College financial data management method and system

Abstract

The invention is suitable for the technical field of financial data management, and particularly relates to a college financial data management method and system, and the method comprises the steps: obtaining a current financial data sequence, and determining a current financial identification sequence based on the current financial data sequence; according to the current financial identifier sequence, predicting each financial identifier of the next period of the current financial identifier sequence to obtain a predicted financial identifier sequence; obtaining an actual financial data sequence, and determining an actual financial identification sequence based on the actual financial data sequence; and comparing the actual financial identification sequence with the predicted financial identification sequence, constructing an actual fund flow graph based on the actual financial identification sequence, judging whether abnormal financial data exists in the actual financial data sequence, and obtaining a judgment result. According to the method, abnormal financial data can be quickly found, meanwhile, manual intervention is reduced, and the intelligent degree of financial management and the data processing efficiency are improved.

Description

Technical Field

[0001] The present application belongs to the technical field of financial data management, and in particular, to a method and system for financial data management in colleges and universities. Background Art

[0002] The management of university financial data refers to the systematic recording, analysis and supervision of university income, expenditure and assets, which is conducive to the efficient use and transparent operation of funds. The management content covers various sources of income such as tuition, government grants, scientific research funds, social donations, as well as expenditure items such as teaching, scientific research, infrastructure, and student services. Through financial statements such as balance sheets and income and expenditure statements, the financial status of universities is fully reflected, supporting budget preparation, cost control and performance evaluation, and providing important decision-making basis for the sustainable development of universities.

[0003] In the existing technology, the financial data of colleges and universities involves multiple dimensions (such as income, expenditure, budget execution, etc.), which are diverse and complex. Due to the huge amount of financial data of colleges and universities, manual reconciliation and abnormal audit are inefficient and prone to errors, making it difficult to fully and timely discover abnormal data. For example, if problems such as illegal expenditure, abnormal fund flow, and repeated reimbursement are not discovered in time, they may cause financial losses or financial risks.

[0004] To sum up, when managing the financial data of universities, there is a problem of difficulty in timely detecting abnormal data due to the huge amount of financial data and low efficiency of manual abnormality review. Summary of the invention

[0005] The embodiments of the present application provide a method and system for managing financial data of colleges and universities, which can solve the problem in the related art that when managing financial data of colleges and universities, it is difficult to find abnormal data in time due to the huge amount of financial data and the low efficiency of manual abnormality review.

[0006] In a first aspect, the present application embodiment provides a method for managing financial data of a university, including: Acquire a current financial data sequence, and determine a current financial identification sequence based on the current financial data sequence; wherein the current financial data sequence is obtained based on the financial data of colleges and universities within a certain period arranged in chronological order, and the current financial identification sequence is used to characterize the financial identification corresponding to each financial data in the current financial data sequence; According to the current financial identification sequence, predicting each financial identification of the next cycle of the current financial identification sequence to obtain a predicted financial identification sequence; Acquire an actual financial data sequence, and determine an actual financial identification sequence based on the actual financial data sequence; wherein the actual financial data sequence is the financial data actually collected in the next period of the current financial identification sequence; Comparing the actual financial identification sequence with the predicted financial identification sequence, and constructing an actual funds flow diagram based on the actual financial identification sequence, determining whether there is abnormal financial data in the actual financial data sequence, and obtaining a determination result; If the judgment result indicates that abnormal financial data exists in the actual financial data sequence, abnormal management is performed on the abnormal financial data.

[0007] The above technical solutions in the embodiments of the present application have at least the following technical effects: The financial data management method for colleges and universities provided in this application first obtains the current financial data sequence (based on the financial data of colleges and universities within a certain period arranged in chronological order), and determines the current financial identification sequence based on the current financial data sequence, and then predicts each financial identification of the next period of the current financial identification sequence according to the current financial identification sequence to obtain the predicted financial identification sequence, and then obtains the actual financial data sequence, and determines the actual financial identification sequence based on the actual financial data sequence (the financial data actually collected in the next period of the current financial identification sequence), and then compares the actual financial identification sequence with the predicted financial identification sequence, and constructs an actual capital flow diagram based on the actual financial identification sequence, and judges whether there is abnormal financial data in the actual financial data sequence, and obtains the judgment result, and finally, if the judgment result indicates that there is abnormal financial data in the actual financial data sequence, abnormal management is performed on the abnormal financial data. The method can quickly discover abnormal financial data and improve the ability of financial risk management and control by comparing the actual financial identification sequence with the predicted financial identification sequence, and can clearly display the flow, source and use of funds through the actual capital flow diagram, improve the transparency of fund management, and help college financial managers to intuitively analyze the flow of funds. This method can automatically extract, analyze and predict financial indicators, reduce human intervention, reduce human errors, and improve the intelligence level of financial management and data processing efficiency.

[0008] In a second aspect, the present application embodiment provides a university financial data management system, including: A current financial identification sequence determination unit is used to obtain a current financial data sequence, and determine a current financial identification sequence based on the current financial data sequence; wherein the current financial data sequence is obtained based on the financial data of colleges and universities within a certain period arranged in chronological order, and the current financial identification sequence is used to characterize the financial identification corresponding to each financial data in the current financial data sequence; A prediction unit, used for predicting each financial identifier of the next period of the current financial identifier sequence according to the current financial identifier sequence to obtain a predicted financial identifier sequence; An actual financial identification sequence determination unit is used to obtain an actual financial data sequence and determine an actual financial identification sequence based on the actual financial data sequence; wherein the actual financial data sequence is the financial data actually collected in the next period of the current financial identification sequence; An abnormality judgment unit is used to compare the actual financial identification sequence with the predicted financial identification sequence, and to construct an actual capital flow diagram based on the actual financial identification sequence, to judge whether there is abnormal financial data in the actual financial data sequence, and to obtain a judgment result; The abnormality management execution unit is used to execute abnormality management on the abnormal financial data if the judgment result indicates that abnormal financial data exists in the actual financial data sequence.

[0009] In a third aspect, an embodiment of the present application provides a financial data management device for a university, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any one of the embodiments of the first aspect when executing the computer program.

[0010] It can be understood that the beneficial effects of the second to third aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0012] Figure 1 It is a flowchart of a method for managing university financial data provided by an embodiment of the present application; Figure 2 It is a schematic diagram of the implementation process of predicting the five-level classification and amount of each financial identifier in the next cycle of the current financial identifier sequence in the university financial data management method provided by the embodiment of the present application. DETAILED DESCRIPTION

[0013] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0014] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0015] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0016] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0017] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0018] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0019] In related technologies, university financial data involves multiple dimensions (such as income, expenditure, budget execution, etc.), which are diverse and complex. Due to the huge amount of financial data in universities, manual reconciliation and abnormal auditing are inefficient and prone to errors, making it difficult to fully and timely discover abnormal data. For example, problems such as illegal expenditures, abnormal fund flow, and repeated reimbursement may cause financial losses or financial risks if not discovered in time.

[0020] To solve the above problems, the embodiment of the present application provides a method and system for managing financial data of colleges and universities. In the method, the current financial data sequence is first obtained (based on the college financial data within a certain period arranged in chronological order), and based on the current financial data sequence, the current financial identification sequence is determined, and then each financial identification of the next period of the current financial identification sequence is predicted according to the current financial identification sequence to obtain the predicted financial identification sequence, and then the actual financial data sequence is obtained, and the actual financial identification sequence is determined based on the actual financial data sequence (the financial data actually collected in the next period of the current financial identification sequence), and then the actual financial identification sequence is compared with the predicted financial identification sequence, and an actual capital flow diagram is constructed based on the actual financial identification sequence to determine whether there is abnormal financial data in the actual financial data sequence, and a judgment result is obtained. Finally, if the judgment result indicates that there is abnormal financial data in the actual financial data sequence, abnormal management is performed on the abnormal financial data. By comparing the actual financial identification sequence with the predicted financial identification sequence, the method can quickly discover abnormal financial data and improve the ability to control financial risks, and through the actual capital flow diagram, the flow direction, source and use of funds can be clearly displayed, the transparency of fund management can be improved, and the financial managers of colleges and universities can be helped to intuitively analyze the flow of funds. This method can automatically extract, analyze and predict financial indicators, reduce human intervention, reduce human errors, and improve the intelligence level of financial management and data processing efficiency.

[0021] The university financial data management method provided in the embodiment of the present application can be applied to the university financial data management device. In this case, the university financial data management device is the executor of the university financial data management method provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the university financial data management device.

[0022] For example, the university financial data management device can be a mobile phone, a tablet computer, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a desktop computer, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a computer, a laptop computer, a handheld computing device, customer premise equipment (CPE) and / or other devices used to communicate on a wireless system and a next-generation communication system, for example, a mobile terminal in a 5G network or a mobile terminal in a future evolved public land mobile network (PLMN).

[0023] In order to better understand the university financial data management method provided by the embodiment of the present application, the specific implementation process of the university financial data management method provided by the embodiment of the present application is exemplarily introduced below.

[0024] Figure 1 A schematic flow chart of a university financial data management method provided by an embodiment of the present application is shown, and the university financial data management method includes: S100, obtaining a current financial data sequence, and determining a current financial identification sequence based on the current financial data sequence, wherein the current financial data sequence is obtained based on the financial data of colleges and universities within a certain period arranged in chronological order, and the current financial identification sequence is used to represent the financial identification corresponding to each financial data in the current financial data sequence.

