AI and RPA Based Bill Information Processing Method, Device and Storage Medium

Abstract

The present disclosure provides a method, apparatus, and storage medium for processing bill information based on AI and RPA. The method is as follows: Whenever the processing cycle arrives, control the RPA robot to log in to the bill system; control the RPA robot to select a target unit and a target account corresponding to the target unit in the bill matching interface of the bill system; when the bill record information and bill detail information corresponding to the target account are displayed in response to the selected target unit and target account in the bill matching interface, control the RPA robot to match the bill record information with the bill detail information. Thus, by controlling the RPA robot to periodically log in to the bill system and automatically match the bill record information with the bill detail information, the staff can be released from mechanical labor, saving a large amount of manpower. At the same time, the matching efficiency and accuracy of the bill record information and bill detail information are improved.

Description

Technical Field

[0001] The present disclosure relates to the technical fields of AI (Artificial Intelligence) and RPA (Robotic Process Automation), and in particular to a method, apparatus, and storage medium for processing bill information based on AI and RPA. Background Art

[0002] Robotic Process Automation, abbreviated as RPA, is to simulate human operations on a computer through specific "robot software" and automatically execute process tasks according to rules.

[0003] Artificial Intelligence (AI) is a technical science that studies, develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence.

[0004] In related technologies, the bill record information and bill detail information in the bill system need to be manually matched and verified. However, due to the complex relationship between the bill record information and the bill detail information (for example, the relationship between the bill record information and the bill detail information can be one-to-one, one-to-many, etc.) and numerous matching rules, and in addition, some bill detail information can be as many as hundreds of items, it is necessary to consume a large amount of manpower to match and verify the bill record information and the bill detail information, with low efficiency and prone to errors during the matching process. Summary of the Invention

[0005] Embodiments of the present disclosure provide a method, apparatus, and storage medium for processing bill information based on AI and RPA to solve the problems existing in related technologies. The technical solutions are as follows:

[0006] In a first aspect, embodiments of the present disclosure provide a method for processing bill information based on artificial intelligence AI and robotic process automation RPA, including: whenever a processing cycle arrives, controlling the RPA robot to log in to the bill system; controlling the RPA robot to select a target unit and a target account corresponding to the target unit in a bill matching interface of the bill system; and when the bill record information and bill detail information corresponding to the target account are displayed in response to the selected target unit and target account in the bill matching interface, controlling the RPA robot to match the bill record information with the bill detail information.

[0007] In one implementation, when the bill matching interface displays the bill record information and bill details information corresponding to the target account in response to the selected target unit and target account, controlling the RPA robot to match the bill record information with the bill details information includes: for any bill record in the bill record information, controlling the RPA robot to determine, from the bill details information, a target bill detail whose second description content matches the first description content corresponding to the any bill record according to the first description content corresponding to the any bill record and the second description content corresponding to each bill detail in the bill details information; controlling the RPA robot to perform a bill value match between the any bill record and the target bill detail.

[0008] In one implementation, the first description content includes the corresponding first bill type and the first bill occurrence date, and the second description content includes the corresponding second bill type and the second bill occurrence date. For any bill record in the bill record information, controlling the RPA robot to determine, from the bill details information, a target bill detail whose second description content matches the first description content corresponding to the any bill record according to the first description content corresponding to the any bill record and the second description content corresponding to each bill detail in the bill details information includes: controlling the RPA robot to match the first bill type in the first description content with the second bill types in the second description content corresponding to each bill detail to determine, from the bill details information, candidate bill details that match the first bill type in the first description content; controlling the RPA robot to match the first bill occurrence date in the first description content with the second bill occurrence dates in the second description content corresponding to the candidate bill details to determine, from the candidate bill details, a target bill detail that matches the first bill occurrence date in the first description content; wherein the difference between the second bill occurrence date of the target bill detail and the first bill occurrence date is less than or equal to a set threshold.

[0009] In one implementation, controlling the RPA robot to perform a bill value match between the any bill record and the target bill detail includes: controlling the RPA robot to obtain the first bill value corresponding to the any bill record and the second bill value corresponding to the target bill detail based on the natural language processing technology NLP; controlling the RPA robot to compare the first bill value with the second bill value to determine whether the any bill record matches the target bill detail.

[0010] In one embodiment, the method further includes: when it is determined that any of the bill records matches the target bill details, controlling the RPA robot to select and save any of the bill records and the target bill details in the bill matching interface.

[0011] In one embodiment, before controlling the RPA robot to match the bill record information with the bill detail information, the method further includes: controlling the RPA robot to extract the content of each bill record in the bill record information based on the natural language processing technology NLP to obtain the first description content corresponding to each bill record; controlling the RPA robot to extract the content of each bill detail in the bill detail information based on the natural language processing technology NLP to obtain the second description content corresponding to each bill detail.

