Intelligent sorting method and device, computer equipment and readable storage medium

Abstract

The invention relates to the technical field of data analysis, and provides an intelligent sorting method and device, computer equipment and a readable storage medium, and the method comprises the steps: obtaining historical data corresponding to a plurality of preset assets, and carrying out the cleaning, denoising and standardization processing of the collected historical data; according to the historical data, obtaining a historical fluctuation condition and a periodic feature, and combining an investment target of a preset user to determine a time length for performing statistics on asset performance; scoring the preset assets based on a preset multi-dimensional index and the time duration to obtain a corresponding comprehensive score, and sorting the plurality of preset assets according to the comprehensive score; the method comprises the steps of obtaining personalized configuration parameters which comprise one or more of an investment target, risk preference, risk tolerance, an income target and asset category preference, adjusting sorting logic according to the personalized configuration parameters, and updating asset sorting results corresponding to a plurality of preset assets based on the adjusted sorting logic.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular to an intelligent sorting method, apparatus, computer device, and readable storage medium. Background Technology

[0002] In the field of financial asset management, historical comparative analysis of major asset classes is a core tool for investors to evaluate asset performance. Traditional technologies rely on users manually setting fixed statistical time periods, can only sort based on single dimensions such as returns and volatility, and lack personalized allocation capabilities. This makes the analysis results susceptible to biases in time period selection, difficult to adapt to rapid market changes, and unable to meet the differentiated risk-return balance needs of different investors. For example, short-term investors with a high risk appetite need to capture market fluctuations in real time, while long-term investors with a low risk appetite focus more on the stability trend of assets. However, existing systems cannot dynamically adjust the analysis dimensions and time range according to investment objectives, resulting in low decision-making efficiency.

[0003] Similar technological bottlenecks are also evident in the fields of healthcare and elderly care. For example, retirement asset allocation requires personalized planning that considers multiple dimensions such as the elderly person's risk tolerance, retirement period, and health status. However, existing systems can only provide fixed, template-based configuration schemes and cannot dynamically adapt to individual differences. The development of health management plans requires a comprehensive assessment of the user's medical history, lifestyle habits, and health goals, but traditional methods lack intelligent integration and dynamic adjustment mechanisms, making it difficult to generate accurate health intervention recommendations. Furthermore, both fields face the problem of insufficient real-time data processing efficiency—the high-frequency data changes in financial markets and the dynamic updates of healthcare data place higher demands on the system's real-time analysis and decision support capabilities. Existing technologies, lacking intelligent dynamic adjustment mechanisms, result in delayed analysis results, failing to meet practical application needs.

[0004] In summary, existing technologies suffer from three core shortcomings in cross-domain (finance, healthcare, elderly care) intelligent analysis: 1. Fixed time periods and analysis dimensions, unable to adapt to dynamic scenarios; 2. Single-dimensional analysis struggles to meet complex decision-making needs; 3. Lack of personalized configuration and real-time decision support capabilities. These issues limit the practicality of traditional systems when facing diverse scenarios, necessitating an innovative approach that integrates intelligent dynamic analysis, multi-dimensional integration, and personalized configuration. Summary of the Invention

[0005] This application provides an intelligent sorting method, apparatus, computer device, and readable storage medium, aiming to address three core shortcomings of existing technologies in cross-domain (finance, healthcare, elderly care) intelligent analysis: 1. Fixed time period selection and analysis dimensions, unable to adapt to dynamic scenarios; 2. Single-dimensional analysis is insufficient to meet complex decision-making needs; 3. Lack of personalized configuration and real-time decision support capabilities. These problems limit the practicality of traditional systems when facing diverse scenarios, necessitating an innovative method that integrates intelligent dynamic analysis, multi-dimensional integration, and personalized configuration.

[0006] Firstly, this application provides an intelligent sorting method, including: Acquire historical data corresponding to multiple preset assets, and clean, denoise, and standardize the collected historical data; Based on the historical data, historical fluctuations and cyclical characteristics are obtained, and combined with the preset user's investment objectives, the time length used to statistically analyze asset performance is determined. The preset assets are scored based on preset multi-dimensional indicators and time lengths to obtain corresponding comprehensive scores, and then the preset assets are sorted according to the comprehensive scores. Obtain personalized configuration parameters, which include one or more of the following: investment objectives, risk preferences, risk tolerance, return objectives, and asset class preferences. Adjust the sorting logic according to the personalized configuration parameters, and update the asset sorting results corresponding to multiple preset assets based on the adjusted sorting logic.

[0007] In some embodiments, the step of obtaining historical volatility and cyclical characteristics based on the historical data, and determining the time frame for statistical analysis of asset performance in conjunction with the investment objectives of a preset user, includes: obtaining the price volatility amplitude and frequency of the preset asset within a historical time period as historical volatility, and analyzing the cyclical patterns of price changes of the preset asset as cyclical characteristics; if the investment objective of the preset user is short-term returns, a shorter time frame is determined based on the volatility frequency corresponding to assets with larger historical volatility to reflect recent market trends; if the investment objective of the preset user is long-term allocation, a longer time frame is determined based on the cyclical characteristics corresponding to assets with smaller historical volatility to reflect the overall trend.

[0008] In some embodiments, the preset multi-dimensional indicators include return rate, volatility, risk-reward ratio, return stability, and market environment adaptability; the step of scoring preset assets based on preset multi-dimensional indicators and time length to obtain a corresponding comprehensive score includes: for each preset asset, calculating the actual value of each dimension indicator within a determined time length, comparing the actual value of each dimension indicator with preset indicator evaluation standards to generate a score for each dimension; and performing a weighted calculation of the scores for each dimension according to a preset indicator weighting system to obtain a comprehensive score corresponding to each preset asset, wherein the indicator weighting system is preset according to industry standards and historical data statistical patterns in the asset management field.

[0009] In some embodiments, sorting multiple preset assets based on comprehensive scores includes: arranging multiple preset assets in descending order of comprehensive scores to generate an initial asset sorting result; if there are preset assets with the same comprehensive score, comparing the return stability index scores of the preset assets, and then arranging the preset assets with the same comprehensive score in descending order of return stability index scores.

