User management method and device based on resource mobility analysis and medium
Through the preprocessing, classification and trend analysis of user resource flow timing data, the problem of insufficient understanding of user status in the prior art is solved, and accurate user management and resource flow reliability and security are achieved.
Patent Information
- Application Number
- CN202510573015.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-06
- Publication Date
- 2025-08-12
Smart Images
Figure CN120471286A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of financial technology, and in particular to a user management method, device, and medium based on resource liquidity analysis. Background Art
[0002] In actual production, managers may not be able to directly understand the current status of users. However, the resource flow time series data of users on the management platform can indirectly reflect the current status of users. By controlling the current status of users, users can be managed, ensuring the stability of resource flow and avoiding losses.
[0003] Existing technologies typically perform simple statistical analysis on user resource flow time series data, and then manage users based on the statistical results. However, simple data statistics only provide static analysis of users. Existing technologies cannot fully explore the complete patterns and trends of time series data, nor can they provide in-depth analysis of user situations. This results in an incomplete and in-depth understanding of users' current situations. Consequently, user management strategies are flawed. Summary of the Invention
[0004] The present invention provides a user management method, device and medium based on resource mobility analysis, so as to conduct in-depth analysis of user status and achieve precise management of users.
[0005] According to one aspect of the present invention, a user management method based on resource mobility analysis is provided, the method comprising:
[0006] Obtain resource flow time series data of each user, and preprocess the resource flow time series data to obtain target resource flow time series data;
[0007] Classify and process the target resource flow time series data of each user to obtain a target classification result, and determine the user's resource flow pattern based on the target classification result;
[0008] Determine a time series trend characteristic value in at least one time window based on the target resource flow time series data of each user;
[0009] Determining a user status assessment result according to the resource flow pattern, the time series trend characteristic value, and the fluctuation state of the resource flow time series data;
[0010] Perform resource management on the user according to the status evaluation result.
[0011] According to another aspect of the present invention, a user management device based on resource mobility analysis is provided, the device comprising:
[0012] A data preprocessing module is used to obtain resource flow time series data of each user and preprocess the resource flow time series data to obtain target resource flow time series data;
[0013] A data classification module is used to classify the target resource flow time series data of each user, obtain a target classification result, and determine the user's resource flow pattern based on the target classification result;
[0014] A time series trend characteristic value determination module is used to determine a time series trend characteristic value in at least one time window based on the target resource flow time series data of each user;
[0015] A status evaluation result determination module, configured to determine a user's status evaluation result based on the resource flow pattern, the time series trend characteristic value, and the fluctuation state of the resource flow time series data;
[0016] The resource management module is used to manage resources for users according to the status evaluation results.
[0017] According to another aspect of the present invention, an electronic device is provided, comprising:
[0018] at least one processor; and
[0019] a memory communicatively connected to the at least one processor; wherein,
[0020] The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the user management method based on resource mobility analysis described in any embodiment of the present invention.
[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the user management method based on resource mobility analysis described in any embodiment of the present invention when executed.
[0022] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the user management method based on resource mobility analysis according to any embodiment of the present invention.
[0023] The technical solution of the embodiment of the present invention obtains the resource flow time series data of each user and pre-processes the resource flow time series data to obtain the target resource flow time series data; classifies the target resource flow time series data of each user to obtain the target classification result, and determines the user's resource flow pattern according to the target classification result; determines the time series trend characteristic value in at least one time window according to the target resource flow time series data of each user; determines the user's status evaluation result according to the resource flow pattern, the time series trend characteristic value, and the fluctuation state of the resource flow time series data; manages the user's resources according to the status evaluation result, thereby solving the problem of accurate user management. By performing in-depth user status analysis on the user's resource flow time series data, accurate user management can be achieved, ensuring the reliability and security of resource flow.
