A financial data monitoring method and device, electronic equipment and storage medium

Abstract

The application discloses a kind of financial data monitoring method, device, electronic equipment and storage medium, comprising: obtaining the financial data to be monitored in monitoring period, the initial category label provided by the associated personnel of the financial data to be monitored;Classify the financial data to be monitored based on initial category label, obtain the target category label of the financial data to be monitored, target category label includes parent category label and the subcategory label under parent category label, the level of subcategory label is at least two levels;From the historical reference data associated with target category label is screened out in financial database;Using historical reference data to analyze the clustering of the financial data to be monitored, to determine whether the financial data to be monitored is abnormal.The application uses the rule of historical financial data to analyze the financial data to be monitored, when screening historical data, by setting parent category label and multilevel subcategory label, greatly improve the rationality and accuracy of financial data monitoring.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of financial management, and in particular to a financial data monitoring method and device, an electronic device and a storage medium. BACKGROUND

[0002] With the rapid development of informatization and intelligentization, a large amount of financial data is formed due to the execution of transactions, operations, reimbursement and other activities in the process of business management of enterprises, especially for enterprises or companies with a large number of business types and a large number of employees. At present, most enterprises or companies adopt the mode of manually auditing financial data. On the one hand, manually auditing a large amount of financial data has the problems of large workload and easy mistakes, and on the other hand, financial personnel may check the company's financial data only once every half month or month, and only enter data and make simple processing in daily life, so that abnormal data cannot be found in time. If abnormal or incorrect data is encountered, it may be difficult to recover the loss. SUMMARY

[0003] In order to solve the above technical problems, the present application provides a financial data monitoring method.

[0004] In a first aspect, the present application provides a financial data monitoring method, comprising:

[0005] obtaining to-be-monitored financial data in a monitoring period and an initial category label provided by an associated personnel of the to-be-monitored financial data;

[0006] classifying the to-be-monitored financial data based on the initial category label to obtain a target category label of the to-be-monitored financial data, the target category label comprising a parent category label and a subcategory label under the parent category label, and the level of the subcategory label being at least two levels;

[0007] screening historical reference data associated with the target category label from a financial database;

[0008] performing clustering analysis on the to-be-monitored financial data by using the historical reference data to determine whether the to-be-monitored financial data is abnormal.

[0009] In a second aspect, the present application provides a financial data monitoring device, comprising:

[0010] a financial data acquisition module configured to obtain to-be-monitored financial data in a monitoring period and an initial category label provided by an associated personnel of the to-be-monitored financial data;

[0011] The target category label determination module is used to classify the financial data to be monitored based on the initial category label to obtain the target category label of the financial data to be monitored. The target category label includes a parent category label and sub-category labels under the parent category label. The sub-category labels have at least two levels.

[0012] The historical reference data acquisition module is used to filter out historical reference data associated with the target category label from the financial database;

[0013] The financial data anomaly detection module is used to perform cluster analysis on the financial data to be monitored using the historical reference data to determine whether the financial data to be monitored is abnormal.

[0014] Thirdly, the present invention provides an electronic device, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the financial data monitoring method described in the first aspect of the present invention.

[0018] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the financial data monitoring method described in the first aspect of the present invention.

[0019] The embodiment of the present application provides a kind of financial data monitoring method, obtain the financial data to be monitored in monitoring period, the initial category label provided by the associated personnel of the financial data to be monitored is included in the financial data to be monitored;The financial data to be monitored is classified based on initial category label, obtain the target category label of the financial data to be monitored, target category label includes parent category label and the subcategory label under parent category label, the level of subcategory label is at least two levels;From financial database, the historical reference data associated with target category label is screened;Using historical reference data, the financial data to be monitored is carried out clustering analysis, to determine whether the financial data to be monitored is abnormal.The law of historical financial data is used in the present application to analyze the financial data to be monitored, when screening historical data, by setting parent category label and multilevel subcategory label, it can make the historical reference data screened out and the characteristics of the financial data to be monitored are relatively close, and then the characteristics of the financial data to be monitored can be judged according to the characteristics of historical reference data, greatly improve the rationality and accuracy of the financial data to be monitored for judging, and long-term automatic monitoring of financial data can be realized, not relying on manual processing, with high efficiency and saving labor cost.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0022] Figure 1 is a flow chart of a financial data monitoring method provided by the embodiment of the present application;

[0023] Figure 2 is a flow chart of the training process of a classification model provided by the embodiment of the present application;

[0024] Figure 3 is a structural schematic diagram of a financial data monitoring device provided by the embodiment of the present application;

[0025] Figure 4 is a structural schematic diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to enable the person skilled in the art to better understand the technical scheme of the present application, the technical scheme in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all. Based on the embodiments in the present application, all other embodiments obtained by the person skilled in the art without creative labor should belong to the protection scope of the present application.

