Data multi-dimensional visual analysis and strategy optimization system and method

Abstract

The invention provides a data multi-dimensional visual analysis and strategy optimization system and method.The data multi-dimensional visual analysis and strategy optimization system comprises a multi-dimensional visual analysis module used for setting the aggregation dimension of data and conducting aggregation processing on the processed data to obtain aggregated data; generating a visual chart according to the aggregated data; performing interactive operation on the aggregated data; performing association analysis on the aggregated data; and the strategy optimization module is used for performing simulation operation and evaluation on the generated strategy to obtain an analysis result. According to the technical scheme, multi-dimensional and interactive analysis of complex data is achieved, the optimization strategy is automatically generated, and the scientificity and efficiency of decision making are improved.

Description

Technical Field

[0001] The present application relates to the technical field of data analysis and decision optimization, and in particular to a system and method for multi-dimensional data visualization analysis and strategy optimization. Background Art

[0002] In today's digital age, businesses and organizations are faced with massive amounts of data, drawn from a wide range of sources and with complex structures. Traditional data analysis methods are often limited to simple statistics and presentation, making it difficult to fully and deeply explore the underlying information. This leaves decision makers without sufficient basis for strategic planning.

[0003] While existing data visualization tools can present data in the form of charts and graphs, most only display a subset of the data dimensions, making it difficult to conduct comprehensive analysis and interactive exploration of multidimensional data. Furthermore, strategy optimization often requires manual subjective judgment and adjustment based on data analysis results, which is inefficient and prone to errors. Therefore, developing a system and method that can perform multidimensional visual analysis of data and automatically generate optimization strategies is of great practical significance. Summary of the Invention

[0004] This application provides a data multidimensional visualization analysis and strategy optimization system and method for constructing a multidimensional visualization analysis model and strategy optimization algorithm, realizing multidimensional and interactive analysis of complex data, and automatically generating optimization strategies to improve the scientificity and efficiency of decision-making.

[0005] In the first aspect, a data multi-dimensional visualization analysis and strategy optimization system is provided, including:

[0006] The data acquisition and preprocessing module is used to collect raw data, and clean, convert and extract features from the raw data to obtain processed data;

[0007] Multi-dimensional visual analysis module, including:

[0008] The data aggregation submodule is used to set the aggregation dimension of the data and aggregate the processed data to obtain aggregated data; the aggregation dimension includes aggregation by time, aggregation by region, and aggregation by product category;

[0009] A visualization chart generation submodule is used to generate visualization charts based on the aggregated data; the visualization charts include bar charts, line charts, pie charts, scatter plots, heat maps and 3D visualization charts;

[0010] An interactive exploration submodule, configured to perform interactive operations on the aggregated data and the visual chart; the interactive operations include zooming, panning, filtering, drilling, and animation generation;

[0011] An association analysis submodule is used to perform association analysis on the aggregated data to obtain potential relationships between the data, and generate a visualization strategy based on the obtained potential relationships between the data;

[0012] A strategy optimization module is used to simulate and evaluate the generated visualization strategy to obtain analysis results;

[0013] The user interaction module is used to view the analysis results and modify and optimize the user's feedback to obtain a final visualization strategy; the final visualization strategy includes a resource allocation plan, a production plan or a marketing plan.

[0014] In the above technical solution, a data acquisition and preprocessing module is set up to collect raw data, and clean, convert and extract features of the raw data to obtain processed data; a multidimensional visual analysis module includes: a data aggregation submodule, which is used to set the aggregation dimension of the data, and aggregate the processed data to obtain aggregated data; a visual chart generation submodule, which is used to generate visual charts based on the aggregated data; an interactive exploration submodule, which is used to perform interactive operations on the aggregated data; a correlation analysis submodule, which is used to perform correlation analysis on the aggregated data; a strategy optimization module, which is used to simulate and evaluate the generated strategy to obtain analysis results; a user interaction module, which is used to view the analysis structure and modify and optimize user feedback; it realizes multi-dimensional and interactive analysis of complex data, and automatically generates optimization strategies, thereby improving the scientificity and efficiency of decision-making.

[0015] In a specific implementation scheme, the data acquisition and preprocessing module includes:

[0016] Data acquisition submodule, used to collect raw data;

[0017] The data preprocessing submodule is used to clean, convert and extract features from the raw data to obtain processed data.

[0018] In a specific implementation scheme, the strategy optimization module includes:

[0019] The goal setting submodule is used to define the optimization goals and constraints;

[0020] The optimization algorithm submodule is used to select a suitable optimization algorithm to perform calculations based on the objectives and constraints to obtain the analysis results;

[0021] A strategy generation submodule, configured to generate the final visualization strategy based on the analysis result;

[0022] A strategy simulation submodule, used for simulating and evaluating the final visualization strategy;

[0023] In a specific implementation scheme, the user interaction module includes:

[0024] User interface submodule, used to optimize the design of the user interface;

[0025] The feedback and collaboration sub-module is used to collect user operation feedback and suggestions.

[0026] In a specific implementation scheme, the optimization algorithm includes a linear programming algorithm, a genetic algorithm, and a particle swarm optimization algorithm.

[0027] In a second aspect, a method for multi-dimensional data visualization analysis and strategy optimization is provided, comprising the following steps:

[0028] Using the data acquisition and preprocessing module to collect raw data, and then cleaning, converting and feature extracting the raw data to obtain processed data;

[0029] aggregating the processed data using a multi-dimensional visualization analysis module to obtain aggregated data; generating a visualization chart based on the aggregated data; performing interactive operations on the aggregated data and the visualization chart; performing correlation analysis on the aggregated data to obtain potential relationships between the data, and generating a visualization strategy based on the obtained potential relationships between the data;

[0030] Using the strategy optimization module to simulate and evaluate the generated visualization strategy to obtain analysis results;

[0031] The analysis results are reviewed using a user interaction module, and user feedback is modified and optimized to obtain a final visualization strategy.

[0032] In the above technical solution, a data acquisition and preprocessing module is set up to collect raw data, and clean, convert and extract features of the raw data to obtain processed data; a multidimensional visual analysis module includes: a data aggregation submodule, which is used to set the aggregation dimension of the data, and aggregate the processed data to obtain aggregated data; a visual chart generation submodule, which is used to generate visual charts based on the aggregated data; an interactive exploration submodule, which is used to perform interactive operations on the aggregated data; a correlation analysis submodule, which is used to perform correlation analysis on the aggregated data; a strategy optimization module, which is used to simulate and evaluate the generated strategy to obtain analysis results; a user interaction module, which is used to view the analysis structure and modify and optimize user feedback; it realizes multi-dimensional and interactive analysis of complex data, and automatically generates optimization strategies, thereby improving the scientificity and efficiency of decision-making.