[0024] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0026] Figure 1 This is a flowchart of a user management method based on resource mobility analysis provided in accordance with the first embodiment of the present invention;
[0027] Figure 2 This is a flowchart of a user management method based on resource mobility analysis provided in accordance with a second embodiment of the present invention;
[0028] Figure 3 This is a structural diagram of a user management device based on resource mobility analysis provided according to a third embodiment of the present invention;
[0029] Figure 4 It is a structural diagram of an electronic device that implements the user management method based on resource mobility analysis according to an embodiment of the present invention. DETAILED DESCRIPTION
[0030] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.
[0031] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0032] Example 1
[0033] Figure 1 This is a flowchart of a user management method based on resource mobility analysis provided in accordance with the first embodiment of the present invention. This embodiment is applicable to situations where the user's resource mobility is analyzed and then the user is managed. The method can be executed by a user management device based on resource mobility analysis. The user management device based on resource mobility analysis can be implemented in the form of hardware and / or software. The user management device based on resource mobility analysis can be configured in an electronic device, which can be a mobile phone or a computer, etc. Figure 1 As shown, the method includes:
[0034] Step 110: Acquire resource flow time series data of each user, and pre-process the resource flow time series data to obtain target resource flow time series data.
[0035] Resource flow time series data can be the relationship between time and resources generated when users call or use resources on a specified platform. For example, resource flow time series data can be transaction flow data from business transactions. Transaction flow data can include user name, transaction time, transaction amount, counterparty, and transaction direction.
[0036] When obtaining a user's resource flow time series data, this can be done within multiple time windows. For example, a user's transaction flow data for the past five years, three years, two years, one year, six months, one quarter, or one month can be obtained as resource flow time series data. The acquisition of a user's resource flow time series data must be authorized by the user and the method of acquisition must be reasonable and legal.
[0037] The preprocessing of resource flow time series data can be one or more of data cleaning, data sparse processing, data missing value filling processing, data numerical compression, standardization conversion, and sequence smoothing processing.
[0038] Optionally, the resource flow time series data is preprocessed, including: dividing the resource flow time series data according to the direction of resource flow to obtain a first preprocessing result; performing numerical compression on the first preprocessing result to obtain a second preprocessing result; wherein the numerical compression maintains the data properties and relative relationships; performing standardization conversion on the second preprocessing result to obtain a third preprocessing result; performing sequence smoothing processing on the second preprocessing result to obtain a fourth preprocessing result; wherein the third preprocessing result is used as the target resource flow time series data for classification processing; and the fourth preprocessing result is used as the target resource flow time series data for determining the time series trend characteristic value.
[0039] Partitioning the resource flow time series data according to resource flow direction may be performed by partitioning the resource flow time series data according to positive and negative resource interactions in the resource flow time series data. For example, the number and amount of resource consumption during a specified time window, such as weekly resource flow, and the number and amount of resource input during weekly resource flow may be recorded, and the total number and amount of weekly resource flows may be calculated to obtain a first preprocessing result.
[0040] Before performing numerical compression on the first preprocessing results, missing values can be filled in. For example, a value of 0 can be recorded for a time window with no resource flow. For example, resource flow data for each user is collected for two years, totaling 104 weeks, i.e., resource flow time series data with a time length of 104.
[0041] When compressing the data, the data properties and relative relationships are maintained. For example, the first preprocessing result can be numerically compressed by a mapping relationship. For example, the first preprocessing result can be numerically compressed by a logarithmic transformation. Specifically, the formula a′ is used. t =ln(1+a t ), numerically compress the first preprocessing result to obtain the second preprocessing result. t is the resource flow value of the user at time point t, a′ t is the data a at time point t tConverted value. By using logarithmic transformation for numerical compression, we can avoid the situation where resource flow time series data is mostly concentrated in low value areas but also has large values, making it easier to more accurately mine the characteristics of user resource flow.