[0010] In some embodiments, adjusting the sorting logic according to the personalized configuration parameters includes: if the personalized configuration parameters include risk tolerance, adjusting the weights of volatility and risk-return ratio indicators according to the level of risk tolerance, wherein when the risk tolerance is high, the weight of the volatility indicator is reduced and the weight of the return indicator is increased, and when the risk tolerance is low, the weight of the volatility indicator is increased and the weight of the return indicator is decreased; if the personalized configuration parameters include asset class preference, adding a preference score for the preferred asset class to the sorting logic, wherein the preference score is a preset fixed bonus value or a bonus value dynamically calculated according to the degree of preference.

[0011] In some embodiments, updating the asset ranking results corresponding to multiple preset assets based on the adjusted ranking logic includes: redetermining the weights and scoring rules of each dimension indicator according to the adjusted ranking logic, recalculating the scores of each dimension indicator and the comprehensive score for multiple preset assets within a determined time period; rearranging the multiple preset assets according to the adjusted comprehensive score, generating an asset ranking result containing personalized configuration, and replacing the initial asset ranking result before adjustment.

[0012] In some embodiments, after updating the asset ranking results corresponding to multiple preset assets based on the adjusted ranking logic, the method further includes: when a preset major event or preset trend change is detected, triggering a dynamic adjustment process to recalculate the comprehensive score of the preset assets and update the ranking results; generating suggestion information based on the asset ranking results; the suggestion information includes the optimal asset allocation plan, risk warnings, or expected return information.

[0013] Secondly, this application provides an intelligent sorting device, comprising: The data acquisition unit is used to acquire historical data corresponding to multiple preset assets, and to clean, denoise and standardize the collected historical data. The length determination unit is used to determine the time length for statistical analysis of asset performance based on the historical data to obtain historical fluctuations and periodic characteristics, combined with the preset user's investment objectives. The asset ranking unit is used to score preset assets based on preset multi-dimensional indicators and time length, obtain corresponding comprehensive scores, and rank multiple preset assets according to the comprehensive scores. The result acquisition unit is used to acquire personalized configuration parameters, which include one or more of the following: investment objectives, risk preferences, risk tolerance, return objectives, and asset class preferences. The sorting logic is adjusted according to the personalized configuration parameters, and the asset sorting results corresponding to multiple preset assets are updated based on the adjusted sorting logic.

[0014] Thirdly, this application also provides a computer device, comprising: Memory and processor; The memory is used to store computer programs; The processor is configured to execute the computer program and, in executing the computer program, implement the steps of the intelligent sorting method as described in the first aspect above.

[0015] Fourthly, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to implement the steps of the intelligent sorting method described in the first aspect above.

[0016] This invention provides an intelligent ranking method that collects, cleans, and standardizes historical data on major asset classes; dynamically determines the statistical time frame (e.g., short-term for high-volatility assets, long-term for low-volatility assets) by combining historical asset volatility, cyclical characteristics, and user investment objectives; calculates a comprehensive score based on a weighted average of multiple indicators such as return, volatility, risk-reward ratio, return stability, and market environment adaptability; dynamically adjusts indicator weights or adds bias scores based on user-input parameters such as risk tolerance and asset preferences to generate customized ranking results; monitors major market events or trend changes in real time, triggering a recalculation of the ranking, and generates decision-making support information such as asset allocation suggestions and risk warnings based on the results.

[0017] By intelligently selecting time periods and integrating multiple dimensions, this system addresses the issue of untimely market fluctuation responses in financial asset analysis and meets the needs of personalized solution development in the healthcare and elderly care sectors, enabling the reuse of technical solutions across different scenarios. It overcomes the limitations of single dimensions by dynamically adjusting the statistical range based on historical volatility characteristics and cyclical patterns, avoiding time period selection bias and ensuring that the ranking results more closely reflect actual performance. It supports user-defined parameters such as risk preferences and return targets, generating personalized rankings through weight adjustments and propensity scoring, overcoming the "one-size-fits-all" shortcomings of traditional systems. Through dynamic process adjustments and intelligent suggestion generation, it achieves rapid response to market changes and transforms data ranking into actionable decision-making solutions (such as financial asset allocation and elderly care and health management plans), significantly enhancing the system's application value.

[0018] The above-mentioned technical solutions, through intelligent, personalized, and dynamic design, effectively compensate for the shortcomings of traditional methods in complex scenarios, and provide more efficient and accurate decision support tools for fields such as financial investment, medical health and elderly care.

[0019] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic flowchart illustrating the steps of an intelligent sorting method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of an intelligent sorting device provided in an embodiment of this application; Figure 3 This is a schematic block diagram of the structure of a computer device provided in an embodiment of this application.

[0022] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0025] It should be understood that, in order to clearly describe the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0026] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0027] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0028] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0029] In the field of financial asset management, historical comparative analysis of major asset classes is a core tool for investors to evaluate asset performance. Traditional technologies rely on users manually setting fixed statistical time periods, can only sort based on single dimensions such as returns and volatility, and lack personalized allocation capabilities. This makes the analysis results susceptible to biases in time period selection, difficult to adapt to rapid market changes, and unable to meet the differentiated risk-return balance needs of different investors. For example, short-term investors with a high risk appetite need to capture market fluctuations in real time, while long-term investors with a low risk appetite focus more on the stability trend of assets. However, existing systems cannot dynamically adjust the analysis dimensions and time range according to investment objectives, resulting in low decision-making efficiency.

[0030] Similar technological bottlenecks are also evident in the fields of healthcare and elderly care. For example, retirement asset allocation requires personalized planning that considers multiple dimensions such as the elderly person's risk tolerance, retirement period, and health status. However, existing systems can only provide fixed, template-based configuration schemes and cannot dynamically adapt to individual differences. The development of health management plans requires a comprehensive assessment of the user's medical history, lifestyle habits, and health goals, but traditional methods lack intelligent integration and dynamic adjustment mechanisms, making it difficult to generate accurate health intervention recommendations. Furthermore, both fields face the problem of insufficient real-time data processing efficiency—the high-frequency data changes in financial markets and the dynamic updates of healthcare data place higher demands on the system's real-time analysis and decision support capabilities. Existing technologies, lacking intelligent dynamic adjustment mechanisms, result in delayed analysis results, failing to meet practical application needs.

[0031] In summary, existing technologies suffer from three core shortcomings in cross-domain (finance, healthcare, elderly care) intelligent analysis: 1. Fixed time periods and analysis dimensions, unable to adapt to dynamic scenarios; 2. Single-dimensional analysis struggles to meet complex decision-making needs; 3. Lack of personalized configuration and real-time decision support capabilities. These issues limit the practicality of traditional systems when facing diverse scenarios, necessitating an innovative approach that integrates intelligent dynamic analysis, multi-dimensional integration, and personalized configuration.

