An automated accounting entry generation method and system based on artificial intelligence

Abstract

The present invention provides an artificial intelligence-based automated accounting entry generation method and system, which belongs to the technical field of data processing, and specifically comprises: when it is determined that the verification processing difficulty of the transaction data does not meet the requirements according to the historical data volume of the transaction data, the constituent data of the associated verification data source and other verification data sources, the transaction data is verified and processed by using the real-time format conversion data source to obtain the verification processing result, the conversion processing order of other verification data sources is determined according to the analysis results of the data formats of other verification data sources and the historical data volume of the associated transaction data, and the conversion processing of other verification data sources and the verification processing of the transaction data are performed according to the conversion processing order, until there is an abnormality in the verification processing result or the verification processing of the verification data source is completed, and the AI ​​model is used to perform automatic accounting entry processing of the transaction data of different data sources, thereby improving the efficiency of the entry processing.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to an automated method and system for generating accounting entries based on artificial intelligence. Background Art

[0002] In order to realize the entry processing of accounts, the existing technical solutions often perform the entry processing of accounts manually, which makes it difficult to meet the requirements for the efficiency and accuracy of the entry processing of accounts. Specifically, in the invention patent application CN202211076576.7 "A banking account processing system, method and device", the accounting entry configuration module is used to obtain the corresponding accounting entry information according to the accounting entry code in the transaction data, initialize the accounting platform accounting mainstream, and call the accounting core system for core accounting processing, but there are the following technical problems:

[0003] The purchase orders, sales invoices, payment vouchers, receipt records, and expense reimbursement forms processed by the existing technical solutions have many data sources, and there are many deviations in the data format. Therefore, the use of the accounting entry configuration module will inevitably lead to deviations in the accuracy of the entry processing.

[0004] In response to the above technical problems, the present invention uses artificial intelligence technology to intelligently identify, understand and process various financial data of an enterprise, so as to automatically, accurately and efficiently generate accounting entries that comply with accounting standards. Specifically, the present invention provides an automated method and system for generating accounting entries based on artificial intelligence. Summary of the invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] According to one aspect of the present invention, an automated method for generating accounting entries based on artificial intelligence is provided.

[0007] An automated method for generating accounting entries based on artificial intelligence, specifically comprising:

[0008] S1 obtains the associated transaction data of the verification data source of the accounting data, and determines the real-time format conversion data source of the verification data source in combination with the historical data volume of the associated transaction data;

[0009] S2 uses the associated verification data source of the transaction data excluding the real-time format conversion data source as other verification data sources, and when it is determined that the verification processing difficulty of the transaction data does not meet the requirements according to the historical data volume of the transaction data, the associated verification data source and the constituent data of the other verification data sources, the real-time format conversion data source is used to verify the transaction data to obtain a verification processing result;

[0010] S3: when the verification processing result meets the requirements, the conversion processing order of the other verification data sources is determined based on the analysis results of the data formats of the other verification data sources and the historical data volume of the associated transaction data;

[0011] S4 performs conversion processing of other verification data sources and verification processing of transaction data in accordance with the conversion processing sequence until the verification processing result is abnormal or the verification processing of the verification data source is completed, and then uses the AI ​​model to automatically process the accounting entries of the transaction data of different data sources.

[0012] The beneficial effects of the present invention are:

[0013] The conversion processing order of other verification data sources is determined based on the analysis results of the data formats of other verification data sources and the historical data volume of related transaction data, thereby taking into account the differences in the difficulty of converting data formats due to differences in data formats of other verification data sources, as well as the differences in the verification processing requirements of related transaction data due to differences in the historical data volume of related transaction data of other verification data sources, thereby realizing the determination of the conversion processing order from multiple angles, which not only improves the conversion efficiency but also meets the verification processing requirements of related transaction data.

[0014] The use of AI models to automatically process account entries of transaction data from different data sources avoids the technical problem of low efficiency of account entry processing caused by the original manual processing method, improves the efficiency of account entry processing, and at the same time, the use of AI models also ensures the reliability and accuracy of account entry processing of transaction data from data sources.

[0015] A further technical solution is that the associated transaction data of the verification data source is determined based on the transaction data that can be verified by the verification data source.

[0016] A further technical solution is that the historical data volume of the associated transaction data includes the number of verification processing times of the associated transaction data and the verification processing data volume of different verification processing times.