[0042] Standardization transformation can be to normalize the data. For example, using the formula The second preprocessing result is subjected to standardization transformation to obtain the third preprocessing result. t is the data a′ at time point t t The converted value. μ is the mean of the second preprocessing result, and σ is the standard deviation of the second preprocessing result.
[0043] Series smoothing can be used to reduce short-term fluctuations and individual extreme values in time series data. For example, within a time window with a certain time step, the mean, median, or mode is selected as the resource flow value at a given time point, replacing the data within that time step.
[0044] Specifically, the formula Smooth the second preprocessing result to obtain the fourth preprocessing result. t is the moving smoothing value at time point t, a' t is the original value of the sequence at time point t, and n is the time window length for the sequence smoothing process. For example, n can be a week, a month, or a quarter. By moving the time series of the resource flow time series data item by item, we can obtain the fourth preprocessing result after the sequence smoothing process.
[0045] In an embodiment of the present invention, the third preprocessing result and the fourth preprocessing result may have different uses. Specifically, the third preprocessing result is used as the target resource flow time series data during classification processing; the fourth preprocessing result is used as the target resource flow time series data when determining the time series trend characteristic value. By performing classification processing through the third preprocessing result, the volatility of the data can be retained during the classification processing, and accurate classification can be performed for users to obtain a reliable resource flow pattern. Determining the time series trend characteristic value through the fourth preprocessing result can avoid fluctuations in the data and the influence of extreme values on the characteristic value, so that the time series trend characteristic value can better reflect the characteristics of the resource flow time series data.
[0046] Step 120: Classify the target resource flow time series data of each user to obtain a target classification result, and determine the user's resource flow pattern based on the target classification result.
[0047] The target resource flow time series data in step 120 may be the third preprocessing result. The classification processing of the target resource flow time series data may be performed using a clustering method, such as K-means, hierarchical clustering, or deep learning-based clustering.
[0048] Through classification processing, users of the same category can be grouped together based on the target resource flow time series data. Users in the same group share common characteristics in the target resource flow time series data. Therefore, users in the same group can be identified as having the same resource flow pattern.
[0049] The resource flow pattern can be determined based on the morphological characteristics of the target resource flow time series data of the cluster center in the target classification result. For example, the resource flow pattern can be determined by analyzing the data characteristics of the cluster center in each group based on manual experience.
[0050] For example, when the target resource flow time series data at the cluster center shows a continuous upward fluctuation, the resource flow pattern of the users in the group where the cluster center is located can be determined as a stable operation type. When the target resource flow time series data at the cluster center shows a large fluctuation, the resource flow pattern of the users in the group where the cluster center is located can be determined as a risky operation type. When the target resource flow time series data at the cluster center shows a continuous downward fluctuation, the resource flow pattern of the users in the group where the cluster center is located can be determined as an operation requiring improvement type.
[0051] By classifying users according to target resource flow data and then determining the resource flow pattern, it is possible to accurately determine the resource flow pattern of each user while reducing the amount of data analysis.
[0052] Step 130: Determine a time series trend characteristic value in at least one time window based on the target resource flow time series data of each user.
[0053] The target resource flow timing data in step 130 may be the fourth preprocessing result.
[0054] For example, the time windows may include the past 24 months, the past 12 months, the past 6 months, and the past 3 months. The time series trend characteristic value can be the slope obtained by linearly fitting the time series data of the target resource flow within the time window. Through multi-time window analysis, a user's long-term, medium-term, short-term, and short-term resource flow trends can be obtained. The time series trend characteristic value can further reflect the user's resource flow characteristics, allowing for user management decisions based on the time series trend characteristic value.
[0055] Optionally, based on the target resource flow timing data of each user, the timing trend characteristic value in at least one time window is determined, including: obtaining the target resource flow timing data of each user in at least one time window; calculating the regression coefficient between the time point and the resource flow value in the target resource flow timing data, and using the regression coefficient as the timing trend characteristic value of the target resource flow timing data.