[0025] It can be understood that the cycle can be a short cycle, such as day, week, month (applicable to cash flow management); it can be a medium cycle, such as quarter (applicable to budget execution analysis); it can be a long cycle, such as year (applicable to financial settlement and financial health assessment).

[0026] For example, the financial data of a university within a certain period can be obtained by querying the university's financial management system (such as Oracle EBS, SAP, UFIDA, Kingdee, etc.) through SQL; it can be obtained from the university's financial statements, such as income statements, expenditure statements, budget execution statements, etc.; the financial data of various departments of the university can be extracted from the ERP system; if the university's financial data is stored in Excel / CSV files, it can be read using tools such as Python.

[0027] Data cleaning and preprocessing of current financial data include: removing duplicate records in current financial data, such as duplicate income or expenditure data; filling or deleting missing data, such as using the previous period's data to fill or delete outliers; unifying all data fields, such as date format, amount unit, account classification, etc. After data cleaning, the current financial data is arranged in chronological order to form the current financial data sequence for subsequent trend analysis.

[0028] It can be understood that financial identifiers can include the time of financial data, the type of financial data, and the amount of financial data. The types of financial data can be divided into income categories, such as tuition income, accommodation income, scientific research funding income, social donation income, other income (such as venue rental fees, investment income), etc.; expenditure categories, such as teaching expenditures (teachers' salaries, teaching equipment purchases), scientific research expenditures (experimental materials, paper publishing expenses), logistics management expenditures (property management, water and electricity fees), administrative management expenditures (office supplies, marketing promotion), student activity expenditures (scholarships, grants), infrastructure expenditures (new school projects, repair costs), etc.

[0029] For example, each piece of financial data can be assigned to a corresponding type based on the data's source, amount, purpose, and other attributes. The data can be automatically categorized using the accounting subject classification preset by the financial system; it can be automatically categorized by identifying keywords in the data (such as salary, scholarship); it can be compared with past financial records and categorized based on historical similarities; for special cases that do not meet the automatic classification rules, financial personnel will manually confirm. For example, if a source of income is tuition payment, its type is tuition income; if a certain expenditure occurs in the purchase of laboratory equipment, its type is scientific research expenditure.

[0030] After completing the classification of financial data, extract the time and amount in the financial data, and arrange the financial data identifiers in chronological order to generate a financial identifier sequence. For example, the financial identifier is 2025.03.01-tuition income-500,000; the financial identifier is 2025.03.03-teaching expenditure-20,000.

[0031] This step is conducive to the structuring and standardization of financial data, laying the foundation for subsequent financial forecasting, cash flow analysis and anomaly detection.

[0032] In a possible implementation, S100, determining a current financial identification sequence based on a current financial data sequence includes: S110, extracting key information of each financial data from the current financial data sequence according to the identification template. The identification template includes teaching cycle, five-level classification, fund attribute and amount. The key information of each financial data includes the teaching cycle of each financial data, the five-level classification of each financial data, the fund attribute of each financial data and the amount of each financial data. The teaching cycle is obtained by converting the time of the financial data into the school year number, the semester stage and the teaching week. The five-level classification is to divide the financial data into five levels: major category, medium category, minor category, special project and sub-item according to the standards of the Ministry of Education. The fund attribute includes the source type of funds and the destination type of funds.

[0033] It can be understood that each financial data in the current financial data sequence can include timestamp (such as 2025.03.10), transaction amount, fund category (such as tuition income, purchase of precision instruments, etc.), relevant departments (such as teaching units, scientific research units, administrative departments), source of funds (such as government grants, self-raised funds (tuition, accommodation fees), social funds) and purpose of funds (such as wages, equipment procurement, scholarship issuance).

[0034] The semester stage can be divided into the school preparation period (the first two weeks of the teaching week), the teaching operation period (the 3rd to 16th weeks of the teaching week), the examination week (the last two weeks of the teaching week), and the holidays (winter vacation / summer vacation).

[0035] The five-level classification is constructed based on the "Guidelines for Financial Accounting in Colleges and Universities" of the Ministry of Education. The major category represents the highest level classification of fund use, the middle category represents the secondary classification of funds, the minor category represents specific expenditure or income categories, the special item represents specific projects that are further subdivided, and the sub-item represents the specific flow of individual funds.

[0036] For example, the timestamp of each financial data can be converted into the academic year number, semester stage, and teaching week. For example, if the timestamp of a financial data is 2025.03.10, then the teaching cycle of the financial data is the academic year number 2024-2025, the semester stage is the teaching operation period, and the teaching week is the 5th week. Converting natural time (timestamp) into a unique teaching calendar system (teaching cycle) of colleges and universities can solve the problem that universal time cannot reflect the periodic fluctuations of college finances.

[0037] According to the funding category of each financial data, a five-level classification tree can be constructed: major category-medium category-minor category-special item-sub-item. For example, if the funding category of a financial data is precision instrument purchase, then the five-level classification of the financial data can be scientific research expenditure-vertical project-equipment fee-national key R&D plan-precision instrument purchase. Constructing the funding category into a five-level classification tree can achieve more detailed fund flow tracking than the traditional three-level classification.

[0038] The fund attribute label of each financial data can be extracted according to the source and purpose of the funds of each financial data. For example, if the source of funds of a certain financial data is government grants and the purpose is scholarship expenditure, then the fund attribute of the financial data is government grants->scholarships.

[0039] S120, filling the key information of each financial data into the identification template to obtain the financial identification corresponding to each financial data.

[0040] For example, after the teaching cycle, five-level classification, fund attributes and amount of each financial data are extracted, they are filled into the identification template to form a standardized financial identification, that is, {school year number}-{semester stage}-{teaching week} / {five-level classification} / {source of funds type}->{destination of funds type} / {amount}. For example, a financial identification is 2024-2025 school year-teaching operation period-week 5 / scientific research expenditure-vertical project-equipment fee-national key R&D plan-precision instrument purchase / self-raised funds->equipment purchase / 20000.

[0041] S130, arranging the financial identifier corresponding to each financial data according to the arrangement order of each financial data in the current financial data sequence to obtain the current financial identifier sequence.

[0042] For example, each generated financial identifier is arranged according to the original order of the current financial data sequence to form a current financial identifier sequence. The current financial identifier sequence can be used for financial analysis, forecasting, fund flow tracking, etc.

[0043] The above steps are conducive to the standardization and traceability of university financial data, providing a solid foundation for subsequent financial analysis, forecasting and anomaly detection.

[0044] S200, predicting each financial identifier of the next period of the current financial identifier sequence according to the current financial identifier sequence to obtain a predicted financial identifier sequence.

[0045] It is understandable that, because university financial data have cyclical patterns (e.g., tuition revenue is concentrated at the beginning of the semester, and research funding expenditures have a quarterly allocation rhythm, etc.), the financial identifier sequence for the next cycle can be predicted by analyzing the patterns of historical financial data.

[0046] For example, linear regression, sliding average method or exponential smoothing can be used to identify the long-term growth or decline trend of the historical financial identifier sequence; Fourier Transform or autocorrelation analysis can be used to identify whether the historical financial identifier sequence has a pattern (periodicity) that repeats at fixed time intervals; Seasonal Decomposition of Time Series (STL) can be used to analyze whether the historical financial identifier sequence is affected by seasonal factors, such as semester changes, fiscal year cycles, etc.; the relationship between different financial identifiers can be analyzed through the Pearson correlation coefficient and Granger causality test to determine whether there is a dependency relationship between certain expenditures or incomes.

[0047] You can choose a suitable forecasting model based on the trend, periodicity, seasonality and correlation of financial data. For example, if the data trend is stable, you can choose ARIMA or exponential smoothing; if the data has long-term dependence, you can choose LSTM neural network. After selecting a suitable forecasting model, you can use historical financial data to train the forecasting model, and use part of the historical data (such as the data of the most recent year) as a test set to evaluate the accuracy of the model and optimize the parameters of the model, such as adjusting the order of ARIMA or the number of layers of LSTM. After the model training is completed, input the current financial identification data, and the model outputs the forecast financial identification sequence for the next period.

[0048] The forecast results can be adjusted based on the experience of university financial managers. For example, if new policies are expected to be introduced in the next cycle, the budget ratio can be adjusted manually; if a certain expenditure is significantly higher than the historical trend, the forecast data can be re-evaluated.

[0049] This step can predict the financial situation of colleges and universities and provide a scientific basis for identifying abnormal financial data.

[0050] In one possible implementation, see Figure 2 S200: predicting each financial identifier of the next cycle of the current financial identifier sequence according to the current financial identifier sequence to obtain a predicted financial identifier sequence, including: S210, encoding the teaching cycle of each financial identifier in the current financial identifier sequence to obtain a semester phase feature vector and a teaching week feature vector of each financial identifier.

[0051] For example, One-Hot Encoding can be used to convert the semester stage to which each financial identifier belongs into a vector representation, such as the feature vector of the school preparation period is (1,0,0,0), the feature vector of the teaching operation period is (0,1,0,0), the feature vector of the exam week is (0,0,1,0), and the feature vector of the holiday is (0,0,0,1).

[0052] Since teaching week is a continuous variable, directly using integer representation may lead to poor understanding of the teaching week feature vector by the model, so sinusoidal encoding can be used here. Sinusoidal encoding can be used to retain periodic information and is particularly suitable for time series prediction tasks. It can map teaching weeks to high-dimensional vector space, making the distance between adjacent weeks more regular.