[0033] In a specific implementation scheme, the multidimensional visualization analysis module includes:

[0034] The data aggregation submodule is used to set the aggregation dimension of the data and aggregate the processed data to obtain aggregated data; the aggregation dimension includes aggregation by time, aggregation by region, and aggregation by product category;

[0035] A visualization chart generation submodule is used to generate visualization charts based on the aggregated data; the visualization charts include bar charts, line charts, pie charts, scatter plots, heat maps and 3D visualization charts;

[0036] An interactive exploration submodule, configured to perform interactive operations on the aggregated data and the visual chart;

[0037] The association analysis submodule is used to perform association analysis on the aggregated data to obtain potential relationships between the data, and generate a visualization strategy based on the obtained potential relationships between the data.

[0038] In a specific implementation scheme, the data acquisition and preprocessing module includes:

[0039] Data acquisition submodule, used to collect raw data;

[0040] The data preprocessing submodule is used to clean, convert and extract features from the raw data to obtain processed data.

[0041] In a specific implementation scheme, the strategy optimization module includes:

[0042] The goal setting submodule is used to define the optimization goals and constraints;

[0043] The optimization algorithm submodule is used to select a suitable optimization algorithm to perform calculations based on the objectives and constraints to obtain the analysis results;

[0044] A strategy generation submodule, configured to generate the final visualization strategy based on the analysis result;

[0045] The strategy simulation submodule is used to simulate and evaluate the final visualization strategy.

[0046] In a specific implementation scheme, the user interaction module includes:

[0047] User interface submodule, used to optimize the design of the user interface;

[0048] The feedback and collaboration sub-module is used to collect user operation feedback and suggestions. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a structural diagram of the data multi-dimensional visualization analysis and strategy optimization system provided in the embodiment of the present application;

[0050] Figure 2 This is a flowchart of the multi-dimensional data visualization analysis and strategy optimization method provided in the embodiment of the present application. DETAILED DESCRIPTION

[0051] The present application will be further described in detail below through the accompanying drawings and examples, through which the features and advantages of the present application will become more clear and distinct.

[0052] The word "exemplary" is used exclusively herein to mean "serving as an example, example, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0053] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0054] To facilitate understanding of the data multidimensional visualization analysis and strategy optimization system and method provided in the embodiments of the present application, its application scenario is first explained. The data multidimensional visualization analysis and strategy optimization system and method provided in the embodiments of the present application are used to construct a multidimensional visualization analysis model and strategy optimization algorithm, realize multidimensional and interactive analysis of complex data, and automatically generate optimization strategies to improve the scientificity and efficiency of decision-making. In today's digital age, enterprises and organizations are faced with massive amounts of data from a wide range of sources and complex structures. Traditional data analysis methods are often only able to perform simple statistics and display of data, and it is difficult to fully and deeply explore the information behind the data, resulting in decision makers lacking sufficient basis when formulating strategies. Although existing data visualization tools can present data in the form of charts, most of them can only display partial dimensions of the data and cannot realize comprehensive analysis and interactive exploration of multidimensional data. Moreover, in terms of strategy optimization, manual subjective judgment and adjustment based on the data analysis results are usually required, which is inefficient and prone to errors. Therefore, it is of great practical significance to develop a system and method that can perform multidimensional visualization analysis of data and automatically generate optimization strategies. To this end, the present invention provides a multidimensional data visualization analysis and strategy optimization system and method. This system and method constructs a multidimensional visualization analysis model and strategy optimization algorithm, enabling multidimensional, interactive analysis of complex data and automatically generating optimization strategies to improve the scientific nature and efficiency of decision-making. This system and method are described in detail below with reference to specific figures and examples.

[0055] refer to Figure 1 and Figure 2 , Figure 1 This is a structural diagram of the data multi-dimensional visualization analysis and strategy optimization system provided in the embodiment of the present application; Figure 2 This is a flowchart of the multi-dimensional data visualization analysis and strategy optimization method provided in the embodiment of the present application.

[0056] exist Figure 1 In the embodiment of the present application, a data multi-dimensional visualization analysis and strategy optimization system is provided, including:

[0057] The data acquisition and preprocessing module is used to collect raw data, and clean, convert and extract features from the raw data to obtain processed data;

[0058] Multi-dimensional visual analysis module, including:

[0059] The data aggregation submodule is used to set the aggregation dimension of the data and aggregate the processed data to obtain aggregated data; the aggregation dimension includes aggregation by time, aggregation by region, and aggregation by product category;

[0060] A visualization chart generation submodule is used to generate visualization charts based on the aggregated data; the visualization charts include bar charts, line charts, pie charts, scatter plots, heat maps and 3D visualization charts;

[0061] An interactive exploration submodule, configured to perform interactive operations on the aggregated data and the visual chart; the interactive operations include zooming, panning, filtering, drilling, and animation generation;

[0062] An association analysis submodule is used to perform association analysis on the aggregated data to obtain potential relationships between the data, and generate a visualization strategy based on the obtained potential relationships between the data;

[0063] A strategy optimization module is used to simulate and evaluate the generated visualization strategy to obtain analysis results;

[0064] The user interaction module is used to view the analysis results and modify and optimize the user's feedback to obtain a final visualization strategy; the final visualization strategy includes a resource allocation plan, a production plan or a marketing plan.

[0065] In the above technical solution, a data acquisition and preprocessing module is set up to collect raw data, and clean, convert and extract features of the raw data to obtain processed data; a multidimensional visual analysis module includes: a data aggregation submodule, which is used to set the aggregation dimension of the data, and aggregate the processed data to obtain aggregated data; a visual chart generation submodule, which is used to generate visual charts based on the aggregated data; an interactive exploration submodule, which is used to perform interactive operations on the aggregated data; a correlation analysis submodule, which is used to perform correlation analysis on the aggregated data; a strategy optimization module, which is used to simulate and evaluate the generated strategy to obtain analysis results; a user interaction module, which is used to view the analysis structure and modify and optimize user feedback; it realizes multi-dimensional and interactive analysis of complex data, and automatically generates optimization strategies, thereby improving the scientificity and efficiency of decision-making.

[0066] Specifically, the beneficial effects include:

[0067] Analysis of the beneficial effects of multi-dimensional data visualization analysis and strategy optimization system

[0068] 1. Overall beneficial effects of the system

[0069] This system integrates data collection, multi-dimensional visual analysis, strategy optimization and user interaction functions to achieve closed-loop management of the entire process from data to decision-making. Its core advantages are:

[0070] Improve scientific decision-making: Through multi-dimensional visualization and correlation analysis, reveal hidden patterns in data and reduce human experience bias;

[0071] Enhanced analysis efficiency: Interactive exploration supports rapid trial and error and iteration, shortening decision-making cycles.

[0072] Support dynamic optimization: Strategy simulation and user feedback mechanism form a closed loop to ensure continuous iterative optimization of strategies;

[0073] Lowering the technical threshold: Visual interfaces and interactive operations enable non-technical personnel to participate in data analysis, promoting the popularization of data-driven decision-making.