[0056] The regression coefficient can be a value obtained by linearly fitting the relationship between the time point and the resource flow value in the target resource flow time series data. For example, the formula Determine the regression coefficient between the time point and resource flow value in the target resource flow time series data. Where a″ t is the time series value at time point t in the fourth preprocessing result, where t = 1, 2, ..., n. The regression coefficient can be used as the time series trend characteristic value of the target resource flow time series data. Determining the time series trend characteristic values under multiple time windows by using the regression coefficient can make the time series trend characteristic value better reflect the volatility of the target resource flow time series data, thereby enabling precise management of users.
[0057] Step 140: Determine the user's status evaluation result based on the resource flow pattern, the time series trend characteristic value, and the fluctuation state of the resource flow time series data.
[0058] The fluctuation state of resource flow time series data can be the inherent volatility of the data. Resource flow patterns, time series trend characteristic values, and the fluctuation state of resource flow time series data can be mapped to scores or weighted summations to obtain a user status assessment result. By determining the user status assessment results across multiple dimensions, the user's overall resource flow status can be accurately reflected.
[0059] Step 150: Perform resource management on the user according to the status evaluation result.
[0060] The user's status assessment results can be used to determine whether the user's resource flow is at risk or requires optimization. Optionally, resource management can be performed on the user based on the status assessment results, including: recommending resource management policies to the user when the status assessment results meet preset policy recommendation conditions; and performing risk monitoring and setting permissions for the user when the status assessment results meet preset risk monitoring conditions.
[0061] For example, if a user's status results indicate that their resource flow is stabilizing, resource flow product recommendations can be made. If a user's status results indicate that their resource flow is decreasing, risk monitoring can be performed on the user. For example, a risk monitoring model can be used to determine whether their resource flow is at risk. While monitoring user risk, permissions can also be set for their resource flow, for example, restricting the use of some resource flow products to the current user.
[0062] By managing users' resources based on their status assessment results, we can conduct differentiated risk management and refined resource flow recommendation management based on their resource flow characteristics, thus meeting the needs of different users, improving user experience, and ensuring the security of resource flow.
[0063] The technical solution of this embodiment obtains the resource flow time series data of each user and pre-processes the resource flow time series data to obtain the target resource flow time series data; classifies the target resource flow time series data of each user to obtain the target classification result, and determines the resource flow pattern of the user according to the target classification result; determines the time series trend characteristic value in at least one time window according to the target resource flow time series data of each user; determines the user's status evaluation result according to the resource flow pattern, the time series trend characteristic value, and the fluctuation state of the resource flow time series data; manages the user's resources according to the status evaluation result, thereby solving the problem of accurate user management. By performing in-depth user status analysis on the user's resource flow time series data, accurate user management can be achieved to ensure the reliability and security of resource flow.
[0064] Example 2
[0065] Figure 2 This is a flowchart of a user management method based on resource mobility analysis provided in accordance with the second embodiment of the present invention. This embodiment is a further refinement of the above technical solution. The technical solution in this embodiment can be combined with various optional solutions in one or more of the above embodiments. Figure 2 As shown, the method includes:
[0066] Step 210: Obtain resource flow time series data of each user.
[0067] Step 220: Divide the resource flow time series data according to the resource flow direction to obtain a first preprocessing result; perform numerical compression on the first preprocessing result to obtain a second preprocessing result.
[0068] Among them, numerical compression maintains data properties and relative relationships.
[0069] Step 230: Perform standardization conversion on the second preprocessing result to obtain a third preprocessing result.
[0070] Step 240: Perform sequence smoothing processing on the second preprocessing result to obtain a fourth preprocessing result.
[0071] Step 250: Classify the third pre-processing results of each user to obtain a target classification result, and determine the user's resource flow pattern based on the target classification result.