[0027] Figure 1 A flow chart of a financial data monitoring method provided by the embodiments of the present application, the embodiments can be applicable to the case of monitoring the financial data of an enterprise or a company, and timely finding the abnormality. The method can be executed by a financial data monitoring device, which can be realized in the form of hardware and / or software, and can be configured in an electronic device. As shown in the figure, the financial data monitoring method comprises: Figure 1

[0028] S101, obtaining initial category labels provided by associated personnel of the to-be-monitored financial data and the to-be-monitored financial data in a monitoring period.

[0029] The main financial data of an enterprise or a company includes key data such as assets, liabilities, equity, income, expenses, profit, and cash flow. The data is generally derived from financial statements, director reports, management analysis, and financial situation descriptions.

[0030] The monitoring period can be set according to actual needs. Since the financial data monitoring is automatically performed, a monitoring period with a small time period can be set, for example, the monitoring period is to monitor once every 2 days, and then the system automatically obtains the to-be-monitored financial data in the database within 2 days.

[0031] The financial data can generally appear in the form of excel reports, invoices, pictures, etc. The associated personnel of the to-be-monitored financial data can be the personnel who submit the to-be-monitored financial data, for example, when the to-be-monitored financial data is reimbursement data, the personnel who submit the to-be-monitored financial data is the reimbursement applicant. The associated personnel of the to-be-monitored financial data can also be the staff of the financial department. The reimbursement applicant / financial personnel first classifies the to-be-monitored financial data when submitting / handling the to-be-monitored financial data, that is, provides the initial classification label.

[0032] S102, classifying the to-be-monitored financial data based on the initial category label to obtain a target category label of the to-be-monitored financial data. The target category label includes a parent category label and a subcategory label under the parent category label, and the level of the subcategory label is at least two levels.

[0033] ​The initial category label can be provided by the person submitting the financial data to be monitored or by the personnel of the financial department, so the initial category label is not necessarily a standard category label. Therefore, the financial data to be monitored is classified based on the initial category label to obtain a target category label of the financial data to be monitored, and the target category label is a standard category label. Specifically, the financial department usually pre-sets a standard category label for each type of financial matter and stores it in a label library.

[0034] In an optional embodiment, based on the initial category label, the financial data to be monitored is classified to obtain a target category label of the financial data to be monitored, specifically including: judging whether there is a parent category label same as the initial category label in the preset label library; if yes, taking the initial category label as the parent category label of the financial data to be monitored; if not, calculating a first semantic cosine value of each parent category label in the label library and the initial category label; taking the parent category label with the largest first semantic cosine value as the parent category label of the financial data to be monitored; and determining a subcategory label of the financial data to be monitored under the parent category label based on a preset classification model.

[0035] In this embodiment, the initial category label is a candidate parent category label, and based on the semantic cosine value of the parent category label in the label library and the initial category label, the standard parent category label of the financial data to be monitored can be quickly determined, and then the financial data to be monitored can be further classified according to the obtained parent category label.

[0036] The subcategory label of the financial data to be monitored under the parent category label is obtained by the classification model, and the classification model can be trained according to the training data. The classification model can be a PromptT intelligent model, which is a low-code platform for assembling workflows using visual components. After receiving the parent category label and the financial data to be monitored, the classification model calls the semantic recognition interface of PromptT, outputs the subcategory label, and locates the specific financial classification to which the financial data to be monitored belongs.

[0037] S103, screening historical reference data associated with the target category label from the financial database.

[0038] After obtaining the target category label of the financial data to be monitored, the specific financial classification to which the financial data to be monitored belongs is located, so the historical reference data associated with the target category label can be obtained from the financial database.

[0039] S104, using the historical reference data to perform cluster analysis on the financial data to be monitored to determine whether the financial data to be monitored is abnormal.