[0074] 2. Beneficial effects of synergistic effects of various modules

[0075] 1. Data acquisition and preprocessing module + multi-dimensional visualization analysis module

[0076] Data quality assurance and visualization adaptability

[0077] The preprocessing module ensures data quality and extracts key features through cleaning (such as removing duplicate values ​​and handling missing values), transformation (such as normalization and encoding categorical variables), and feature extraction (such as PCA dimensionality reduction and time series feature extraction). These processed data provide highly adaptable input for the multidimensional visualization analysis module:

[0078] The data aggregation submodule can flexibly aggregate based on pre-processed feature dimensions (such as user portrait labels and time series segments) to avoid noise interference from the original data;

[0079] The visualization chart generation submodule can more accurately present data distribution (such as heat maps showing feature correlations), trends (such as line charts showing time series changes) and anomalies (such as box plots identifying outliers), thereby improving analysis efficiency.

[0080] 2. Multi-dimensional visualization analysis module + strategy optimization module

[0081] Closed loop from data insight to strategy generation

[0082] The output of the multidimensional visualization analysis module (such as association rules and clustering results) directly drives the strategy optimization module:

[0083] The association analysis submodule uses the Apriori algorithm or graph network analysis to discover strong association rules in the data (such as "80% of users who buy product A will also buy product B"), providing a basis for cross-selling strategies for the strategy optimization module;

[0084] The hierarchical aggregation results of the data aggregation submodule (such as sales data grouped by region and time) can support the strategy optimization module to design differentiated promotion strategies (such as regional targeted discounts).

[0085] Strategy simulation and verification

[0086] The Strategy Optimization module evaluates strategy effectiveness (such as ROI improvement and risk exposure) through Monte Carlo simulation or historical data backtesting. For example, in supply chain optimization, based on the problem of "low inventory turnover in a certain region" discovered through visual analysis, the Strategy Optimization module can simulate and adjust replenishment strategies and select the optimal solution by visually comparing inventory costs and out-of-stock rates under different strategies.

[0087] 3. Strategy Optimization Module + User Interaction Module

[0088] Decision optimization of human-machine collaboration

[0089] The user interaction module displays strategy optimization results (such as strategy return curves and risk heat maps) through a visual interface and supports user feedback:

[0090] Strategy Adjustment: Users can modify strategy parameters (such as adjusting promotion intensity and inventory thresholds) through interactive operations and observe changes in simulation results in real time;

[0091] Multi-version comparison: The system can save historical strategy versions, and users can visually compare the advantages and disadvantages of different versions to avoid blind decision-making.

[0092] 4. Internal collaboration of the multi-dimensional visualization analysis module

[0093] Linking interactive exploration and association analysis

[0094] The interactive exploration submodule allows users to dynamically filter data (e.g., by time range or user group), while the association analysis submodule recalculates association rules based on the filtered data. For example, in medical data analysis, users can first filter "blood glucose monitoring data of diabetic patients" through interactive exploration. The association analysis submodule then explores the "correlation between blood glucose levels and diet and exercise" to generate personalized health management recommendations.

[0095] Dynamic adaptation of data aggregation and visualization charts

[0096] The dimension settings in the data aggregation submodule (such as aggregation by week / month or by product category) directly affect the presentation of visualization charts. For example, in sales data analysis, aggregating by "quarter + region" to generate a stacked bar chart allows for a direct comparison of sales contributions by region per quarter; while aggregating by "product category + customer type" to generate a Sankey diagram reveals customer flow and product conversion paths.

[0097] 3. Innovative Value Brought by Module Collaboration

[0098] From passive analysis to active exploration

[0099] While traditional data analysis systems rely on pre-set reports, this system enables users to proactively explore the value of data through interactive exploration submodules and visual charts. For example, in market research, users can drag and drop dimension fields to generate cross-dimensional analysis tables in real time, quickly discovering insights such as "young users prefer short video ads."

[0100] From static strategy to dynamic optimization

[0101] The integration of the strategy optimization module and the user interaction module makes strategy generation no longer a one-time task, but a continuous iterative process. For example, in logistics route optimization, the system dynamically adjusts delivery strategies based on real-time traffic data and user feedback (such as driver feedback on congestion on a certain road section), and displays a cost comparison before and after optimization through a visual interface.

[0102] From technology silos to business empowerment

[0103] By integrating data preprocessing, visual analysis, strategy optimization, and user interaction into a unified platform, this system breaks down the barriers between technical and business teams. For example, business personnel can directly express requirements (such as "analyze user engagement for a promotion") through visual charts in the system. Based on this requirement, the technical team quickly generates analysis reports and optimization strategies, forming an efficient closed loop of "requirement-analysis-decision-making."

[0104] In a specific implementation scheme, the data acquisition and preprocessing module includes:

[0105] Data acquisition submodule, used to collect raw data;

[0106] The data preprocessing submodule is used to clean, convert and extract features from the raw data to obtain processed data.

[0107] Specifically, the beneficial effects of the data acquisition and preprocessing module include:

[0108] Closed-loop linkage between data quality and subsequent analysis

[0109] The raw data captured by the acquisition submodule is directly fed into the preprocessing submodule, forming an "acquisition-preprocessing" pipeline. For example, in industrial equipment monitoring, the acquisition submodule collects sensor data in real time, while the preprocessing submodule immediately identifies and flags abnormal values ​​(such as sudden temperature changes) to prevent erroneous data from affecting subsequent fault prediction.

[0110] Aligning feature engineering with business goals

[0111] The feature extraction logic of the preprocessing submodule can be dynamically adjusted based on business needs. For example, in e-commerce user analysis, after the collection submodule obtains user browsing and purchase data, the preprocessing submodule can extract features such as "user activity" and "purchase conversion rate" to directly serve the optimization of user stratification strategies.

[0112] Balance between efficiency and flexibility

[0113] The modular design supports rapid iteration. For example, when business requirements change (such as adding a new data source), only the configuration of the acquisition submodule needs to be adjusted. When the analysis target changes (such as switching from classification to regression), the preprocessing submodule can quickly adapt to the feature engineering process, reducing system reconstruction costs.

[0114] The data acquisition and preprocessing module ensures high data quality and usability through a closed-loop process of "acquisition-cleaning-conversion-feature extraction," providing a solid foundation for subsequent multi-dimensional visualization analysis and strategy optimization. Its modular design balances efficiency and flexibility, enabling rapid response to changing business needs and significantly lowering the barrier to entry for data-driven decision-making.

[0115] In a specific implementation scheme, the strategy optimization module includes:

[0116] The goal setting submodule is used to define the optimization goals and constraints;

[0117] The optimization algorithm submodule is used to select the appropriate optimization algorithm according to the objectives and constraints to perform calculations and obtain the optimization results;

[0118] A strategy generation submodule, configured to generate an optimization strategy based on the optimization result;

[0119] The strategy simulation submodule is used to simulate and evaluate the optimization strategy.