[0072] Optionally, the target resource flow time series data of each user (which may be the third preprocessing result) is classified to obtain a target classification result, including: randomly grouping the target resource flow time series data of each user (which may be the third preprocessing result) under the target category number to obtain an initial grouping result; determining the cluster center in the initial grouping result, and calculating the time series distance between the target resource flow time series data of each user (which may be the third preprocessing result) and the cluster center; regrouping the target resource flow time series data of each user (which may be the third preprocessing result) according to the time series distance, and updating the initial grouping result; returning to the step of determining the cluster center in the initial grouping result until the iteration termination condition is met, and obtaining the target classification result corresponding to the target category number.
[0073] The target number of categories can be the optimal number of groups for grouping users. There are various ways to determine the target number of categories. For example, the target number of categories can be determined through empirical analysis. Alternatively, grouping can be performed using multiple preset numbers of categories, and corresponding candidate classification results can be determined. The optimal target classification result and target number of categories can then be determined from among the candidate classification results.
[0074] The cluster center can be the target resource flow time series data with the smallest cumulative time series distance to other target resource flow time series data in the group. j The cluster center is Among them, C j For group P j The target resource flow time series data within C j =(c1, c2, ..., c n ). A ij Represents group P j Time series data of target resource flow within i, CC s (A, B) represents the correlation coefficient between target resource flow time series data A and B. Target resource flow time series data A=(a1,a2,...,a n ),B=(b1,b2,...,b n ), s is the phase difference between the target resource flow timing data A and B.
[0075] The time series distance between the target resource flow time series data of each user and the cluster center can be the sequence morphology similarity between the target resource flow time series data and the cluster center. The sequence morphology similarity can be determined by Euclidean distance, Manhattan distance, or Pearson correlation coefficient.
[0076] Optionally, the timing distance between each user's target resource flow timing data (which may be the third preprocessing result) and the cluster center is calculated, including: determining the mutual correlation coefficient between each user's target resource flow timing data (which may be the third preprocessing result) and the cluster center based on the phase difference between each user's target resource flow timing data (which may be the third preprocessing result) and the cluster center; determining the sequence morphological similarity between each user's target resource flow timing data (which may be the third preprocessing result) and the cluster center based on the mutual correlation coefficient, the norm of each user's target resource flow timing data (which may be the third preprocessing result), and the norm of the cluster center; and using the sequence morphological similarity as the timing distance.
[0077] Among them, the formula can be used Determine the sequence morphology similarity between the target resource flow time series data of each user and the cluster center. SBD(A, B) represents the sequence morphology similarity between the target resource flow time series data A and B. is the norm of the target resource flow time series data A.
[0078] After determining the time series distance between each user's target resource flow time series data and the cluster center, the target resource flow time series data can be assigned to the group with the closest cluster center to update the initial grouping result. Then, return to the step of determining the cluster center in the initial grouping result until the iteration termination condition is met, and obtain the target classification result corresponding to the target number of categories.
[0079] The iteration termination condition may be that the cluster center no longer changes, that is, the algorithm converges, or the iteration termination condition may be that the maximum number of iterations is reached.
[0080] By categorizing users based on target classification results, we can ensure the rationality and accuracy of the classification. By determining the user's resource flow pattern based on the target classification results, we can consider the commonalities of user resource flow across the entire user group and the individuality of user resource flow, thereby enabling more precise resource flow management for users.
[0081] On the basis of the above implementation, optionally, the target resource flow timing data of each user is classified and processed to obtain a target classification result, which also includes: classifying the target resource flow timing data of each user (which may be the third preprocessing result) under at least two preset category numbers to obtain alternative classification results corresponding to each preset category number; calculating the cumulative value of the timing distance from the target resource flow timing data in each group in the alternative classification result (which may be the third preprocessing result) to the corresponding cluster center; taking the preset category number corresponding to the minimum timing distance cumulative value as the target category number, and taking the alternative classification result corresponding to the target category number as the target classification result.