[0032] To resolve the above issues, please refer to [link / reference]. Figure 1 , Figure 1 This is a schematic flowchart of an embodiment of the intelligent sorting method provided in this application. The intelligent sorting method can be implemented by a computer device, which can be deployed on a single server or a server cluster. It can also be deployed on a handheld terminal, laptop, wearable device, or robot, etc.

[0033] It should be noted that the acquisition of any information mentioned in the provided methods is in compliance with relevant regulations and is carried out with the user's consent, and will not infringe on the user's privacy or violate relevant laws and regulations.

[0034] To solve the above problem, please refer to Figure 1 Specifically, such as Figure 1 As shown, the provided intelligent sorting method includes steps S101 to S104. Details are as follows: Step S101. Obtain historical data corresponding to multiple preset assets, and perform cleaning, noise reduction and standardization processing on the collected historical data.

[0035] Specifically, historical data of preset assets is extracted through data interfaces or databases, and missing and outlier values ​​in the data are cleaned and denoised. The data format is then unified through normalization and standardization to ensure the accuracy and compatibility of subsequent analyses.

[0036] In financial scenarios, data types include: historical prices, trading volumes, exchange rates, and macroeconomic indicators (such as CPI and interest rates) of assets such as stocks, bonds, and funds. Time granularity includes minute-level (high-frequency trading), daily-level (routine analysis), or monthly-level (long-term trends). Data cleaning processes include: removing abnormal price data during trading halts; filling in missing values ​​due to data transmission interruptions (e.g., using the average of adjacent time points); converting assets denominated in different currencies to the target currency unit; and converting indicators with different dimensions, such as price and volatility, into dimensionless data within the [0,1] range using Z-score standardization or Min-Max standardization.

[0037] In the healthcare and elderly care scenario, data types include: collection of elderly care assets (such as pension account balances, historical returns of insurance products), health indicators (blood pressure, blood sugar, medical history records), lifestyle habits (exercise frequency, dietary data), and retirement cycle (retirement years, life expectancy). Data cleaning and processing involves: filtering out invalid health data (such as abnormal physiological indicators caused by equipment malfunctions); logically completing missing medical history records (e.g., by linking and filling in data through electronic medical record systems); converting unstructured data (such as doctor's diagnosis texts) into structured indicators (such as chronic disease severity scores); and standardizing indicators such as health risk levels and the liquidity of elderly care assets to eliminate dimensional differences caused by factors such as age and region.

[0038] By employing unified data cleaning and standardized processes, the heterogeneity between financial asset data and healthcare data is addressed, laying the foundation for subsequent cross-dimensional analysis. Noisy data is removed and missing values ​​are filled in to avoid sorting biases caused by data quality issues, ensuring that historical data accurately reflects the actual performance of assets / health status.

[0039] Step S102. Based on the historical data, obtain historical fluctuations and cycle characteristics, and combine them with the preset user's investment goals to determine the time length for statistical analysis of asset performance.

[0040] Specifically, by analyzing the fluctuation range, frequency, and cyclical patterns of historical data (such as bull and bear cycles of financial assets and seasonal fluctuations of health indicators), and combining this with users' investment / health management goals (short-term returns and long-term retirement planning), the time range for statistical asset / health performance is adaptively determined.

[0041] In financial scenarios, volatility and cycle analysis involves calculating the historical volatility (e.g., annualized standard deviation) and price fluctuation frequency (number of times daily price fluctuations exceed 1%) of equity assets to identify high-volatility assets (e.g., tech stocks) and low-volatility assets (e.g., government bonds). Fourier transforms or moving averages are used to extract cyclical characteristics of asset prices (e.g., interest rate cycles for bonds, supply and demand cycles for commodities). The time frame determination logic is as follows: If the user's goal is short-term arbitrage (investment period < 3 months), for high-volatility assets (e.g., cryptocurrencies), the statistical period is the time period with the highest volatility frequency over the past 30 days (e.g., trading days) to capture short-term market trends. If the user's goal is long-term allocation (investment period > 5 years), for low-volatility assets (e.g., gold ETFs), the statistical period is a complete economic cycle (e.g., 5-10 years) to filter out short-term noise from interfering with long-term trends.

[0042] In the healthcare and elderly care scenarios, fluctuation and cycle analysis involves analyzing the daily fluctuation range (e.g., diurnal variation) and monthly fluctuation frequency (number of outliers) of physiological indicators such as blood pressure and blood sugar to identify key health indicators requiring monitoring (e.g., blood sugar fluctuations in diabetic patients); extracting the return cycle of retirement assets (e.g., the dividend cycle of annuity insurance) and the seasonal patterns of health indicators (e.g., the increased incidence of cardiovascular and cerebrovascular diseases in winter). The logic for determining the time frame is as follows: If the user's goal is short-term health intervention (e.g., a 3-month weight loss plan), the statistical period is based on the physiological indicator fluctuation data of the most recent 90 days, focusing on recent health changes; if the user's goal is long-term retirement planning (20 years before retirement), the historical return stability of retirement assets and the long-term trends of health indicators (e.g., the rate of bone density decline with age) are statistically analyzed over a 10-year period to assess long-term risks and expectations.

[0043] It changes the traditional mechanical analysis model based on fixed time periods (such as "the past year") and dynamically adjusts the statistical range according to asset characteristics and user goals to avoid analysis bias caused by "one-size-fits-all" approaches. Short-term scenarios focus on high-frequency fluctuation data, while long-term scenarios focus on cyclical patterns, so that the time length is deeply matched with the analysis objectives, thereby improving the timeliness and reference value of the ranking results.

[0044] Step S103. Based on preset multi-dimensional indicators and time length, score the preset assets to obtain the corresponding comprehensive score, and sort the multiple preset assets according to the comprehensive score.

[0045] Specifically, by constructing an indicator system covering dimensions such as returns, risks, stability, and environmental adaptability, the indicator values ​​of each asset / health plan are calculated within a defined time period. A comprehensive score is generated through weighted scoring, and the plans are ranked according to their scores.