[0012] In one embodiment, the method further includes: when the bill matching interface does not display the bill record information and the bill detail information corresponding to the target account in response to the selected target unit and target account, or when it is determined whether the bill record information corresponding to the target account matches the bill detail information, controlling the RPA robot to update the target unit or the target account.

[0013] In a second aspect, an embodiment of the present disclosure provides a bill information processing device based on artificial intelligence AI and robotic process automation RPA, including: a login module for controlling the RPA robot to log in to the bill system whenever a processing cycle arrives; a selection module for controlling the RPA robot to select a target unit and a target account corresponding to the target unit in the bill matching interface of the bill system; a matching module for controlling the RPA robot to match the bill record information with the bill detail information when the bill matching interface displays the bill record information and the bill detail information corresponding to the target account in response to the selected target unit and target account.

[0014] In one embodiment, the matching module is configured to: for any of the bill records in the bill record information, control the RPA robot to determine, from the bill detail information, a target bill detail whose second description content matches the first description content corresponding to any of the bill records according to the first description content corresponding to any of the bill records and the second description content corresponding to each bill detail in the bill detail information; control the RPA robot to perform a bill value match between any of the bill records and the target bill detail.

[0015] In one embodiment, the first description content includes the corresponding first bill type and the first bill occurrence date, and the second description content includes the corresponding second bill type and the second bill occurrence date. The matching module is further configured to: control the RPA robot to match the first bill type in the first description content with the second bill types of the second description contents corresponding to the respective bill details, so as to determine candidate bill details that match the first bill type in the first description content from the bill detail information; control the RPA robot to match the first bill occurrence date in the first description content with the second bill occurrence dates of the second description contents corresponding to the candidate bill details, so as to determine target bill details that match the first bill occurrence date in the first description content from the candidate bill details; wherein, the difference between the second bill occurrence date of the target bill details and the first bill occurrence date is less than or equal to a set threshold value.

[0016] In one embodiment, the matching module is further configured to: control the RPA robot to obtain the first bill value corresponding to any bill record and the second bill value corresponding to the target bill details based on the natural language processing technology NLP; control the RPA robot to compare the first bill value with the second bill value to determine whether the any bill record matches the target bill details.

[0017] In one embodiment, the device further includes: a processing module, configured to, when it is determined that the any bill record matches the target bill details, control the RPA robot to select and save the any bill record and the target bill details in the bill matching interface.

[0018] In one embodiment, the device further includes: an obtaining module, configured to control the RPA robot to perform content extraction on each bill record in the bill record information based on the natural language processing technology NLP to obtain the first description content corresponding to each bill record; the obtaining module is further configured to control the RPA robot to perform content extraction on each bill detail in the bill detail information based on the natural language processing technology NLP to obtain the second description content corresponding to each bill detail.

[0019] In one embodiment, the device further includes: an updating module, configured to, when the bill matching interface does not display the bill record information and the bill detail information corresponding to the target account in response to the selected target unit and target account, or when it is determined whether the bill record information corresponding to the target account matches the bill detail information, control the RPA robot to update the target unit or the target account.

[0020] In a third aspect, embodiments of the present disclosure provide an electronic device, including: a processor and a memory, where instructions are stored in the memory and loaded and executed by the processor to implement the method described in the embodiments of the first aspect above.

[0021] In a fourth aspect, embodiments of the present disclosure provide a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the method described in the embodiments of the first aspect above is implemented.

[0022] The advantages or beneficial effects in the above technical solutions at least include:

[0023] In the technical solution of the present disclosure, by controlling the RPA robot to periodically log in to the billing system and automatically match the billing record information and the billing detail information, the staff can be released from mechanical labor. At the same time, the matching efficiency and accuracy of the billing record information and the billing detail information are improved.

[0024] The above summary is only for the purpose of the specification and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present disclosure will be readily apparent by reference to the drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In the drawings, unless otherwise specified, the same reference numerals throughout the several views denote the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in accordance with the present disclosure and should not be regarded as limiting the scope of the present disclosure.

[0026] Figure 1 is a flowchart of a method for processing billing information based on AI and RPA according to an embodiment of the present disclosure;

[0027] Figure 2 is a schematic diagram of a billing matching interface according to an embodiment of the present disclosure;

[0028] Figure 3 is a flowchart of a method for processing billing information based on AI and RPA according to another embodiment of the present disclosure;

[0029] Figure 4 is a flowchart of a method for processing billing information based on AI and RPA according to another embodiment of the present disclosure;

[0030] Figure 5 is a schematic diagram of the matching of a billing record and a billing detail according to an embodiment of the present disclosure;

[0031] Figure 6It is a flowchart of a bill information processing method based on AI and RPA according to another embodiment of the present disclosure;

[0032] Figure 7 It is a schematic structural diagram of a bill information processing device based on AI and RPA according to an embodiment of the present disclosure;

[0033] Figure 8 It is a structural block diagram of an electronic device according to an embodiment of the disclosure. Detailed implementation manners

[0034] The embodiments of the present disclosure are described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary only for explaining the present disclosure and should not be construed as a limitation to the present disclosure.