[0082] For example, by the formula Determine the cumulative time series distance between the target resource flow time series data within each group in the candidate classification results and the corresponding cluster center. The candidate classification result corresponding to the minimum cumulative time series distance value can be used as the target classification result, and the corresponding preset number of categories can be used as the target number of categories.
[0083] By determining the number of target categories, we can ensure the optimization of target classification results and the most rational and accurate management of user resource flow.
[0084] Step 260: Determine a time series trend characteristic value in at least one time window based on the fourth preprocessing result of each user.
[0085] Optionally, based on the target resource flow timing data of each user (which may be the fourth preprocessing result), the timing trend characteristic value in at least one time window is determined, including: obtaining the target resource flow timing data of each user in at least one time window (which may be the fourth preprocessing result); calculating the regression coefficient between the time point and the resource flow value in the target resource flow timing data (which may be the fourth preprocessing result), and using the regression coefficient as the timing trend characteristic value of the target resource flow timing data (which may be the fourth preprocessing result).
[0086] Step 270: Determine the user's status evaluation result based on the resource flow pattern, the time series trend characteristic value, and the fluctuation state of the resource flow time series data.
[0087] Step 280: Perform resource management on the user according to the status evaluation result.
[0088] Optionally, resource management is performed on the user based on the status assessment results, including: recommending resource management policies to the user when the status assessment results meet preset policy recommendation conditions; and performing risk monitoring and permission setting on the user when the status assessment results meet preset risk monitoring conditions.
[0089] The technical solution of the embodiment of the present invention obtains resource flow time series data of each user; divides the resource flow time series data according to the resource flow direction to obtain a first preprocessing result; performs numerical compression on the first preprocessing result to obtain a second preprocessing result; performs standardization conversion on the second preprocessing result to obtain a third preprocessing result; performs sequence smoothing processing on the second preprocessing result to obtain a fourth preprocessing result; classifies the third preprocessing result of each user to obtain a target classification result, and determines the resource flow pattern of the user according to the target classification result; determines the time series trend feature value in at least one time window according to the fourth preprocessing result of each user; and determines the resource flow pattern of the user according to the resource flow. The user's status assessment results are determined by the dynamic pattern, time series trend characteristic values, and the fluctuation status of resource flow time series data; user resources are managed according to the status assessment results, which solves the problem of accurate user management. By extracting the complete time series morphological characteristics and long-term and short-term trend characteristics and performing cluster analysis, the user's complete resource fluctuation information can be extracted, the user's short-term resource fluctuations can be identified, and the long-term resource trend can be captured; through the evaluation of the user's resource flow pattern and status, the user can be deeply understood, and the user's behavior and needs can be understood; overall, differentiated and refined user resource management is achieved, which can realize accurate management of users and ensure the reliability and security of resource flow.
[0090] Example 3
[0091] Figure 3 Schematic diagram of a user management device based on resource mobility analysis according to the third embodiment of the present invention. Figure 3 As shown, the device includes: a data preprocessing module 310, a data classification module 320, a time series trend characteristic value determination module 330, a state assessment result determination module 340 and a resource management module 350. Among them:
[0092] The data preprocessing module 310 is used to obtain resource flow time series data of each user and preprocess the resource flow time series data to obtain target resource flow time series data;
[0093] The data classification module 320 is used to classify the target resource flow time series data of each user, obtain a target classification result, and determine the user's resource flow pattern based on the target classification result;
[0094] A time series trend characteristic value determination module 330 is configured to determine a time series trend characteristic value in at least one time window based on the target resource flow time series data of each user;
[0095] A status evaluation result determination module 340 is configured to determine a user's status evaluation result based on the resource flow pattern, the time series trend characteristic value, and the fluctuation state of the resource flow time series data;
[0096] The resource management module 350 is used to manage resources for users according to the status evaluation results.