[0046] In financial scenarios, multi-dimensional indicators are used: Return-related indicators: annualized return, Sharpe ratio (risk-adjusted return); Risk-related indicators: maximum drawdown, volatility (reflecting price fluctuations); Stability-related indicators: standard deviation of the return series (measuring return volatility), number of consecutive months of positive returns; Environmental adaptability indicators: excess returns during economic recessions, performance scores under different market styles (growth / value). Scoring and ranking: For equity funds, the Sharpe ratio over the past year (measuring risk-return ratio) is calculated. If the value is 1.5, the score is 85 points (compared to the percentile of similar funds); a comprehensive score is calculated by weighting "return (40%) + Sharpe ratio (30%) + maximum drawdown (20%) + number of consecutive months of positive returns (10%)", with higher scores ranking higher; if two funds have the same comprehensive score, the fund with the higher "number of consecutive months of positive returns" is prioritized (reflecting stability advantage).

[0047] In the context of healthcare and elderly care, multi-dimensional indicators are used: Health-related indicators include BMI, blood pressure target achievement rate, and chronic disease control scores (such as glycated hemoglobin target achievement rate); Risk-related indicators include the probability of developing serious diseases (based on medical history and genetic data) and the volatility coefficient of health indicators (reflecting stability); Elderly care suitability indicators include the liquidity score of elderly care assets (such as whether they can be withdrawn early) and the stability of returns (the volatility of annuity insurance dividends); Goal matching degree is calculated based on the user's retirement goals (such as "average monthly consumption of 15,000 yuan after retirement"), determining the matching degree between asset returns and expected expenditures. Scoring and ranking: For elderly care plans, a comprehensive score is calculated based on "health risk score (30%) + elderly care asset liquidity (25%) + return stability (25%) + goal matching degree (20%)"; if two plans have the same score, the plan with the lower "health risk score" is prioritized (reflecting the principle of health priority).

[0048] Breaking away from the limitations of traditional single indicators (such as looking only at the rate of return or blood pressure value), it comprehensively portrays the overall performance of asset / health solutions through multi-dimensional weighted scoring; the indicator system can be flexibly adapted to financial and medical scenarios, and by adjusting the indicator weights (such as finance focusing on return and risk, and medical care focusing on health stability), it meets the professional analysis needs of different fields.

[0049] Step S104. Obtain personalized configuration parameters, which include one or more of the following: investment objectives, risk preferences, risk tolerance, return objectives, and asset class preferences. Adjust the sorting logic according to the personalized configuration parameters, and update the asset sorting results corresponding to multiple preset assets based on the adjusted sorting logic.

[0050] Specifically, the system obtains parameters such as user input regarding risk preference, return goals, and asset / health category preferences. By dynamically adjusting indicator weights or adding bias scores, the initial sorting logic is personalized to generate a sorting result tailored to the user's needs.

[0051] In financial scenarios, the parameter adjustment logic is as follows: If a user has a high risk tolerance (e.g., a risk assessment result of "aggressive"), the weight of the "volatility" indicator is reduced from 30% to 20%, while the weight of the "yield" indicator is increased from 40% to 50%, highlighting the priority of high-yield assets. If a user prefers the new energy industry, a 10% preference score is added to that asset category (e.g., the overall score of new energy funds is directly increased by 10 points) to reflect industry preference. Ranking updates: Based on the adjusted weights, the overall score of all assets is recalculated. For example, a high-volatility new energy fund originally scored 75 points; after the addition of points, its score increases to 85 points, moving its ranking from 10th to 3rd.

[0052] In healthcare and elderly care scenarios, the parameter adjustment logic is as follows: If a user's health goal is "controlling hypertension," the weight of "blood pressure achievement rate" is increased from 20% to 35%, while the weight of "BMI index" is decreased from 25% to 15%, focusing on blood pressure management-related solutions. If a user prefers traditional Chinese medicine (TCM) health solutions, a 15% preference score is added to that category of solutions to reflect personalized selection. Ranking updates: Health solution scores are recalculated. For example, a TCM treatment solution that originally scored 70 points might rise to 85 points after the score is increased, becoming a prioritized recommended solution.

[0053] It changes the traditional "standardized report" model by dynamically adjusting the sorting logic through user parameters, so that the results are tailored to individual risk tolerance, preferences and goals (such as conservative investors prioritizing the sorting of assets to avoid high volatility); it directly outputs sorting results that meet the user's personalized needs, reducing the cost of manual screening for users, especially in medical and elderly care scenarios, providing "one-click adaptation" intelligent support for non-professional users such as the elderly.

[0054] In some embodiments, the step of obtaining historical volatility and cyclical characteristics based on the historical data, and determining the time frame for statistical analysis of asset performance in conjunction with the investment objectives of a preset user, includes: obtaining the price volatility amplitude and frequency of the preset asset within a historical time period as historical volatility, and analyzing the cyclical patterns of price changes of the preset asset as cyclical characteristics; if the investment objective of the preset user is short-term returns, a shorter time frame is determined based on the volatility frequency corresponding to assets with larger historical volatility to reflect recent market trends; if the investment objective of the preset user is long-term allocation, a longer time frame is determined based on the cyclical characteristics corresponding to assets with smaller historical volatility to reflect the overall trend.

[0055] By analyzing the price fluctuation range, frequency, and cyclical patterns of preset assets, and combining this with the user's investment goals (short-term returns / long-term allocation), the time frame for statistical asset performance is dynamically determined: Short-term goal: For high-volatility assets, a short time window is determined based on high-frequency volatility data; Long-term goal: For low-volatility assets, a long time window covering the entire cycle is determined based on cyclical patterns.

[0056] In financial scenarios, data extraction involves: extracting the daily closing prices of stocks over the past year, calculating the number of times daily price fluctuations exceeded 2% (fluctuation frequency), and the average fluctuation (fluctuation amplitude); and identifying the 3-year interest rate cycle of bond prices (cycle characteristics) through Fourier transform. Time period determination: if the user's goal is short-term arbitrage (within 3 months), the past 60 days (the period with the highest recent volatility) are selected as the statistical period to focus on high-frequency trading opportunities; if the user's goal is long-term retirement planning (10 years), the past 10 years (covering two complete interest rate cycles) are selected as the statistical period to filter out short-term market noise.

[0057] In the healthcare and elderly care scenarios, data extraction involves: extracting daily blood pressure monitoring data from hypertensive patients over the past year, calculating the percentage of days with blood pressure exceeding 140 / 90 mmHg (fluctuation frequency), and the average difference between systolic and diastolic blood pressure (fluctuation amplitude); analyzing the dividend data of annuity insurance policies over the past 20 years to identify the 5-year return cycle (cycle characteristics). Time frame determination: if the user's goal is short-term blood pressure control (3 months), blood pressure data from the most recent 90 days (the period with the highest fluctuation frequency) is selected to monitor the intervention effect in real time; if the user's goal is long-term retirement planning (20 years before retirement), retirement asset return data from the past 20 years (covering 4 dividend cycles) is selected to assess long-term stability.