[0040] The historical reference data is historical financial data that is closest or relatively close to the type of the financial data to be monitored, and the historical financial data is by default normal financial data that is monitored. Therefore, the historical reference data can be compared with the financial data to be monitored for analysis to determine whether the financial data to be monitored is abnormal.

[0041] In an optional embodiment, the financial data to be monitored includes multiple financial types, including balance sheets, profit statements, cash flow statements, and financial ratios. The financial data to be monitored can also be clustered according to specific financial types. For each financial type, the financial data to be monitored and the historical reference data are clustered for analysis to determine whether the financial data to be monitored is abnormal. Before clustering, the data is standardized to ensure that each feature has the same dimension, which helps to reduce the clustering center deviation caused by different data dimensions, i.e., to reduce the error of financial data analysis.

[0042] Balance sheet: reflects the assets, liabilities, and owner's equity of the enterprise within the monitoring period.

[0043] Profit statement: reflects the operating results of the enterprise within the monitoring period. The profit statement includes operating income, operating cost, tax, sales expense, management expense, and financial expense. Through the profit statement, the profitability and profit level of the enterprise can be understood.

[0044] Cash flow statement: reflects the inflow and outflow of cash of the enterprise within the monitoring period.

[0045] Financial ratio: includes current ratio, quick ratio, asset-liability ratio, and gross profit ratio. Through the analysis of these ratios, the financial situation and operational efficiency of the enterprise can be better understood.

[0046] The embodiment of the present application provides a kind of financial data monitoring method, obtain the financial data to be monitored in monitoring period, the financial data to be monitored includes the initial category label provided by the associated personnel of the financial data to be monitored;The financial data to be monitored is classified based on initial category label, obtain the target category label of the financial data to be monitored, category label includes parent category label and the subcategory label under parent category label, the level of subcategory label is at least two levels;From financial database, the historical reference data associated with target category label is screened out;Using historical reference data, the financial data to be monitored is carried out cluster analysis, to determine whether the financial data to be monitored is abnormal.The rule of historical financial data is used to analyze the financial data to be monitored in the present application, when screening historical data, by setting parent category label and multilevel subcategory label, it can make the historical reference data screened out and the characteristics of the financial data to be monitored relatively close, and then the characteristics of the financial data to be monitored can be judged according to the characteristics of historical reference data, greatly improve the rationality and accuracy of the financial data to be monitored for judging, and long-term automatic monitoring financial data can be realized, not dependent on manual processing, with high efficiency and saving labor cost.

[0047] In an optional embodiment, the training process of the classification model is limited, Figure 2 The flow chart of the training process of a classification model is shown in Figure 2 The preset classification model is trained by the following steps:

[0048] S1, for each parent category label, obtain the financial training data labeled with the preset parent category label and N reference subcategory labels.

[0049] N is a positive integer greater than or equal to 2, the semantics of the reference subcategory label in front contains the semantics of the reference subcategory label behind. For example, N=3, i.e. the semantics of the first reference subcategory label contains the semantics of the second reference subcategory label, and the semantics of the second reference subcategory label contains the semantics of the third reference subcategory label.

[0050] S2, the classification model is trained using the preset parent category label and the financial training data to obtain N actual subcategory labels.

[0051] S3, determine whether N actual subcategory labels can form a semantic tree structure.

[0052] If yes, S5 is executed, and if no, S4 is executed. First, semantic features of each actual sub-category label are obtained based on semantic analysis, and then a semantic tree structure is constructed based on the semantic features, in which the number of actual sub-category labels in each layer of the semantic tree structure is 1. In the semantic tree structure, there is a hierarchical relationship between nodes, in which one node can serve as a parent node of another node, and the latter becomes a child node of the former.

[0053] S4, updating parameters of the classification model based on semantic relationships between actual sub-category labels, and returning to S2.

[0054] Through repeated training, the classification model can output sub-category labels with semantic hierarchical relationships, i.e., the classification model learns the ability to output sub-category labels in layers.

[0055] S5, determining the position order of the N actual sub-category labels based on the semantic tree structure.

[0056] The semantics of an actual sub-category label in an earlier position contain the semantics of an actual sub-category label in a later position. For example, N=3, i.e., the semantics of the first actual sub-category label contain the semantics of the second actual sub-category label, and the semantics of the second actual sub-category label contain the semantics of the third actual sub-category label.