[0053] The sinusoidal position encoding is defined as , ,in, Indicates the number of teaching weeks (18 weeks), represents the encoding dimension (set to 4 or 8 to control the computational complexity), and The coding values ​​of the even and odd dimensions correspond to each other. 10000 is the scaling factor, which is used to make the values ​​of different weeks distributed in a more suitable range. is 5, the encoding dimension is 4, and the sinusoidal position encoding is calculated: , , , , the characteristic vector of teaching week is [0.4999, 0.8660, 0.0099, 0.9999].

[0054] This step can make full use of the teaching cycle information, capture the characteristics of the semester stage, and retain the time series characteristics of the teaching week, thereby improving the accuracy of financial data prediction.

[0055] S220, classify and encode the five-level classification of each financial identifier in the current financial identifier sequence to obtain a five-level classification feature vector of each financial identifier, wherein the five-level classification feature vector includes a major category feature vector, a medium category feature vector, a minor category feature vector, a special feature vector, and a sub-item feature vector.

[0056] Exemplarily, one-hot encoding can be used to encode major categories, medium categories, and minor categories to obtain major category feature vectors, medium category feature vectors, and minor category feature vectors; label encoding can be used to encode special items and sub-items to obtain special item feature vectors and sub-item feature vectors.

[0057] S230, converting the capital attribute in each financial identifier in the current financial identifier sequence into a capital attribute feature vector through a type mapping matrix.

[0058] Exemplarily, a number-source type table and a number-destination type table can be constructed, and a type mapping matrix can be constructed based on the number-source type table and the number-destination type table, as well as the probability of each source type flowing to each destination type. The source and destination of funds of each financial identifier are converted into a One-Hot vector, i.e., a source of funds vector and a destination of funds vector. According to the type mapping matrix, the source of funds vector and the destination of funds vector are mapped and converted to obtain a fund attribute feature vector.

[0059] Assume that the number-source type table is as follows: Table 1 The number-destination type table is as follows: Table 2 Here we can construct a 5×5 type mapping matrix, which represents the relationship weights of funds from source type (row index) to destination type (column index). for , each element Represents the source of funds To destination type The value range is 0~1 (1 means high correlation, 0 means no correlation). For example, It indicates that government funding is mainly used for teachers’ salaries, and the correlation is relatively high.

[0060] The source of funds for a certain financial identifier is tuition income, and the destination of funds is equipment purchase. They are converted into one-hot vectors through one-hot encoding, that is, the source of funds vector is S=[0,1,0,0,0], and the destination of funds vector is D=[0,0,1,0,0]. Calculate the product of the source of funds vector and the type mapping matrix, and the product of the transposed determinant of the destination of funds vector and the type mapping matrix, add the two products, and get the fund attribute feature vector, that is, , , the capital attribute feature vector is .

[0061] This step is conducive to enhancing the accuracy of subsequent fund flow modeling and can be effectively used in university financial analysis and forecasting.

[0062] S240, normalizing the amount in each financial identifier in the current financial identifier sequence to obtain an amount feature vector of each financial identifier.

[0063] For example, the Min-Max normalization method can be used to map the amount in each financial identifier in the current financial identifier sequence to 0, 1 or -1, 1, which helps to improve the stability of the amount prediction. That is, the difference between the amount of each financial identifier and the minimum amount in the current financial identifier sequence, and the difference between the maximum amount and the minimum amount in the current financial identifier sequence are calculated, and the ratio of the two (the difference between the amount of each financial identifier and the minimum amount in the current financial identifier sequence / the difference between the maximum amount and the minimum amount in the current financial identifier sequence) is the amount feature vector of each financial identifier.

[0064] S250, based on the semester stage feature vector and the five-class classification feature vector of each financial identifier, the classification model is used to predict the five-class classification of each financial identifier in the next cycle of the current financial identifier sequence to obtain a class prediction result.

[0065] Exemplarily, the five-level classification can be regarded as a hierarchical structure. Based on the Random Forest, each level category is predicted step by step. Five independent random forest classifiers can be constructed and trained to predict the major category (major category classification model), medium category (medium category classification model), minor category (minor category classification model), special category (special category classification model), and sub-item (sub-item classification model), respectively.

[0066] Training process: Collect the financial data of colleges and universities in the past 3-5 years, convert the financial data into financial identifiers, and construct a collection of financial identifier sequences of multiple periods. The collection of financial identifier sequences of multiple periods is divided into a training set (80%) and a validation set (20%). The input data in the training set and validation set include the semester stage feature vector and five-level classification of the financial identifier sequence of the previous period, and the output data includes the five-level classification of each financial identifier of the next period corresponding to the financial identifier sequence of the previous period.

[0067] You can set the number of decision trees (such as 100-500 trees), the maximum depth (such as 10-20), the minimum number of sample splits (such as 5-10), and the minimum number of sample leaves (such as 2-5). Use Bootstrap sampling training sets to generate multiple sub-datasets. Each decision tree uses a different sub-dataset for training. The best feature split point is selected by information gain or Gini coefficient. All decision trees vote to determine the final five-level classification result. Model optimization can use K-Fold cross-validation (K=5 or 10) to avoid overfitting, calculate the accuracy, F1-score, and recall rate of the model, use Grid Search or Bayesian optimization to adjust the number of trees to improve stability, and adjust the maximum depth (max_depth) to control model complexity and prevent overfitting.

[0068] After the model training is completed, the semester stage feature vector and five-class classification feature vector of each financial identifier are input into the model, and the model outputs the five-class classification prediction results.

[0069] Optionally, see Figure 2 , S250, based on the semester stage feature vector and the five-class classification feature vector of each financial identifier, the classification model is used to predict the five-class classification of each financial identifier in the next cycle of the current financial identifier sequence, and the category prediction results are obtained, including: S251, for each financial identifier, the following operations are performed: based on the hierarchical attention mechanism, the weight of each feature vector in the five-level classification feature vector is calculated, and the weight of each feature vector and each feature vector are weighted summed to obtain a classification comprehensive feature vector; the classification weight corresponding to the semester stage feature vector is selected from the classification weight matrix. The classification weight matrix is ​​pre-set, and the classification weight matrix includes classification weights corresponding to feature vectors of different semester stages.

[0070] For example, the feature vector of the major category can be set as , the feature vector of the middle class is set to , the small class feature vector is set to , the special feature vector is set to , the sub-item eigenvector is set to , we can use splicing, weighted summation, dimensionality reduction projection and other methods to , , , , Combine to form the total feature vector ,like , the contribution (weight) of each level to the final classification is calculated through the hierarchical attention mechanism. The calculation formula is: ,in, is a trainable hierarchical attention parameter. Based on the calculated hierarchical weights, each feature vector in the five-level classification feature vector is weighted and summed to obtain the classification comprehensive feature vector, that is, ,in, Represents the classification comprehensive feature vector. The hierarchical attention mechanism of five-level classification can solve the problem that traditional single-layer classification cannot handle the complex system of universities.

[0071] The classification weight matrix can be set as - Preparation period for the start of school, - Teaching operation period, -Exam week, -Holiday. According to the semester phase feature vector of the financial identifier, select the corresponding classification weight The setting of the classification weight matrix can overcome the prediction bias of the general model at different stages of the semester.

[0072] The product of the corresponding classification weight and the classification comprehensive feature vector can be used as the input feature vector of the classification model, that is, .

[0073] S252, based on the classification weight and classification comprehensive feature vector of each financial identifier, a classification model is used to predict the five-level classification of each financial identifier in the next cycle of the current financial identifier sequence to obtain a category prediction result. The classification model is a machine learning model.

[0074] Exemplarily, the training set and the validation set in step S250 may be used to convert the five-class classification of each financial identifier in the training set into an input feature vector through the method of step S251.

[0075] The classification model can be selected from Random Forest, XGBoost or Neural Network (MLP / Transformer). Neural Network is used here. Construct the neural network structure (input layer, hidden layer, output layer): Construct the input layer of the neural network by the dimension of the input feature vector. Construct the hidden layer through multi-layer fully connected network, normalization layer, and Dropout. The ReLU activation function can be used to construct a multi-layer fully connected network to enhance the nonlinear learning ability of the model. The normalization layer prevents the gradient from disappearing or exploding, and Dropout prevents overfitting. The output layer can use Softmax activation to output the probability distribution of five-level classification.

[0076] Training process: Use Xavier to initialize weights, set bias to zero, calculate the output of the input feature vector after passing through the hidden layer, obtain classification probability through the Softmax layer, calculate gradient update weights, use Adam optimizer for gradient update, use Mini-Batch SGD to improve training efficiency, Batch Size can be set to 32~256, adjust the number of hidden layers and neurons, add Dropout to prevent overfitting, use K-Fold cross validation (K=5 or 10) to facilitate the generalization ability of the model on different data sets, calculate accuracy, F1, recall rate, confusion matrix, and verify the output results of the model.

[0077] After the model training is completed, the input feature vector corresponding to each financial identifier in the current financial identifier sequence is input into the model, and the model outputs the probability distribution of the five-level classification of each financial identifier in the next period.

[0078] The above steps are combined with the hierarchical attention mechanism to improve the accuracy of classification prediction and consider the semester stage information to make the prediction more reasonable. The neural network model can accurately predict the five-level classification of financial identification for the next period and provide scientific data support for the financial management of universities.

[0079] S260, based on the teaching week feature vector, fund attribute feature vector and amount feature vector of each financial identifier, the amount corresponding to each five-level classification in the category prediction result is predicted using a regression model to obtain an amount prediction result.