[0035] In the description of the present disclosure, the term "a plurality" means two or more.

[0036] In the description of the present disclosure, the term "bill record information" refers to the bill records initiated internally by the user in the bill system.

[0037] In the description of the present disclosure, the term "bill detail information" refers to the specific detail information of each bill processing returned by the electronic bank (such as online banking) to the bill system.

[0038] In the description of the present disclosure, the term "first description content" is the description content corresponding to each bill record in the bill record information. The first description content may include the bill occurrence date, bill type, and bill value corresponding to the bill record.

[0039] In the description of the disclosure, the term "second description content" is the description content corresponding to each bill detail in the bill detail information. The second description content may include the bill occurrence date, bill type, and bill value corresponding to the bill detail.

[0040] In the description of the present disclosure, the term "bill type" may be the bill category, for example, "salary payment", "taxes", etc.

[0041] In the description of the present disclosure, the term "bill system" may be a system for recording and matching and verifying bills;

[0042] In the description of the present disclosure, the term "processing cycle" is the cycle for matching and processing bills in the bill system;

[0043] In the description of the present disclosure, the term "update" means replacing the target unit or target account.

[0044] These and other aspects of the embodiments of the present disclosure will be apparent from the following description and the accompanying drawings. In these descriptions and drawings, specific embodiments of the embodiments of the present disclosure are specifically disclosed to represent some ways of implementing the principles of the embodiments of the present disclosure, but it should be understood that the scope of the embodiments of the present disclosure is not limited thereto. On the contrary, the embodiments of the present disclosure include all variations, modifications, and equivalents that fall within the spirit and scope of the appended claims.

[0045] The following describes a method, apparatus, and storage medium for processing bill information based on Artificial Intelligence (AI) and Robotic Process Automation (RPA) in an open embodiment with reference to the accompanying drawings.

[0046] Figure 1 is a flowchart of a method for processing bill information based on AI and RPA according to an embodiment of the present disclosure, as Figure 1 shown, the method may include the following steps:

[0047] Step 101, whenever a processing cycle arrives, control the RPA robot to log in to the bill system.

[0048] In the embodiments of the present disclosure, the processing cycle may be one day, one week, or one month, and the present disclosure does not make specific limitations.

[0049] In the embodiments of the present disclosure, taking one day as an example of the processing cycle, the RPA robot can be controlled to automatically log in to the bill system every day. Among them, the bill system can record and match and verify bills.

[0050] It should be noted that before controlling the RPA robot to periodically log in to the bill system, a login account and a login password can be preset for the RPA robot so that the RPA robot can log in to the bill system according to the login account and password.

[0051] Step 102, control the RPA robot to select a target unit and a target account corresponding to the target unit in the bill matching interface of the bill system.

[0052] It should be understood that one target unit may correspond to one or more accounts. In the embodiments of the present disclosure, the RPA robot can be controlled to select a target unit in the bill matching interface of the bill system and select a target account from the accounts corresponding to the target unit.

[0053] For example, as Figure 2 shown, the target unit can be selected in the upper left side of Figure 2 , such as "Company A", and the target account corresponding to the target unit, such as "Account XXXX".

[0054] Step 103, when the bill matching interface responds to the selected target unit and target account and displays the bill record information and bill detail information corresponding to the target account, control the RPA robot to match the bill record information with the bill detail information.

[0055] In the embodiment of the present disclosure, on the bill matching interface, in response to the selected target unit and target account, the RPA robot can query according to the target account to determine whether there is corresponding bill record information and bill detail information for the target account. When there is corresponding bill record information and bill detail information for the target account, the corresponding bill record information and bill detail information are displayed on the bill matching interface; when there is no corresponding bill record information and bill detail information for the target account, the bill matching interface is displayed as empty. When the corresponding bill record information and bill detail information are displayed on the bill matching interface, control the RPA robot to match the bill record information with the bill detail information. Among them, the bill record information can be the bill records initiated internally by the user in the bill system, and the bill detail information can be the specific details of each bill process returned by the electronic bank (such as, online banking) to the bill system. The electronic bank and the bill system can communicate to return the bill detail information to the bill system.

[0056] In summary, by controlling the RPA robot to periodically log in to the bill system and automatically match the bill record information and bill detail information, the staff can be released from mechanical labor, saving a large amount of manpower. At the same time, the matching efficiency and accuracy of the bill record information and bill detail information are improved.

[0057] To accurately control the RPA robot to match the bill record information with the bill detail information, as Figure 3 shown, Figure 3 is a flowchart of a bill information processing method based on AI and RPA according to another embodiment of the present disclosure. In the embodiment of the present disclosure, the target bill detail matching any bill record can be determined from the bill detail information according to the first description content of any bill record in the bill record information and the second description content corresponding to each bill detail in the bill detail information. Figure 3 The embodiment shown may include the following steps:

[0058] Step 301, whenever the processing cycle arrives, control the RPA robot to log in to the bill system.