[0017] A further technical solution is that the method for determining the real-time format conversion data source of the verification data source is:

[0018] Determining the quantity of the associated transaction data based on the associated transaction data of the verification data source of the account data;

[0019] Determine the number of verification processing times of the associated transaction data according to the historical data volume of the associated transaction data, and determine the total number of verification processing times in combination with the volume of the associated transaction data;

[0020] Based on the total number of verification processes, it is determined whether the verification data source is a real-time format conversion data source.

[0021] A further technical solution is that, when the total number of verification processes is greater than a preset number threshold, it is determined that the verification data source is a real-time format conversion data source.

[0022] A further technical solution is to determine whether the verification result is abnormal, specifically including:

[0023] When the transaction data and the data associated with the verification data source are inconsistent, it is determined that there is an abnormality in the verification processing result.

[0024] A further technical solution is to use AI models to automatically process account entries of transaction data from different data sources, including:

[0025] Automatically identify the types of different data sources using AI models and determine the items of account entries corresponding to the data sources;

[0026] Automatic entry processing of different data sources is performed based on the items of account entries corresponding to the data sources.

[0027] In a second aspect, the present invention provides a computer system comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned artificial intelligence-based automated method for generating accounting entries when running the computer program.

[0028] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0029] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0031] Figure 1 It is a flowchart of an automated method for generating accounting entries based on artificial intelligence;

[0032] Figure 2 is a flow chart of a method for verifying a data source and converting a data source in real time format;

[0033] Figure 3 It is a flow chart to determine that the verification and processing difficulty of transaction data does not meet the requirements;

[0034] Figure 4 is a flow chart of a method for determining a conversion processing sequence of other verification data sources;

[0035] Figure 5 It is a framework diagram of a computer system. DETAILED DESCRIPTION

[0036] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0037] In response to the above technical problems, the present invention uses artificial intelligence technology to intelligently identify, understand and process various types of financial data of an enterprise, so as to automatically, accurately and efficiently generate accounting entries that comply with accounting standards. Specifically, the AI ​​model is used to automatically process accounting entries of transaction data from different data sources.

[0038] Based on the associated transaction data of the verification data source of the accounting data, the verification processing times of the associated transaction data are determined, and the total verification processing times are determined in combination with the number of associated transaction data. The verification data source whose total verification processing times is greater than the preset number threshold is used as the real-time format conversion data source.

[0039] The data source difficulty coefficient is determined based on the product of the preset weight coefficient corresponding to the number of other verification data sources in the associated verification data source and the proportion of the quantity. The verification processing difficulty of the transaction data is determined based on the product of the preset correction coefficient corresponding to the historical data volume of the transaction data and the data source difficulty coefficient. When the verification processing difficulty is less than 0.6, it is determined that the verification processing difficulty of the transaction data meets the requirements.

[0040] When there is no real-time format conversion data source with inconsistent data in the verification processing result of the transaction data, it is determined that the verification processing result meets the requirements.

[0041] Based on the analysis results of the data formats of other verification data sources, the preset processing difficulty corresponding to the data formats of other verification data sources is determined, and the conversion priority coefficients of other verification data sources are determined according to the ratio of the number of related transaction data to the preset number of transaction data and the product of the conversion processing difficulty. The conversion priority coefficients are used to determine the conversion processing order of other verification data sources from large to small.

[0042] Use AI models to automatically identify the types of different data sources, determine the accounting entry items corresponding to the data source, and perform automatic entry processing on different data sources based on the accounting entry items corresponding to the data source.

[0043] Embodiment 1 To solve the above problem, according to one aspect of the present invention, Figure 1 As shown, a first aspect is provided, and the present invention provides an automated method for generating account entries based on artificial intelligence, specifically comprising:

[0044] S1 obtains the associated transaction data of the verification data source of the accounting data, and determines the real-time format conversion data source of the verification data source in combination with the historical data volume of the associated transaction data;

[0045] Furthermore, the associated transaction data of the verification data source is determined based on the transaction data that can be verified by the verification data source.

[0046] Optionally, the historical data volume of the associated transaction data includes the number of verification processing times of the associated transaction data and the verification processing data volume of different verification processing times.