[0080] Exemplarily, random forests can also be used to predict the amount, with the fund attribute feature vector, teaching week feature vector and amount feature vector of each financial identifier in the previous period in the training set and validation set in step S250 and the corresponding five-level classification of each financial identifier in the next period annotated as input data, and the amount of each financial identifier in the next period annotated as output data.

[0081] You can randomly select multiple data subsets from the training set, train multiple decision trees, and find the optimal feature split point (such as five-level classification vs. teaching week) on each tree. Select the best split feature through information gain or minimum variance to build a regression tree. Adjust the number of decision trees, control the maximum depth of the tree, prevent overfitting, set the minimum number of sample splits, and adjust the minimum number of leaf samples to reduce model complexity. Use Bootstrap sampling to train multiple sub-models, calculate the predicted amount of each decision tree, and take the weighted average of all trees as the final predicted amount.

[0082] After the training is completed, the teaching week feature vector, fund attribute feature vector and amount feature vector of each financial identifier in the current financial identifier sequence and each five-level classification in the category prediction result are input, and the model outputs the amount corresponding to each five-level classification in the category prediction result.

[0083] Optionally, see Figure 2 , S260, based on the teaching week feature vector, fund attribute feature vector and amount feature vector of each financial identifier, the amount corresponding to each five-level classification in the category prediction result is predicted using the regression model to obtain the amount prediction result, including: S261, based on the fund attribute and fund attribute feature vector of each financial identifier, construct a current fund flow graph, and generate fund flow features based on the current fund flow graph using a graph convolutional network. The nodes of the current fund flow graph are each financial identifier, and the edges of the current fund flow graph represent the flow direction of funds.

[0084] Exemplarily, each financial identifier is used as a node of the current capital flow graph, and the node feature can be a capital attribute feature vector. The directed edges between nodes are determined according to the source and destination of funds of each financial identifier (such as funds flow from A to B, A->B). The weight of the directed edge can be calculated according to the amount of capital flow, that is, the ratio of the outflow amount of each edge to the total outflow amount.

[0085] According to the weights of directed edges, a capital flow adjacency matrix is ​​constructed. Based on the current capital flow graph and the capital flow adjacency matrix, the graph convolutional network can be used to calculate the capital flow characteristics of each layer, perform inter-layer information propagation, and update the weight matrix by minimizing the loss function, and finally output the capital flow characteristics. The current capital flow graph and the graph convolutional network can capture the implicit association of capital flow.

[0086] S262, based on a preset time window, extract teaching week scale features, semester scale features and school year scale features from historical financial data, and based on the teaching week feature vector of each financial identifier, fuse the teaching week scale features, semester scale features and school year scale features through a temporal attention mechanism to obtain multi-scale features corresponding to each financial identifier.

[0087] Exemplarily, the preset time window of the teaching week scale can be 20 weeks. The financial data of the first 20 weeks of the current cycle are subjected to sliding window statistics to extract statistical characteristics of capital fluctuations (teaching week scale characteristics), such as average capital flow, capital flow change rate, and capital peak within the week. The teaching week scale characteristics can reflect short-term capital flow trends.

[0088] The preset time window of the semester scale feature can be 2 semesters. The fund usage of the past 2 semesters is extracted, and the total fund expenditure of the semester, the fund category distribution trend and the peak fund expenditure within the semester are calculated as the semester scale feature. The semester scale feature can reflect the fund usage pattern at the semester level.

[0089] The preset time window of the academic year scale feature can be three academic years. The financial data of colleges and universities in the past three years are extracted, and the annual funding growth rate, annual budget execution and funding utilization stability (variance) are calculated as the academic year scale feature. The academic year scale feature can identify long-term funding trends.

[0090] The teaching week feature vectors of different financial identifiers may be at different time points, so their attention weights on the historical time scale features can be calculated separately, and their respective fusion features can be generated separately. The role of the time attention mechanism is to make the teaching week feature vector of each financial identifier match the information of different time scales.

[0091] For each financial identifier: In order to ensure that different time scale features can be effectively combined, the temporal attention mechanism can be used to adaptively adjust the contribution (weight) of each time scale feature. The formula for calculating the weights corresponding to different time scale features through the temporal attention mechanism is: ,in, Indicates The teaching week feature vector of financial identifiers, Represents different time scale characteristics, express The characteristic dimension of Represents the weights corresponding to different time scale features. The weights corresponding to different time scale features and the weighted sum of different time scale features are obtained. Multi-scale features corresponding to each financial identifier.

[0092] This step can simultaneously consider the short-term, medium-term and long-term trends of capital changes, and adaptively adjust the influence of different time scales through the temporal attention mechanism to accurately extract the multi-scale features corresponding to each financial identifier.

[0093] S263, based on the fund flow characteristics, the multi-scale characteristics corresponding to each financial identifier and the amount feature vector of each financial identifier, the amount corresponding to each five-level classification in the category prediction result is predicted using a regression model to obtain an amount prediction result. The regression model is a machine learning model.

[0094] Exemplarily, the training set and validation set in step S250 are divided into multiple previous cycles and corresponding next cycles, and all financial data of the previous cycle are converted into fund flow features, multi-scale features corresponding to each financial identifier, and amount feature vectors of each financial identifier, and the corresponding five-level classification annotations of each financial identifier in the next cycle as input data, and the amount annotations of each financial identifier in the next cycle as output data through steps S261 and S262. A suitable regression model can be selected, such as random forest regression, XGBoost regression, and LSTM time series regression.

[0095] Training process: You can set the initial parameters of random forest / XGBoost / LSTM, such as tree depth, learning rate, batch size, etc. The capital flow features, multi-scale features, and amount feature vectors are merged and input into the regression model. The five-class classification prediction results are converted to One-Hot encoding so that the model can learn the relationship between the five-class classification and the amount, and calculate the output of the regression model, that is, the predicted amount. The error between the predicted value and the actual amount can be calculated as a loss function, such as mean square error (MSE) or root mean square error (RMSE). For XGBoost and LSTM, you can use gradient descent to optimize the weights and gradually reduce the prediction error; for random forest regression, increase or decrease the number of decision trees and optimize the maximum depth of the tree to improve model stability. You can train multiple epochs (such as 100 rounds) or the tree growth process until the loss function converges.

[0096] After the model training is completed, the capital flow characteristics, the multi-scale features corresponding to each financial identifier, the amount feature vector of each financial identifier, and each five-level classification in the category prediction results are input into the regression model, and the model outputs the predicted amount corresponding to each five-level classification.

[0097] This step combines the characteristics of capital flow to improve prediction accuracy. Multi-scale characteristics can enhance time dependence so that the regression model can accurately predict the financial amount of the next cycle and provide scientific decision-making support for university financial management.

[0098] S270, arranging the category prediction results and the amount prediction results in the time sequence of the next period of the current financial identification sequence to obtain a predicted financial identification sequence.

[0099] Exemplarily, the predicted five-level classifications and corresponding amounts may be arranged in the time sequence of the next period of the current financial identification sequence to form a complete predicted financial identification sequence.

[0100] In a possible implementation, the university financial data management method further includes: It should be noted here that the current financial identification sequence may not contain all the five-level classifications predicted for the next cycle, which will cause some of the predicted five-level classifications not to appear in the current cycle, resulting in the inability to directly calculate the budget execution rate and determine the current cumulative expenditure, thereby affecting the calculation of the remaining budget amount. There are two solutions: If a predicted five-level classification does not exist in the current cycle, you can find historical data or similar classification data in the past N cycles to fill in the budget execution rate and cumulative expenditure; if a predicted five-level classification does not exist in the current cycle and there is no historical data at all, the full-year budget allocation rule is used, that is, the full-year budget is used as the remaining budget amount, and the budget execution rate is set to the initial value (such as 0%).

[0101] S201, calculating the budget execution rate and remaining budget amount corresponding to each five-level classification in the category prediction result.

[0102] Exemplarily, find out from the current financial identification sequence which five-level classifications are the same as the five-level classifications in the category prediction results, and directly use the total budget amount of the five-level classification to subtract the cumulative expenditure amount of the same five-level classification in the current financial identification sequence to get the remaining budget amount, and the ratio of the cumulative expenditure amount of the same five-level classification in the current financial identification sequence to the total budget amount is the budget execution rate.

[0103] For five-level classifications that do not exist in the current financial identification sequence, if historical data is available, the total budget amount corresponding to the five-level classification in the past N periods and the expenditure amount of the historical periods can be used to calculate the historical average budget execution rate. The remaining budget amount can be calculated based on the total budget amount and the historical average budget execution rate.

[0104] For the five-level classification that does not exist in the current financial identification sequence, if there is no historical data at all, the remaining budget amount of the five-level classification is the annual budget, and the budget execution rate is 0%.

[0105] This step solves the problem that the current financial identification sequence lacks some five-level classifications in the forecast results and cannot calculate the corresponding budget execution rate and remaining budget amount, making the budget adjustment more scientific and reasonable.

[0106] S202, if the budget execution rate exceeds the budget threshold, the predicted amount of the five-level classification exceeding the budget threshold is attenuated according to the excess ratio of the budget execution rate to obtain the attenuated amount of the five-level classification exceeding the budget threshold.