[0057] S6, calculating the second semantic cosine value of the actual sub-category label and the reference sub-category label in the same position.

[0058] S7, determining whether the second semantic cosine value is less than 1.

[0059] If yes, S8 is executed, and if no, S9 is executed.

[0060] Here, the standard value of the second semantic cosine value is set to 1, considering that the classification of financial data is usually a pre-set professional term. If some semantic similar sub-category labels with a large number are expanded, it does not meet the actual needs of financial data monitoring. Therefore, the actual sub-category label of the present embodiment needs to be the same as the reference sub-category label to determine that the classification model training is completed.

[0061] S8, determining that the current classification model training is completed, and obtaining the trained classification model.

[0062] S9, updating parameters of the classification model based on the difference between the second cosine value and 1, and returning to S2.

[0063] In the process of training the classification model, when the actual subcategory label at the same position and the second semantic cosine value of the reference subcategory label are not 1, the parameters of the classification model are adjusted so that the actual subcategory label output by the classification model is close to the reference subcategory label (finally the same as the reference subcategory label), that is, the ability of the classification model to output specific subcategory labels according to the financial data is learned.

[0064] In an optional embodiment, historical reference data is used to perform cluster analysis on the to-be-monitored financial data to determine whether the to-be-monitored financial data is abnormal, including: performing first clustering on the historical reference data to obtain first clusters and center points of the first clusters; the number of the first clusters is at least 1; performing second clustering on the historical reference data and the to-be-monitored financial data to obtain second clusters and center points of the second clusters; the number of the second clusters is at least 1; determining whether the number of the second clusters is the same as the number of the first clusters; if not, determining that the to-be-monitored financial data is abnormal; if yes, for each second cluster, taking the first cluster closest to the second cluster as a neighboring cluster; and determining whether the to-be-monitored financial data is abnormal based on the distance relationship between the second cluster and the neighboring cluster.

[0065] By performing cluster analysis on the historical reference data and the combination of the historical reference data and the to-be-monitored financial data respectively, and comparing the two clustering results, it can be determined whether the to-be-monitored financial data is abnormal. On the one hand, if a new cluster appears after the to-be-monitored financial data is added, it means that the to-be-monitored financial data is abnormal; on the other hand, if no new cluster appears, but the to-be-monitored financial data has a great influence on the original clustering result, it also means that the to-be-monitored financial data is abnormal.

[0066] In an optional example, determining whether the to-be-monitored financial data is abnormal based on the distance relationship between the second cluster and the neighboring cluster includes: calculating the distance between the center point of the second cluster and the center point of the corresponding neighboring cluster to obtain a sub-distance; determining whether the sum of all sub-distances is greater than a preset distance value; if yes, determining that the to-be-monitored financial data is abnormal; if no, determining that the to-be-monitored financial data is normal.

[0067] In this example, no new cluster appears after the combination of the historical reference data and the to-be-monitored financial data is clustered, and then a secondary judgment is made from the influence degree of the to-be-monitored financial data on the original clustering result. The distance (sub-distance) between the center point of the second cluster and the center point of the neighboring cluster is calculated, that is, the influence degree of the to-be-monitored financial data on the original clustering result is calculated, all sub-distances are accumulated to obtain the total influence degree, and when the influence degree is large, it also means that the to-be-monitored financial data is abnormal.

[0068] Through the comparative analysis of the two clustering results, the abnormal financial data can be accurately and efficiently monitored, and the whole process is automated.

[0069] In an optional example, after determining the abnormal financial data to be monitored, the method further includes: sending the financial data to be monitored to an artificial end for auditing according to the sub-category label of the financial data to be monitored.

[0070] Specifically, sending the financial data to be monitored to an artificial end for auditing according to the sub-category label of the financial data to be monitored includes: determining the financial auditing object of the artificial end according to the lowest sub-category label of the level corresponding to the financial data to be monitored; and setting an abnormal label for the financial data to be monitored and sending it to the financial auditing object for auditing. The financial data to be monitored can be classified in more detail to accurately locate the classification of the financial data to be monitored, and the abnormal financial data to be monitored can be sent to the corresponding financial auditing object for auditing according to the classification, so as to achieve professional and targeted processing, thereby accurately and efficiently processing the financial data to be monitored and verifying whether the financial data to be monitored is abnormal.

