Running Information Tests for DIKWP Artificial Consciousness System 

Yucong Duan

International Standardization Committee of Networked DIKWP for Artificial Intelligence Evaluation(DIKWP-SC)

World Artificial Consciousness CIC(WAC)

World Conference on Artificial Consciousness(WCAC)

(Email: duanyucong@hotmail.com)

Introduction

We'll proceed from where we left off in the data scenario, moving into the information scenario. We'll focus on transforming the processed data from the Data Module (D) into meaningful information in the Information Module (I), handling the 3-No Problem (incomplete, imprecise, and inconsistent data). We'll provide detailed explanations and code examples to illustrate each step.

Recap: Data Module (D)

In the previous data scenario, we processed data with incomplete, imprecise, or inconsistent attributes by:

• Generating Hypotheses to fill in missing data.

• Abstracting Data to simplify and focus on key attributes.

• Handling Imprecision and Inconsistency through categorization and reconciliation.

Example Processed Data (D_subj):

pythonCopy code# Abstracted data points after processing in the Data ModuleD_subj = [     {'id': 1, 'color_category': 'Red', 'size': 0.80},     {'id': 2, 'color_category': 'Red', 'size': 0.75},     {'id': 3, 'color_category': 'Green', 'size': 0.85}, ]Proceeding to the Information Module (I)

The Information Module is responsible for processing the abstracted data from the Data Module to extract meaningful information by identifying subjective differences and relationships, even when data is incomplete, imprecise, or inconsistent.

Goals of the Information Module:

1. Extract Subjective Differences: Identify and quantify differences between data points.

2. Handle Uncertainty: Recognize that differences may be based on hypothesized or abstracted data.

3. Prepare for Knowledge Construction: Provide a foundation for building the knowledge network in the Knowledge Module.

Step-by-Step Implementation of the Information Module (I)1. Define the Scope of Information Extraction

We need to decide which attributes are significant for extracting information. Based on the processed data (D_subj), we'll focus on:

• Categorical Attributes: color_category

• Numerical Attributes: size

2. Extracting Subjective Differences

We'll calculate the differences between each pair of data points for the selected attributes.

2.1. For Categorical Attributes

Since color_category is categorical, we'll determine if the categories are the same or different.

pythonCopy codedef Delta_subj_categorical(data_point_i, data_point_j, attribute_key):    # Determine if the categorical attributes are the same or different     if data_point_i[attribute_key] == data_point_j[attribute_key]:         difference = 0  # No difference     else:         difference = 1  # Different categories     return difference2.2. For Numerical Attributes

For size, we'll calculate the absolute difference.

pythonCopy codedef Delta_subj_numerical(data_point_i, data_point_j, attribute_key):    # Calculate the absolute difference between numerical attributes     if attribute_key in data_point_i and attribute_key in data_point_j:         difference = abs(data_point_i[attribute_key] - data_point_j[attribute_key])    else:         difference = None  # Handle missing data     return difference2.3. Combining the Differences

We'll loop through each pair of data points and extract differences for both color_category and size.

pythonCopy codeI_subj = [] attributes = ['color_category', 'size']for attr in attributes:    for i in range(len(D_subj)):        for j in range(i + 1, len(D_subj)):             data_point_i = D_subj[i]             data_point_j = D_subj[j]            if attr == 'color_category':                 difference = Delta_subj_categorical(data_point_i, data_point_j, attr)            else:                 difference = Delta_subj_numerical(data_point_i, data_point_j, attr)             I_subj.append({                'data_point_i': data_point_i['id'],                'data_point_j': data_point_j['id'],                'attribute': attr,                'difference': difference,             })3. Resulting Information Set (I_subj)

Subjective Information Set (I_subj):

pythonCopy code[     {'data_point_i': 1, 'data_point_j': 2, 'attribute': 'color_category', 'difference': 0},     {'data_point_i': 1, 'data_point_j': 3, 'attribute': 'color_category', 'difference': 1},     {'data_point_i': 2, 'data_point_j': 3, 'attribute': 'color_category', 'difference': 1},     {'data_point_i': 1, 'data_point_j': 2, 'attribute': 'size', 'difference': 0.05},     {'data_point_i': 1, 'data_point_j': 3, 'attribute': 'size', 'difference': 0.05},     {'data_point_i': 2, 'data_point_j': 3, 'attribute': 'size', 'difference': 0.10}, ]4. Handling Uncertainty and Imprecision4.1. Recognizing Subjectivity

• The differences calculated are based on potentially hypothesized or abstracted data.