[0107] For example, the over-limit ratio of the budget execution rate is the difference between the budget execution rate and the budget threshold. If the over-limit ratio is large, the forecast amount can be reduced more significantly; if the over-limit ratio is small, the forecast amount is only slightly adjusted. The attenuation formula of the forecast amount is: ,in, Indicates the attenuation amount, represents the initial forecast amount, Indicates the adjustment coefficient, which determines the attenuation strength (such as 0.5). represents the budget execution rate, Indicates the budget threshold (such as 80%). Exceed , the forecast amount is reduced proportionally.

[0108] S203: Determine the budget upper limit of the five-level classification that exceeds the budget threshold based on the remaining budget amount corresponding to the five-level classification that exceeds the budget threshold.

[0109] For example, to prevent the forecast amount from still being overspent, even after attenuation, the value may still be large, so an upper limit can be set for the five-level classification that exceeds the budget threshold, that is, , Indicates the budget ceiling, 1.2 is the adjustable coefficient (which can be changed according to actual conditions), indicating that the maximum amount that can exceed the remaining budget is 20%. Indicates the remaining budget. If Too small, will also become smaller to prevent over-prediction.

[0110] S204, based on the budget upper limit of the five-level classification that exceeds the budget threshold, the attenuation amount of the five-level classification that exceeds the budget threshold is corrected to obtain the corrected amount of the five-level classification that exceeds the budget threshold.

[0111] For example, the calculated decay amount may still be greater than the budget cap, in which case the decay amount can be revised, i.e., the budget cap is determined as the revised amount; even if the budget execution rate of a five-level classification does not exceed the budget threshold and the amount does not need to be decayed, there may be a situation where the initial forecast amount exceeds the budget cap, in which case the budget cap is also determined as the revised amount of the five-level classification. ,in, Indicates the correction amount.

[0112] Assume that the current five-level classification is as follows: Table 3 The budget execution rate of Category A is 85 / 100=85%, and the remaining budget amount is 100-85=150,000 yuan; the budget execution rate of Category B is 90 / 150=60%, and the remaining budget amount is 150-90=600,000 yuan; assuming that the average budget execution rate of Category C in the past three cycles is 80%, the remaining budget amount is 200-200×80%=400,000 yuan, and the budget execution rate of Category D is 0%, and the remaining budget amount is 2.5 million yuan. Assuming the budget threshold is 80%, then only Class A exceeds it, and the forecast amount of Class A is attenuated, that is, y1=20×(1-0.5×(85%-80%))=19 (million yuan), and the budget upper limit of Class A is y2=1.2×15=18 (million yuan). Since y1>y2, the revised amount of Class A is 180,000 yuan; the budget upper limit of Class B is y2=1.2×60=72 (million yuan), and the forecast amount of Class B does not exceed the budget upper limit, so the revised amount of Class B is still the forecast amount of 300,000 yuan; the budget upper limit of Class C is y2=1.2×40=48 (million yuan), and the forecast amount of 500,000 yuan is greater than the budget upper limit of 480,000 yuan, so the revised amount of Class C is 480,000 yuan; and Class D does not need to be adjusted, and the budget amount is the final amount corresponding to Class D.

[0113] Through these steps, a process of dynamic constraints on the forecast amount is established, which is conducive to adjusting the forecast amount when the budget execution rate or forecast amount exceeds the limit, so as to avoid overvaluation or unreasonable forecasts.

[0114] S300, obtaining an actual financial data sequence, and determining an actual financial identification sequence based on the actual financial data sequence, wherein the actual financial data sequence is the financial data actually collected in the next period of the current financial identification sequence.

[0115] Exemplarily, after the actual financial data of the next period is collected, an actual financial data sequence is constructed by a method consistent with step S100, and an actual financial identification sequence is obtained based on the actual financial data sequence.

[0116] S400, comparing the actual financial identification sequence with the predicted financial identification sequence, and constructing an actual capital flow diagram based on the actual financial identification sequence, determining whether there is abnormal financial data in the actual financial data sequence, and obtaining a determination result.

[0117] It can be understood that the fund flow diagram is used to visualize the flow of funds between different financial identifiers in order to detect abnormal fund flows.

[0118] For example, the error rate between the actual value and the predicted value can be calculated for each financial identifier. If the error rate is small (such as within ±5%), it means that the prediction is relatively accurate; if the error rate is too large (such as more than ±20%), the actual financial identifier sequence may be abnormal, and the cause of the abnormality can be further analyzed. Or for all financial identifiers, the mean square error (MSE) between all actual values ​​and predicted values ​​is calculated, and the root mean square error (RMSE) is calculated from the mean square error. If the root mean square error is too large, it means that the overall prediction error is high and there may be abnormalities.

[0119] When it is determined that there is an anomaly in the actual financial identification sequence, an actual funds flow graph is constructed: each financial identification in the actual financial identification sequence can be determined as a node of the graph, the edge of the graph can represent the direction of fund flow, and the weight of the edge can represent the amount of fund flow.

[0120] The actual fund flow chart can be used to identify abnormal flow paths, such as when a certain amount of funds does not flow to the node as required according to the established process; the actual fund flow chart can be used to identify abnormal transaction amounts, such as when the amount of a certain fund flow is far higher or far lower than the historical average; the actual fund flow chart can be used to identify sudden changes, such as the sudden appearance of a fund flow path that has never existed in the past. If at least one of the above abnormal situations exists in the actual fund flow chart, it is determined that abnormal financial data exists in the actual financial data sequence.

[0121] The predicted financial identification sequence is used as a baseline to help financial personnel determine whether the actual financial identification sequence has any anomalies. The prediction does not represent the final true financial situation, but provides an expected value for comparison and anomaly detection. The predicted financial identification sequence is only used to discover possible abnormal trends in financial data in advance. The actual fund flow diagram constructed in combination with the actual financial identification sequence can ultimately determine whether the actual financial data sequence is really abnormal and take corresponding management measures.

[0122] This step can timely discover and handle abnormal situations, improving the transparency of financial management and risk prevention and control capabilities of colleges and universities.

[0123] In a possible implementation, S400 compares the actual financial identification sequence with the predicted financial identification sequence, and constructs an actual capital flow diagram based on the actual financial identification sequence to determine whether there is abnormal financial data in the actual financial data sequence, and obtains a determination result, including: S410, comparing each financial identifier in the actual financial identifier sequence with each financial identifier in the predicted financial identifier sequence one by one, calculating the difference between each financial identifier in the actual financial identifier sequence and each financial identifier in the predicted financial identifier sequence, and obtaining a difference collection.

[0124] For example, it should be noted that in the process of comparing the actual financial identification and the predicted financial identification, two situations may occur: one is that the predicted five-level classification does not exist in reality, indicating that the five-level classification did not occur during the actual execution, which may be due to budget adjustment, project cancellation or non-disbursement of funds. It is impossible to directly calculate the amount difference because the actual amount does not exist; the other is that there is a five-level classification that does not appear in the prediction, indicating that the five-level classification was not predicted, but the actual income or expenditure occurred, which may be due to sudden expenditure, unplanned capital flow, or the prediction model failed to accurately capture the classification. Since these situations cannot be judged by the amount difference, a new method is needed to judge abnormal data. For the five-level classification for which the amount difference cannot be calculated, historical data pattern matching (checking whether the classification has ever appeared) can be used to determine whether the financial data corresponding to the five-level classification is abnormal financial data.

[0125] Historical data pattern matching: Calculate the average frequency of occurrence of the five-level classifications in the past N cycles that have at least one of the above situations. If the classification appears frequently in historical data but does not appear in this cycle, it may be an anomaly; if the classification has never appeared in historical data but suddenly appears in this cycle, it may be an anomaly. For example, if Class A appears in the past three cycles, appears in the predicted financial identification sequence but does not exist in the actual financial identification sequence, then the financial data corresponding to Class A may be anomaly; if Class B does not appear in the past three cycles, does not appear in the predicted financial identification sequence but exists in the actual financial identification sequence, then the financial data corresponding to Class B may be anomaly.

[0126] For actual financial indicators and forecasted financial indicators that do not have the above situation, the difference between the amount of the actual financial indicator and the amount of the forecasted financial indicator corresponding to the actual financial indicator can be directly calculated.

[0127] This step takes into account the possible errors between the prediction and the actual situation, and solves the problem of being unable to calculate the difference in amount due to the error, which is beneficial to the integrity of anomaly detection.

[0128] S420, comparing each difference in the difference set with a difference threshold, and if each difference in the difference set is within the difference threshold, determining that there is no abnormal financial data in the actual financial data sequence. The difference threshold changes dynamically according to the teaching calendar of the university.

[0129] It is understandable that the difference threshold can change dynamically according to the academic calendar of the university. For example, at the beginning of the semester (first 2 weeks), the budget execution fluctuates greatly and a higher error is allowed; in the middle of the semester (3-12 weeks), the expenditure is stable and the threshold is smaller; at the end of the semester (13-18 weeks), high expenditures may increase (such as equipment purchases).

[0130] For example, each difference in the difference set calculated in step S410 is compared with the corresponding difference threshold range. If all the differences are within the difference threshold range, it can be determined that there is no abnormal financial data in the actual financial data sequence. If at least one difference exceeds the difference threshold range, the next step is to analyze the capital flow pattern.

[0131] It should be noted that if the situation in step S410 exists and it is determined to be abnormal data through historical data pattern matching, the next step of analyzing the capital flow pattern will also be entered.