[0120] Specifically, the beneficial effects of the strategy optimization module include:

[0121] 1. Beneficial effects of individual module functions

[0122] Goal Setting Submodule

[0123] Precision decision-making guidance: By defining multi-dimensional optimization goals (such as cost minimization, profit maximization, and risk control) and constraints (such as resource limitations and compliance requirements), we ensure that the strategic direction is consistent with business goals and avoid blind optimization.

[0124] Flexibility: Supports dynamic adjustment of target weights (such as increasing risk control priority in emergency scenarios) to quickly respond to business changes.

[0125] Optimization algorithm submodule

[0126] Algorithm adaptability: Automatically select algorithms (such as genetic algorithms, gradient descent, reinforcement learning) according to the target type (such as linear / nonlinear, single-objective / multi-objective) to improve computing efficiency and result quality.

[0127] Robustness: Built-in algorithm parameter adjustment mechanism (such as automatic adjustment of learning rate and population size) reduces manual intervention and enhances optimization stability.

[0128] Strategy generation submodule

[0129] Explainability: Convert optimization results into business-understandable strategies to facilitate decision makers' understanding and execution.

[0130] Diversified output: supports the generation of multiple sets of strategy solutions (such as conservative and aggressive) for users to choose according to their needs.

[0131] Strategy simulation submodule

[0132] Risk prediction: Through historical data backtesting or simulation (such as Monte Carlo simulation), evaluate the performance of the strategy in different scenarios (such as return volatility and risk exposure) to reduce the cost of trial and error.

[0133] Quantitative evaluation: Output key indicators (such as ROI, out-of-stock rate, and user satisfaction) to provide data support for strategic selection.

[0134] 2. Beneficial Effects of Module Synergy

[0135] Goal-driven closed-loop optimization

[0136] The goals and constraints defined in the goal-setting submodule are directly passed to the optimization algorithm submodule, ensuring that algorithm calculations are centered around core business requirements. For example, in supply chain optimization, the goal is set as "reducing inventory costs by 10% and maintaining a stock-out rate of ≤5%." The optimization algorithm submodule generates parameter combinations that meet these constraints. The strategy generation submodule translates these into specific replenishment strategies, which are then verified by the strategy simulation submodule, forming a closed loop of "goal-algorithm-strategy-verification."

[0137] Strategy iteration and risk control

[0138] The evaluation results of the strategy simulation submodule are fed back to the goal setting submodule to dynamically adjust the optimization direction. For example, if the simulation finds that a certain strategy reduces costs but increases user churn, the system can reset the goal (such as adding a "user retention rate ≥ 90%" constraint), triggering a new round of optimization to ensure the strategy strikes a balance between benefits and risks.

[0139] Efficient decision support

[0140] Automated data flow between modules (e.g., direct strategy generation from optimization results and automatic visualization of simulation results) reduces manual transmission and conversion errors, significantly shortening decision cycles. For example, in marketing campaign optimization, the process from goal setting to strategy generation takes only minutes, supporting real-time adjustment of campaign parameters.

[0141] The Strategy Optimization module efficiently transforms business requirements into executable strategies through a collaborative mechanism of "goal setting - algorithm calculation - strategy generation - simulation evaluation." Its closed-loop iteration capabilities ensure continuous strategy optimization and manageable risks. Automated processes significantly lower the decision-making threshold, improving the speed and scientificity of enterprises' responses to market changes.

[0142] In a specific implementation scheme, the user interaction module includes:

[0143] User interface submodule, used to optimize the design of the user interface;

[0144] The feedback and collaboration sub-module is used to collect user operation feedback and suggestions.

[0145] Specifically, the beneficial effects of the user interaction module include:

[0146] Dynamic matching of interface iteration and user needs

[0147] The user interface submodule rapidly iterates on interface design based on suggestions collected by the feedback and collaboration submodule (e.g., "Add sliders for strategy parameters" and "Optimize multi-chart interaction"). For example, if a user reports that the comparison of strategy simulation results is not intuitive enough, the interface submodule can add a side-by-side comparison view and notify the user of the updated content through the feedback submodule, forming a closed loop of "user needs-interface optimization-effectiveness verification."

[0148] User participation drives system optimization

[0149] The feedback and collaboration submodule combines user feedback on the effectiveness of strategies (e.g., "A certain promotional strategy led to a decrease in profit margins") with user interface operation data (e.g., frequent use of a function but a high rate of incorrect operation) to provide optimization directions for the interface submodule (e.g., simplifying complex processes, adding operation prompts). For example, if users frequently accidentally delete important charts, the interface submodule could add a second confirmation pop-up or an undo function, and confirm the improvement results through the feedback submodule.

[0150] Reduce training and support costs

[0151] Through the guided design of the interface sub-module (such as new function highlighting prompts and operation step animations) and the self-service help of the feedback sub-module (such as FAQs and feedback case libraries), users' dependence on system training is reduced, and the workload of the technical support team is reduced.

[0152] The user interaction module transforms user needs into driving force for system iteration through a collaborative mechanism of "interface optimization, feedback collection, and collaborative improvement." Its closed-loop design ensures that the interface and functionality continuously adapt to user scenarios, enhancing user satisfaction. Real-time feedback and collaboration enhance user engagement, driving the system's evolution from "usable" to "easy and user-friendly," ultimately achieving efficient data-driven decision-making.

[0153] In a specific implementation scheme, the optimization algorithm includes a linear programming algorithm, a genetic algorithm, and a particle swarm optimization algorithm.

[0154] Specifically, the beneficial effects of the optimization algorithm include:

[0155] 1. Beneficial Effects of Algorithm’s Individual Functions

[0156] Linear programming algorithm

[0157] Efficiently solve deterministic problems: Applicable to scenarios where both the objective function and constraints are linear (such as resource allocation and production planning), it can find the global optimal solution in polynomial time, ensuring the accuracy of the results.

[0158] Strong interpretability: The output results are clear parameter values ​​(such as "produce 100 pieces of product A and 50 pieces of product B"), which is easy for business personnel to understand and execute.

[0159] Genetic Algorithm

[0160] Handling nonlinearity and complex constraints: By simulating biological evolution (selection, crossover, mutation), it can handle non-convex optimization problems (such as combinatorial optimization and multi-objective optimization) and avoid falling into local optimality.

[0161] High flexibility: supports customized fitness functions (such as comprehensive consideration of cost, risk, and benefit) to adapt to diverse business needs.

[0162] Particle Swarm Optimization Algorithm

[0163] Fast convergence and global search balance: Through the information sharing mechanism of particle swarm (individual optimal and global optimal guidance), while maintaining global search capabilities, it converges faster than genetic algorithms and is suitable for scenarios with high real-time requirements (such as dynamic pricing and real-time scheduling).