[0047] Specifically, Figure 2 As shown, the method for determining the real-time format conversion data source of the verification data source is:

[0048] Determining the quantity of the associated transaction data based on the associated transaction data of the verification data source of the account data;

[0049] Determine the number of verification processing times of the associated transaction data according to the historical data volume of the associated transaction data, and determine the total number of verification processing times in combination with the volume of the associated transaction data;

[0050] Based on the total number of verification processes, it is determined whether the verification data source is a real-time format conversion data source.

[0051] Further, when the total number of verification processes is greater than a preset number threshold, it is determined that the verification data source is a real-time format conversion data source.

[0052] S2: using the associated verification data source of the transaction data excluding the real-time format conversion data source as another verification data source, and determining that the verification processing difficulty of the transaction data does not meet the requirements according to the historical data volume of the transaction data, the associated verification data source, and the constituent data of the other verification data sources, using the associated verification data source of the transaction data excluding the real-time format conversion data source as another verification data source, and determining that the verification processing difficulty of the transaction data does not meet the requirements according to the historical data volume of the transaction data, the associated verification data source, and the constituent data of the other verification data sources, verifying the transaction data using the real-time format conversion data source to obtain a verification processing result;

[0053] Further, such as Figure 3 As shown, it is determined that the verification and processing difficulty of the transaction data does not meet the requirements, specifically including:

[0054] Determining the number of other data sources of the transaction data based on the constituent data of the associated verification data source and other verification data sources;

[0055] Determining a historical data volume threshold of the transaction data according to the number of other data sources of the transaction data;

[0056] According to the historical data volume of the transaction data and in combination with the historical data volume threshold of the transaction data, it is determined whether the difficulty of verifying and processing the transaction data meets the requirements.

[0057] Optionally, when the historical data volume of the transaction data is less than the historical data volume threshold, it is determined that the difficulty of verifying the transaction data meets the requirement.

[0058] In another embodiment, determining that the verification processing difficulty of the transaction data does not meet the requirement specifically includes:

[0059] Determine the number of verification data sources and the number of other data sources of the transaction data based on the constituent data of the associated verification data source and other verification data sources;

[0060] Determine the verification difficulty ratio coefficient of the transaction data according to the number of verification data sources and the number of other data sources;

[0061] Based on the historical data volume of the transaction data, determine the verification processing data volume of the transaction data, use the verification processing data volume and the verification difficulty ratio coefficient to determine the verification processing difficulty of the transaction data, and combine with the preset difficulty coefficient to determine whether the verification processing difficulty of the transaction data meets the requirements.

[0062] Furthermore, the verification difficulty proportional coefficient of the transaction data is determined according to the product of a preset proportional coefficient corresponding to the number of verification data sources and a preset proportional coefficient corresponding to the number of other data sources.

[0063] Specifically, when the difficulty of verifying the transaction data is less than a preset difficulty coefficient, it is determined that the difficulty of verifying the transaction data does not meet the requirements.

[0064] It should be noted that when the verification processing result of the transaction data meets the requirements, the verification processing of the transaction data is performed after the format of the verification data source of the transaction data is converted.

[0065] Optionally, determining that the verification processing difficulty of the transaction data does not meet the requirement specifically includes:

[0066] S11 determines the number of verification processing times of the transaction data and the verification processing data volume of different verification processing times according to the historical data volume of the transaction data, and determines the basic verification processing difficulty of the transaction data by using the verification processing times and the verification processing data volume of different verification processing times;

[0067] S12, determining the number of verification data sources and the number of other data sources of the transaction data based on the constituent data of the associated verification data source and other verification data sources, and determining the data source processing complexity coefficient of the transaction data based on the number of verification data sources and the number of other data sources of the transaction data;

[0068] S13 determines the difficulty of verifying and processing the transaction data based on the basic difficulty of verifying and processing the transaction data and the complexity coefficient of data source processing, and determines whether the difficulty of verifying and processing the transaction data meets the requirements in combination with a preset difficulty coefficient.

