CN113297846A - Account checking processing method and device - Google Patents

Abstract

The application provides a reconciliation processing method and a device, wherein the method comprises the following steps: acquiring the bank account checking data and the remark information in the enterprise account checking data within a preset time period; according to the bank reconciliation data and the remark information in the enterprise reconciliation data, determining first reconciliation data in the bank reconciliation data and second reconciliation data in the enterprise reconciliation data corresponding to the first reconciliation data, wherein the similarity between the remark information of the first reconciliation data and the remark information of the second reconciliation data meets a preset threshold value; and matching according to the first reconciliation data and the corresponding second reconciliation data to obtain a matching result. Based on the method, the bank can simultaneously acquire the account checking data of the bank and the account checking data of the enterprise in real time, and screen the account checking data to realize account checking processing, so that the efficiency of the account checking processing can be improved.

Description

Reconciliation processing method and device

technical field

The present application relates to the field of Internet technologies, and in particular, to a method and device for reconciliation processing.

Background technique

Strengthening the accounting check between banks and enterprises is a requirement of the People's Bank of China for commercial banks, which helps banks to detect financial risks of enterprises in a timely manner, and then notify relevant enterprises as soon as possible, so that they can take corresponding prevention and control measures; on the other hand , For enterprises, grasping the status of their own accounts in a timely manner is also helpful for the operation, management and safety prevention and control of enterprises.

In the prior art, the financial system of the bank and the financial system of the enterprise carry out bookkeeping according to their own methods. When performing reconciliation processing, the financial system of the bank generates a balance statement at a certain frequency (monthly, quarterly, etc.). The account balance at each time point), send the statement to the enterprise financial system, and the enterprise will check it. After the enterprise check is completed, the reconciliation result will be fed back to the bank's financial system, and the bank's financial system will record the reconciliation result.

In the above scheme, due to the differences in the accounting methods of the enterprise financial system and the bank financial system, it is difficult to match the accounts recorded in the enterprise financial system and the bank financial system one-to-one, resulting in a technology with low efficiency in reconciliation processing. question.

SUMMARY OF THE INVENTION

The present application provides an account reconciliation processing method and device, which are used to solve the technical problem of low efficiency of account reconciliation processing in the prior art.

In a first aspect, an embodiment of the present application provides a reconciliation processing method, including: acquiring remark information in bank reconciliation data and enterprise reconciliation data within a preset time period; Remark information in the reconciliation data, determine the first reconciliation data in the bank reconciliation data and the second reconciliation data in the corresponding enterprise reconciliation data, the first reconciliation data and the second reconciliation data The similarity between the remarks information meets a preset threshold; and according to the first reconciliation data and its corresponding second reconciliation data, a matching process is performed to obtain a matching result.

Optionally, in the above method, the first reconciliation data in the bank reconciliation data and the corresponding enterprise reconciliation are determined according to the bank reconciliation data and the remark information in the enterprise reconciliation data. The second reconciliation data in the data includes: extracting keywords of remark information in each piece of bank reconciliation data and enterprise reconciliation data; The first reconciliation data and the corresponding second reconciliation data, wherein the semantic similarity between the keywords of the remark information in the first reconciliation data and the second reconciliation data satisfies a preset threshold.

Optionally, in the method described above, determining the first reconciliation data and the corresponding second reconciliation data according to the keywords corresponding to each piece of bank reconciliation data and enterprise reconciliation data, including: : Convert the keywords corresponding to each bank reconciliation data and enterprise reconciliation data into word vectors; by calculating the angle between the word vector corresponding to each bank reconciliation data and the word vector corresponding to each enterprise reconciliation data , obtain the semantic similarity between the keywords corresponding to each piece of bank reconciliation data and the keywords corresponding to each piece of enterprise reconciliation data; determine the first reconciliation data and its corresponding second reconciliation data, Wherein, the semantic similarity between the keywords corresponding to the first reconciliation data and the second reconciliation data satisfies a preset threshold.