[0071] The artificial end is the back end, and the types of financial data are various. The artificial end is provided with a plurality of financial auditing objects. The financial auditing objects can be personnel specialized in solving different functional problems. For example, the financial auditing object of group A is specialized in financial data of the financial reimbursement type, and the working object of group B is specialized in solving financial data of the financial ratio type. Therefore, the user feedback information can be fed back to the corresponding group based on the parent category label, and the sub-category label can quickly locate the small class to which the financial data to be monitored belongs, which helps the financial auditing object to quickly respond and process, thereby improving the work efficiency and accuracy.

[0072] Corresponding to the financial data monitoring method of the present application, in an embodiment of the present application, a financial data monitoring device is also provided, Figure 3 A structural schematic diagram of a financial data monitoring device provided for an embodiment of the present application is shown in FIG. 1. Figure 3 As shown in the figure, the financial data monitoring device includes:

[0073] The financial data acquisition module 301 is configured to acquire the financial data to be monitored in a monitoring period and an initial category label provided by an associated personnel of the financial data to be monitored;

[0074] The target category label determination module 302 is configured to classify the financial data to be monitored based on the initial category label to obtain a target category label of the financial data to be monitored, wherein the target category label includes a parent category label and a sub-category label under the parent category label, and the level of the sub-category label is at least two levels.

[0075] The historical reference data acquisition module 303 is configured to filter historical reference data associated with the target category label from a financial database;

[0076] The financial data anomaly judgment module 304 is configured to perform cluster analysis on the to-be-monitored financial data by using the historical reference data to determine whether the to-be-monitored financial data is abnormal.

[0077] Optionally, the target category label determination module 302 comprises:

[0078] The label judgment submodule is configured to determine whether there is a parent category label identical to the initial category label in a preset label library; if yes, the content of the first label determination submodule is executed; if no, the content of the first semantic cosine value calculation submodule is executed.

[0079] The first label determination submodule is configured to take the initial category label as the parent category label of the to-be-monitored financial data.

[0080] The first semantic cosine value calculation submodule is configured to calculate, for each parent category label in the label library, a first semantic cosine value of the parent category label and the initial category label.

[0081] The second label determination submodule is configured to take the parent category label with the maximum first semantic cosine value as the parent category label of the to-be-monitored financial data.

[0082] The third label determination submodule is configured to determine, based on a preset classification model, a subcategory label of the to-be-monitored financial data under the parent category label.

[0083] Optionally, the model training module comprises:

[0084] The training data acquisition module is configured to, for each parent category label, acquire financial training data labeled with a preset parent category label and N reference subcategory labels; N is a positive integer greater than or equal to 2, and the semantic of a reference subcategory label in front contains the semantic of a reference subcategory label behind.

[0085] The training classification module is configured to train a classification model by using the preset parent category label and the financial training data to obtain N actual subcategory labels.

[0086] The hierarchical judgment module is configured to determine whether the N actual subcategory labels can constitute a semantic tree hierarchical structure; in the semantic tree hierarchical structure, the number of actual subcategory labels of each hierarchical structure is 1; if yes, the content of the position sorting module is executed; if no, the content of the first updating module is executed.

[0087] The first updating module is configured to update parameters of the classification model based on semantic relations among the actual sub-category labels; and after execution, the content of the training classification module is executed.

[0088] The position ordering module is configured to determine position ordering of the N actual sub-category labels based on the semantic tree hierarchy; semantic of an actual sub-category label in front of the position contains semantic of an actual sub-category label behind the position.

[0089] The second semantic cosine value calculation module is configured to calculate a second semantic cosine value of an actual sub-category label at the same position and a reference sub-category label.

[0090] The second semantic cosine value judgment module is configured to judge whether the second semantic cosine value is less than 1; if yes, the content of the training completion determination module is executed; if no, the content of the second updating module is executed.

[0091] The training completion determination module is configured to determine that the current classification model training is completed, and obtain a trained classification model.

[0092] The second updating module is configured to update parameters of the classification model based on a difference between the second cosine value and 1.

[0093] After execution, the content of the training classification module is executed.

[0094] Optionally, the financial data anomaly judgment module 304 comprises:

[0095] The first clustering submodule is configured to perform first clustering on the historical reference data, and obtain a first cluster and a center point of the first cluster; the number of the first cluster is at least one.