[0097] Optionally, the data preprocessing module 310 includes:
[0098] a first preprocessing result determining unit, configured to divide the resource flow time series data according to resource flow directions to obtain a first preprocessing result;
[0099] a second preprocessing result determining unit, configured to perform numerical compression on the first preprocessing result to obtain a second preprocessing result; wherein the numerical compression maintains data properties and relative relationships;
[0100] a third preprocessing result determining unit, configured to perform a standardization conversion on the second preprocessing result to obtain a third preprocessing result;
[0101] a fourth preprocessing result determining unit, configured to perform sequence smoothing processing on the second preprocessing result to obtain a fourth preprocessing result;
[0102] Among them, the third preprocessing result is used as the target resource flow time series data during classification processing; the fourth preprocessing result is used as the target resource flow time series data when determining the time series trend characteristic value.
[0103] Optionally, the data classification module 320 includes:
[0104] An initial grouping result determining unit, configured to randomly group the target resource flow time series data of each user under the target number of categories to obtain an initial grouping result;
[0105] A time series distance calculation unit, configured to determine the cluster center in the initial grouping result and calculate the time series distance between the target resource flow time series data of each user and the cluster center;
[0106] An initial grouping result updating unit, configured to regroup the target resource flow time series data of each user according to the time series distance and update the initial grouping result;
[0107] The iteration unit is used to return to the step of determining the cluster center in the initial grouping result until the iteration termination condition is met, and the target classification result corresponding to the target category number is obtained.
[0108] Optionally, the data classification module 320 further includes:
[0109] a candidate classification result determination unit, configured to classify the target resource flow time series data of each user under at least two preset categories to obtain candidate classification results corresponding to each preset category;
[0110] A time series distance cumulative value calculation unit is used to calculate the time series distance cumulative value of the target resource flow time series data in each group in the candidate classification result to the corresponding cluster center;
[0111] The target classification result determination unit is configured to use the preset number of categories corresponding to the minimum temporal distance cumulative value as the target number of categories, and use the candidate classification result corresponding to the target number of categories as the target classification result.
[0112] Optionally, a temporal distance calculation unit includes:
[0113] a mutual correlation coefficient calculation subunit, configured to determine the mutual correlation coefficient between the target resource flow time series data of each user and the cluster center according to the phase difference between the target resource flow time series data of each user and the cluster center;
[0114] A sequence morphology similarity determination subunit is used to determine the sequence morphology similarity between each user's target resource flow time series data and the cluster center based on the mutual correlation coefficient, the norm of each user's target resource flow time series data, and the norm of the cluster center;
[0115] The temporal distance determination subunit is used to take the sequence morphological similarity as the temporal distance.
[0116] Optionally, the time series trend characteristic value determination module 330 includes:
[0117] A multi-time window data acquisition unit, configured to acquire target resource flow time series data of each user in at least one time window;
[0118] The time series trend characteristic value determination unit is used to calculate the regression coefficient between the time point and the resource flow value in the target resource flow time series data, and use the regression coefficient as the time series trend characteristic value of the target resource flow time series data.
[0119] Optionally, the resource management module 350 includes:
[0120] A resource management policy recommendation unit is used to recommend resource management policies to users when the status assessment result meets the preset policy recommendation conditions;
[0121] The risk monitoring unit is used to monitor risks and set permissions for users when the status assessment results meet the preset risk monitoring conditions.
[0122] The user management device based on resource mobility analysis provided by the embodiment of the present invention can execute the user management method based on resource mobility analysis provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0123] In the technical solutions of the embodiments of the present invention, the collection, storage, use, processing, transmission, provision and disclosure of user personal information (such as resource flow time series data, resource flow patterns, time series trend characteristic values, and status assessment results, etc.) are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0124] The information collected is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0125] Example 4
[0126] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.
[0127] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0128] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.
[0129] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the user management method based on resource mobility analysis.