[0069] Optionally, the above step S11 includes the following contents:

[0070] S111 determines the verification processing times of the transaction data and the verification processing data amounts of different verification processing times according to the historical data amount of the transaction data, and determines the total amount of verification processing data according to the verification processing data amounts of different verification processing times. When the total amount of verification processing data does not meet the requirement, it is determined that the verification processing difficulty of the transaction data does not meet the requirement. When the total amount of verification processing data meets the requirement, the process proceeds to step S112;

[0071] S112 determines that when there is a verification processing number with a verification processing data amount greater than a preset verification data amount based on the verification processing data amount of different verification processing times, it is used as the screening processing number and the process goes to step S113. When there is no verification processing number with a verification processing data amount greater than the preset verification data amount, the process goes to step S114;

[0072] S113: When the number of screening processes is greater than the preset screening number threshold, it is determined that the verification processing difficulty of the transaction data does not meet the requirement; when the number of screening processes is not greater than the preset screening number threshold, the process proceeds to step S114;

[0073] S114 determines the basic verification processing difficulty of the transaction data using the verification processing times and the verification processing data volume of different verification processing times. When the basic verification processing difficulty of the transaction data does not meet the requirements, it is determined that the verification processing difficulty of the transaction data does not meet the requirements. When the basic verification processing difficulty of the transaction data meets the requirements, proceed to step S12.

[0074] Optionally, the above step S12 includes the following contents:

[0075] S121 obtains the basic verification processing difficulty of the transaction data. When the basic verification processing difficulty of the transaction data is within the preset difficulty range, the process proceeds to step S122. When the basic verification processing difficulty of the transaction data is not within the preset difficulty range, the process proceeds to step S123.

[0076] S122 determines the number of verification data sources and other data sources of the transaction data based on the constituent data of the associated verification data source and other verification data sources. When the number of other data sources is greater than a preset data source number threshold, it is determined that the verification processing difficulty of the transaction data does not meet the requirement. When the number of other data sources is not greater than the preset data source number threshold, the process proceeds to step S123.

[0077] S123 determines the data source processing complexity coefficient of the transaction data based on the number of verification data sources of the transaction data and the number of other data sources. When the data source processing complexity coefficient of the transaction data is greater than the preset complexity coefficient threshold, it is determined that the verification processing difficulty of the transaction data does not meet the requirements. When the data source processing complexity coefficient of the transaction data is not greater than the preset complexity coefficient threshold, proceed to step S13.

[0078] S3: when the verification processing result meets the requirements, the conversion processing order of the other verification data sources is determined based on the analysis results of the data formats of the other verification data sources and the historical data volume of the associated transaction data;

[0079] Further, when there is no real-time format conversion data source with inconsistent data in the verification processing result of the transaction data, it is determined that the verification processing result meets the requirements.

[0080] Specifically, Figure 4 As shown, the method for determining the conversion processing order of the other verification data sources is:

[0081] Determining the difficulty of converting the data format of the other verification data source based on the analysis result of the data format of the other verification data source;

[0082] Determining the amount of the associated transaction data according to the historical data amount of the associated transaction data;

[0083] Based on the amount of the associated transaction data and the difficulty of conversion processing, the conversion priority coefficients of the other verification data sources are determined, and the conversion processing order of the other verification data sources is determined using the conversion priority coefficients.

[0084] Furthermore, the difficulty of converting the data format of the other verification data source is determined according to a preset processing difficulty corresponding to the data format.

[0085] It should also be noted that the conversion priority coefficient is determined based on the product of the ratio of the number of associated transaction data to the number of preset transaction data and the difficulty of conversion processing.

[0086] Further, determining the conversion processing order of the other verification data sources by using the conversion priority coefficient specifically includes:

[0087] The conversion processing order of the other verification data sources is determined based on the conversion priority coefficients from large to small.

[0088] Optionally, the method for determining the conversion processing order of the other verification data sources is:

[0089] S41: determining the amount of associated transaction data of the other verification data sources according to the historical data amount of the associated transaction data, and determining the verification requirement coefficient of the other verification data sources in combination with the historical data amounts of different associated transaction data;

[0090] Optionally, the above step S41 includes the following contents:

[0091] S411 determines the quantity of the associated transaction data of the other verification data sources according to the historical data volume of the associated transaction data, and when the quantity of the associated transaction data of the other verification data sources is within the preset transaction data quantity interval, proceeds to step S412; when the quantity of the associated transaction data of the other verification data sources is not within the preset transaction data quantity interval, proceeds to step S413;

[0092] S412: based on the historical data volume of the associated transaction data, determine the total historical data volume of the associated transaction data of the other verification data sources; when the total historical data volume is greater than the preset data volume threshold, set the verification processing priority of the other verification data sources to the first level, and use the total historical data volume of the associated transaction data of the other verification data sources to determine the conversion processing order of the other verification data sources; when the total historical data volume is not greater than the preset data volume threshold, proceed to step S413;

[0093] S413 determines the verification requirement coefficient of the other verification data source according to the number of associated transaction data of the other verification data source and the historical data volume of different associated transaction data. When the verification requirement coefficient of the other verification data source is greater than the preset requirement coefficient threshold, the verification processing priority of the other verification data source is set to the second level, and the conversion processing order of the other verification data source is determined by using the verification requirement coefficient of the other verification data source. When the verification requirement coefficient of the other verification data source is not greater than the preset requirement coefficient threshold, proceed to step S42.