[0058] To avoid the mismatch between fixed time periods (such as "the past year") and different investment / health goals, the statistical period is deeply tied to user needs; short-term scenarios focus on identifying opportunities through high-frequency fluctuation data, while long-term scenarios extract core trends through periodic coverage, thereby improving the relevance of the analysis.

[0059] In some embodiments, the preset multi-dimensional indicators include return rate, volatility, risk-reward ratio, return stability, and market environment adaptability; the step of scoring preset assets based on preset multi-dimensional indicators and time length to obtain a corresponding comprehensive score includes: for each preset asset, calculating the actual value of each dimension indicator within a determined time length, comparing the actual value of each dimension indicator with preset indicator evaluation standards to generate a score for each dimension; and performing a weighted calculation of the scores for each dimension according to a preset indicator weighting system to obtain a comprehensive score corresponding to each preset asset, wherein the indicator weighting system is preset according to industry standards and historical data statistical patterns in the asset management field.

[0060] The system constructs a multi-dimensional indicator system that includes return, volatility, risk-reward ratio, return stability, and market environment adaptability. It calculates the actual value of the asset within a defined time period, compares it with preset evaluation standards to generate dimensional scores, and calculates the comprehensive score by weighting it through a preset weighting system.

[0061] In a financial context, the indicators are calculated as follows: Return: Calculate the annualized return of the equity fund over the past year (actual value), and compare it with the top 20% percentile of similar funds (evaluation standard). A score of 90 is awarded if the standard is met. Risk-Return Ratio: Calculate the Sharpe ratio (actual value). A score above 1.0 is awarded 80, and below 0.5 is awarded 50. Weighting System: Return (40%), Volatility (25%), Risk-Return Ratio (20%), Return Stability (15%). Overall Score: For a fund with a return score of 90, volatility score of 70, risk-return ratio score of 85, and return stability score of 80, the overall score = 90 × 40% + 70 × 25% + 85 × 20% + 80 × 15% = 83.5.

[0062] In the context of healthcare and elderly care, the indicators are converted as follows: Health stability: Calculate the standard deviation (actual value) of blood glucose levels in diabetic patients over the past year; a score of 85 is awarded if the value is below a preset threshold (e.g., 1.5 mmol / L). Elderly care suitability: Calculate the liquidity score of elderly care assets (actual value; 90 points for early withdrawal, 70 points for a 5-year lock-in period). Weighting system: Health stability (30%), elderly care asset liquidity (25%), return stability (25%), and target matching degree (20%). Overall score: For a certain elderly care plan with a health stability score of 80, a liquidity score of 85, a return stability score of 75, and a target matching degree score of 90, the overall score = 80 × 30% + 85 × 25% + 75 × 25% + 90 × 20% = 82.5.

[0063] Breaking through the limitations of single indicators, it comprehensively portrays the overall performance of assets / solutions through multi-dimensional weighted scoring (such as finance taking into account both returns and risks, and healthcare taking into account the suitability of health and retirement assets); the weighting system is based on historical data and industry norms to ensure that the scoring results conform to the professional logic of the field (such as in finance, the risk-return ratio is weighted higher than the single rate of return).

[0064] In some embodiments, sorting multiple preset assets based on comprehensive scores includes: arranging multiple preset assets in descending order of comprehensive scores to generate an initial asset sorting result; if there are preset assets with the same comprehensive score, comparing the return stability index scores of the preset assets, and then arranging the preset assets with the same comprehensive score in descending order of return stability index scores.

[0065] An initial ranking is generated in descending order of the overall score. If the scores are the same, a secondary ranking is performed based on the return stability index, prioritizing assets / plans with higher stability.

[0066] In a financial context, the initial ranking is as follows: stocks, bonds, funds, and other assets are ranked from highest to lowest based on their overall scores. The secondary ranking rule is as follows: if two funds both have an overall score of 85, the "number of consecutive months of positive returns" (a return stability indicator) is compared, and the fund with more consecutive months of positive returns is ranked higher (e.g., if fund A has 10 months of positive returns and fund B has 8 months of positive returns, then fund A is ranked higher).

[0067] In the context of healthcare and elderly care, the initial ranking is as follows: different elderly care plans are arranged in descending order of comprehensive score; the secondary ranking rule is as follows: if two plans both score 80 points, the "health indicator fluctuation coefficient" (such as the standard deviation of blood pressure value, stability index) is compared, and the one with the lower coefficient is given priority (for example, if the fluctuation coefficient of plan X is 0.8 and the fluctuation coefficient of plan Y is 1.2, then X is given priority).

[0068] To address the issue of "tied" scores, the stability index highlights implicit advantages (e.g., in finance, avoiding assets with "high scores but large returns volatility," and in healthcare, prioritizing options with "same scores but more stable health"). The stability index acts as a "safety valve," ensuring that the ranking results better reflect actual application needs (especially for users with low risk tolerance).

[0069] In some embodiments, adjusting the sorting logic according to the personalized configuration parameters includes: if the personalized configuration parameters include risk tolerance, adjusting the weights of volatility and risk-return ratio indicators according to the level of risk tolerance, wherein when the risk tolerance is high, the weight of the volatility indicator is reduced and the weight of the return indicator is increased, and when the risk tolerance is low, the weight of the volatility indicator is increased and the weight of the return indicator is decreased; if the personalized configuration parameters include asset class preference, adding a preference score for the preferred asset class to the sorting logic, wherein the preference score is a preset fixed bonus value or a bonus value dynamically calculated according to the degree of preference.

[0070] The ranking logic is modified by dynamically adjusting the weights of indicators such as volatility and return based on users' risk tolerance, or by adding preference scores based on asset class preferences.

[0071] In financial scenarios, risk tolerance adjustments are made as follows: For aggressive users (high risk tolerance): the volatility weight is reduced from 30% to 20%, while the yield weight is increased from 40% to 50%, prioritizing high-volatility, high-yield assets (such as tech stocks). For conservative users (low risk tolerance): the weights are adjusted in the opposite direction, increasing the volatility weight to 40% and decreasing the yield weight to 30%, prioritizing low-volatility assets (such as government bonds). Category preference bonuses: If a user prefers "green energy funds," an additional 5 points are awarded for each dimension of that asset category (a fixed bonus), or dynamic bonuses are awarded based on preference level (e.g., 10 points for "strong preference," 5 points for "moderate preference").