Optionally, in the above-mentioned method, the extracting the keywords of the remarks information in each piece of bank reconciliation data and the enterprise reconciliation data includes: performing remarks on each piece of bank reconciliation data and the remarks information in the enterprise reconciliation data. Word segmentation processing, to obtain the word segmentation corresponding to the bank reconciliation data and the enterprise reconciliation data, and the word segmentation carries a part-of-speech tag; according to the stop thesaurus, remove the stop words in the word segmentation corresponding to each bank reconciliation data and the enterprise reconciliation data. Words: According to the word segmentation corresponding to each current bank reconciliation data and enterprise reconciliation data, and based on the TextRank algorithm, the keywords of the remark information in each bank reconciliation data and enterprise reconciliation data are obtained.

Optionally, in the above method, the first reconciliation data and/or the second reconciliation data respectively include multiple pieces of reconciliation data, wherein the reconciliation data includes amount data and loan direction information , then performing matching processing according to the first reconciliation data and its corresponding second reconciliation data to obtain a matching result includes: calculating the first pair according to the amount data and the loan direction information respectively. The sum of income and expenditure corresponding to the account data and the sum of income and expenditure corresponding to the second reconciliation data, the sum of income and expenditure includes the sum of income and the sum of expenditure; If it is equal to the total expenditure of the enterprise, it is determined that the matching is successful; otherwise, it is determined that the matching fails.

Optionally, in the method described above, after acquiring the remark information in the bank reconciliation data and the enterprise reconciliation data within a preset time period, the method further includes: filtering the bank reconciliation data and the enterprise reconciliation data. Invalid reconciliation data is deleted, wherein the invalid reconciliation data is reconciliation data corresponding to a scenario where no balance change occurs.

Optionally, in the above method, the method further includes: if the matching result is that the matching fails, pushing the first reconciliation data and the corresponding second reconciliation data to the user.

In a second aspect, the embodiments of the present application provide an account reconciliation processing device, including: an acquisition module for acquiring remark information in bank reconciliation data and enterprise reconciliation data within a preset time period; a determination module for The bank reconciliation data and the remarks in the enterprise reconciliation data are determined, and the first reconciliation data in the bank reconciliation data and the second reconciliation data in the corresponding enterprise reconciliation data are determined. The similarity between the remark information of the account data and the second account reconciliation data meets a preset threshold; the matching module is configured to perform matching processing according to the first account reconciliation data and its corresponding second account reconciliation data , get matching results.

In a third aspect, an embodiment of the present application provides an electronic device, including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the reconciliation processing method according to the first aspect .

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, are used to implement the method described in the first aspect reconciliation processing method.

In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which implements the account reconciliation processing method described in the first aspect when the computer program is executed by a processor.

The reconciliation processing method and device provided by the embodiments of the present application, by acquiring the remark information in the bank reconciliation data and the enterprise reconciliation data, and determining the first reconciliation data and the second reconciliation data according to the remark information. The reconciliation data and the second reconciliation data are matched to obtain a matching result. Based on this method, the bank can simultaneously acquire bank reconciliation data and enterprise reconciliation data in real time, and filter out the reconciliation data to realize reconciliation processing, so the efficiency of reconciliation processing can be improved.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description serve to explain the principles of the application.

1 is a schematic diagram of an application scenario provided by the present application;

FIG. 2 is a schematic flowchart of an account reconciliation processing method provided by an embodiment of the present application;

Fig. 3 is a schematic diagram of many-to-many detailed matching;

4 is a schematic diagram of one-to-one detailed matching;

Fig. 5 is a natural language processing process diagram;

6 is a schematic structural diagram of an account reconciliation processing device provided in Embodiment 3 of the present application;

FIG. 7 is a schematic structural diagram of an electronic device according to Embodiment 4 of the present application.

Specific embodiments of the present application have been shown by the above-mentioned drawings, and will be described in more detail hereinafter. These drawings and written descriptions are not intended to limit the scope of the concepts of the present application in any way, but to illustrate the concepts of the present application to those skilled in the art by referring to specific embodiments.