[0059] Step 302, control the RPA robot to select the target unit and the target account corresponding to the target unit in the bill matching interface of the bill system.

[0060] Step 303: For any bill record in the bill record information, control the RPA robot to determine, from the bill detail information, a target bill detail whose second description content matches the first description content corresponding to any bill record, based on the first description content corresponding to any bill record and the second description content corresponding to each bill detail in the bill detail information.

[0061] In an embodiment of the present disclosure, for any bill record in the bill record information, the RPA robot can be controlled to obtain the first description content corresponding to any bill record and the second description content corresponding to each bill detail in the bill detail information. Further, the RPA robot is controlled to compare the first description content corresponding to any bill record with the second description content corresponding to each bill detail in the bill detail information, and determine, from the bill detail information, a target bill detail whose second description content matches the first description content corresponding to any bill record according to the comparison result. The first description content can be the description content corresponding to each bill record in the bill record information, and can include the occurrence date, bill type, and bill value corresponding to the bill record. The second description content can be the description content corresponding to each bill detail in the bill detail information, and can include the occurrence date, type, and bill value corresponding to the bill detail. For example, if the occurrence date corresponding to the bill record is "September 10, 2015", the bill type is "salary payment", and the bill value is "A yuan", then the first description content is "September 10, 2021 salary payment A yuan". If the occurrence date corresponding to the bill detail is "September 11, 2015", the bill type is "wages", and the bill value is "B yuan", then the second description content is "September 11, 2021 wages B yuan".

[0062] Step 304: Control the RPA robot to match the bill value of any bill record with the target bill detail.

[0063] In an embodiment of the present disclosure, the first bill value corresponding to any bill record is compared with the second bill value corresponding to the target bill detail to determine whether any bill record matches the target bill detail.

[0064] As an example, when there is one target bill detail, the first bill value can be compared with the second bill value. When the first bill value is equal to the second bill value, it can be determined that any bill record matches the target bill detail. When the first bill value is not equal to the second bill value, it can be determined that any bill record does not match the target bill detail.

[0065] As another example, when there are at least two target bill details, multiple second bill values can be added together, and the sum of the second bill values can be compared with the first bill value. When the sum of the second bill values is equal to the first bill value, it can be determined that any one of the bill records matches the target bill details. When the first bill value is not equal to the sum of the second bill values, it can be determined that any one of the bill records does not match the target bill details.

[0066] It should be noted that in actual applications, there may also be multiple bill records in the bill record information that match one or more bill details in the bill detail information. As an example, for any one of the bill details in the bill detail information, an RPA robot can be controlled to compare the second description content corresponding to any one of the bill details with the first description content corresponding to each bill record in the bill record information, and determine the target bill record in the bill record information whose first description content matches the second description content corresponding to any one of the bill details. Furthermore, based on the second bill value corresponding to any one of the bill details and the first bill value corresponding to the bill record, it can be determined whether any one of the bill details matches the target bill record. For example, multiple bill records correspond to bill records in different periods (such as installment payments), and the bill detail is a total incoming account detail (one-time incoming account). The second description content of the bill detail (such as the project payment of A yuan transferred from Company B to Company A on September 10, 2021) can be matched with the first description content corresponding to multiple bill records (the first description contents are respectively the project payment of B yuan transferred from Company B to Company A on July 10, 2021, the project payment of C yuan transferred from Company B to Company A on August 10, 2021, and the project payment of D yuan transferred from Company B to Company A on September 10, 2021). When the second description content of the bill detail matches the first description content corresponding to multiple bill records, the second bill value corresponding to the bill detail is compared with the sum of the first bill values corresponding to multiple bill records to determine whether multiple bill records in the bill record information match one bill detail in the bill detail information. Among them, the date in the second description content is within the set range of the dates corresponding to each first description content, the second bill type corresponding to the second description content matches the first bill type corresponding to each first description content, and the second description content of the bill detail matches the first description content corresponding to multiple bill records.

[0067] As another example, each bill record in the bill record information can be classified and counted according to the first description content corresponding to each bill record. For example, if the first description content corresponding to multiple bill records all contains "project payment transferred from Company B to Company A", the bill records whose first description content contains "project payment transferred from Company B to Company A" are counted. Similarly, each bill detail in the bill detail information is classified and counted according to the second description content corresponding to each bill detail. For example, if the second description content corresponding to multiple bill details all contains "project payment transferred from Company B to Company A", the bill details whose second description content contains "project payment transferred from Company B to Company A" are counted, and the first bill values corresponding to the multiple bill records obtained by the statistics are compared with the second bill values corresponding to the multiple bill details obtained by the statistics to determine whether the multiple bill records match the multiple bill details.