[0096] The second clustering submodule is configured to perform second clustering on the historical reference data and the to-be-monitored financial data, and obtain a second cluster and a center point of the second cluster; the number of the second cluster is at least one.

[0097] The clustering analysis submodule is configured to judge whether the number of the second cluster is same as the number of the first cluster; if no, the content of the anomaly determination submodule is executed; if yes, the content of the adjacent cluster determination submodule is executed.

[0098] The anomaly determination submodule is configured to determine that the to-be-monitored financial data is abnormal.

[0099] The adjacent cluster determination submodule is configured to, for each of the second cluster, take the first cluster closest to the second cluster as an adjacent cluster.

[0100] Anomaly judgment submodule, used for judging whether the to-be-monitored financial data is abnormal based on a distance relationship between the second cluster and the adjacent cluster.

[0101] Optionally, the anomaly judgment submodule comprises:

[0102] Sub-distance calculation unit, used for calculating a distance from a center point of the second cluster to a center point of the corresponding adjacent cluster to obtain a sub-distance;

[0103] Sub-distance judgment unit, used for judging whether a sum of all sub-distances is greater than a preset distance value; if yes, the content of the anomaly determination unit is executed; if no, the content of the normal determination unit is executed;

[0104] Anomaly determination unit, used for determining that the to-be-monitored financial data is abnormal;

[0105] Normal determination unit, used for determining that the to-be-monitored financial data is normal.

[0106] Optionally, the financial data anomaly judgment module 304 further comprises:

[0107] Review submodule, used for sending the to-be-monitored financial data to a manual end for review according to a sub-category label of the to-be-monitored financial data after determining that the to-be-monitored financial data is abnormal.

[0108] Optionally, the review submodule comprises:

[0109] Review object determination unit, used for determining a financial review object of the manual end according to a lowest sub-category label of a corresponding level of the to-be-monitored financial data;

[0110] Financial review unit, used for setting an abnormal label for the to-be-monitored financial data and sending the to-be-monitored financial data to the financial review object for review.

[0111] The financial data monitoring device provided in the embodiments of the present application can execute the financial data monitoring method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0112] Figure 4A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0113] like Figure 4 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 or a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded into the RAM 43 from storage unit 48. The RAM 43 may also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0114] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0115] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as financial data monitoring methods.

[0116] In some embodiments, the financial data monitoring method can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 48. In some embodiments, parts or all of the computer program can be loaded and / or installed onto electronic device 40 via, e.g., ROM 42 and / or communication unit 49. When the computer program is loaded onto RAM 43 and executed by processor 41, one or more steps of the financial data monitoring method described above can be performed. Alternatively, in other embodiments, processor 41 can be configured to perform the financial data monitoring method by other means, e.g., with the aid of firmware.

[0117] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0118] Computer programs used to implement the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor of the machine, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0119] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0120] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0121] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0122] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0123] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present application can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0124] The above detailed description does not constitute a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method of financial data monitoring, characterized by, The method comprises the following steps: acquiring to-be-monitored financial data and an initial category label provided by a related person of the to-be-monitored financial data in a monitoring period; classifying the to-be-monitored financial data based on the initial category label to obtain a target category label of the to-be-monitored financial data, wherein the target category label comprises a parent category label and a subcategory label under the parent category label, the subcategory label has at least two levels, and the subcategory label under the parent category label is determined based on a preset classification model; screening historical reference data associated with the target category label from a financial database; performing cluster analysis on the to-be-monitored financial data by using the historical reference data to determine whether the to-be-monitored financial data is abnormal, comprising: performing cluster analysis on the historical reference data and combined data of the historical reference data and the to-be-monitored financial data respectively, comparing the two cluster results, and determining whether the to-be-monitored financial data is abnormal; the preset classification model is obtained by training through the following steps: S1, for each parent category label, acquiring financial training data labeled with a preset parent category label and N reference subcategory labels; N is a positive integer greater than or equal to 2, and the semantics of the reference subcategory label in the front position contains the semantics of the reference subcategory label in the rear position; S2, training the classification model by using the preset parent category label and the financial training data to obtain N actual subcategory labels; S3, determining whether the N actual subcategory labels can form a semantic tree structure; if yes, performing S5, and if no, performing S4; in the semantic tree structure, the number of actual subcategory labels in each level structure is 1; S4, updating the parameters of the classification model based on the semantic relationship between the actual subcategory labels, and returning to perform S2; S5, determining the position order of the N actual subcategory labels based on the semantic tree structure, wherein the semantics of the actual subcategory label in the front position contains the semantics of the actual subcategory label in the rear position; S6, calculating a second semantic cosine value of the actual subcategory label and the reference subcategory label in the same position; the value range of the second semantic cosine value is 0-1, representing the similarity between the actual subcategory label and the reference subcategory label, and when the second semantic cosine value is 1, it means that the actual subcategory label is the same as the reference subcategory label; S7, determining whether there is a second semantic cosine value less than 1; if yes, performing S8, and if no, performing S9; S8, determining that the current classification model training is completed to obtain a trained classification model; S9, updating the parameters of the classification model based on the difference between the second semantic cosine value and 1, and returning to perform S2.

