BEIJING, Aug. 24, 2023 /PRNewswire/ — WiMi Hologram Cloud Inc. (NASDAQ: WIMI) (“WiMi” or the “Company”), a leading global Hologram Augmented Reality (“AR”) Technology provider, today announced that it developed DPCEngine, an efficient density-peak clustering algorithm for improving the performance of policy evaluation. It reduces the complexity of policy evaluation by identifying the clustering structure in the policy sets. The structure and algorithmic process of WiMi’s DPCEngine, which includes key steps such as data pre-processing, density-peak clustering, strategy matching and evaluation.

To evaluate the performance and effectiveness of DPCEngine, experiments were conducted using a real dataset containing a large and complex set of policies. This dataset contains policies from different domains and covers a wide range of access control scenarios. This dataset is divided into a training set and a test set, where the training set is used to build the model of DPCEngine and the test set is used to evaluate its performance.

WiMi’s researchers compared DPCEngine with those traditional policy evaluation methods, including linear search-based and tree structure-based methods. Two aspects of performance metrics were evaluated: policy evaluation time and matching accuracy. Policy evaluation time is the time required to evaluate an access request, while matching accuracy is the consistency between DPCEngine’s matching results and traditional methods.

DPCEngine offers significant performance advantages in terms of policy evaluation time. Compared to traditional methods, DPCEngine is able to significantly reduce the policy evaluation time, especially when the policy set is large and complex. This is attributed to the density-peak-based clustering algorithm used by DPCEngine, which is able to cluster the policy set into smaller subsets, thus reducing the search space for evaluation.

The experimental results of WiMi’s DPCEngine in terms of matching accuracy show that there is a high degree of consistency between DPCEngine’s matching results and traditional methods. This indicates that DPCEngine does not sacrifice accuracy while improving the performance of strategy evaluation. In addition, we conducted scalability experiments to evaluate the performance of DPCEngine under different sizes of policy sets. The results show that DPCEngine can effectively cope with large-scale policy sets and has good scalability.

WiMi’s DPCEngine, a policy evaluation engine based on a density-peak clustering algorithm, has three main functions: preprocessing policy sets, clustered policy sets, and matching policies. The combined use of these functions can significantly improve the effectiveness and accuracy of strategy evaluation.

Preprocessing the policy sets: before strategy evaluation, DPCEngine prepares the data by preprocessing the policy set to make it more suitable for density peak clustering. The preprocessing process includes steps such as data cleaning, feature extraction and data transformation. By cleaning the data, redundant, incomplete or incorrect strategy information is removed to ensure the accuracy and consistency of the data. Avoid negative impact on the evaluation results. The feature extraction process, on the other hand, extracts key features from the policy set, such as user roles, resource types, and operation privileges, for subsequent clustering operations. Data transformation converts the policy set into a data representation, such as a vector or matrix, suitable for density-peaked clustering algorithms for clustering analysis.

Clustered policy sets: DPCEngine utilizes the DPC algorithm to perform clustering operations on policy sets. The Density Peak Clustering Algorithm(DPCA) identifies the clustering structure in a set of strategies by evaluating the density and distance between strategies. The algorithm identifies peak points based on the density and distance between strategies and divides the strategies between peak points into different clusters. This reduces the time and complexity of policy evaluation by clustering a large and complex set of policies into smaller subsets, where each cluster represents a set of policies with similar characteristics and behavioral patterns. The result of a clustered policy set is a set of policy clusters with similar characteristics and behavioral patterns, and this clustered policy set approach reduces the time and computational complexity of policy evaluation and improves the performance and efficiency of the system.

Matching policies: DPCEngine utilizes the clustering results for policy matching. When an access request arrives, DPCEngine compares and matches it with pre-generated policy clusters. By searching for the most similar policies in each cluster, DPCEngine is able to quickly determine the set of policies that match the access request. This clustering-based matching approach can significantly speed up policy matching and provide accurate matching results. In addition, DPCEngine can be combined with other access control technologies and rules engines to further optimize the policy matching process and ensure system security and compliance.