[0068] It should be noted that the execution processes of steps 301 to 302 can be implemented in any one of the embodiments of the present disclosure respectively. The embodiments of the present disclosure do not limit this and will not be elaborated further.

[0069] In summary, according to the first description content corresponding to the bill record and the second description content corresponding to the bill detail, the target bill detail whose second description content matches the first description content corresponding to the bill record can be accurately determined. Furthermore, any bill record is further matched with the target bill detail in terms of the bill value, which improves the matching accuracy between any bill record and the target bill detail.

[0070] In order to accurately determine the target bill detail in the bill detail information whose second description content matches the first description content corresponding to any bill record, as Figure 4 shown, Figure 4 is a flowchart of a bill information processing method based on AI and RPA according to another embodiment of the present disclosure. In the embodiments of the present disclosure, the first description content may include the corresponding first bill type and the first bill occurrence date, and the second description content may include the corresponding second bill type and the second bill occurrence date. The candidate bill details that match the first bill type can be determined from the bill detail information according to the first bill type and the second bill types of the second description content corresponding to each bill detail. Furthermore, the target bill detail is determined from the candidate bill details according to the first bill occurrence date and the second bill occurrence date corresponding to the candidate bill details. Figure 4 The embodiment shown may include the following steps:

[0071] Step 401, whenever the processing cycle arrives, control the RPA robot to log in to the bill system.

[0072] Step 402, control the RPA robot to select the target unit and the target account corresponding to the target unit in the bill matching interface of the bill system.

[0073] Step 403, when in the bill matching interface, in response to the selected target unit and target account, and the bill record information and bill detail information corresponding to the target account are displayed, control the RPA robot to match the first bill type in the first description content with the second bill types in the second description content corresponding to each bill detail, so as to determine candidate bill details that match the first bill type in the bill detail information.

[0074] In the embodiments of the present disclosure, the first description content may include the corresponding first bill occurrence date, first bill type, and first bill value, and the second description content may include the corresponding second bill occurrence date, second bill type, and second bill value. For example, the first description content is "Salary paid A yuan on December 16, 2021", the first bill type corresponding to the first description content is "Salary payment", and the first bill occurrence date is "December 16, 2021"; the second description content is "Wage paid A yuan on December 17, 2021", the second bill type corresponding to the second description content is "Wage payment", and the second bill occurrence date is December 17, 2021. It should be noted that the difference between the second bill occurrence date and the first bill occurrence date is less than or equal to the set threshold. For example, the second bill occurrence date can be the next one or two working days after the first bill occurrence date.

[0075] Optionally, the first bill type corresponding to the first description content can be matched with the second bill types corresponding to each bill detail in the bill detail information, and the bill details that match the first bill type are used as candidate bill details, where the number of candidate bill details can be one or more.

[0076] Step 404, control the RPA robot to match the first bill occurrence date in the first description content with the second bill occurrence date in the second description content corresponding to the candidate bill details, so as to determine the target bill details that match the first bill occurrence date in the candidate bill details.

[0077] Furthermore, match the first bill occurrence date in the first description content with the second bill occurrence date in the second description content corresponding to the candidate bill details, and use the candidate dates that match the first bill occurrence date in the candidate bills as the target bill details, where the number of target bill details can be one or more.

[0078] Step 405, control the RPA robot to perform bill value matching between any bill record and the target bill details.

[0079] For example, as Figure 5 shown, the bill record information contains a bill record, the bill detail information contains a bill detail, the first description content (date, summary, and amount) corresponding to the bill record is "Salary payment of A yuan on December 16, 2000", the second description content corresponding to the bill detail is "Wage payment of A yuan on December 17, 2000", the first bill type corresponding to the first description content is "Salary payment" which matches the "Wage payment" corresponding to the second description content, the first bill occurrence date corresponding to the bill record is "December 16, 2000", the second bill occurrence date corresponding to the bill detail is "December 17, 2000", and the first bill occurrence date matches the second bill occurrence date. Then, this bill detail is the target bill detail that matches the bill record. By comparing the first bill value of A yuan in the bill record with the second bill value of A yuan corresponding to the second bill, it can be determined that the bill record matches the target bill detail.

[0080] It should be noted that in actual applications, the bill detail information may also include the handling fees of the electronic bank (such as, service charges). The bill detail can be matched with the bill record according to the date of the handling fees of the electronic bank.

[0081] In the embodiment of the present disclosure, in order to prevent the RPA robot from repeatedly matching the bill record information and the bill detail information in the bill matching interface, when it is determined that any bill record matches the target bill detail, the RPA robot is controlled to select and save any bill record and the target bill detail in the bill matching interface, and the selected and saved bill record and bill detail are no longer displayed in the bill matching interface.

[0082] In order to further improve the matching accuracy of the bill record and the bill detail, after the RPA robot matches the bill record information and the bill detail information, a human-machine collaboration working link can be added to check the matching result of the bill record and the bill detail.