[0072] In the healthcare and elderly care scenarios, risk tolerance is adjusted as follows: For users with high health risk tolerance (such as young, healthy individuals): the weight of the "probability of chronic disease incidence" indicator is reduced (from 30% to 20%), while the weight of "convenience of health intervention" is increased (from 15% to 25%); For users with low health risk tolerance (such as elderly patients with chronic diseases): the weight of "health stability" is increased to 40%, while the weight of "intervention cost" is reduced to 10%. Category preference bonus: If a user prefers "Traditional Chinese Medicine (TCM) health preservation programs," an additional 15 points are awarded to the "health suitability" dimension of that category (reflecting the user's trust and preference for TCM).

[0073] By adjusting weights and adding preference scores, the system incorporates users' subjective preferences into the ranking logic, solving the "one-size-fits-all" problem of traditional systems (e.g., high-risk investors are no longer forced to accept low-volatility assets as a priority); non-professional users can obtain customized results by inputting simple parameters (such as risk level and preference category), thus improving the system's usability.

[0074] In some embodiments, updating the asset ranking results corresponding to multiple preset assets based on the adjusted ranking logic includes: redetermining the weights and scoring rules of each dimension indicator according to the adjusted ranking logic, recalculating the scores of each dimension indicator and the comprehensive score for multiple preset assets within a determined time period; rearranging the multiple preset assets according to the adjusted comprehensive score, generating an asset ranking result containing personalized configuration, and replacing the initial asset ranking result before adjustment.

[0075] Based on the adjusted sorting logic (changes in weighting / scoring rules), the scores for each dimension of the asset / solution and the overall score are recalculated, generating a sorting result that includes personalized configurations and replacing the initial result.

[0076] In financial scenarios, the recalculation process is as follows: If a user increases the weight of "yield" from 40% to 50%, the overall score of all assets is recalculated: Original score = yield × 40% + volatility × 30% + ...; New score = yield × 50% + volatility × 20% + ...; The assets are then re-ranked according to the new scores. For example, a high-yield, high-volatility stock that originally had a score of 75 points may have its score increased to 85 points, moving it from 10th place to 3rd place.

[0077] In the context of healthcare and elderly care, the process is recalculated: If users prefer "low-intervention intensity health plans", the weight of the "convenience of health intervention" indicator is increased (from 15% to 30%), and the plan score is recalculated: Original score = health stability × 30% + convenience × 15% + ...; New score = health stability × 20% + convenience × 30% + ...; A certain home rehabilitation plan has a high convenience score, and its new score has increased from 70 points to 80 points, and its ranking has increased from 8th to 2nd.

[0078] Ensure that personalized parameters are reflected in the sorting results in real time to avoid the problem of "parameter adjustment and result disconnect"; after replacing the initial result, users get a personalized sort that is fully adapted to their needs, avoiding confusion between the initial value and the adjusted value.

[0079] In some embodiments, after updating the asset ranking results corresponding to multiple preset assets based on the adjusted ranking logic, the method further includes: when a preset major event or preset trend change is detected, triggering a dynamic adjustment process to recalculate the comprehensive score of the preset assets and update the ranking results; generating suggestion information based on the asset ranking results; the suggestion information includes the optimal asset allocation plan, risk warnings, or expected return information.

[0080] After updating the ranking results, the system monitors preset major events / trend changes in real time (such as black swan events in the financial market or abnormal fluctuations in medical and health indicators), triggers dynamic recalculation of the ranking, and generates asset allocation plans, risk warnings, return expectations and other suggestions based on the results.

[0081] In a financial scenario, the trigger conditions are: detecting a 25 basis point rate hike by the Federal Reserve (major event) or a weekly decline of more than 5% in the S&P 500 index (trend change); dynamic adjustment: recalculating the overall score of all assets (e.g., the weight of the bond yield indicator increases after the rate hike), generating a new ranking; generating suggested information: "Current market risk is high, it is recommended to reduce the stock allocation to 40% and increase the government bond allocation to 30%" (optimal allocation plan), "Technology stock volatility exceeds the threshold, pay attention to stop loss" (risk warning).

[0082] In the healthcare and elderly care scenario, the trigger conditions are: detecting that a user's blood pressure is ≥160 / 100 mmHg for 3 consecutive days (major health event) or that the return on retirement assets is lower than the inflation rate for 6 consecutive months (trend change); dynamic adjustment: recalculate the health plan score (increase the weight of the blood pressure control indicator) or the retirement plan score (add the asset's ability to resist inflation indicator); generate the following suggestions: "If blood pressure remains high, it is recommended to increase the frequency of taking antihypertensive medication and make an appointment with a doctor" (health intervention suggestion) and "If the return on retirement assets is lower than inflation, it is recommended to allocate 5% of the assets to gold ETFs to hedge against risks" (retirement allocation suggestion).

[0083] Please see Figure 2 As shown, Figure 2 This is a schematic diagram of the structure of the intelligent sorting device 200 provided in the embodiments of this application. The intelligent sorting device 200 is used to execute the steps of the intelligent sorting method shown in the above embodiments. The intelligent sorting device 200 can be a single server or a server cluster, or the intelligent sorting device 200 can be a terminal, such as a handheld terminal, a laptop computer, a wearable device, or a robot.

[0084] like Figure 2 As shown, the intelligent sorting device 200 includes: The data acquisition unit 201 is used to acquire historical data corresponding to multiple preset assets and to clean, denoise and standardize the acquired historical data. The length determination unit 202 is used to determine the time length for statistical analysis of asset performance based on the historical data to obtain historical fluctuations and periodic characteristics, combined with the preset user's investment objectives. The asset sorting unit 203 is used to score preset assets based on preset multi-dimensional indicators and time length, obtain corresponding comprehensive scores, and sort multiple preset assets according to the comprehensive scores. The result acquisition unit 204 is used to acquire personalized configuration parameters, which include one or more of the following: investment objectives, risk preferences, risk tolerance, return objectives, and asset class preferences. The sorting logic is adjusted according to the personalized configuration parameters, and the asset sorting results corresponding to multiple preset assets are updated based on the adjusted sorting logic.