[0132] S430, if at least one difference in the difference set is not within the difference threshold, construct an actual fund flow graph based on the actual financial data sequence, analyze the fund flow pattern of the actual fund flow graph, and if there is any abnormal feature in the actual fund flow graph, determine that there is abnormal financial data in the actual financial data sequence. The actual fund flow graph is a three-layer fund flow graph, the nodes of the actual fund flow graph are the accounts corresponding to each financial identifier in the actual financial identifier sequence, the edges of the actual fund flow graph represent the flow direction of funds, and the abnormal features include closed-loop fund chains, a single node fund outflow ratio greater than 40%, and direct transactions with high-risk list accounts.

[0133] It can be understood that the first layer (fund source layer) of the three-layer fund flow diagram is the fund source account (such as fiscal appropriation account, tuition income account, scientific research fund account); the second layer (fund allocation layer) is the fund use account (such as various colleges, research centers, and administrative department accounts); the third layer (final use layer) is the final flow of funds (such as faculty salary payment, equipment procurement, and payment to external cooperative institutions).

[0134] Exemplarily, the account corresponding to each financial data is taken as a node, and then the directed edges between nodes are connected according to the fund attributes of each financial data, and the amount flowing between nodes is used as the weight of the edge to construct the actual fund flow graph. In the actual fund flow graph, multiple financial identifiers may point to the same source account (such as tuition income account), multiple financial identifiers may share the same destination account (such as teacher salary account), and some financial identifiers may involve multiple fund flows, resulting in account duplication. If these cases are not processed, node duplication may occur, resulting in unclear fund flow graph structure; fund flow information is dispersed, affecting the accuracy of fund anomaly detection. Therefore, when multiple financial identifiers point to the same account, only one node is retained in the graph, and the fund inflow and outflow information of the account are merged according to the total fund amount.

[0135] It can be understood that closed-loop funds are funds that flow repeatedly between multiple accounts, forming a closed-loop transaction (such as A→B→C→A). The funds are not actually used but transferred back and forth between multiple accounts, which may involve fund abuse or money laundering.

[0136] For example, depth-first search (DFS) or breadth-first search (BFS) can be used to identify closed-loop paths in the actual capital flow graph and calculate the closed-loop amount. If the closed-loop amount exceeds a certain proportion (such as 20%), it is considered abnormal.

[0137] It can be understood that the proportion of capital outflow from a single node exceeding 40% means that if the proportion of capital outflow from a single direction of an account exceeds 40%, there may be abnormal concentrated outflow of funds, which may involve risky payment or financial fraud.

[0138] For example, the total amount of funds outflow from each node can be calculated, and the proportion of funds outflow from the node to a single account can be calculated. If the proportion is greater than 40%, the transaction may be risky. For example, the funds from account A to account X are 800,000 yuan, the funds from account A to account Y are 400,000 yuan, and the funds from account A to account Z are 400,000 yuan. The fund outflow from account A to account X accounts for 50%, which exceeds the 40% threshold and is judged to be abnormal.

[0139] It is understandable that if there is a direct transaction with an account on the high-risk list, or if a certain fund flow involves a known high-risk account (such as a non-compliant company or a regulated account), there may be abnormal transactions.

[0140] For example, a list of high-risk accounts is established (such as from financial regulatory authorities or internal audit). If an account directly trades with an account on the list of high-risk accounts, it is marked as a high-risk transaction.

[0141] If the actual funds flow chart does not contain the above-mentioned abnormal features, it is determined that the financial data is normal; if the funds flow chart contains any of the above-mentioned abnormal features, it is determined that the financial data is abnormal.

[0142] This step is conducive to the rational flow of funds, preventing abnormal fund transactions, and improving financial transparency. When multiple financial identifiers correspond to the same account, they are merged into one node, which makes the actual fund flow diagram clearer, reduces redundant data, and improves the accuracy of anomaly detection.

[0143] S500: If the judgment result indicates that abnormal financial data exists in the actual financial data sequence, abnormal management is performed on the abnormal financial data.

[0144] For example, before performing exception management, it is possible to confirm whether the abnormal data actually exists, rather than being misjudged due to factors such as data entry errors and forecasting model errors. Financial personnel can check the vouchers, accounts, and transaction records of abnormal data to confirm the authenticity of the data, and can identify whether there are emergencies (such as epidemics, changes in fiscal budgets) that affect financial data; they can check whether there are errors in data entry (such as over-entry / under-entry of amounts, date errors), and check whether there are technical problems in the financial system (such as data import errors, calculation errors). If it is confirmed that it is a system or entry error, the data will be corrected directly without entering the exception management process.

[0145] If abnormal data does exist, the abnormal data can be classified, and the abnormal type (income type or expenditure type) of the abnormal data can be determined based on the abnormal data, and the abnormal situation in the fund flow diagram corresponding to the abnormal data can be determined. The degree of abnormality (minor abnormality, moderate abnormality or severe abnormality) can be determined based on the abnormal type and abnormal situation, and appropriate handling methods can be taken according to the degree of abnormality.

[0146] If it is a minor anomaly, it can be recorded in the financial report and subsequent data can be closely monitored to prevent the anomaly from continuing to expand; if it is a moderate anomaly, the source of the abnormal data can be traced (such as checking relevant invoices, contracts, and bank statements), and the relevant financial management personnel and project leaders can be contacted to confirm the cause of the anomaly. The amount of the abnormal data can be monitored. If the abnormal amount continues to rise, it will be upgraded to a serious anomaly. If it is a serious anomaly, the financial audit department can be notified to allow the financial audit department to check the approval process and capital flow of the financial data, and investigate whether it involves any illegal operations (such as budget overspending, misappropriation of funds, false reimbursement, etc.).

[0147] This step ensures the identification, analysis, and processing of abnormal financial data, making university financial management more transparent and efficient and reducing financial risks.

[0148] In a possible implementation, at S500, if the judgment result indicates that abnormal financial data exists in the actual financial data sequence, performing abnormal management on the abnormal financial data includes: S510: If the judgment result indicates that there is abnormal financial data in the actual financial data sequence, an abnormal capital flow diagram is constructed with the abnormal financial data as the center, wherein the abnormal capital flow diagram is a 5-layer capital flow diagram.

[0149] Exemplarily, the structure of the abnormal funds flow diagram is as follows: the first layer (fund source layer) is the initial inflow point of funds, such as government grant accounts, tuition accounts, and scientific research funding accounts; the second layer (intermediate account layer) is the allocation of funds to school-level management accounts or department accounts (such as financial centers, college and department fund accounts); the third layer (business flow layer) is the allocation of funds to specific purpose accounts (such as laboratory equipment procurement, teacher salaries, administrative expenses); the fourth layer (external transaction layer) is the flow of funds from the school to external partners, suppliers or personal accounts; the fifth layer (final funds flow layer) is the account where the funds finally land (such as personal salary accounts, corporate bank accounts, and cooperative institutions).

[0150] With abnormal financial data as the center, we can trace back the source of funds, track the destination of funds, establish the flow path of funds, and confirm that all accounts involved in the transaction are tracked. For example, the first layer: financial appropriation account → the second layer: school-level scientific research fund account → the third layer: research institute procurement account → the fourth layer: backup supplier account → the fifth layer: personal account.

[0151] The hierarchical structure of the abnormal funds flow diagram helps to track the source, flow and scope of influence of funds.

[0152] S520, identifying abnormal fund aggregation nodes and key propagation paths in the abnormal fund flow graph, and obtaining graph analysis results.

[0153] It can be understood that an abnormal fund convergence node refers to an account where a large amount of funds flow into the abnormal fund flow diagram, which may involve abnormal convergence of large amounts of funds in a single account (such as an external company account suddenly receiving a large amount of funds, which is inconsistent with the historical fund flow pattern), confluence of multiple accounts (such as funds from different departments flowing to the same external supplier, which may pose a risk of concentrated fund transfer), and long-term fund stagnation (that is, funds enter an account and do not move for a long time, which may involve abnormal accumulation or potential fund retention behavior).

[0154] For example, the proportion of capital inflow can be calculated. If the proportion of total capital inflow of a certain account in the capital flow diagram is greater than 50%, it will be marked as an abnormal convergence node. The abnormal capital residence time can be calculated. If the capital inflow is not spent for a long time and exceeds the historical average residence time by more than 2 times, it will be marked as suspicious.

[0155] It can be understood that the key transmission path refers to how abnormal funds flow between different accounts, involving the transfer chain of multiple accounts. Abnormal transmission modes may include: chain transfer, where funds flow continuously between multiple accounts (A→B→C→D), and eventually fall into personal accounts or high-risk accounts; fund reflux, where funds are transferred from A to B and then back to A, forming a fund reflux path; fund splitting, where large funds are split into multiple small transactions and flow to different accounts to evade supervision.

[0156] For example, the number of layers of fund transfer can be tracked. If the funds are transferred continuously in more than 3 layers, they are marked as suspicious. The proportion of single transaction amount can be calculated. If the single transaction amount accounts for more than 40% of the total funds in a certain account after the funds are transferred out, it may be an abnormal path.

[0157] This step can identify high-risk accounts where funds are concentrated, discover potential fund abuse, money laundering or misappropriation, and detect abnormal fund flows across multiple levels, prevent illegal fund operations, and reduce financial risks. Through graph analysis, abnormal fund flows can be managed and audited more intuitively, efficiently, and systematically, which is conducive to financial security and compliance.

[0158] S530, performing abnormal management on abnormal financial data according to the graph analysis result.