• We acknowledge that our information is subjective and may not represent absolute truths.

4.2. Incorporating Confidence Levels (Optional Enhancement)

To handle uncertainty more effectively, we can assign confidence levels to our differences based on the quality of the data.

pythonCopy codedef assign_confidence(data_point_i, data_point_j, attribute_key):    # Assign higher confidence if data is complete and precise     confidence = 1.0  # Maximum confidence     # Reduce confidence if data was hypothesized or abstracted     if 'hypothesized' in data_point_i or 'hypothesized' in data_point_j:         confidence *= 0.8  # Reduce confidence due to hypothesis     if 'imprecise' in data_point_i or 'imprecise' in data_point_j:         confidence *= 0.9  # Reduce confidence due to imprecision     return confidence# Modify the information extraction to include confidencefor info in I_subj:     data_point_i = next(dp for dp in D_subj if dp['id'] == info['data_point_i'])     data_point_j = next(dp for dp in D_subj if dp['id'] == info['data_point_j'])     confidence = assign_confidence(data_point_i, data_point_j, info['attribute'])     info['confidence'] = confidence

Updated Information Set with Confidence Levels:

pythonCopy code[     {'data_point_i': 1, 'data_point_j': 2, 'attribute': 'color_category', 'difference': 0, 'confidence': 1.0},     {'data_point_i': 1, 'data_point_j': 3, 'attribute': 'color_category', 'difference': 1, 'confidence': 1.0},    # ... and so on for other entries]5. Preparing for the Knowledge Module

The information set (I_subj) now contains:

• Differences between data points.

• The attributes these differences are based on.

• Confidence levels indicating the reliability of each piece of information.

This enriched information will be used in the Knowledge Module to build a network that reflects not only the relationships between data points but also the certainty we have about these relationships.

Conclusion of the Information Scenario

We've successfully transitioned from the Data Module to the Information Module, transforming our processed data into meaningful information. By extracting subjective differences and handling uncertainty, we've prepared a robust information set that will serve as the foundation for constructing the knowledge network in the next module.

Next Steps:

• Knowledge Module (K): We'll proceed to build the knowledge network using the information extracted, incorporating confidence levels to represent the certainty of relationships.

• Wisdom Module (W): Apply reasoning to make decisions based on the knowledge network, accounting for uncertainty.

• Purpose Module (P): Ensure that the decisions align with the system's overarching goals, even in the presence of incomplete or uncertain information.

References for Further Reading

1. International Standardization Committee of Networked DIKWP for Artificial Intelligence Evaluation (DIKWP-SC),World Association of Artificial Consciousness(WAC),World Conference on Artificial Consciousness(WCAC). Standardization of DIKWP Semantic Mathematics of International Test and Evaluation Standards for Artificial Intelligence based on Networked Data-Information-Knowledge-Wisdom-Purpose (DIKWP ) Model. October 2024 DOI: 10.13140/RG.2.2.26233.89445 .  https://www.researchgate.net/publication/384637381_Standardization_of_DIKWP_Semantic_Mathematics_of_International_Test_and_Evaluation_Standards_for_Artificial_Intelligence_based_on_Networked_Data-Information-Knowledge-Wisdom-Purpose_DIKWP_Model

2. Duan, Y. (2023). The Paradox of Mathematics in AI Semantics. Proposed by Prof. Yucong Duan:" As Prof. Yucong Duan proposed the Paradox of Mathematics as that current mathematics will not reach the goal of supporting real AI development since it goes with the routine of based on abstraction of real semantics but want to reach the reality of semantics. ".

转载本文请联系原作者获取授权，同时请注明本文来自段玉聪科学网博客。
链接地址：https://blog.sciencenet.cn/blog-3429562-1456774.html

上一篇：Running Data Tests for DIKWP Artificial Consciousness （初学者版）
下一篇：Running Knowledge Test for DIKWP Artificial Conscious（初学者版）