Methods used to process financial data

Abstract

The present disclosure relates to a method for processing financial data, including: determining subjects with abnormal budget usage and expense detail data corresponding to the subjects based on financial data; extracting detail keywords from the expense detail data; and fusing the detail keywords based on the relevance of the detail keywords to generate an abnormal reason prompt for the subject. With the method of the present disclosure, subjects with abnormal budget usage can be obtained and an abnormal reason prompt for the subject can be generated, so that users can intuitively know the subjects with abnormal budget usage and the abnormal reasons that cause the subjects to exceed the budget, which is convenient for users who are not from financial majors to intuitively know the financial status of the department, and is conducive to users making relevant decisions.

Description

Background Art

[0002] For enterprises, financial data is an important reference data for their business operations. The relevant financial system generally only outputs financial data in the form of financial statements. However, this output method is not intuitive, especially for users who are not financial professionals, they cannot intuitively understand the financial status from the financial statements. For example, the leaders of the company cannot intuitively see from the financial statements whether the department they are responsible for is over budget and the main reason for the over budget. Summary of the invention

[0003] According to an embodiment of the present disclosure, a method for processing financial data is proposed, one purpose of which is to solve at least one of the problems mentioned above and present the financial status to the user in an intuitive manner.

[0004] According to one aspect of the present disclosure, a method for processing financial data is provided, the method comprising:

[0005] Determine, based on the financial data, accounts with abnormal budget usage and detailed expense data corresponding to the accounts;

[0006] Extracting detail keywords from the expense detail data; and

[0007] The detail keywords are merged based on the relevance of the detail keywords to generate a prompt of the abnormal cause of the subject.

[0008] Optionally, extracting detail keywords from the expense detail data includes:

[0009] Detail keywords are extracted from the expense description in the expense detail data based on the amount data in the expense detail data.

[0010] Optionally, extracting detail keywords from the expense description in the expense detail data based on the amount data in the expense detail data includes:

[0011] Preprocess the expense descriptions by merging expense descriptions with similar meanings and removing special symbols in the expense descriptions, and create a project-customized dictionary based on the preprocessed expense descriptions;

[0012] Segment the cost description according to the project-customized dictionary;

[0013] weighting the words obtained after word segmentation based on the amount data in the expense detail data; and

[0014] Select detailed keywords based on the weighted amount of each word.

[0015] Optionally, a natural language processing model is used to segment the expense descriptions in the expense detail data.

[0016] Optionally, fusing the detail keywords based on the relevance of the detail keywords to generate the abnormality cause prompt of the subject includes:

[0017] Determine the relevance of the detail keywords using a relevance algorithm, and group the mutually related detail keywords into detail keyword groups; and

[0018] The detail keywords in the detail keyword group are integrated into the abnormal cause prompt.

[0019] Optionally, using an association algorithm to determine the relevance of the detail keywords includes: determining whether the number of times multiple detail keywords appear in the same expense description exceeds a preset number threshold; if the determination result is yes, it is considered that the multiple detail keywords are interrelated; if the determination result is no, it is considered that the multiple detail keywords are not interrelated.

[0020] Optionally, if all detail keywords are not related to each other, each individual detail keyword is used as an abnormality cause prompt.

[0021] Optionally, determining the account with abnormal budget usage based on the financial data further includes:

[0022] Based on user permissions, determine the accounts with abnormal budget usage, including:

[0023] In the case where the category of the user authority is department authority, determining the items with abnormal budget usage in the department to which the user authority belongs;

[0024] In the case where the category of the user authority is functional authority, determining the departments with abnormal budget usage in the departments related to the functional authority and further determining the subjects with abnormal budget usage in the departments with abnormal budget usage;

[0025] In the case where the category of the user authority is market authority, determining a market with abnormal budget usage related to the market authority and further determining an account with abnormal budget usage in the market with abnormal budget usage; and

[0026] In the case where the category of the user authority is executive authority, objects with abnormal budget usage are determined among objects related to the executive authority, and subjects with abnormal budget usage among the objects with abnormal budget usage are further determined, wherein the objects include one or more of departments, functions, markets, and brands.

[0027] Optionally, determining the subjects with abnormal budget usage based on the financial data further includes determining categories of abnormal budget usage, the categories including: failure to make a budget resulting in an over-budget, and / or a budget being made and exceeding the budget.

[0028] Optionally, the accounts for which budget usage abnormality is determined based on financial data include:

[0029] Based on the financial data, select the accounts that meet at least one of the following conditions as the accounts with budget usage exceptions:

[0030] The difference between actual expenses and budgeted expenses exceeds the difference threshold;

[0031] the extent to which actual costs exceed budgeted costs exceeds the threshold; and

[0032] The difference or degree to which actual costs exceed budgeted costs ranks high among all subjects.