Detailed ways

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as recited in the appended claims.

First, the terms involved in this application are explained:

Reconciliation: that is, reconciling the accounts, which refers to the work of checking and verifying the relevant data in the account books in order to ensure the correctness and reliability of the records in the account books;

Natural language processing: refers to an important direction in the field of computer science and artificial intelligence, which studies various theories and methods that can realize effective communication between humans and computers using natural language;

Participle: refers to dividing a sentence into separate words according to the meaning of the sentence;

Stop words: are words that are useless or meaningless, they do not contribute much to the subject of the text, such as auxiliary verbs, modal particles, etc.;

Keyword extraction: refers to extracting representative words from text.

Strengthening the accounting check between banks and enterprises is a requirement of the People's Bank of China for commercial banks, which helps banks to detect financial risks of enterprises in a timely manner, and then notify relevant enterprises as soon as possible, so that they can take corresponding prevention and control measures; on the other hand , For enterprises, grasping the status of their own accounts in a timely manner is also helpful for the operation, management and safety prevention and control of enterprises.

FIG. 1 is a schematic diagram of an application scenario provided for this application, which includes an enterprise financial system 1 and a bank financial system 2. Exemplarily, every time an enterprise generates an account, the enterprise financial system 1 sends the account to the bank financial system 2 information, and then, the bank financial system 2 and the enterprise financial system 1 respectively record the account in their own way. In the prior art, the account reconciliation processing method includes: when a preset time point is reached, the bank financial system generates a customer statement, and distributes the customer statement to the enterprise financial system through channels such as SMS and WeChat, and the enterprise Relevant responsible personnel conduct reconciliation, specifically: compare the amount and balance in the accounts recorded in the enterprise financial system with the amount and balance in the accounts recorded in the corresponding bank financial system. If the elements are consistent, the account is determined to be correct; otherwise, the account is determined to be incorrect and recorded separately. After the company completes the reconciliation, the reconciliation result will be fed back to the bank. If the reconciliation result fed back is incorrect, the bank will communicate with the company to verify the incorrect account; if the feedback reconciliation result is correct, the reconciliation will be conducted Results are recorded to complete the reconciliation process.

However, due to the differences in the accounting methods of the enterprise financial system and the bank financial system, it is difficult to match the accounts recorded in the enterprise financial system and the bank financial system one-to-one, resulting in a technical problem of low efficiency in reconciliation processing.

The account reconciliation processing method and device provided by the present application aim to solve the above technical problems in the prior art.

The technical solutions of the present application and how the technical solutions of the present application solve the above-mentioned technical problems will be described in detail below with specific examples. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

Example 1

FIG. 2 is a schematic flowchart of an account reconciliation processing method provided by an embodiment of the present application. As shown in Figure 2, the method includes:

S101. Acquire remark information in bank reconciliation data and enterprise reconciliation data within a preset time period.

Among them, the remark information is used to indicate the whereabouts of the balance in the reconciliation data.

In practical applications, the financial system of the bank and the financial system of the enterprise conduct bookkeeping according to their own methods. For a piece of reconciliation data in the financial system of the bank, the enterprise can record it into multiple pieces of reconciliation data as needed, so it may be The reconciliation data of the bank's financial system and the reconciliation data of the enterprise's financial system are many-to-many (including one-to-many). In one example, there is one piece of reconciliation data in the bank's financial system, and there are multiple pieces of reconciliation data in the corresponding enterprise financial system, that is, the sum of the amount of the reconciliation data in the enterprise's financial system and the bank's financial system The balances in one of the reconciliation data are equal. Therefore, in this embodiment, it is necessary to acquire multiple pieces of reconciliation data within a preset time period, and then perform reconciliation processing. Among them, the amount incurred includes the amount of income and the amount of expenses.

In this embodiment, the bank reconciliation data and the enterprise reconciliation data within a preset time period are respectively obtained from the bank financial system and the enterprise financial system by the reconciliation processing device, and then the remark information in each reconciliation data is obtained for the purpose of Use in subsequent steps.