[0130] In some embodiments, the user management method based on resource mobility analysis can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the user management method based on resource mobility analysis described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the user management method based on resource mobility analysis in any other appropriate manner (for example, by means of firmware).
[0131] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0132] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.
[0133] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0134] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0135] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0136] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.
[0137] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.
[0138] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.
Claims
1. A user management method based on resource mobility analysis, characterized in that: include: Obtain resource flow time series data of each user, and preprocess the resource flow time series data to obtain target resource flow time series data; Classify and process the target resource flow time series data of each user to obtain a target classification result, and determine the user's resource flow pattern based on the target classification result; Determine a time series trend characteristic value in at least one time window based on the target resource flow time series data of each user; Determining a user status assessment result according to the resource flow pattern, the time series trend characteristic value, and the fluctuation state of the resource flow time series data; Perform resource management on the user according to the status evaluation result.
2. The method according to claim 1, characterized in that Preprocessing the resource flow time series data includes: Dividing the resource flow time series data according to resource flow direction to obtain a first preprocessing result; Performing numerical compression on the first preprocessing result to obtain a second preprocessing result; wherein the numerical compression maintains data properties and relative relationships; performing standardization conversion on the second preprocessing result to obtain a third preprocessing result; performing sequence smoothing processing on the second preprocessing result to obtain a fourth preprocessing result; Among them, the third preprocessing result is used as the target resource flow time series data during classification processing; the fourth preprocessing result is used as the target resource flow time series data when determining the time series trend characteristic value.
3. The method according to claim 1 or 2, characterized in that Classify the target resource flow time series data of each user to obtain target classification results, including: Under the target number of categories, the target resource flow time series data of each user is randomly grouped to obtain the initial grouping results; Determine a cluster center in the initial grouping result, and calculate the time series distance between the target resource flow time series data of each user and the cluster center; Regrouping the target resource flow time series data of each user according to the time series distance and updating the initial grouping result; Return to the step of determining the cluster center in the initial grouping result until the iteration termination condition is met, and obtain the target classification result corresponding to the number of target categories.
4. The method according to claim 3, characterized in that Classify and process the target resource flow time series data of each user to obtain the target classification results, which also includes: Classify the target resource flow time series data of each user under at least two preset categories to obtain candidate classification results corresponding to each preset category; Calculate the cumulative time series distance between the target resource flow time series data in each group in the candidate classification results and the corresponding cluster center; The preset number of categories corresponding to the minimum temporal distance cumulative value is used as the target number of categories, and the candidate classification results corresponding to the target number of categories are used as the target classification results.
5. The method according to claim 3, characterized in that Calculating the time series distance between the target resource flow time series data of each user and the cluster center includes: Determining a correlation coefficient between each user's target resource flow time series data and the cluster center according to a phase difference between each user's target resource flow time series data and the cluster center; Determining the sequence morphology similarity between the target resource flow time series data of each user and the cluster center based on the mutual correlation coefficient, the norm of the target resource flow time series data of each user, and the norm of the cluster center; The sequence morphology similarity is used as the temporal distance.
6. The method according to claim 1 or 2, characterized in that Determine a time series trend characteristic value in at least one time window based on the target resource flow time series data of each user, including: Obtaining target resource flow time series data for each user in at least one time window; The regression coefficient between the time point and the resource flow value in the target resource flow time series data is calculated, and the regression coefficient is used as the time series trend characteristic value of the target resource flow time series data.
7. The method according to claim 1, characterized in that Performing resource management on the user based on the status assessment result includes: When the status evaluation result meets the preset policy recommendation conditions, recommend resource management policies to the user; When the status assessment result meets the preset risk monitoring conditions, risk monitoring and permission setting are performed on the user.
8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the user management method based on resource mobility analysis according to any one of claims 1 to 7.
9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the user management method based on resource mobility analysis according to any one of claims 1 to 7 when executed.
10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the user management method based on resource mobility analysis according to any one of claims 1 to 7.