[0094] S42: determining the difficulty of converting the data format of the other verification data source based on the analysis result of the data format of the other verification data source, and determining the conversion difficulty coefficient of the other verification data source in combination with the data volume of the other verification data source;

[0095] Optionally, the above step S42 includes the following contents:

[0096] S421 determines the difficulty of conversion processing of the data format of the other verification data source based on the analysis result of the data format of the other verification data source, and determines the conversion difficulty coefficient of the other verification data source in combination with the data volume of the other verification data source. When the conversion difficulty coefficient of the other verification data source is less than the preset conversion difficulty coefficient threshold, proceed to step S422; when the conversion difficulty coefficient of the other verification data source is not less than the preset conversion difficulty coefficient threshold, proceed to step S43;

[0097] S422 When the verification requirement coefficient of the other verification data source is within the preset requirement coefficient range, the verification processing priority of the other verification data source is set to the third level, and the conversion processing order of the other verification data source is determined using the conversion difficulty coefficient of the other verification data source. When the verification requirement coefficient of the other verification data source is not within the preset requirement coefficient range, proceed to step S43.

[0098] S43: Based on the verification requirement coefficient and the conversion difficulty coefficient of the other verification data source, the conversion priority coefficient of the other verification data source is determined, and the conversion processing order of the other verification data source is determined by using the conversion priority coefficient.

[0099] S4 performs conversion processing of other verification data sources and verification processing of transaction data in accordance with the conversion processing sequence until the verification processing result is abnormal or the verification processing of the verification data source is completed, and then uses the AI ​​model to automatically process the accounting entries of the transaction data of different data sources.

[0100] Further, determining that the verification processing result is abnormal includes:

[0101] When the transaction data and the data associated with the verification data source are inconsistent, it is determined that there is an abnormality in the verification processing result.

[0102] Optionally, AI models can be used to automatically process transaction data from different data sources, including:

[0103] Automatically identify the types of different data sources using AI models and determine the items of account entries corresponding to the data sources;

[0104] Automatic entry processing of different data sources is performed based on the items of account entries corresponding to the data sources.

[0105] Embodiment 2 In the second aspect, as Figure 5 As shown, the present invention provides a computer system, comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned artificial intelligence-based automated accounting entry generation method when running the computer program.

[0106] Optionally, the method for determining the real-time format conversion data source of the verification data source is:

[0107] Determining the quantity of the associated transaction data based on the associated transaction data of the verification data source of the account data, and determining that the verification data source is a real-time format conversion data source when the quantity of the associated transaction data is greater than a preset quantity threshold;

[0108] When the amount of the associated transaction data is not greater than the preset amount threshold:

[0109] Determining the number of verification processing times of the associated transaction data according to the historical data volume of the associated transaction data, determining the total number of verification processing times using the number of verification processing times of the associated transaction data, and determining that the verification data source is a real-time format conversion data source when the total number of verification processing times is greater than a preset number threshold;

[0110] When the total number of verification processes is not greater than the preset number threshold:

[0111] Determine the filtered transaction data in the verification data source by using the verification processing times of the associated transaction data, and when the amount of the filtered transaction data is greater than a preset transaction amount threshold, determine that the verification data source is a real-time format conversion data source;

[0112] When the amount of the filtered transaction data is not greater than the preset transaction amount threshold:

[0113] Determine the verification requirement coefficients of different associated transaction data according to different verification processing times of associated transaction data and different verification processing data volumes of verification processing times; when there is no associated transaction data whose verification requirement coefficient is greater than a preset requirement coefficient threshold, obtain the number of associated transaction data; when the number of associated transaction data is within a preset number range, determine that the verification data source does not belong to the real-time format conversion data source;

[0114] When there is related transaction data whose verification demand coefficient is greater than the preset demand coefficient threshold or the number of related transaction data is not within the preset quantity range:

[0115] The associated transaction data whose verification demand coefficient is greater than a preset demand coefficient threshold is used as verification transaction data, and when the quantity of the verification transaction data is greater than a preset verification quantity threshold: determining that the verification data source belongs to a real-time format conversion data source;

[0116] When the amount of verified transaction data is not greater than the preset verification amount threshold:

[0117] A demand coefficient evaluation amount is determined based on the verification demand coefficients of different associated transaction data, and the demand coefficient evaluation amount is used to determine whether the verification data source is a real-time format conversion data source.