In practical applications, after obtaining the remark information in the bank reconciliation data and the enterprise reconciliation data within a preset time period, the reconciliation data will also be filtered. After the remark information in the bank reconciliation data and the enterprise reconciliation data, the method further includes: filtering out invalid reconciliation data from the bank reconciliation data and the enterprise reconciliation data, wherein the invalid reconciliation data is an invalid reconciliation data. Reconciliation data corresponding to scenarios that generate balance changes. For example, in one scenario, the enterprise financial system records an erroneous reconciliation data during the accounting process, and the erroneous reconciliation data is invalid reconciliation data. In this embodiment, by filtering invalid reconciliation data, the workload of subsequent steps can be reduced, thereby improving the efficiency of reconciliation processing.

S102. Determine the first reconciliation data in the bank reconciliation data and the second reconciliation data in the corresponding enterprise reconciliation data according to the bank reconciliation data and the remark information in the enterprise reconciliation data, and The similarity between the remark information of the first reconciliation data and the second reconciliation data satisfies a preset threshold.

The first reconciliation data and the second reconciliation data have a corresponding relationship, that is, the objects of reconciliation processing are the first reconciliation data and the second reconciliation data. Wherein, the preset threshold is determined according to empirical data, and its size may be 0.6.

In this embodiment, the first reconciliation data and the second reconciliation data may be determined according to the similarity between the bank reconciliation data and the remark information in the enterprise reconciliation data. Specifically, in an example, for a set of data, a natural language processing model can be used to obtain the similarity between the bank reconciliation data and the remark information in the enterprise reconciliation data, when the value of the similarity is greater than or equal to a preset value When the threshold is reached, the group of reconciliation data is determined as the first reconciliation data and the second reconciliation data respectively; otherwise, the group of data is filtered out, that is, they will not be reconciled subsequently; The method determines the similarity between the bank reconciliation data and the enterprise reconciliation data, which is not limited in this embodiment.

S103. Perform matching processing according to the first reconciliation data and the corresponding second reconciliation data to obtain a matching result.

Among them, the matching processing refers to the reconciliation processing.

In one example, the matching process may be performed according to the amount data and the loan direction information. Specifically, the first reconciliation data and/or the second reconciliation data respectively include multiple pieces of reconciliation data, for example, as shown in FIG. 3 . As shown, it is a schematic diagram of many-to-many detail matching. The enterprise-side detail and the bank-side detail are the first reconciliation data and the second reconciliation data, respectively. The number of details contained in the two is different, which is a many-to-many relationship. Wherein, the reconciliation data includes amount data and loan direction information, and performing matching processing according to the first reconciliation data and the corresponding second reconciliation data to obtain a matching result includes: according to the Occurrence data and loan direction information, respectively calculate the sum of income and expenditure corresponding to the first reconciliation data and the sum of income and expenditure corresponding to the second reconciliation data, and the sum of income and expenditure includes the sum of income and the sum of expenditure; if the bank The sum of the income of the bank is equal to the sum of the expenditure of the enterprise, and the sum of the income of the bank is equal to the sum of the expenditure of the enterprise, then it is determined that the matching is successful; otherwise, it is determined that the matching fails. In this example, a method for reconciliation processing in the case where the reconciliation data of the bank financial system and the reconciliation data of the enterprise financial system are many-to-many (including one-to-many or many-to-one) is given. The sum of the income of the bank and the sum of the income of the enterprise and the sum of the sum of the expenditure of the bank and the sum of the expenditure of the enterprise within a preset time period is used to determine whether the accounts are wrong.

In another example, as shown in Figure 4, it is a schematic diagram of one-to-one detail matching, the enterprise-side detail and the bank-side detail are the first reconciliation data and the second reconciliation data, respectively, and both contain the same number of details and are One-to-one correspondence. In the case where the reconciliation data of the bank's financial system and the reconciliation data of the enterprise's financial system are one-to-one, matching processing can be performed according to the amount data and/or the balance data. Specifically, if the amount data and/or balance data in the first reconciliation data and the second reconciliation data are consistent, it is determined that the matching is successful; otherwise, it is determined that the matching fails.