[0033] Optionally, the method further comprises presenting to the user the items with abnormal budget usage and prompts of the reasons for the abnormalities corresponding to the items.

[0034] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. The computer program includes executable instructions. When the executable instructions are executed by a processor, the method described above is implemented.

[0035] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the executable instructions to implement the method as described above.

[0036] The method for processing financial data proposed in the present disclosure has at least the following advantages:

[0037] Through the method disclosed in the present invention, it is possible to obtain accounts with abnormal budget usage and generate abnormal reason prompts for the accounts, so that users can intuitively know the accounts with abnormal budget usage and the abnormal reasons that cause the accounts to exceed the budget, making it convenient for users who are not from financial majors to intuitively know the financial status of the department, which is beneficial for users to make relevant decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Other details and advantages of the present disclosure will become apparent from the detailed description provided below. It should be understood that the following drawings are merely schematic and not drawn to scale, and thus cannot be considered as limiting the present disclosure. The following will be described in detail with reference to the drawings, wherein:

[0039] Figure 1A schematic flow chart of a method for processing financial data according to a specific embodiment of the present disclosure is shown.

[0040] Figures 2A-2D A schematic flow chart of a method for processing financial data according to another specific embodiment of the present disclosure is shown.

[0041] Figure 3 is a schematic structural block diagram of an electronic device according to another embodiment of the present disclosure. DETAILED DESCRIPTION

[0042] The exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in a variety of forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided to make the disclosure of the present disclosure comprehensive and complete and to fully convey the concepts of the exemplary embodiments to those skilled in the art. In the drawings, the size of some elements may be exaggerated or deformed for clarity. The same reference numerals in the drawings represent the same or similar structures, and thus their detailed descriptions will be omitted.

[0043] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, elements, etc. may be adopted. In other cases, known structures, methods or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0044] Combine the following Figure 1 An exemplary method for processing financial data according to an embodiment of the present disclosure is introduced.

[0045] First, in step S110, based on the financial data, the account with abnormal budget usage and the expense detail data corresponding to the account are determined.

[0046] The relevant person in charge of the enterprise generally pays attention to the expenditure of each financial account in the department (for example, travel expenses, conference expenses, consulting fees, communication expenses, etc.), and hopes to understand the specific situation of the over-budgeted accounts. The method disclosed in the present invention can determine the accounts with abnormal budget usage based on user permissions, and the user's permissions can be related to the user's position in the enterprise. For example, when the category of user permissions is departmental permissions, the accounts with abnormal budget usage in the department to which the user permissions belong are determined. When the category of user permissions is functional permissions, the departments with abnormal budget usage in the departments related to the functional permissions are determined, and the accounts with abnormal budget usage in the departments with abnormal budget usage are further determined. When the category of user permissions is market permissions (for example, the user is a marketing manager or a regional vice president), the markets with abnormal budget usage related to the market permissions (for example, markets with abnormal budget usage) are determined, and the accounts with abnormal budget usage in the markets with abnormal budget usage are further determined. When the category of user authority is executive (CEO) authority, the departments, functions, markets and / or brands with abnormal budget usage in the departments, functions, markets and / or brands (e.g., KFC brand) related to the executive authority are determined, and the accounts with abnormal budget usage in the departments, functions, markets and / or brands with abnormal budget usage are further determined.

[0047] Determining the subjects with abnormal budget usage based on financial data may further include determining the categories of abnormal budget usage, and the categories of abnormal budget usage may be defined according to the actual needs of the user. For example, in an optional embodiment, the categories of abnormal budget usage may include one of the following: failure to make a budget resulting in an over-budget, and having made a budget and exceeding the budget.

[0048] Determining the accounts with abnormal budget usage based on the financial data may include: selecting an account that satisfies at least one of the following conditions as the account with abnormal budget usage based on the financial data:

[0049] 1. The difference between the actual cost and the budgeted cost exceeds the difference threshold. The specific value of the difference threshold can be set by the user. For example, the difference threshold can be set to any amount between 100,000 yuan and 1 million yuan, and the account where the difference between the actual cost and the budgeted cost exceeds this amount will be regarded as an account with abnormal budget usage.

[0050] 2. The degree to which the actual cost exceeds the budgeted cost exceeds the degree threshold. The specific value of the degree threshold can be set by the user. For example, the degree threshold can be set to any value between 10% and 50%, and the items whose actual cost exceeds the budgeted cost by more than this value will be treated as items with abnormal budget usage.