[0085] In some embodiments, the step of obtaining historical volatility and cyclical characteristics based on the historical data, and determining the time frame for statistical analysis of asset performance in conjunction with the investment objectives of a preset user, includes: obtaining the price volatility amplitude and frequency of the preset asset within a historical time period as historical volatility, and analyzing the cyclical patterns of price changes of the preset asset as cyclical characteristics; if the investment objective of the preset user is short-term returns, a shorter time frame is determined based on the volatility frequency corresponding to assets with larger historical volatility to reflect recent market trends; if the investment objective of the preset user is long-term allocation, a longer time frame is determined based on the cyclical characteristics corresponding to assets with smaller historical volatility to reflect the overall trend.

[0086] In some embodiments, the preset multi-dimensional indicators include return rate, volatility, risk-reward ratio, return stability, and market environment adaptability; the step of scoring preset assets based on preset multi-dimensional indicators and time length to obtain a corresponding comprehensive score includes: for each preset asset, calculating the actual value of each dimension indicator within a determined time length, comparing the actual value of each dimension indicator with preset indicator evaluation standards to generate a score for each dimension; and performing a weighted calculation of the scores for each dimension according to a preset indicator weighting system to obtain a comprehensive score corresponding to each preset asset, wherein the indicator weighting system is preset according to industry standards and historical data statistical patterns in the asset management field.

[0087] In some embodiments, sorting multiple preset assets based on comprehensive scores includes: arranging multiple preset assets in descending order of comprehensive scores to generate an initial asset sorting result; if there are preset assets with the same comprehensive score, comparing the return stability index scores of the preset assets, and then arranging the preset assets with the same comprehensive score in descending order of return stability index scores.

[0088] In some embodiments, adjusting the sorting logic according to the personalized configuration parameters includes: if the personalized configuration parameters include risk tolerance, adjusting the weights of volatility and risk-return ratio indicators according to the level of risk tolerance, wherein when the risk tolerance is high, the weight of the volatility indicator is reduced and the weight of the return indicator is increased, and when the risk tolerance is low, the weight of the volatility indicator is increased and the weight of the return indicator is decreased; if the personalized configuration parameters include asset class preference, adding a preference score for the preferred asset class to the sorting logic, wherein the preference score is a preset fixed bonus value or a bonus value dynamically calculated according to the degree of preference.

[0089] In some embodiments, updating the asset ranking results corresponding to multiple preset assets based on the adjusted ranking logic includes: redetermining the weights and scoring rules of each dimension indicator according to the adjusted ranking logic, recalculating the scores of each dimension indicator and the comprehensive score for multiple preset assets within a determined time period; rearranging the multiple preset assets according to the adjusted comprehensive score, generating an asset ranking result containing personalized configuration, and replacing the initial asset ranking result before adjustment.

[0090] In some embodiments, after updating the asset ranking results corresponding to multiple preset assets based on the adjusted ranking logic, the method further includes: when a preset major event or preset trend change is detected, triggering a dynamic adjustment process to recalculate the comprehensive score of the preset assets and update the ranking results; generating suggestion information based on the asset ranking results; the suggestion information includes the optimal asset allocation plan, risk warnings, or expected return information.

[0091] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the intelligent sorting device and its modules described above can be referred to the corresponding processes in the intelligent sorting method embodiments described above, and will not be repeated here.

[0092] The aforementioned intelligent sorting method can be implemented as a computer program, which can, for example... Figure 2 It runs on the device shown.

[0093] Please see Figure 3 , Figure 3 This is a schematic block diagram of the structure of a computer device provided in an embodiment of this application. The computer device includes a processor, a memory, and a network interface connected via a device bus, wherein the memory may include a storage medium and internal memory.

[0094] The storage medium may store operating devices and computer programs. The computer program includes program instructions that, when executed, cause the processor to perform any intelligent sorting method.

[0095] The processor provides computing and control capabilities, supporting the operation of the entire computer device.

[0096] Internal memory provides an environment for the execution of computer programs stored in non-volatile storage media, which, when executed by a processor, enable the processor to perform any intelligent sorting method.

[0097] This network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 3The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the terminal to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0098] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0099] In one embodiment, the processor is configured to run a computer program stored in memory to perform the following steps: Acquire historical data corresponding to multiple preset assets, and clean, denoise, and standardize the collected historical data; Based on the historical data, historical fluctuations and cyclical characteristics are obtained, and combined with the preset user's investment objectives, the time length used to statistically analyze asset performance is determined. The preset assets are scored based on preset multi-dimensional indicators and time lengths to obtain corresponding comprehensive scores, and then the preset assets are sorted according to the comprehensive scores. Obtain personalized configuration parameters, which include one or more of the following: investment objectives, risk preferences, risk tolerance, return objectives, and asset class preferences. Adjust the sorting logic according to the personalized configuration parameters, and update the asset sorting results corresponding to multiple preset assets based on the adjusted sorting logic.

[0100] In some embodiments, the step of obtaining historical volatility and cyclical characteristics based on the historical data, and determining the time frame for statistical analysis of asset performance in conjunction with the investment objectives of a preset user, includes: obtaining the price volatility amplitude and frequency of the preset asset within a historical time period as historical volatility, and analyzing the cyclical patterns of price changes of the preset asset as cyclical characteristics; if the investment objective of the preset user is short-term returns, a shorter time frame is determined based on the volatility frequency corresponding to assets with larger historical volatility to reflect recent market trends; if the investment objective of the preset user is long-term allocation, a longer time frame is determined based on the cyclical characteristics corresponding to assets with smaller historical volatility to reflect the overall trend.

[0101] In some embodiments, the preset multi-dimensional indicators include return rate, volatility, risk-reward ratio, return stability, and market environment adaptability; the step of scoring preset assets based on preset multi-dimensional indicators and time length to obtain a corresponding comprehensive score includes: for each preset asset, calculating the actual value of each dimension indicator within a determined time length, comparing the actual value of each dimension indicator with preset indicator evaluation standards to generate a score for each dimension; and performing a weighted calculation of the scores for each dimension according to a preset indicator weighting system to obtain a comprehensive score corresponding to each preset asset, wherein the indicator weighting system is preset according to industry standards and historical data statistical patterns in the asset management field.

[0102] In some embodiments, sorting multiple preset assets based on comprehensive scores includes: arranging multiple preset assets in descending order of comprehensive scores to generate an initial asset sorting result; if there are preset assets with the same comprehensive score, comparing the return stability index scores of the preset assets, and then arranging the preset assets with the same comprehensive score in descending order of return stability index scores.