In this embodiment, by matching the reconciliation data within a preset time period, the accuracy of the reconciliation process can be improved.

Based on the above embodiment, the method further includes: if the matching result is that the matching fails, pushing the first reconciliation data and the corresponding second reconciliation data to the user. In this embodiment, by sending the corresponding data to the enterprise after the matching fails, it can support the enterprise to continue to perform account reconciliation processing based on the data in the future, find the data in question in time, and take corresponding measures.

In this embodiment, the remark information in the bank reconciliation data and the enterprise reconciliation data is obtained, the first reconciliation data and the second reconciliation data are determined according to the remark information, and the first reconciliation data and the second reconciliation data are determined. The data is subjected to matching processing to obtain matching results. Based on this method, the bank can simultaneously acquire bank reconciliation data and enterprise reconciliation data in real time, and filter out the reconciliation data to realize reconciliation processing, so the efficiency of reconciliation processing can be improved.

Embodiment 2

The second embodiment of the present application provides an account reconciliation processing method, which mainly relates to an acquisition method of the first account reconciliation data and the second account reconciliation data. Specific examples are as follows:

In one example, the reconciliation data can be determined according to the keywords in the remarks information in the reconciliation data. Specifically, on the basis of Embodiment 1, the reconciliation data is based on the bank reconciliation data and the enterprise reconciliation data. Remark information in the bank reconciliation data, determine the first reconciliation data in the bank reconciliation data and the second reconciliation data in the corresponding enterprise reconciliation data, including: extracting each piece of bank reconciliation data and remark information in the enterprise reconciliation data according to the keywords corresponding to each bank reconciliation data and enterprise reconciliation data, determine the first reconciliation data and the corresponding second reconciliation data, wherein the first reconciliation data The semantic similarity with the keywords of the remark information in the second reconciliation data satisfies a preset threshold.

In practical applications, for example, the similarity between the remarks information introduced in the above embodiment 1 is the semantic similarity between the keywords of the remarks information. Correspondingly, the natural language processing model is also used to obtain the similarity between the keywords. semantic similarity.

Wherein, extracting the keywords of remark information in each piece of bank reconciliation data and enterprise reconciliation data may include various methods. For example, TextRank algorithm can be used to extract. Keywords for remark information in account data, including: performing word segmentation on each piece of bank reconciliation data and remark information in enterprise reconciliation data to obtain word segments corresponding to bank reconciliation data and enterprise reconciliation data, and the word segments carry part of speech Labeling; according to the stop word database, remove the stop words in the word segmentation corresponding to each bank reconciliation data and enterprise reconciliation data; according to the word segmentation corresponding to each current bank reconciliation data and enterprise reconciliation data, based on TextRank Algorithm to obtain the keywords of the remarks in each bank reconciliation data and enterprise reconciliation data. In an example, the process of extracting keywords is roughly as follows: the first step is to perform word segmentation processing on the original text. Optionally, the word segmentation processing includes: for a piece of remark information, firstly divide it into individual sentences, and then divide it into individual sentences. Each sentence is divided into words (that is, word segmentation), and then the words obtained by segmentation are marked with parts of speech; in the next step, stop words in the words obtained by segmentation are removed; The weight of each word is sorted, and the obtained weight is sorted from large to small, and the top N words with high weight are selected as keywords. Among them, the value of N is not limited. It should be noted that other methods may also be used to extract keywords, and the method for extracting keywords is not limited in this embodiment.