[0164] Parameter tuning is simple: only a few parameters such as the number of particles and inertia weight need to be adjusted, which reduces the usage threshold.

[0165] 2. Beneficial Effects of Algorithm Synergy

[0166] Algorithm complementarity improves optimization quality

[0167] Linear Programming + Genetic Algorithm: In supply chain optimization, linear programming can quickly solve basic resource allocation problems (such as warehouse capacity and transportation costs), while genetic algorithms are used to optimize nonlinear objectives (such as balancing total cost and risk in multi-supplier selection). For example, linear programming can be used to determine an initial solution, and then genetic algorithms can be used to iteratively optimize the supplier portfolio, ultimately generating a procurement strategy that balances cost and stability.

[0168] Genetic Algorithm + Particle Swarm Optimization: In complex engineering optimization (such as drone path planning), the genetic algorithm is used to generate the initial path population, while the particle swarm optimization accelerates convergence through information sharing, avoiding the decline in efficiency of the genetic algorithm's later search. Combining the two can significantly shorten computation time while improving path smoothness and safety.

[0169] Adaptive strategy generation in dynamic scenarios

[0170] Multi-algorithm switching mechanism: The system dynamically selects algorithms based on the complexity of the problem. For example, in user demand forecasting, if historical data shows a linear trend, linear programming is used; if there are seasonal fluctuations or unexpected events, genetic algorithms or particle swarm algorithms are used to improve forecast accuracy through nonlinear modeling.

[0171] Real-time feedback drives algorithm tuning: The evaluation results of the strategy simulation submodule (such as strategy return volatility and risk overrun) can be fed back to the optimization algorithm submodule to dynamically adjust algorithm parameters (such as the mutation rate of the genetic algorithm and the inertia weight of the particle swarm algorithm) to achieve continuous optimization of the strategy.

[0172] Collaborative solution of multi-objective optimization

[0173] Combined Application of Genetic Algorithms and Particle Swarm Optimization: In portfolio optimization, genetic algorithms are used to generate initial asset allocations (e.g., the ratio of stocks to bonds). Particle Swarm Optimization iteratively optimizes multiple objectives (e.g., maximizing returns, minimizing volatility), ultimately generating a Pareto frontier solution. Users can select their preferred approach (e.g., "high risk, high return" or "robust") through a user interaction module, and the system automatically generates a corresponding strategy.

[0174] 3. Beneficial Effects of Combining Algorithms and System Modules

[0175] Linking algorithms with goal setting

[0176] The multiple objectives defined by the goal-setting submodule (e.g., cost, efficiency, and risk) are directly mapped to optimization algorithms. For example, if the goal is "minimize cost and keep delivery time ≤ 7 days," the optimization algorithm submodule can use linear programming to find the optimal solution under deterministic constraints, or use genetic algorithms to handle delivery uncertainty, generating multiple strategies for the user to choose from.

[0177] Connecting Algorithm Results with Strategy Generation

[0178] The outputs of the optimization algorithm submodule (such as parameter combinations and weight assignments) are directly fed into the strategy generation submodule, where they are converted into executable strategies. For example, in logistics scheduling, the vehicle routing results optimized by the genetic algorithm are converted into driver operation instructions (such as "deliver to area A first, then detour to area B") by the strategy generation submodule. These instructions are then visualized and facilitated through the user interface submodule.

[0179] Closed loop of algorithm evaluation and strategy simulation

[0180] The evaluation metrics of the strategy simulation submodule (such as ROI and stock-out rate) can be used to reversely optimize the algorithm. For example, if a simulation finds that a strategy performs poorly under extreme market conditions, the system can adjust the optimization algorithm's constraints (such as adding a "black swan event" scenario) or switch to a more robust algorithm (such as the particle swarm optimization algorithm), regenerate the strategy, and simulate and verify it, forming an iterative closed loop of "algorithm-strategy-simulation-algorithm".

[0181] By integrating linear programming, genetic algorithms, and particle swarm optimization, the system achieves comprehensive optimization coverage, from deterministic problems to complex nonlinear ones. The complementarity between algorithms enhances optimization quality and efficiency, while deep integration with other system modules (such as goal setting, strategy generation, and simulation evaluation) ensures the interpretability, enforceability, and dynamic adaptability of optimization results. This multi-algorithm fusion significantly enhances the system's ability to address complex business scenarios, providing scientific, flexible, and efficient support for enterprise decision-making.

[0182] In a specific implementation scheme, the data multi-dimensional visualization analysis and strategy optimization system includes a data acquisition and pre-processing module, a multi-dimensional visualization analysis module, a strategy optimization module, and a user interaction module. Each module works together to achieve full-process processing from data to strategy. Specifically:

[0183] 1. Data acquisition and preprocessing module includes:

[0184] Data Collection Submodule: This module supports access to a variety of data sources, including relational databases (such as MySQL and Oracle), non-relational databases (such as MongoDB and Redis), file systems (such as CSV and Excel files), and real-time data streams (such as Kafka message queues). By writing collectors that adapt to different data sources, data can be automatically collected and synchronized.

[0185] The data preprocessing submodule cleans, converts, and extracts features from the collected raw data. Data cleaning includes removing duplicate data and addressing missing and outliers. Data conversion converts data in different formats into a unified format for subsequent analysis. Feature extraction extracts meaningful features from the data and reduces its dimensionality. Data preprocessing uses a combination of statistical methods and machine learning algorithms to improve data quality and analysis efficiency.

[0186] 2. Multidimensional Visual Analysis Module

[0187] Data Aggregation Submodule: Aggregates data based on user-specified dimensions and supports a variety of aggregation functions, such as sum, average, maximum, minimum, and count. Users can flexibly select aggregation dimensions, such as by time, region, or product category, to meet different analysis needs.

[0188] Visualization Chart Generation Submodule: This module integrates a variety of visualization charts, including bar charts, line charts, pie charts, scatter plots, heat maps, and 3D visualization charts. It automatically recommends appropriate visualization chart types based on the data type and analysis purpose. It also supports user-defined chart styles and layouts, enhancing visualization personalization.

[0189] Interactive Exploration submodule: This module provides a wealth of interactive features, such as zooming, panning, filtering, and drilling. Users can use interactive operations to deeply explore data and view data details from different dimensions and levels. For example, users can drill down to view detailed data for a specific region or time period, and can also use filtering to display only data that meets specific criteria.

[0190] Association Analysis Submodule: This module uses improved association rule mining algorithms (including optimization algorithms based on the Apriori algorithm) to analyze data and discover potential relationships between data. By setting minimum support and minimum confidence thresholds, meaningful association rules are screened and presented to users in a visual format, helping them understand the inherent connections between data.