[0051] 3. The difference or degree of actual expenses exceeding budgeted expenses ranks first among all items. That is, the items that rank in the top N in terms of the difference or degree of exceeding budgeted expenses can be used as items with abnormal budget usage, where N is a positive integer. The value of N can be selected according to the actual needs of the user. For example, the items that rank in the top three in terms of the difference or degree of exceeding budgeted expenses can be used as items with abnormal budget usage.

[0052] In step S120, detail keywords are extracted from the expense detail data.

[0053] Detail keywords may be extracted from the expense description in the expense detail data based on the amount data in the expense detail data.

[0054] Specifically, the expense description in the expense detail data may be preprocessed first. Specifically, the expense description may be preprocessed, for example, by merging expense descriptions with similar meanings and removing special symbols in the expense description, so as to reduce the amount of data and reduce the computing pressure. Then, a project customized dictionary is created based on the preprocessed expense description. After that, the expense description in the expense detail data may be segmented according to the project customized dictionary, and the words obtained after segmentation may be weighted based on the amount data in the expense detail data. Finally, a detail keyword is selected based on the weighted amount after each word is weighted. For example, the words may be sorted according to the weighted amount, and the N words with the highest weighted amount may be used as detail keywords, and the specific value of N may be specified by the user, for example, any integer from 3 to 10. Alternatively, the weighted amount may be compared with a preset amount threshold, and the words with a weighted amount greater than the preset amount threshold may be used as detail keywords, and the preset amount threshold may be specified by the user, for example, any amount from 100,000 yuan to 1,000,000 yuan. Any suitable natural language processing model may be used to segment the expense description in the expense detail data, for example, the NLP-jieba model may be used.

[0055] The following is a specific example to illustrate the method of extracting detail keywords from the expense detail data. In this example, the expense description in the expense detail data and the amount data corresponding to the expense description are shown in Table 1:

[0056]

[0057]

[0058] Table 1

[0059] After segmenting the expense description, the following five words are obtained: "City A", "City B", "City C", "Business trip" and "Meeting". The corresponding relationship between each word and the weighted amount is shown in Table 2:

[0060] word Weighted amount (Yuan) City A 100 City B 900 City C 200 On business trip 500 Meeting 700

[0061] Table 2

[0062] If the first three words with the highest weighted amounts are used as detailed keywords, the obtained detailed keywords are: "city B", "business trip" and "conference".

[0063] In step S130, the detail keywords are fused based on the relevance of the detail keywords to generate a prompt for the abnormal cause of the subject.

[0064] The relevance of the detail keywords can be determined by using an association algorithm, and the detail keywords that are related to each other are formed into corresponding detail keyword groups, and the detail keywords in the detail keyword group are merged into an abnormal reason prompt. Specifically, in the process of merging, detail keywords with high relevance are selected and merged by splicing. Any suitable association algorithm can be used to determine the relevance of detail keywords, for example, the Apriori algorithm can be used to determine the relevance of detail keywords. Specifically, it can be determined whether the number of times that multiple detail keywords appear in the same expense description exceeds a preset number threshold. If the judgment result is yes, it is considered that the multiple detail keywords are related to each other. If the judgment result is no, it is considered that the multiple detail keywords are not related to each other. The specific value of the number threshold can be specified by the user. For example, the number threshold can be specified as any number from 10 to 50 times. If the number of times that multiple detail keywords appear in the same expense description exceeds this number, it is considered that the multiple detail keywords are related to each other, and the multiple detail keywords should form the same detail keyword group and merge into the same abnormal reason prompt. In addition, if all detail keywords are not related to each other, each individual detail keyword will be used as a prompt of the abnormality cause.

[0065] Continuing with the specific example in step S120, after obtaining the three detail keywords "city B", "business trip" and "conference", the association algorithm determines that "city B" and "business trip" are related to each other, and "city B" and "conference" are related to each other, thereby obtaining two detail keyword groups: "city B" and "business trip", and "city B" and "conference". Finally, the abnormal reason prompts obtained by fusion are "city B business trip" and "city B meeting".

[0066] After obtaining the abnormal reason prompt of the budget usage abnormal account, the account with budget usage abnormality and the abnormal reason prompt corresponding to the account can also be presented to the user. The output can be performed through any suitable output device, such as a display screen of a desktop computer, a laptop computer or a smart phone.

[0067] Through the above method, the user (for example, the relevant person in charge of the enterprise) can intuitively know the items with abnormal budget usage in the department he is responsible for and the abnormal reasons that cause the items to exceed the budget, thereby facilitating the user to make relevant decisions.

[0068] according to Figure 1 The principles of the methods used to process financial data, Figures 2A-2D A more specific schematic flow chart of a method for processing financial data is disclosed in .