[0083] As an example, the RPA robot is controlled to display the matching result of the bill record information and the bill detail information for the relevant business personnel to check the matching result.

[0084] As another example, the RPA robot is controlled to send a prompt message, where the prompt message includes the matching result of the bill record information and the bill detail information, and is used to prompt the checking of the matching result.

[0085] As yet another example, the RPA robot is controlled to send the matching result of the bill record information and the bill detail information to a designated account for the business personnel associated with the designated account to check the matching result.

[0086] As yet another example, the control RPA robot saves the matching result of the bill record information and the bill detail information to the bill system, and relevant personnel can log in to the bill system to check the saved matching result. For example, for the bill records and bill details that the RPA robot cannot match, the user can log in to the bill system (e.g., once a month) to complete the matching process.

[0087] It should be noted that the execution processes of steps 401 to 402 and step 405 can be implemented in any one of the embodiments of the present disclosure respectively. The embodiments of the present disclosure do not limit this and will not be described in detail again.

[0088] In summary, by matching the first bill type in the first description content corresponding to any bill record with the second bill type in the second description content corresponding to each bill detail, candidate bill details can be determined from the bill detail information. Further, by matching the first bill occurrence date in the first description content corresponding to any bill record with the second bill occurrence date in the second description content corresponding to the candidate bill details, the target bill details can be accurately determined from the candidate bill details.

[0089] To accurately match the first description content corresponding to any bill record with the second description content corresponding to each bill detail in the bill detail information, as Figure 6 shown, Figure 6 is a flowchart of a bill information processing method based on AI and RPA according to another embodiment of the present disclosure. In the embodiments of the present disclosure, before matching the bill record information and the bill detail information, the first description content corresponding to each bill record and the second description content corresponding to each bill detail can be obtained first. Figure 6 The embodiments shown may include the following steps:

[0090] Step 601, whenever the processing cycle arrives, control the RPA robot to log in to the bill system.

[0091] Step 602, control the RPA robot to select a target unit and a target account corresponding to the target unit in the bill matching interface of the bill system.

[0092] Step 603, when the bill record information and the bill detail information corresponding to the target account are displayed in response to the selected target unit and target account in the bill matching interface, control the RPA robot to extract the content of each bill record in the bill record information based on natural language processing technology (Natural Language Process, abbreviated as NLP) to obtain the first description content corresponding to each bill record in the bill record information.

[0093] In an embodiment of the present disclosure, through NLP, the description content corresponding to each bill record in the bill record information can be extracted to obtain the first description content corresponding to each bill record. For example, by extracting the occurrence date, summary, and bill value of the bill record, based on the extracted occurrence date, summary, and bill value, the first description content corresponding to each bill record can be determined.

[0094] Step 604: Control the RPA robot to extract the content of each bill detail in the bill detail information through NLP to obtain the second description content corresponding to each bill detail.

[0095] Similarly, through NLP, the description content corresponding to each bill detail in the bill detail information can be extracted to obtain the second description content corresponding to each bill detail in the bill detail information. For example, by extracting the occurrence date, summary, and bill value of the bill detail, based on the extracted occurrence date, summary, and bill value, the second description content corresponding to each bill detail can be determined.

[0096] Step 605: For any bill record in the bill record information, control the RPA robot to determine, from the bill detail information, the target bill detail whose second description content matches the first description content corresponding to the any bill record according to the first description content corresponding to the any bill record and the second description content corresponding to each bill detail in the bill detail information.

[0097] Step 606: Control the RPA robot to match the bill value of any bill record with the target bill detail.

[0098] It should be noted that the execution processes of steps 601 to 602 and the execution processes of steps 605 to 606 can be implemented in any one of the embodiments of the present disclosure. The embodiments of the present disclosure do not make any limitations in this regard and will not be elaborated further.

[0099] In summary, by pre-obtaining the first description content corresponding to each bill record in the bill record information and the second description content corresponding to each bill detail in the bill detail information, furthermore, the matching of the first description content corresponding to each bill record in the bill record information and the second description content corresponding to each bill detail in the bill detail information can be accurately achieved.

[0100] It should be noted that when, in the bill matching interface, in response to the selected target unit and target account, the bill record information and bill details information corresponding to the target account are not displayed, or when determining whether the bill record information corresponding to the target account matches the bill details information, the RPA robot is controlled to update the target unit or target account. That is to say, when there is no bill record information and bill details information to be matched under the corresponding target unit and target account, or when it is determined whether the bill record information corresponding to the target account matches the bill details information, other target units or other target accounts are selected to continue the matching process of the bill record information and bill details information.