[0191] 3. Strategy Optimization Module

[0192] Goal setting submodule: allows users to define optimization goals, such as maximizing profits, minimizing costs, increasing market share, etc. At the same time, multiple constraints can be set, such as resource limitations, time limits, etc.

[0193] Optimization Algorithm Submodule: This module integrates multiple optimization algorithms, including linear programming, genetic algorithms, and particle swarm optimization. The appropriate algorithm is selected based on the characteristics of the optimization problem. For example, linear programming is suitable for problems where both the objective function and constraints are linear, while genetic algorithms and particle swarm optimization are suitable for complex nonlinear optimization problems. A hybrid optimization algorithm is proposed, combining the strengths of different algorithms to improve optimization efficiency and accuracy.

[0194] Strategy Generation Submodule: Based on the results of the optimization algorithm, it generates specific optimization strategies. Strategies can include resource allocation plans, production plans, marketing plans, etc. At the same time, it evaluates and compares the generated strategies to provide users with the optimal strategy selection.

[0195] The Strategy Simulation submodule simulates generated strategies and predicts their effectiveness after implementation. By building data models, it simulates business scenarios under different strategies and evaluates their feasibility and effectiveness. Users can adjust and optimize strategies based on simulation results.

[0196] 4. User interaction module

[0197] User Interface Submodule: Designed with a concise and intuitive user interface, it provides functional areas such as the menu bar, toolbar, data panel, visualization panel, and strategy panel. Users can complete data analysis tasks and strategy optimization operations through simple operations such as dragging and clicking.

[0198] Feedback and Collaboration Submodule: This module collects user feedback and suggestions, and uses the user feedback system to promptly understand user needs and issues. It also supports multi-person collaboration, allowing users to share analysis results and strategic plans, discuss and modify them, and improve team collaboration efficiency.

[0199] In this embodiment, the beneficial effects include:

[0200] Comprehensive and in-depth data analysis: This system supports multi-dimensional data analysis and interactive exploration, and can mine the information behind the data from different angles and levels to help users fully understand the characteristics and patterns of the data.

[0201] Intuitive visual display: Through a variety of visual charts and personalized chart styles, complex data is presented to users in an intuitive way, improving the readability and comprehension of data.

[0202] Efficient strategy optimization: Integrating multiple optimization algorithms and proposing a hybrid optimization algorithm can quickly generate the optimal optimization strategy and improve the scientificity and efficiency of decision-making.

[0203] Good user interaction experience: The simple and intuitive user interface and rich interactive functions lower the user's usage threshold, while supporting multi-person collaboration and improving team collaboration efficiency.

[0204] In a specific implementation plan, the application process of the data multi-dimensional visualization analysis and strategy optimization system is as follows:

[0205] Choose a high-performance server as the system's operating platform to ensure that the system can handle large-scale data and complex computing tasks. The server should have sufficient memory, storage capacity, and computing power.

[0206] Install operating systems (including Linux), database management systems (including MySQL, MongoDB), big data processing frameworks (including Hadoop, Spark) and visual analysis tools (including Tableau, Echarts) software to provide operational support for various modules of the system.

[0207] Data collection and preprocessing

[0208] Data Collection: Configure the data collection submodule of the data collection and preprocessing module to connect with different data sources to achieve automatic data collection and synchronization. Set the collection frequency and collection rules to ensure the timeliness and accuracy of data.

[0209] Data preprocessing: Write data preprocessing scripts and use the Python programming language and related data processing libraries (including Pandas and Numpy) to clean, transform, and extract features from the collected raw data. For example, use the Pandas library to remove duplicate data and handle missing values, and use the Scikit-learn library for feature extraction and dimensionality reduction.

[0210] Multidimensional visual analysis

[0211] Data aggregation: Users select aggregation dimensions and aggregation functions through the data aggregation submodule of the multi-dimensional visual analysis module. The system uses the SQL or Spark data processing engine to aggregate the data.

[0212] Visualization chart generation: Based on the aggregated data, the visualization chart generation submodule uses the Echarts visualization library to generate appropriate visualization charts. Users can adjust the style and layout of the chart through the interface.

[0213] Interactive exploration: Users explore data through the interactive functions of the interactive exploration submodule. The system responds to user operations in real time, updates visual charts, and displays data details.

[0214] Association analysis: The association analysis submodule uses an improved association rule mining algorithm to perform association analysis on the data and presents the analysis results to the user in a visual manner.

[0215] Strategy Optimization

[0216] Goal setting: The user enters the optimization goal and constraints in the goal setting submodule of the strategy optimization module, and the system converts the goal and constraints into a mathematical model.

[0217] Optimization algorithm selection and calculation: The optimization algorithm submodule selects the appropriate optimization algorithm according to the characteristics of the mathematical model and uses Python optimization libraries (including SciPy and Pulp) for calculation.

[0218] Strategy generation and simulation: The strategy generation submodule generates optimization strategies based on the results of the optimization algorithm. The strategy simulation submodule uses the data model to simulate the strategy and evaluate its effectiveness.

[0219] User interaction and feedback

[0220] User interface operation: Users can operate through the user interface submodule of the user interaction module to view analysis results and strategy solutions. The interface provides friendly interactive prompts and operation instructions for user convenience.

[0221] Feedback and Collaboration: Users submit feedback through the Feedback and Collaboration submodule, and other users can view and discuss the feedback to jointly modify and optimize the strategy.

[0222] In a specific implementation scheme, the data multi-dimensional visualization analysis and strategy optimization system includes:

[0223] (1) Data acquisition and preprocessing module

[0224] Data acquisition components

[0225] Supports access to a variety of data sources, including relational databases (such as MySQL and Oracle), non-relational databases (such as MongoDB and Redis), file systems (such as CSV and Excel files), and API interfaces. By writing collectors that adapt to different data sources, automatic data collection and synchronization can be achieved.

[0226] It has two modes: real-time data collection and batch data collection. Real-time data collection is suitable for scenarios with high requirements for data timeliness, such as financial transaction data; batch data collection is used to regularly obtain large-scale historical data, such as a company's monthly sales data.

[0227] Data preprocessing components

[0228] Data cleaning: Remove duplicate data, handle missing values, and detect and correct outliers. Use a combination of statistical methods (such as the 3σ principle) and machine learning methods (such as the isolation forest algorithm) to detect outliers and improve the accuracy of outlier identification.

[0229] Data conversion: Convert data in different formats into a unified format, such as standardizing date formats and encoding categorical variables (such as one-hot encoding or label encoding). At the same time, normalize or standardize the data to eliminate the impact of different dimensions on the analysis results.

[0230] Feature engineering: Extract and construct meaningful features, and use feature selection algorithms (such as chi-square test and mutual information method) to screen out features that have a greater impact on the analysis target, reduce data dimensions, and improve analysis efficiency.