Through the combined use of these three functions, DPCEngine is able to provide companies with efficient and accurate policy evaluation.

This DPCEngine’s preprocessing policy sets, clustered policy sets, and matching policy capabilities work in tandem to provide companies with an efficient, accurate, and scalable policy evaluation performance. By utilizing a density-peaked clustering algorithm and the clustering structure of policy sets, DPCEngine enables fast policy matching in the presence of large and complex policy sets. This clustering-based approach reduces the time and computational complexity of policy evaluation and improves system performance and efficiency.

The three main functions of DPCEngine have a wide range of applications. First, the preprocessing policy set function helps companies process and prepare huge amounts of strategy data to ensure data quality and consistency. This is critical for cleaning and transforming data before policy evaluation to improve the accuracy of subsequent clustering and matching. Second, the clustered policy set function enables companies to divide large and complex policy sets into relatively small clusters of policies with similar characteristics. This clustering operation reduces the size and complexity of policy evaluation and improves system performance and efficiency. By clustering similar policies together, companies can more quickly match access requests and provide fine-grained management and control of policies. Finally, the Matching policies function allows companies to compare and match access requests against pre-generated clusters of policies. This clustering-based matching method can quickly locate the set of policies that match an access request, improving the speed and accuracy of policy matching. At the same time, DPCEngine can be used in conjunction with other access control technologies and rules engines to further optimize policy matching results and ensure system security and compliance.

The three functions of WiMi’s DPCEngine enable companies to efficiently evaluate access control policies. This policy evaluation engine based on the DPCA has a wide range of applications in various industries and domains, and can help companies build robust security protection systems and meet growing security challenges. With the continuous development and improvement of the technology, DPCEngine will further enhance the performance and accuracy of policy evaluation, providing reliable support for enterprises to secure their data and resources.

About WIMI Hologram Cloud

WIMI Hologram Cloud, Inc. (NASDAQ:WIMI) is a holographic cloud comprehensive technical solution provider that focuses on professional areas including holographic AR automotive HUD software, 3D holographic pulse LiDAR, head-mounted light field holographic equipment, holographic semiconductor, holographic cloud software, holographic car navigation and others. Its services and holographic AR technologies include holographic AR automotive application, 3D holographic pulse LiDAR technology, holographic vision semiconductor technology, holographic software development, holographic AR advertising technology, holographic AR entertainment technology, holographic ARSDK payment, interactive holographic communication and other holographic AR technologies.

Safe Harbor Statements

This press release contains “forward-looking statements” within the Private Securities Litigation Reform Act of 1995. These forward-looking statements can be identified by terminology such as “will,” “expects,” “anticipates,” “future,” “intends,” “plans,” “believes,” “estimates,” and similar statements. Statements that are not historical facts, including statements about the Company’s beliefs and expectations, are forward-looking statements. Among other things, the business outlook and quotations from management in this press release and the Company’s strategic and operational plans contain forward−looking statements. The Company may also make written or oral forward−looking statements in its periodic reports to the US Securities and Exchange Commission (“SEC”) on Forms 20−F and 6−K, in its annual report to shareholders, in press releases, and other written materials, and in oral statements made by its officers, directors or employees to third parties. Forward-looking statements involve inherent risks and uncertainties. Several factors could cause actual results to differ materially from those contained in any forward−looking statement, including but not limited to the following: the Company’s goals and strategies; the Company’s future business development, financial condition, and results of operations; the expected growth of the AR holographic industry; and the Company’s expectations regarding demand for and market acceptance of its products and services.

Further information regarding these and other risks is included in the Company’s annual report on Form 20-F and the current report on Form 6-K and other documents filed with the SEC. All information provided in this press release is as of the date of this press release. The Company does not undertake any obligation to update any forward-looking statement except as required under applicable laws.