[0069] Figure 2A The example in Figure 1 shows the case where the user authority is a department authority. For example, the department to which the department authority belongs is the retail department. Figure 2A In the method shown, it is first determined whether the retail department as a whole is over budget, that is, whether the retail department is not over budget, over budget due to failure to make a budget, or has made a budget and over budget. Then, according to the method disclosed in the present invention, find out the accounts in the retail department with abnormal budget usage and generate a prompt for the abnormal reason of the account. An exemplary output result is as follows: In January 2021, the retail department is over budget. Among the accounts, supplies (Supplies) are over budget, and the following should be paid attention to: office insect control, xx office stationery reservations, and printing paper purchases; outside services (outside-service) are over budget, and the following should be paid attention to: xx service fees, xx consulting fees, and xx fees.

[0070] Figure 2B The case where the user authority is a functional authority is shown in FIG. For example, the functional authority corresponds to the IT function. Figure 2A In the method shown, it is first determined whether the IT function is over budget, that is, whether the IT function is not over budget, the over budget is caused by not making a budget, or the budget has been made and the budget is over budget. Then, the department with abnormal budget usage in the department related to the IT function is determined, and then, according to the method disclosed in the present invention, the subject with abnormal budget usage in the department with abnormal budget usage is found and the abnormal reason prompt of the subject is generated. An exemplary output result is as follows: In January 2021, the IT function is not over budget. Among them, the data department is over budget due to not making a budget. In the subject, depreciation is over budget, and it is necessary to focus on: xx chip, xx project, xx processor purchase; travel is over budget, and it is necessary to focus on: city B business trip, xx conference fare, city A air ticket. The digital department is over budget. In the subject, consulting is over budget, and it is necessary to focus on: xx company expert consulting fees, xx fees, xx conference fees. The advertising department is over budget due to not making a budget. In the subject, training is over budget due to not making a budget, and it is necessary to focus on: xx live broadcast, xx conference.

[0071] Figure 2CThe example in Figure 1 shows that the user authority is market authority. For example, the market authority corresponds to the regional vice president. Figure 2C In the method shown, it is first determined whether the market of each relevant city is over budget, that is, it is determined whether the market of each relevant city is not over budget, is over budget due to lack of budget, or is over budget due to lack of budget. Then, according to the method disclosed in the present invention, find out the items with abnormal budget usage in the market of each relevant city and generate a prompt for the abnormal reason of the item. An exemplary output result is as follows: the market of city A is over budget due to lack of budget. Among the items, travel is over budget, and the focus should be on: xx conference air ticket fee; the market of city B is over budget. Among the items, training is over budget, and the focus should be on: xx purchase fee.

[0072] Figure 2D The example in Figure 1 shows the case where the user authority is that of an executive. Figure 2D In the method shown, first determine whether the departments, functions, markets and / or brands related to the executive authority are over budget, that is, determine whether the departments, functions, markets and / or brands related to the executive authority are not over budget, are over budget due to not making a budget, or have made a budget and are over budget. Then, according to the method disclosed in the present invention, find out the subjects with abnormal budget usage in the departments, functions, markets and / or brands with abnormal budget usage and generate a prompt for the abnormal reason of the subject. An exemplary output result is as follows: In the function, please pay special attention to: xx (functional person in charge) City B market is over budget, of which xx subject is over budget due to not making a budget. In the subject, travel is over budget, and special attention should be paid to: xx conference air ticket fee. In the brand, please pay special attention to: City A market is over budget, of which xx subject is over budget, and special attention should be paid to: A4 paper purchase, stationery purchase.

[0073] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a computer program is stored, the program including executable instructions, which can implement the steps of the method for processing financial data in any of the above embodiments when executed by, for example, a processor. In some possible implementations, various aspects of the present disclosure can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present disclosure described in the method for processing financial data in this specification.

[0074] The program product for implementing the above method according to an embodiment of the present disclosure may adopt a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus, or device.

[0075] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0076] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0077] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0078] In an exemplary embodiment of the present disclosure, an electronic device is also provided, which may include a processor and a memory for storing executable instructions of the processor, wherein the processor is configured to execute the steps of the method for processing financial data in any one of the above embodiments by executing the executable instructions.

[0079] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0080] Refer to the following Figure 3 The electronic device 200 according to this embodiment of the present disclosure is described. Figure 3 The electronic device 200 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0081] like Figure 3 As shown, the electronic device 200 is in the form of a general computing device. The components of the electronic device 200 may include, but are not limited to: at least one processing unit 210, at least one storage unit 220, a bus 230 connecting different system components (including the storage unit 220 and the processing unit 210), a display unit 240, etc.