[0159] For example, the risk level in the graph analysis results can be identified and corresponding measures can be implemented according to the risk level. The abnormal characteristics corresponding to the high risk level are large-scale abnormal transactions at the capital aggregation node, such as a single account absorbing more than 50% of the funds, the account can be frozen immediately and a compliance investigation can be initiated; the abnormal characteristics corresponding to the medium risk level are key transmission paths involving multi-layer transfers, such as funds transferred across more than 4 layers of accounts, and internal audits can be conducted to track transaction vouchers; the abnormal characteristics corresponding to the low risk level are abnormal fluctuations in the use of funds, such as a transaction exceeding the budget by 50%, and the account can be marked with a warning and subsequently monitored.

[0160] In the case where funds in a key transmission path eventually flow into a high-risk account, the account will be frozen immediately, a report will be submitted to the financial audit department, and the capital chain will be traced and transaction vouchers will be checked.

[0161] The risk grading process in this step can improve management efficiency, freeze high-risk accounts, and prevent capital losses.

[0162] Optionally, S530, performing abnormal management on abnormal financial data according to the graph analysis result, including: S531: If the concentration of abnormal fund aggregation nodes exceeds 50% or there are multiple node-to-node loops in the key transmission path, high-risk management is performed on the source account of abnormal financial data. Among them, abnormal management includes high-risk management, medium-risk management and low-risk management, and high-risk management includes freezing the source account of abnormal financial data.

[0163] For example, the concentration of abnormal fund aggregation nodes is greater than 50%, that is, a large amount of funds are concentrated in a single account, forming a high-risk fund accumulation; there are multiple node cycles in the key transmission path, that is, funds are transferred back and forth between multiple accounts, which may involve money laundering or illegal fund transfer. If any of the above conditions are met, it is judged as high risk. Execute high-risk management: immediately freeze the source account of the abnormal fund aggregation node in the fund flow diagram to prevent further transfer; during the period when the account is frozen, suspend the fund operation of the account and notify the relevant financial management department; submit the frozen account to the internal audit department or judicial regulatory agency for review.

[0164] High risk management can prevent further outflow of funds.

[0165] S532: If the key transmission path involves multiple nodes or the capital outflow of a single node accounts for more than 40%, the key transmission path shall be subject to medium risk management. Among them, medium risk management includes real-time monitoring of capital flows on the key transmission path.

[0166] For example, a key transmission path involves multiple nodes, that is, funds flow from one source account to multiple accounts, which may involve the risk of fund splitting to evade supervision; a single node fund outflow accounts for more than 40%, that is, funds mainly flow to a certain account, which may involve abnormal fund allocation or benefit transfer. If any of the above conditions are met, it is judged as medium risk. Execute medium-risk management: In the financial management system, set up transaction monitoring for key transmission paths to capture abnormal fund flows; if the fund flow exceeds the set threshold (such as a single transaction amount exceeding 1 million yuan or multiple transfers from the same source of funds within 48 hours), trigger an alarm and record transaction details; for key transmission paths, regularly review fund flows to ensure compliance with fund use regulations.

[0167] Medium-risk management can help track the dynamics of funds.

[0168] S533: If the abnormal fund flow chart involves an account on the high-risk list, low-risk management is implemented, including sending early warning information to the regulatory authorities.

[0169] For example, if the transaction account involved in the capital flow is on the list of high-risk accounts listed by the regulator, but no abnormal capital aggregation or key transmission path is formed, it is judged as low risk. Execute low-risk management: mark transactions involving high-risk accounts in the financial system for subsequent analysis; automatically generate transaction reports and submit relevant data to the financial regulatory department, such as transaction time, amount, source and destination of funds, account information (such as account opening institution, bank information); if high-risk accounts continue to have transactions, they can be upgraded to medium-risk or high-risk management. Low-risk management can improve risk prevention capabilities.

[0170] The above steps are conducive to transparent capital flow, secure transactions, and efficient financial management, providing strong support for the financial management of institutions such as universities, enterprises, and governments.

[0171] In a possible implementation, exception management further includes: S501, determine the source department corresponding to the abnormal financial data based on the abnormal funds flow diagram, generate an audit list of the departments associated with the abnormal financial data, and implement transaction limit control measures on the accounts in the audit list.

[0172] For example, in the abnormal fund flow chart, the account with the most fund inflow can be found and its source of funds can be traced. If the fund inflow of the account accounts for more than 50%, the department to which it belongs may be the source department of abnormal financial data. According to the hierarchical structure of the fund flow chart, the source department of the funds of the account is determined. If the account receives funds from multiple departments, all related departments are marked as potential source departments. All direct transaction objects of the source department are included in the audit list. If a department has abnormal fund flow for three consecutive periods, it will be audited more strictly. The content of the audit list may include the name of the department, the abnormal accounts involved, the main fund inflow / outflow accounts, the abnormal transaction amount, whether it involves circular transactions, and whether it is related to the high-risk list. For high-risk accounts in the audit list (abnormal fund aggregation, circular transactions), the daily transaction limit is reduced to 20%, and the single transaction amount shall not exceed 500,000 yuan; for medium-risk accounts in the audit list (single fund outflow is greater than 40%), the daily transaction limit is reduced to 50%, and the number of transactions per week shall not exceed 10; for low-risk accounts in the audit list (accounts involved in the high-risk list), only monitoring is required, and no limit adjustment is required.

[0173] S502, determine whether there are three or more levels of circular transactions in the abnormal capital flow diagram. If there are three or more levels of circular transactions in the abnormal capital flow diagram, start blockchain evidence storage and transmit it to the regulatory department.

[0174] For example, the capital path in the abnormal capital flow diagram can be traced to check whether the transaction link is closed. If the funds circulate between more than three accounts and the capital inflow ratio exceeds 50%, it is determined to be a circular transaction. The abnormal capital flow path, transaction amount, and transaction account can be recorded to generate a blockchain hash value to facilitate data integrity; an asymmetric encryption algorithm can be used to protect the security of transaction information, and only the regulatory authorities are authorized to access the evidence data; the evidence data is uploaded to the supervision chain in real time and synchronized to the financial regulatory agency.

[0175] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0176] Corresponding to the university financial data management method described in the above embodiment, the embodiment of the present application also provides a university financial data management system, and each unit of the system can implement each step of the university financial data management method.

[0177] The system includes: The current financial identification sequence determination unit is used to obtain the current financial data sequence and determine the current financial identification sequence based on the current financial data sequence. The current financial data sequence is obtained based on the financial data of colleges and universities within a certain period arranged in chronological order, and the current financial identification sequence is used to represent the financial identification corresponding to each financial data in the current financial data sequence.

[0178] The prediction unit is used to predict each financial identifier of the next cycle of the current financial identifier sequence according to the current financial identifier sequence to obtain a predicted financial identifier sequence.

[0179] The actual financial identification sequence determination unit is used to obtain the actual financial data sequence and determine the actual financial identification sequence based on the actual financial data sequence, wherein the actual financial data sequence is the financial data actually collected in the next cycle of the current financial identification sequence.

[0180] The abnormality judgment unit is used to compare the actual financial identification sequence with the predicted financial identification sequence, and to construct an actual capital flow diagram based on the actual financial identification sequence, to judge whether there is abnormal financial data in the actual financial data sequence, and to obtain a judgment result.

[0181] The abnormality management execution unit is used to execute abnormality management on the abnormal financial data if the judgment result indicates that there is abnormal financial data in the actual financial data sequence.

[0182] It should be noted that the information interaction, execution process and other contents between the above-mentioned units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0183] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0184] An embodiment of the present application also provides a university financial data management device. The university financial data management device of this embodiment includes: at least one processor, at least one memory, and a computer program stored in the at least one memory and executable on the at least one processor. When the processor executes the computer program, the university financial data management device implements the steps of any of the above-mentioned university financial data management method embodiments, or enables the university financial data management device to implement the functions of each unit in the above-mentioned system embodiments.

[0185] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the university financial data management device.

[0186] The university financial data management device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The university financial data management device can include, but is not limited to, a processor and a memory. It can include more or fewer components, or a combination of certain components, or different components, for example, it can also include input and output devices, network access devices, buses, etc.

[0187] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0188] In some embodiments, the memory may be an internal storage unit of the college financial data management device, such as a hard disk or memory of the college financial data management device. In other embodiments, the memory may also be an external storage device of the college financial data management device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the college financial data management device. Further, the memory may also include both an internal storage unit and an external storage device of the college financial data management device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0189] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0190] An embodiment of the present application provides a computer program product. When the computer program product runs on a university financial data management device, the university financial data management device implements the steps in any of the above-mentioned method embodiments.

[0191] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or system that can carry the computer program code to the university financial data management device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0192] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0193] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0194] In the embodiments provided in the present application, it should be understood that the disclosed college financial data management system, equipment and method can be implemented in other ways. For example, the college financial data management system and equipment embodiments described above are merely schematic, for example, the division of the modules or units is only a logical function division, and there can be other division modes during actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored, or not executed. Another point, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0195] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0196] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for managing financial data of a university, characterized in that: include: Acquire a current financial data sequence, and determine a current financial identification sequence based on the current financial data sequence; wherein the current financial data sequence is obtained based on the financial data of colleges and universities within a certain period arranged in chronological order, and the current financial identification sequence is used to characterize the financial identification corresponding to each financial data in the current financial data sequence; According to the current financial identification sequence, predicting each financial identification of the next cycle of the current financial identification sequence to obtain a predicted financial identification sequence; Acquire an actual financial data sequence, and determine an actual financial identification sequence based on the actual financial data sequence; wherein the actual financial data sequence is the financial data actually collected in the next period of the current financial identification sequence; Comparing the actual financial identification sequence with the predicted financial identification sequence, and constructing an actual funds flow diagram based on the actual financial identification sequence, determining whether there is abnormal financial data in the actual financial data sequence, and obtaining a determination result; If the judgment result indicates that abnormal financial data exists in the actual financial data sequence, abnormal management is performed on the abnormal financial data.

