mostly used to estimate the possibility of something. It is a method of learning f:X->Y equation or P(Y|X), where Y is a discrete value , and X= is any vector, where each feature component Xi can take discrete or continuous values. It can be used for probability prediction and classification, and does not require that the features Xi are independent of each other. It is a commonly used machine learning method in the industry. Logistic regression methods include
[0109] 1) Construct a prediction function h;
[0110] 2) Construct loss function J;
[0111] 3) Find a way to minimize the J function and obtain the regression parameters (θ) in three steps, where:
[0112] 1) Construction predictive function h, the present invention uses Logistic function (or claims Sigmoid function), and the form is:
[0113] For the case of a lin...
Embodiment 3
[0153] attached by the manual image 3 , Figure 4 As can be seen from Example 1:
[0154] The analysis results of these classifiers were integrated using the Adaboost iterative algorithm. The core idea of Adaboost is to train different weak classifiers for the same training set, and then combine these weak classifiers to form a stronger final strong classifier. Adaboost determines the weight of each sample according to whether the classification of each sample in each training set is correct and the accuracy of the last overall classification. Send the new data set with modified weights to the lower-level classifier for training, and finally integrate the classifiers obtained from each training, and use it as MBTI for the analysis of motivation, information collection, decision-making methods, and lifestyle. classifier.
[0155] The algorithm of Adaboost in the described step 4 is described as follows:
[0156] Let the training data set T={(x1,y1),(x2,y2)...(xN,yN)}
...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com