[0103] In some embodiments, adjusting the sorting logic according to the personalized configuration parameters includes: if the personalized configuration parameters include risk tolerance, adjusting the weights of volatility and risk-return ratio indicators according to the level of risk tolerance, wherein when the risk tolerance is high, the weight of the volatility indicator is reduced and the weight of the return indicator is increased, and when the risk tolerance is low, the weight of the volatility indicator is increased and the weight of the return indicator is decreased; if the personalized configuration parameters include asset class preference, adding a preference score for the preferred asset class to the sorting logic, wherein the preference score is a preset fixed bonus value or a bonus value dynamically calculated according to the degree of preference.

[0104] In some embodiments, updating the asset ranking results corresponding to multiple preset assets based on the adjusted ranking logic includes: redetermining the weights and scoring rules of each dimension indicator according to the adjusted ranking logic, recalculating the scores of each dimension indicator and the comprehensive score for multiple preset assets within a determined time period; rearranging the multiple preset assets according to the adjusted comprehensive score, generating an asset ranking result containing personalized configuration, and replacing the initial asset ranking result before adjustment.

[0105] In some embodiments, after updating the asset ranking results corresponding to multiple preset assets based on the adjusted ranking logic, the method further includes: when a preset major event or preset trend change is detected, triggering a dynamic adjustment process to recalculate the comprehensive score of the preset assets and update the ranking results; generating suggestion information based on the asset ranking results; the suggestion information includes the optimal asset allocation plan, risk warnings, or expected return information.

[0106] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the task publishing method described in the first aspect above.

[0107] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0108] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An intelligent sorting method, characterized in that, include: Acquire historical data corresponding to multiple preset assets, and clean, denoise, and standardize the collected historical data; Based on the historical data, historical fluctuations and cyclical characteristics are obtained, and combined with the preset user's investment objectives, the time length used to statistically analyze asset performance is determined. The preset assets are scored based on preset multi-dimensional indicators and time lengths to obtain corresponding comprehensive scores, and then the preset assets are sorted according to the comprehensive scores. Obtain personalized configuration parameters, which include one or more of the following: investment objectives, risk preferences, risk tolerance, return objectives, and asset class preferences. Adjust the sorting logic according to the personalized configuration parameters, and update the asset sorting results corresponding to multiple preset assets based on the adjusted sorting logic.

2. The method according to claim 1, characterized in that, The step of obtaining historical fluctuations and cyclical characteristics based on the historical data, and determining the time frame for statistical analysis of asset performance in conjunction with the preset investment objectives of the user, includes: The price fluctuation range and frequency of the preset asset within a historical time period are obtained as historical fluctuation data, and the periodic pattern of the price change of the preset asset is analyzed as periodic characteristics. If the investment goal of the preset user is short-term returns, a shorter time period is determined based on the volatility frequency of assets with large historical volatility to reflect recent market trends. If the preset user's investment goal is long-term allocation, a longer time period is determined based on the cycle characteristics of assets with relatively small historical fluctuations to reflect the overall trend.

3. The method according to claim 1, characterized in that, The preset multi-dimensional indicators include return rate, volatility, risk-reward ratio, return stability, and market environment adaptability; the scoring of preset assets based on preset multi-dimensional indicators and time length to obtain a corresponding comprehensive score includes: For each preset asset, calculate the actual values ​​of each dimension indicator within a defined time period, compare the actual values ​​of each dimension indicator with the preset indicator evaluation standards, and generate scores for each dimension. Based on a pre-set indicator weighting system, the scores of each dimension are weighted and calculated to obtain a comprehensive score for each pre-set asset. The indicator weighting system is pre-set according to industry standards and historical data statistical patterns in the asset management field.

4. The method according to claim 1, characterized in that, The process of ranking multiple preset assets based on a comprehensive score includes: The initial asset ranking results are generated by arranging multiple preset assets in descending order of their overall scores. If there are preset assets with the same overall score, compare the return stability index score of the preset assets, and then arrange the preset assets with the same overall score in descending order of return stability index score.

5. The method according to claim 1, characterized in that, The sorting logic based on the personalized configuration parameters includes: If the personalized configuration parameters include risk tolerance, the weights of volatility and risk-return ratio indicators are adjusted according to the level of risk tolerance. Specifically, when the risk tolerance is high, the weight of the volatility indicator is reduced and the weight of the return indicator is increased; when the risk tolerance is low, the weight of the volatility indicator is increased and the weight of the return indicator is decreased. If the personalized configuration parameters include asset category preferences, a preference score for the preferred asset category is added to the sorting logic. The preference score is a preset fixed bonus value or a bonus value dynamically calculated based on the degree of preference.

6. The method according to claim 5, characterized in that, The step of updating the asset ranking results corresponding to multiple preset assets based on the adjusted ranking logic includes: Based on the adjusted sorting logic, the weights and scoring rules of each dimension indicator are redefined, and the scores of each dimension indicator and the overall score are recalculated for multiple preset assets within a defined time period. The system rearranges multiple preset assets based on the adjusted overall score, generates an asset ranking result that includes personalized configurations, and replaces the initial asset ranking result before the adjustment.

7. The method according to claim 1, characterized in that, After updating the asset ranking results corresponding to multiple preset assets based on the adjusted ranking logic, the method further includes: When a preset major event or preset trend change is detected, a dynamic adjustment process is triggered to recalculate the overall score of the preset assets and update the ranking results; Based on the asset ranking results, recommended information is generated; the recommended information includes the optimal asset allocation plan, risk warnings, or expected return information.

8. An intelligent sorting device, characterized in that, include: The data acquisition unit is used to acquire historical data corresponding to multiple preset assets, and to clean, denoise and standardize the collected historical data. The length determination unit is used to determine the time length for statistical analysis of asset performance based on the historical data to obtain historical fluctuations and periodic characteristics, combined with the preset user's investment objectives. The asset ranking unit is used to score preset assets based on preset multi-dimensional indicators and time length, obtain corresponding comprehensive scores, and rank multiple preset assets according to the comprehensive scores. The result acquisition unit is used to acquire personalized configuration parameters, which include one or more of the following: investment objectives, risk preferences, risk tolerance, return objectives, and asset class preferences. The sorting logic is adjusted according to the personalized configuration parameters, and the asset sorting results corresponding to multiple preset assets are updated based on the adjusted sorting logic.

9. A computer device, characterized in that, The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and, in executing the computer program, implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to implement the method as described in any one of claims 1 to 7.

Images