[0101] In the bill information processing method based on AI and RPA according to the embodiments of the present disclosure, by controlling the RPA robot to log in to the bill system whenever the processing cycle arrives; controlling the RPA robot to select a target unit and the target account corresponding to the target unit in the bill matching interface of the bill system; when, in the bill matching interface, in response to the selected target unit and target account, the bill record information and bill details information corresponding to the target account are displayed, controlling the RPA robot to match the bill record information with the bill details information. Thus, by controlling the RPA robot to periodically log in to the bill system and automatically match the bill record information with the bill details information, the staff can be released from mechanical labor, saving a large amount of manpower. At the same time, the matching efficiency and accuracy of the bill record information and bill details information are improved.

[0102] To implement the above embodiments, the present disclosure also proposes a bill information processing device based on artificial intelligence AI and robotic process automation RPA.

[0103] Figure 7 It is a schematic structural diagram of a bill information processing device based on AI and RPA according to an embodiment of the present disclosure. As Figure 7 shown, the bill information processing device 700 based on AI and RPA may include: a login module 710, a selection module 720, and a matching module 730.

[0104] Among them, the login module 710 is used to control the RPA robot to log in to the bill system whenever the processing cycle arrives; the selection module 720 is used to control the RPA robot to select a target unit and the target account corresponding to the target unit in the bill matching interface of the bill system; the matching module 730 is used to control the RPA robot to match the bill record information with the bill details information when, in the bill matching interface, in response to the selected target unit and target account, the bill record information and bill details information corresponding to the target account are displayed.

[0105] As a possible implementation manner of the embodiments of the present disclosure, the matching module 730 is configured to: for any bill record in the bill record information, control the RPA robot to determine, from the bill detail information, a target bill detail whose second description content matches the first description content corresponding to any bill record according to the first description content corresponding to any bill record and the second description content corresponding to each bill detail in the bill detail information; control the RPA robot to perform bill value matching between any bill record and the target bill detail.

[0106] As a possible implementation manner of the embodiments of the present disclosure, the first description content includes the corresponding first bill type and the first bill occurrence date, and the second description content includes the corresponding second bill type and the second bill occurrence date. The matching module 730 is further configured to: control the RPA robot to match the first bill type in the first description content with the second bill types in the second description contents corresponding to each bill detail, so as to determine, from the bill detail information, candidate bill details that match the first bill type in the first description content; control the RPA robot to match the first bill occurrence date in the first description content with the second bill occurrence dates in the second description contents corresponding to the candidate bill details, so as to determine, from the candidate bill details, a target bill detail that matches the first bill occurrence date in the first description content; wherein, the difference between the second bill occurrence date of the target bill detail and the first bill occurrence date is less than or equal to a set threshold.

[0107] As a possible implementation manner of the embodiments of the present disclosure, the matching module 730 is further configured to: control the RPA robot to obtain the first bill value corresponding to any bill record and the second bill value corresponding to the target bill detail based on the natural language processing technology NLP; control the RPA robot to compare the first bill value with the second bill value to determine whether any bill record matches the target bill detail.

[0108] As a possible implementation manner of the embodiments of the present disclosure, the bill information processing device 700 based on AI and RPA further includes: a processing module.

[0109] Wherein, the processing module is configured to, when it is determined that any bill record matches the target bill detail, control the RPA robot to select and save any bill record and the target bill detail in the bill matching interface.

[0110] As a possible implementation manner of the embodiments of the present disclosure, the bill information processing device 700 based on AI and RPA further includes: an acquisition module.

[0111] Among them, the obtaining module is used to control the RPA robot to extract the content of each bill record in the bill record information based on the natural language processing technology NLP, so as to obtain the first description content corresponding to each bill record; the obtaining module is also used to control the RPA robot to extract the content of each bill detail in the bill detail information based on the natural language processing technology NLP, so as to obtain the second description content corresponding to each bill detail.

[0112] As a possible implementation manner of the embodiments of the present disclosure, the bill information processing device 700 based on AI and RPA further includes: an updating module.

[0113] Among them, the updating module is used to control the RPA robot to update the target unit or the target account in the case that the bill matching interface does not display the bill record information and the bill detail information corresponding to the target account in response to the selected target unit and target account, or to determine whether the bill record information corresponding to the target account matches the bill detail information.

[0114] For the functions of the modules in each device of the embodiments of the present disclosure, reference may be made to the corresponding descriptions in the above methods, which will not be elaborated here.

[0115] The bill information processing device based on AI and RPA according to the embodiments of the present disclosure controls the RPA robot to log in to the bill system whenever the processing cycle arrives; controls the RPA robot to select a target unit and a target account corresponding to the target unit in the bill matching interface of the bill system; and controls the RPA robot to match the bill record information and the bill detail information in the case that the bill matching interface displays the bill record information and the bill detail information corresponding to the target account in response to the selected target unit and target account. Thus, by controlling the RPA robot to periodically log in to the bill system and automatically match the bill record information and the bill detail information, the staff can be released from mechanical labor, saving a large amount of manpower. At the same time, the matching efficiency and accuracy of the bill record information and the bill detail information are improved.