[0082] The storage unit stores program codes, which can be executed by the processing unit 210, so that the processing unit 210 performs the steps according to various exemplary embodiments of the present disclosure described in the method for processing financial data in this specification. For example, the processing unit 210 can perform the following steps: Figure 1 Follow the steps shown in .

[0083] The storage unit 220 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 2201 and / or a cache memory unit 2202 , and may further include a read-only memory unit (ROM) 2203 .

[0084] The storage unit 220 may also include a program / utility 2204 having a set (at least one) of program modules 2205, such program modules 2205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0085] Bus 230 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0086] The electronic device 200 may also communicate with one or more external devices 300 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 200, and / or communicate with any device that enables the electronic device 200 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 250. Furthermore, the electronic device 200 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 260. The network adapter 260 may communicate with other modules of the electronic device 200 via the bus 230. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0087] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation methods of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the method for processing financial data according to the implementation methods of the present disclosure.

[0088] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing what is disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A method for processing financial data, comprising: Determine, based on the financial data, accounts with abnormal budget usage and detailed expense data corresponding to the accounts; Extracting detail keywords from the expense detail data; as well as Based on the relevance of the detail keywords, the detail keywords are integrated to generate the abnormal cause prompt of the subject. The extraction of detail keywords from the expense detail data includes: Extract detailed keywords from the expense description in the expense detail data based on the amount data in the expense detail data, The detailed keywords extracted from the expense description in the expense detail data based on the amount data in the expense detail data include: Preprocess the expense descriptions by merging expense descriptions with similar meanings and removing special symbols in the expense descriptions, and create a project-customized dictionary based on the preprocessed expense descriptions; Segment the cost description according to the project-customized dictionary; weighting the words obtained after word segmentation based on the amount data in the expense detail data; and Select detailed keywords based on the weighted amount of each word. Wherein, the step of fusing the detail keywords based on the relevance of the detail keywords to generate the abnormality cause prompt of the subject includes: Using an association algorithm to determine the association of the detail keywords, and grouping the mutually associated detail keywords into corresponding detail keyword groups; and Merge the detailed keywords in the detailed keyword grouping into the abnormal cause prompt. Wherein, using the association algorithm to determine the association of the detailed keywords includes: It is determined whether the number of times that multiple detail keywords appear in the same expense description exceeds a preset number threshold. If the determination result is yes, it is considered that the multiple detail keywords are related to each other. If the determination result is no, it is considered that the multiple detail keywords are not related to each other. If all detail keywords are not related to each other, each individual detail keyword will be used as a prompt of the abnormality cause.

2. The method according to claim 1, characterized in that Use a natural language processing model to segment expense descriptions in expense detail data.

3. The method according to claim 1, characterized in that Accounts that are determined to have abnormal budget usage based on financial data further include: Determine the accounts with abnormal budget usage based on user permissions, including In the case where the category of the user authority is department authority, determining the items with abnormal budget usage in the department to which the user authority belongs; In the case where the category of the user authority is functional authority, determining the departments with abnormal budget usage in the departments related to the functional authority and further determining the subjects with abnormal budget usage in the departments with abnormal budget usage; In the case where the category of the user authority is market authority, determining a market with abnormal budget usage related to the market authority and further determining an account with abnormal budget usage in the market with abnormal budget usage; and In the case where the category of the user authority is executive authority, objects with abnormal budget usage are determined among objects related to the executive authority, and subjects with abnormal budget usage among the objects with abnormal budget usage are further determined, wherein the objects include one or more of departments, functions, markets, and brands.

4. The method according to claim 1, characterized in that: Determining the items with abnormal budget usage based on the financial data further includes determining the categories of abnormal budget usage, which include: failure to make a budget resulting in an over-budget, and / or a budget being made and exceeding the budget.

5. The method according to claim 1, characterized in that Accounts that have been identified as having abnormal budget usage based on financial data include: Based on the financial data, select the accounts that meet at least one of the following conditions as the accounts with budget usage exceptions: The difference between actual expenses and budgeted expenses exceeds the difference threshold; the extent to which actual costs exceed budgeted costs exceeds the threshold; and The difference or degree to which actual costs exceed budgeted costs ranks high among all subjects.

6. The method according to claim 1, characterized in that The method further includes presenting to the user the subjects with abnormal budget usage and the abnormal reason prompts corresponding to the subjects.

7. A computer-readable storage medium having a computer program stored thereon, the computer program comprising executable instructions, and when the executable instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

8. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to execute the executable instructions to implement the method according to any one of claims 1 to 6.

Images