[0231] (2) Multidimensional Data Analysis Module

[0232] Data aggregation component

[0233] Supports a variety of aggregation functions, such as sum, average, maximum, minimum, count, etc. Users can customize aggregation dimensions according to analysis needs, such as aggregating sales data by time, region, product category, etc.

[0234] Use parallel computing technologies (such as MapReduce and Spark) to efficiently aggregate large-scale data and improve data processing speed.

[0235] Association Analysis Component

[0236] The Apriori algorithm and FP-Growth algorithm are used to mine frequent itemsets and generate association rules. By setting minimum support and minimum confidence thresholds, meaningful association rules can be screened out, such as finding that users who purchase product A are more likely to also purchase product B.

[0237] We innovatively introduce an association analysis method based on a graph model, representing the entities and relationships in the data as a graph structure, and use graph algorithms (such as community discovery algorithms and shortest path algorithms) to explore deeper association relationships.

[0238] Trend Analysis Component

[0239] Time series analysis methods (such as ARIMA models and LSTM neural networks) are used to model and predict the temporal trends of data. ARIMA models are suitable for stationary time series, while LSTM neural networks are better able to handle non-stationary time series data and time series data with long-term dependencies.

[0240] Provides a variety of trend visualization methods, such as line charts, area charts, etc., to intuitively show the changing trends of data over time.

[0241] (3) Visual display module

[0242] Visual Chart Library

[0243] It integrates a variety of common visualization charts, such as bar charts, line charts, pie charts, scatter plots, heat maps, etc. At the same time, it supports 3D visualization and dynamic visualization effects to enhance the intuitiveness and expressiveness of data.

[0244] Automatically recommend appropriate visualization chart types based on data type and analysis purpose, lowering the user's usage threshold.

[0245] Visual interaction components

[0246] Provides rich interactive functions such as zooming, panning, filtering, drilling, etc. Users can explore data in depth through interactive operations and view data details from different dimensions and levels.

[0247] It supports multi-view linkage. When the user operates in one view, other related views will be updated synchronously to help the user fully understand the relationship between the data.

[0248] (4) Strategy Optimization Module

[0249] Goal Setting Component

[0250] Allows users to define optimization goals, such as maximizing profits, minimizing costs, increasing market share, etc. At the same time, multiple constraints can be set, such as resource limitations, time limitations, etc.

[0251] Optimization algorithm components

[0252] Integrate multiple optimization algorithms, such as linear programming, genetic algorithms, and particle swarm optimization algorithms. Select the appropriate algorithm based on the characteristics of the optimization problem. For example, linear programming is suitable for problems where the objective function and constraints are linear, while genetic algorithms and particle swarm optimization algorithms are suitable for complex nonlinear optimization problems.

[0253] This application proposes a hybrid optimization algorithm that combines the advantages of different algorithms to improve optimization efficiency and accuracy. For example, a genetic algorithm is used to perform a global search to find a better solution space, and then a local search algorithm (such as gradient descent) is used to perform a detailed search in a local range.

[0254] Policy Evaluation Component

[0255] Establish a strategy evaluation indicator system, such as return on investment (ROI), net present value (NPV), internal rate of return (IRR), etc. Evaluate the optimized strategy and compare the advantages and disadvantages of different strategies.

[0256] Provides sensitivity analysis function to analyze the impact of different parameter changes on strategy effects, helping users understand the stability and risks of the strategy.

[0257] (5) User Interaction Module

[0258] User interface design

[0259] It uses a simple and intuitive user interface design, providing functional areas such as menu bar, toolbar, data panel, and visualization panel. Users can complete data analysis tasks through simple operations such as dragging and clicking.

[0260] It supports personalized settings, and users can adjust the interface layout, color theme, etc. according to their preferences.

[0261] User Feedback Component

[0262] Collect user feedback and suggestions, and promptly understand user needs and issues through the user feedback system. Optimize and improve the system based on user feedback to enhance user experience.

[0263] In this embodiment, a graph-based association analysis algorithm is used. While traditional association analysis algorithms primarily focus on frequent co-occurrence relationships between data items, graph-based association analysis algorithms represent entities and relationships in the data as a graph structure, enabling the discovery of deeper relationships. For example, in social network data, not only can friendships between users be discovered, but also relationships such as similar interests and social influence can be discovered.

[0264] The algorithm divides the graph structure into multiple communities through a community discovery algorithm, analyzes the association characteristics within the community and the association patterns between communities, and provides enterprises with more comprehensive association analysis results.

[0265] A hybrid optimization algorithm combines the global search capabilities of a genetic algorithm with the refined search capabilities of a local search algorithm. During the optimization process, the genetic algorithm continuously generates new solutions through operations such as selection, crossover, and mutation, expanding the search space. The local search algorithm conducts a refined search near the current optimal solution, seeking a better solution. By dynamically adjusting the execution order and parameters of the genetic and local search algorithms, optimization efficiency and accuracy are improved, avoiding being trapped in a local optimal solution.

[0266] In this embodiment, the beneficial effects include:

[0267] Comprehensiveness: The system covers the entire process of data collection, preprocessing, analysis, visualization, and strategy optimization, meeting the diverse data analysis needs of enterprises.

[0268] Efficiency: Using parallel computing technology and optimized algorithms to improve the speed of data processing and analysis, suitable for large-scale data processing;

[0269] Intuitive: Through rich visual charts and interactive functions, complex data is presented in an intuitive way to help users better understand the data;

[0270] Intelligence: It integrates multiple optimization algorithms and intelligent analysis methods to automatically generate optimization strategies and provide a scientific basis for corporate decision-making.

[0271] exist Figure 2 In the embodiment of the present application, a method for multi-dimensional visualization analysis of data and strategy optimization is provided, which is characterized by comprising the following steps:

[0272] Using the data acquisition and preprocessing module to collect raw data, and then cleaning, converting and feature extracting the raw data to obtain processed data;

[0273] aggregating the processed data using a multi-dimensional visualization analysis module to obtain aggregated data; generating a visualization chart based on the aggregated data; performing interactive operations on the aggregated data and the visualization chart; performing correlation analysis on the aggregated data to obtain potential relationships between the data, and generating a visualization strategy based on the obtained potential relationships between the data;

[0274] Using the strategy optimization module to simulate and evaluate the generated visualization strategy to obtain analysis results;

[0275] The analysis results are reviewed using a user interaction module, and user feedback is modified and optimized to obtain a final visualization strategy.

[0276] In a specific embodiment, the method comprises:

[0277] Data acquisition and preprocessing: The data acquisition submodule of the data acquisition and preprocessing module collects data from various data sources, and then uses the data preprocessing submodule to clean, convert and extract features from the data.