[0118] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0119] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0120] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. An automated method for generating accounting entries based on artificial intelligence, characterized in that: Specifically include: Acquire the associated transaction data of the verification data source of the accounting data, and determine the real-time format conversion data source of the verification data source in combination with the historical data volume of the associated transaction data; The associated verification data source of the transaction data excluding the real-time format conversion data source is used as another verification data source, and when it is determined that the verification processing difficulty of the transaction data does not meet the requirements according to the historical data volume of the transaction data, the associated verification data source and the constituent data of the other verification data sources, the real-time format conversion data source is used to verify the transaction data to obtain a verification processing result; When the verification processing result meets the requirements, the conversion processing order of the other verification data sources is determined based on the analysis results of the data formats of the other verification data sources and the historical data volume of the associated transaction data; Perform conversion processing of other verification data sources and verification processing of transaction data in accordance with the conversion processing sequence until there is an abnormality in the verification processing result or the verification processing of the verification data source is completed, and then use the AI ​​model to automatically process the account entries of transaction data from different data sources; The method for determining the real-time format conversion data source of the verification data source is: Determining the quantity of the associated transaction data based on the associated transaction data of the verification data source of the account data; Determine the number of verification processing times of the associated transaction data according to the historical data volume of the associated transaction data, and determine the total number of verification processing times in combination with the volume of the associated transaction data; Determining whether the verification data source is a real-time format conversion data source based on the total number of verification processes; Determining that the verification and processing difficulty of the transaction data does not meet the requirements, specifically including: Determining the number of other verification data sources for the transaction data based on the constituent data of the associated verification data source and other verification data sources; Determining a historical data volume threshold of the transaction data according to the number of other verification data sources of the transaction data; Determining whether the verification and processing difficulty of the transaction data meets the requirements based on the historical data volume of the transaction data and in combination with the historical data volume threshold of the transaction data; The method for determining the conversion processing order of the other verification data sources is: Determining the difficulty of converting the data format of the other verification data source based on the analysis result of the data format of the other verification data source; Determining the amount of the associated transaction data according to the historical data amount of the associated transaction data; Based on the amount of the associated transaction data and the difficulty of conversion processing, the conversion priority coefficients of the other verification data sources are determined, and the conversion processing order of the other verification data sources is determined using the conversion priority coefficients.

2. The method for generating automated accounting entries based on artificial intelligence according to claim 1, characterized in that: The associated transaction data of the verification data source is determined based on the transaction data that can be verified by the verification data source.

3. The method for generating automated accounting entries based on artificial intelligence according to claim 1, characterized in that: The historical data volume of the associated transaction data includes the number of verification processing times of the associated transaction data and the verification processing data volume of different verification processing times.

4. The method for automating the generation of accounting entries based on artificial intelligence according to claim 1, characterized in that: When the total number of verification processes is greater than a preset number threshold, it is determined that the verification data source is a real-time format conversion data source.

5. The method for generating automated accounting entries based on artificial intelligence according to claim 1, characterized in that: When there is no real-time format conversion data source with inconsistent data in the verification processing result of the transaction data, it is determined that the verification processing result meets the requirements.

6. The method for automating the generation of accounting entries based on artificial intelligence according to claim 1, characterized in that: The difficulty of converting the data format of the other verification data source is determined according to the preset processing difficulty corresponding to the data format.

7. The method for automating the generation of accounting entries based on artificial intelligence according to claim 1, characterized in that: AI models are used to automatically process account entries of transaction data from different data sources, including: Automatically identify the types of different data sources using AI models and determine the items of account entries corresponding to the data sources; Automatic entry processing of different data sources is performed based on the items of account entries corresponding to the data sources.

8. A computer system comprising: A memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, characterized in that when the processor runs the computer program, an artificial intelligence-based automated accounting entry generation method as described in any one of claims 1 to 7 is executed.

Images