When determining the first reconciliation data and the second reconciliation data according to the keywords corresponding to the reconciliation data, various methods may be included. In an example, a set of reconciliation data includes a bank reconciliation data and an enterprise reconciliation data Reconciliation data, if both of the two reconciliation data include a keyword, the natural language processing model is used to obtain the semantic similarity between the two keywords, if the value of the semantic similarity is greater than or equal to a preset threshold When the set of reconciliation data is determined as the first reconciliation data and the second reconciliation data, respectively; otherwise, the set of reconciliation data is filtered out, that is, the reconciliation processing will not be performed on them in the future; Other methods determine the similarity between bank reconciliation data and enterprise reconciliation data, which is not limited in this embodiment. In this embodiment, the first reconciliation data and the second reconciliation data are determined according to the semantic similarity between the keywords of the remark information in the reconciliation data, which can improve the screening accuracy of the reconciliation data, thereby improving the efficiency of reconciliation processing. efficiency.

In practical applications, there are various ways to obtain the semantic similarity between keywords. Determining the first reconciliation data and the corresponding second reconciliation data includes: converting keywords corresponding to each bank reconciliation data and enterprise reconciliation data into word vectors; calculating each bank reconciliation The angle between the word vector corresponding to the data and the word vector corresponding to each enterprise reconciliation data, to obtain the semantic similarity between the keywords corresponding to each bank reconciliation data and the keywords corresponding to each enterprise reconciliation data ; Determine the first reconciliation data and its corresponding second reconciliation data, wherein the semantic similarity between the keywords corresponding to the first reconciliation data and the second reconciliation data satisfies the predetermined set threshold.

The word vector is a method for representing keywords. In this embodiment, the semantic similarity is calculated based on the word vector. Therefore, in this embodiment, the keyword is first converted into a word vector, and then the keyword is calculated. semantic similarity between them. It should be noted that the open-source word vector computing tool Word2vec may be used to convert keywords into word vectors, or other tools may be used for processing, which is not limited in this embodiment. In an example, as shown in FIG. 5 , which is a natural language processing process diagram, the process of S102 is roughly as follows: first, keywords are extracted through text preprocessing, and then word vector calculation is performed on the extracted keywords. The keywords are converted into word vectors; finally, the semantic similarity calculation is performed on the word vectors, and the first reconciliation data and the second reconciliation data are obtained according to the semantic similarity calculation results.

In this embodiment, the keywords are first converted into word vectors, and then the semantic similarity between the keywords is calculated, which can make the calculation result of the semantic similarity more accurate, thereby improving the efficiency of account reconciliation processing.

In this embodiment, by determining the first reconciliation data and the second reconciliation data according to the keywords in the remark information in the reconciliation data, the accuracy of screening the reconciliation data can be improved, thereby improving the efficiency of reconciliation processing.

Embodiment 3

FIG. 6 is a schematic structural diagram of an account reconciliation processing apparatus provided in Embodiment 3 of the present application. As shown in FIG. 6 , the account reconciliation processing apparatus provided in this embodiment includes an acquisition module 21 , a determination module 22 and a matching module 23 .

Wherein, the obtaining module 21 is configured to obtain the remark information in the bank reconciliation data and the enterprise reconciliation data within a preset time period. The determining module 22 is configured to determine the first reconciliation data in the bank reconciliation data and the second pair in the corresponding enterprise reconciliation data according to the bank reconciliation data and the remark information in the enterprise reconciliation data Account data, the similarity between the remark information of the first account reconciliation data and the second account reconciliation data satisfies a preset threshold. The matching module 23 is configured to perform matching processing according to the first reconciliation data and its corresponding second reconciliation data to obtain a matching result.

Optionally, the determination module 22 is specifically configured to: extract the keywords of the remark information in each piece of bank reconciliation data and the enterprise reconciliation data; The first reconciliation data and the corresponding second reconciliation data, wherein the semantic similarity between the keywords of the remark information in the first reconciliation data and the second reconciliation data satisfies a preset the threshold value.

Optionally, the determination module 22 is also specifically used to: convert the keywords corresponding to each piece of bank reconciliation data and enterprise reconciliation data into word vectors; The angle between the word vectors corresponding to the reconciliation data, to obtain the semantic similarity between the keywords corresponding to each bank reconciliation data and the keywords corresponding to each enterprise reconciliation data; determine the first reconciliation data and the corresponding second reconciliation data, wherein the semantic similarity between the keywords corresponding to the first reconciliation data and the second reconciliation data satisfies a preset threshold.