[0278] Multidimensional Visual Analysis: Users specify aggregation dimensions in the Data Aggregation submodule of the Multidimensional Visual Analysis module. The Visual Chart Generation submodule generates appropriate visualizations based on the aggregated data. Users can interactively manipulate data and delve deeper into data details using the Interactive Exploration submodule. The Association Analysis submodule performs association analysis on data to uncover potential relationships.

[0279] Strategy Optimization: Users define optimization objectives and constraints in the Goal Setting submodule of the Strategy Optimization module. The Optimization Algorithm submodule selects an appropriate optimization algorithm based on the objectives and constraints. The Strategy Generation submodule generates an optimization strategy based on the results of the optimization algorithm. The Strategy Simulation submodule simulates and evaluates the generated strategy.

[0280] User interaction and feedback: Users operate and view analysis results through the user interface sub-module of the user interaction module. The feedback and collaboration sub-module collects user feedback and supports multi-person collaboration to modify and optimize strategies.

[0281] In this embodiment, the beneficial effects include:

[0282] Comprehensive and in-depth data analysis: This system supports multi-dimensional data analysis and interactive exploration, and can mine the information behind the data from different angles and levels to help users fully understand the characteristics and patterns of the data.

[0283] Intuitive visual display: Through a variety of visual charts and personalized chart styles, complex data is presented to users in an intuitive way, improving the readability and comprehension of data.

[0284] Efficient strategy optimization: Integrating multiple optimization algorithms and proposing a hybrid optimization algorithm can quickly generate the optimal optimization strategy and improve the scientificity and efficiency of decision-making.

[0285] Good user interaction experience: The simple and intuitive user interface and rich interactive functions lower the user's usage threshold, while supporting multi-person collaboration and improving team collaboration efficiency.

[0286] Those skilled in the art will appreciate that the present application may be implemented as a system, method, or computer program product.

[0287] Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the present disclosure may be implemented in the form of a computer program product embodied in one or more computer-readable media, wherein the computer-readable media contains computer-readable program code.

[0288] Any combination of one or more computer-readable media can be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0289] Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application. Various substitutions and improvements may be made to the present application on this basis, all of which fall within the scope of protection of the present application.

Claims

1. A data multi-dimensional visualization analysis and strategy optimization system, characterized by: include: The data acquisition and preprocessing module is used to collect raw data, and clean, convert and extract features from the raw data to obtain processed data; Multi-dimensional visual analysis module, including: The data aggregation submodule is used to set the aggregation dimension of the data and aggregate the processed data to obtain aggregated data; the aggregation dimension includes aggregation by time, aggregation by region, and aggregation by product category; A visualization chart generation submodule is used to generate visualization charts based on the aggregated data; the visualization charts include bar charts, line charts, pie charts, scatter plots, heat maps and 3D visualization charts; An interactive exploration submodule, configured to perform interactive operations on the aggregated data and the visual chart; the interactive operations include zooming, panning, filtering, drilling, and animation generation; An association analysis submodule is used to perform association analysis on the aggregated data to obtain potential relationships between the data, and generate a visualization strategy based on the obtained potential relationships between the data; A strategy optimization module is used to simulate and evaluate the generated visualization strategy to obtain analysis results; The user interaction module is used to view the analysis results and modify and optimize the user's feedback to obtain a final visualization strategy; the final visualization strategy includes a resource allocation plan, a production plan or a marketing plan.

2. The data multi-dimensional visualization analysis and strategy optimization system according to claim 1 is characterized in that: The data acquisition and preprocessing module includes: Data acquisition submodule, used to collect raw data; The data preprocessing submodule is used to clean, convert and extract features from the raw data to obtain processed data.

3. The data multi-dimensional visualization analysis and strategy optimization system according to claim 2 is characterized in that: The strategy optimization module includes: The goal setting submodule is used to define the optimization goals and constraints; The optimization algorithm submodule is used to select a suitable optimization algorithm to perform calculations based on the objectives and constraints to obtain the analysis results; A strategy generation submodule, configured to generate the final visualization strategy based on the analysis result; The strategy simulation submodule is used to simulate and evaluate the final visualization strategy.

4. The data multi-dimensional visualization analysis and strategy optimization system according to claim 3 is characterized in that: The user interaction module includes: User interface submodule, used to optimize the design of the user interface; The feedback and collaboration sub-module is used to collect user operation feedback and suggestions.

5. The data multi-dimensional visualization analysis and strategy optimization system according to claim 4 is characterized in that: The optimization algorithms include linear programming algorithm, genetic algorithm and particle swarm optimization algorithm.

6. A data multi-dimensional visualization analysis and strategy optimization method, characterized in that: The following steps are involved: Using the data acquisition and preprocessing module to collect raw data, and then cleaning, converting and feature extracting the raw data to obtain processed data; Performing aggregation processing on the processed data using a multi-dimensional visualization analysis module to obtain aggregated data; generating a visual chart based on the aggregated data; and performing interactive operations on the aggregated data and the visual chart; Performing association analysis on the aggregated data to obtain potential relationships between the data, and generating a visualization strategy based on the obtained potential relationships between the data; Using the strategy optimization module to simulate and evaluate the generated visualization strategy to obtain analysis results; The analysis results are reviewed using a user interaction module, and user feedback is modified and optimized to obtain a final visualization strategy.

7. The data multi-dimensional visualization analysis and strategy optimization method according to claim 6 is characterized in that: The multidimensional visualization analysis module includes: The data aggregation submodule is used to set the aggregation dimension of the data and aggregate the processed data to obtain aggregated data; the aggregation dimension includes aggregation by time, aggregation by region, and aggregation by product category; A visualization chart generation submodule is used to generate visualization charts based on the aggregated data; the visualization charts include bar charts, line charts, pie charts, scatter plots, heat maps and 3D visualization charts; An interactive exploration submodule, configured to perform interactive operations on the aggregated data and the visual chart; The association analysis submodule is used to perform association analysis on the aggregated data to obtain potential relationships between the data, and generate a visualization strategy based on the obtained potential relationships between the data.

8. The data multi-dimensional visualization analysis and strategy optimization method according to claim 7 is characterized in that: The data acquisition and preprocessing module includes: Data acquisition submodule, used to collect raw data; The data preprocessing submodule is used to clean, convert and extract features from the raw data to obtain processed data.

9. The data multi-dimensional visualization analysis and strategy optimization method according to claim 8, characterized in that: The strategy optimization module includes: The goal setting submodule is used to define the optimization goals and constraints; The optimization algorithm submodule is used to select a suitable optimization algorithm to perform calculations based on the objectives and constraints to obtain the analysis results; A strategy generation submodule, configured to generate the final visualization strategy based on the analysis result; The strategy simulation submodule is used to simulate and evaluate the final visualization strategy.

10. The data multi-dimensional visualization analysis and strategy optimization method according to claim 9, characterized in that: The user interaction module includes: User interface submodule, used to optimize the design of the user interface; The feedback and collaboration sub-module is used to collect user operation feedback and suggestions.

Images