2. The method for managing university financial data as claimed in claim 1, characterized in that: The determining of the current financial identification sequence based on the current financial data sequence includes: Extract key information of each financial data from the current financial data sequence according to the identification template; wherein the identification template includes teaching cycle, five-level classification, fund attribute and amount; the key information of each financial data includes the teaching cycle of each financial data, the five-level classification of each financial data, the fund attribute of each financial data and the amount of each financial data; the teaching cycle is obtained by converting the time of the financial data into the school year number, the semester stage and the teaching week; the five-level classification is to divide the financial data into five levels of major category, medium category, minor category, special item and sub-item according to the standards of the Ministry of Education; the fund attribute includes the source type of funds and the destination type of funds; Fill the key information of each financial data into the identification template to obtain the financial identification corresponding to each financial data; The financial identifier corresponding to each financial data is arranged according to the arrangement order of each financial data in the current financial data sequence to obtain the current financial identifier sequence.

3. The method for managing university financial data as claimed in claim 2, characterized in that: The step of predicting each financial identifier of the next cycle of the current financial identifier sequence according to the current financial identifier sequence to obtain a predicted financial identifier sequence includes: Encoding the teaching cycle of each financial identifier in the current financial identifier sequence to obtain a semester phase feature vector and a teaching week feature vector for each financial identifier; Performing category coding on the five-level classification of each financial identification in the current financial identification sequence to obtain a five-level classification feature vector of each financial identification; wherein the five-level classification feature vector includes a major category feature vector, a medium category feature vector, a minor category feature vector, a special feature vector, and a sub-item feature vector; Converting the fund attribute in each financial identifier in the current financial identifier sequence into a fund attribute feature vector through a type mapping matrix; Normalizing the amount in each financial identifier in the current financial identifier sequence to obtain an amount feature vector for each financial identifier; Based on the semester stage feature vector and the five-class classification feature vector of each financial identifier, a classification model is used to predict the five-class classification of each financial identifier in the next cycle of the current financial identifier sequence to obtain a class prediction result; Based on the teaching week feature vector, fund attribute feature vector and amount feature vector of each financial identifier, a regression model is used to predict the amount corresponding to each five-level classification in the category prediction result to obtain an amount prediction result; The category prediction results and the amount prediction results are arranged in the time sequence of the next cycle of the current financial identification sequence to obtain the predicted financial identification sequence.

4. The method for managing university financial data as claimed in claim 3, characterized in that: The semester phase feature vector and the five-class classification feature vector of each financial identifier are used to predict the five-class classification of each financial identifier in the next cycle of the current financial identifier sequence using the classification model to obtain the category prediction result, including: For each financial identifier, the following operations are performed: based on the hierarchical attention mechanism, the weight of each feature vector in the five-level classification feature vector is calculated, and the weight of each feature vector and each feature vector are weighted summed to obtain a classification comprehensive feature vector; the classification weight corresponding to the semester stage feature vector is selected from the classification weight matrix; wherein the classification weight matrix is ​​pre-set, and the classification weight matrix includes classification weights corresponding to feature vectors of different semester stages; Based on the classification weight and classification comprehensive feature vector of each financial identifier, the classification model is used to predict the five-level classification of each financial identifier in the next period of the current financial identifier sequence to obtain a category prediction result; wherein the classification model is a machine learning model.

5. The university financial data management method according to claim 3, characterized in that: The teaching week feature vector, fund attribute feature vector and amount feature vector based on each financial identifier are used to predict the amount corresponding to each five-level classification in the category prediction result using a regression model to obtain an amount prediction result, including: Based on the fund attributes and fund attribute feature vectors of each financial identifier, a current fund flow graph is constructed, and based on the current fund flow graph, a fund flow feature is generated using a graph convolutional network; wherein the nodes of the current fund flow graph are each financial identifier, and the edges of the current fund flow graph represent the flow direction of funds; Based on a preset time window, teaching week scale features, semester scale features and school year scale features are extracted from historical financial data, and based on the teaching week feature vector of each financial identifier, the teaching week scale features, the semester scale features and the school year scale features are fused through a temporal attention mechanism to obtain a multi-scale feature corresponding to each financial identifier; Based on the capital flow characteristics, the multi-scale characteristics corresponding to each financial identifier and the amount feature vector of each financial identifier, the regression model is used to predict the amount corresponding to each five-level classification in the category prediction results to obtain an amount prediction result; wherein the regression model is a machine learning model.

6. The university financial data management method according to claim 5, characterized in that: The method further comprises: Calculate the budget execution rate and remaining budget amount corresponding to each five-level classification in the category forecast results; If the budget execution rate exceeds the budget threshold, the amount of the five-level classification exceeding the budget threshold is attenuated according to the excess ratio of the budget execution rate to obtain the attenuated amount of the five-level classification exceeding the budget threshold; Determine the budget upper limit of the five-level classification that exceeds the budget threshold based on the remaining budget amount corresponding to the five-level classification that exceeds the budget threshold; Based on the budget upper limit of the five-level classification that exceeds the budget threshold, the attenuation amount of the five-level classification that exceeds the budget threshold is corrected to obtain the corrected amount of the five-level classification that exceeds the budget threshold.

7. The university financial data management method according to claim 1, characterized in that: The actual financial identification sequence is compared with the predicted financial identification sequence, and an actual fund flow diagram is constructed based on the actual financial identification sequence to determine whether there is abnormal financial data in the actual financial data sequence, and obtain a determination result, including: Compare each financial identifier in the actual financial identifier sequence with each financial identifier in the predicted financial identifier sequence one by one, calculate the difference between each financial identifier in the actual financial identifier sequence and each financial identifier in the predicted financial identifier sequence, and obtain a difference collection; Comparing each difference in the difference set with a difference threshold, and if each difference in the difference set is within the difference threshold, determining that there is no abnormal financial data in the actual financial data sequence; wherein the difference threshold changes dynamically according to the teaching calendar of the university; If at least one difference in the difference collection is not within the difference threshold, the actual funds flow graph is constructed based on the actual financial data sequence, and the funds flow pattern analysis is performed on the actual funds flow graph. If there is any abnormal feature in the actual funds flow graph, it is determined that abnormal financial data exists in the actual financial data sequence; wherein, the actual funds flow graph is a three-layer funds flow graph, the nodes of the actual funds flow graph are the accounts of each financial identifier in the actual financial identifier sequence, the edges of the actual funds flow graph represent the flow direction of funds, and abnormal features include closed-loop funds chain, a single node funds outflow accounting for more than 40%, and direct transactions with high-risk list accounts.

8. The university financial data management method according to claim 1, characterized in that: If the judgment result indicates that abnormal financial data exists in the actual financial data sequence, performing abnormal management on the abnormal financial data includes: If the judgment result indicates that there is abnormal financial data in the actual financial data sequence, an abnormal funds flow diagram is constructed with the abnormal financial data as the center; wherein the abnormal funds flow diagram is a 5-layer funds flow diagram; Identify abnormal fund aggregation nodes and key propagation paths in the abnormal fund flow graph to obtain graph analysis results; Exception management is performed on the abnormal financial data according to the graph analysis results.

9. The university financial data management method according to claim 8, characterized in that: The performing abnormal management on the abnormal financial data according to the graph analysis result includes: If the concentration of the abnormal fund aggregation node exceeds 50% or there are multiple node loops in the key propagation path, high-risk management is performed on the source account of the abnormal financial data; wherein the abnormal management includes high-risk management, medium-risk management and low-risk management, and the high-risk management includes freezing the source account of the abnormal financial data; If the key transmission path involves multiple nodes or the capital outflow of a single node accounts for more than 40%, medium risk management is performed on the key transmission path; wherein the medium risk management includes real-time monitoring of the capital flow on the key transmission path; If the abnormal funds flow diagram involves an account on the high-risk list, low-risk management is implemented; wherein, the low-risk management includes sending early warning information to the regulatory department.

10. A university financial data management system, characterized in that: include: An acquisition unit is used to acquire a current financial data sequence, and determine a current financial identification sequence based on the current financial data sequence; wherein the current financial data sequence is obtained based on the financial data of colleges and universities within a certain period arranged in chronological order, and the current financial identification sequence is used to characterize the financial identification corresponding to each financial data in the current financial data sequence; A prediction unit, used for predicting each financial identifier of the next period of the current financial identifier sequence according to the current financial identifier sequence to obtain a predicted financial identifier sequence; An actual financial identification sequence determination unit is used to obtain an actual financial data sequence and determine an actual financial identification sequence based on the actual financial data sequence; wherein the actual financial data sequence is the financial data actually collected in the next period of the current financial identification sequence; A judgment unit, used to compare the actual financial identification sequence with the predicted financial identification sequence, and to construct an actual capital flow diagram based on the actual financial identification sequence, to judge whether there is abnormal financial data in the actual financial data sequence, and to obtain a judgment result; An exception management unit is used to perform exception management on the abnormal financial data if the judgment result indicates that there is abnormal financial data in the actual financial data sequence.

Images