Optionally, the determination module 22 is also specifically configured to: perform word segmentation processing on each piece of bank reconciliation data and remark information in the enterprise reconciliation data, and obtain the word segmentation corresponding to the bank reconciliation data and the enterprise reconciliation data, the word segmentation. Carry part-of-speech tagging; according to the stop word database, remove the stop words in the word segmentation corresponding to each bank reconciliation data and enterprise reconciliation data; according to the current word segmentation corresponding to each bank reconciliation data and enterprise reconciliation data, Based on the TextRank algorithm, the keywords of the remarks in each bank reconciliation data and enterprise reconciliation data are obtained.

Optionally, the first reconciliation data and/or the second reconciliation data respectively include multiple pieces of reconciliation data, wherein the reconciliation data includes amount data and loan direction information, the The first reconciliation data and its corresponding second reconciliation data are matched, and a matching result is obtained. The matching module 23 is specifically configured to: calculate the first pair according to the amount data and the loan direction information respectively. The sum of income and expenditure corresponding to the account data and the sum of income and expenditure corresponding to the second reconciliation data, the sum of income and expenditure includes the sum of income and the sum of expenditure; If it is equal to the total expenditure of the enterprise, it is determined that the matching is successful; otherwise, it is determined that the matching fails.

Optionally, the above-mentioned apparatus further includes: a filtering module 24 . The filtering module 24 is specifically configured to: filter out invalid reconciliation data from the bank reconciliation data and the enterprise reconciliation data, wherein the invalid reconciliation data is the pair corresponding to the scenario where no balance change occurs. account data.

Optionally, the above apparatus further includes: a sending module 25 . The sending module 25 is specifically configured to: if the matching result is that the matching fails, push the first reconciliation data and the corresponding second reconciliation data to the user.

The account reconciliation processing apparatus provided in this embodiment can execute the technical solutions of the first and second embodiments of the foregoing method, and the implementation principles and technical effects thereof are similar, and details are not repeated here.

Embodiment 4

FIG. 7 is a schematic structural diagram of an electronic device according to Embodiment 4 of the present application. As shown in FIG. 7 , the electronic device includes: a memory 31 and a processor 32 .

Memory 31 is configured to store processor-executable instructions. Memory 31 may be implemented by any type of volatile or non-volatile storage device or combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic or Optical Disk.

The memory 31 and the processor 32 are interconnected by circuits. Specifically, the various components are interconnected using a bus, and may be mounted on a common motherboard or in other ways as desired. The processor may process instructions executed within the electronic device.

Embodiment 5

The fifth embodiment of the present application provides a computer-readable storage medium.

When the instructions in the storage medium are executed by the processor, the electronic device can execute the above method for reconciliation processing.

Embodiment 6

Embodiment 6 of the present application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the above-mentioned reconciliation processing method.

Other embodiments of the present application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of this application that follow the general principles of this application and include common knowledge or conventional techniques in the technical field not disclosed in this application . The specification and examples are to be regarded as exemplary only, with the true scope and spirit of the application being indicated by the following claims.

It is to be understood that the present application is not limited to the precise structures described above and illustrated in the accompanying drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (11)

1. A reconciliation processing method is characterized by comprising the following steps:

acquiring the bank account checking data and the remark information in the enterprise account checking data within a preset time period;

according to the bank reconciliation data and the remark information in the enterprise reconciliation data, determining first reconciliation data in the bank reconciliation data and second reconciliation data in the enterprise reconciliation data corresponding to the first reconciliation data, wherein the similarity between the remark information of the first reconciliation data and the remark information of the second reconciliation data meets a preset threshold value;

and matching according to the first reconciliation data and the corresponding second reconciliation data to obtain a matching result.