2. The method of claim 1, wherein, The classification of the to-be-monitored financial data based on the initial category label to obtain the target category label of the to-be-monitored financial data comprises the following steps: determining whether there is a parent category label identical to the initial category label in a preset label library; if yes, taking the initial category label as the parent category label of the to-be-monitored financial data; If not, for each parent category label in the label library, a first semantic cosine value of the parent category label and the initial category label is calculated; The parent category label with the largest first semantic cosine value is taken as the parent category label of the to-be-monitored financial data; Based on a preset classification model, a subcategory label of the to-be-monitored financial data under the parent category label is determined.

3. The method of claim 1, wherein, The clustering analysis of the to-be-monitored financial data by using the historical reference data to determine whether the to-be-monitored financial data is abnormal, comprises: The historical reference data is clustered for the first time to obtain a first cluster and a center point of the first cluster; the number of the first cluster is at least one; The historical reference data and the to-be-monitored financial data are clustered for the second time to obtain a second cluster and a center point of the second cluster; the number of the second cluster is at least one; It is judged whether the number of the second cluster is the same as the number of the first cluster; If not, it is determined that the to-be-monitored financial data is abnormal; If yes, for each second cluster, the first cluster closest to the second cluster is taken as a neighboring cluster; Based on the distance relationship between the second cluster and the neighboring cluster, it is determined whether the to-be-monitored financial data is abnormal.

4. The method of claim 3, wherein, The determination of whether the to-be-monitored financial data is abnormal based on the distance relationship between the second cluster and the neighboring cluster, comprises: The distance from the center point of the second cluster to the center point of the corresponding neighboring cluster is calculated to obtain a sub-distance; It is judged whether the sum of all sub-distances is greater than a preset distance value; If yes, it is determined that the to-be-monitored financial data is abnormal; If not, it is determined that the to-be-monitored financial data is normal.

5. The method of claim 4, wherein, After it is determined that the to-be-monitored financial data is abnormal, further comprising: The to-be-monitored financial data is sent to an artificial end for auditing according to the subcategory label of the to-be-monitored financial data.

6. The method of claim 5, wherein, The to-be-monitored financial data is sent to the artificial end for auditing according to the subcategory label of the to-be-monitored financial data, comprising: A financial auditing object of the artificial end is determined according to the lowest subcategory label corresponding to the to-be-monitored financial data; The to-be-monitored financial data is set with an abnormal label and sent to the financial auditing object for auditing.

7. A financial data monitoring apparatus characterized by comprising: Comprise: A financial data acquisition module is configured to acquire to-be-monitored financial data in a monitoring period and an initial category label provided by an associated personnel of the to-be-monitored financial data; A target category label determination module is configured to classify the to-be-monitored financial data based on the initial category label to obtain a target category label of the to-be-monitored financial data, wherein the target category label comprises a parent category label and a subcategory label under the parent category label, and the level of the subcategory label is at least two levels; A historical reference data acquisition module is configured to filter historical reference data associated with the target category label from a financial database; A financial data abnormality judgment module is configured to perform clustering analysis on the to-be-monitored financial data by using the historical reference data to determine whether the to-be-monitored financial data is abnormal; The financial data monitoring device is configured to perform the financial data monitoring method of any one of claims 1-6.

8. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the financial data monitoring method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing the processor to implement the financial data monitoring method according to any one of claims 1-6 when executed.

Images