2. The method of claim 1, wherein determining the first reconciliation data in the bank reconciliation data and the second reconciliation data in the corresponding enterprise reconciliation data according to the bank reconciliation data and the remark information in the enterprise reconciliation data comprises:

extracting key words of remark information in each piece of bank account checking data and enterprise account checking data;

and determining the first reconciliation data and the second reconciliation data corresponding to the first reconciliation data according to the key words corresponding to each piece of bank reconciliation data and enterprise reconciliation data, wherein the semantic similarity between the key words of the remark information in the first reconciliation data and the second reconciliation data meets a preset threshold value.

3. The method of claim 2, wherein the determining the first reconciliation data and the second reconciliation data corresponding thereto according to the key word corresponding to each piece of bank reconciliation data and enterprise reconciliation data comprises:

converting the key words corresponding to each piece of bank account checking data and enterprise account checking data into word vectors;

obtaining semantic similarity between the key words corresponding to each bank reconciliation data and the key words corresponding to each enterprise reconciliation data by calculating an included angle between the word vector corresponding to each bank reconciliation data and the word vector corresponding to each enterprise reconciliation data;

and determining the first account checking data and the second account checking data corresponding to the first account checking data, wherein the semantic similarity between keywords corresponding to the first account checking data and the second account checking data meets a preset threshold value.

4. The method of claim 2, wherein the extracting the keyword of the remark information in each of the bank reconciliation data and the enterprise reconciliation data comprises:

performing word segmentation processing on remark information in each piece of bank account checking data and enterprise account checking data to obtain words corresponding to the bank account checking data and the enterprise account checking data, wherein the words carry part-of-speech labels;

removing stop words in the participles corresponding to each piece of bank account checking data and enterprise account checking data according to the stop word bank;

and obtaining keywords of remark information in each piece of bank reconciliation data and the enterprise reconciliation data based on a TextRank algorithm according to the present segmentation corresponding to each piece of bank reconciliation data and the enterprise reconciliation data.

5. The method according to claim 1, wherein the first reconciliation data and/or the second reconciliation data respectively include a plurality of pieces of reconciliation data, wherein the reconciliation data includes occurrence data and loan direction information, and the matching processing is performed according to the first reconciliation data and the corresponding second reconciliation data to obtain a matching result, including:

respectively calculating a total sum of income and expenditure corresponding to the first reconciliation data and a total sum of income and expenditure corresponding to the second reconciliation data according to the occurrence data and the loan direction information, wherein the total sum of income and expenditure comprises a total sum of income and a total sum of expenditure;

if the income sum of the bank is equal to the income sum of the enterprise and the expenditure sum of the bank is equal to the expenditure sum of the enterprise, the matching is determined to be successful; otherwise, determining that the matching fails.

6. The method according to claim 1, wherein after acquiring the remark information in the bank reconciliation data and the enterprise reconciliation data within the preset time period, the method further comprises:

and filtering invalid reconciliation data from the bank reconciliation data and the enterprise reconciliation data, wherein the invalid reconciliation data is reconciliation data corresponding to a scene without balance change.

7. The method of claim 1, further comprising:

and if the matching result is that the matching fails, pushing the first account checking data and the corresponding second account checking data to the user.

8. A reconciliation processing apparatus, comprising:

the acquisition module is used for acquiring the remark information in the bank account checking data and the enterprise account checking data within a preset time period;

the determining module is used for determining first reconciliation data in the bank reconciliation data and second reconciliation data in the enterprise reconciliation data corresponding to the first reconciliation data according to the bank reconciliation data and the remark information in the enterprise reconciliation data, wherein the similarity between the remark information of the first reconciliation data and the remark information of the second reconciliation data meets a preset threshold value;

and the matching module is used for performing matching processing according to the first reconciliation data and the corresponding second reconciliation data to obtain a matching result.

9. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the reconciliation processing method of any of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the reconciliation processing method of any of claims 1-7.

11. A computer program product comprising a computer program which, when executed by a processor, implements the reconciliation processing method according to any one of claims 1 to 7.

Images