[0116] To implement the above embodiments, the present disclosure also proposes an electronic device.

[0117] Figure 8 The structural block diagram of an electronic device according to an embodiment of the disclosure is shown. As Figure 8 shown, the electronic device includes: a memory 810 and a processor 820, and a computer program that can run on the processor 820 is stored in the memory 810. When the processor 820 executes the computer program, the bill information processing method based on AI and RPA in the above embodiments is implemented. The number of the memory 810 and the processor 820 can be one or more.

[0118] The electronic device further includes:

[0119] A communication interface 830 for communicating with external devices and performing data interaction and transmission.

[0120] If the memory 810, the processor 820, and the communication interface 830 are implemented independently, the memory 810, the processor 820, and the communication interface 830 can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 8 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0121] Optionally, in a specific implementation, if the memory 810, the processor 820, and the communication interface 830 are integrated on a single chip, the memory 810, the processor 820, and the communication interface 830 can communicate with each other through an internal interface.

[0122] An embodiment of the present disclosure provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the bill information processing method provided in the embodiments of the present disclosure based on AI and RPA.

[0123] An embodiment of the present disclosure further provides a chip including a processor for calling and running instructions stored in a memory, so that a communication device installed with the chip executes the bill information processing method provided in the embodiments of the present disclosure.

[0124] An embodiment of the present disclosure further provides a chip including: an input interface, an output interface, a processor, and a memory. The input interface, the output interface, the processor, and the memory are connected through an internal connection path. The processor is configured to execute code in the memory, and when the code is executed, the processor is configured to execute the bill information processing method provided in the embodiments of the present disclosure.

[0125] It should be understood that the above-mentioned processor can be a Central Processing Unit (CPU), or it can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. It is worth noting that the processor can be a processor that supports the advanced RISC machines (ARM) architecture.

[0126] Furthermore, optionally, the above-mentioned memory can include a read-only memory and a random access memory, and can also include a non-volatile random access memory. The memory can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchlink dynamic random access memory (SLDRAM), and direct rambus random access memory (DR RAM).

[0127] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the present disclosure are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0128] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0129] Furthermore, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" can explicitly or implicitly include at least one of the features. In the description of the present disclosure, "a plurality" means two or more, unless otherwise specifically defined.

[0130] Any process or method description represented in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of the code including one or more executable instructions for implementing a specific logical function or process. And the scope of the preferred embodiments of the present disclosure includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in the reverse order according to the functions involved, rather than in the order shown or discussed.

[0131] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in connection with these instruction execution systems, apparatus, or devices.

[0132] It should be understood that each part of the present disclosure can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above-described example methods can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0133] In addition, in each embodiment of the present disclosure, each functional unit can be integrated in a processing module, or each unit can exist physically alone, or two or more units can be integrated in a module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. When the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a magnetic disk, an optical disk, or the like.

[0134] The above is only the specific implementation manner of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various changes or substitutions, and these should all be covered by the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method for processing bill information based on artificial intelligence AI and robotic process automation RPA, characterized in that, Including: Whenever a processing cycle is reached, control the RPA robot to log in to the billing system; Control the RPA robot to select a target unit and a target account corresponding to the target unit in the bill matching interface of the billing system; When the bill record information and bill details information corresponding to the target account are displayed in response to the selected target unit and target account in the bill matching interface, control the RPA robot to match the bill record information with the bill details information; Before the control of the RPA robot to match the bill record information with the bill details information, it further includes: Control the RPA robot to perform content extraction on each bill record in the bill record information based on the natural language processing technology NLP to obtain the first description content corresponding to each bill record; Control the RPA robot to perform content extraction on each bill detail in the bill details information based on the natural language processing technology NLP to obtain the second description content corresponding to each bill detail; wherein, the first description content includes the occurrence date, bill type and bill value of the bill record, and the second description content includes the occurrence date, bill type and bill value of the bill detail; The control of the RPA robot to match the bill record information with the bill details information includes: For any bill record in the bill record information, control the RPA robot to determine, according to the first description content corresponding to the any bill record and the second description content corresponding to each bill detail in the bill details information, a target bill detail in the bill details information whose second description content matches the first description content corresponding to the any bill record; Control the RPA robot to perform bill value matching between the any bill record and the target bill detail.

2. The method according to claim 1, characterized in that, The first description content includes the corresponding first bill type and the first bill occurrence date, and the second description content includes the corresponding second bill type and the second bill occurrence date. For any bill record in the bill record information, control the RPA robot to determine, according to the first description content corresponding to the any bill record and the second description content corresponding to each bill detail in the bill details information, a target bill detail in the bill details information whose second description content matches the first description content corresponding to the any bill record, including: Control the RPA robot to match the first bill type in the first description content with the second bill types in the second description content corresponding to each bill detail to determine candidate bill details in the bill details information that match the first bill type in the first description content; Control the RPA robot to match the first bill occurrence date in the first description content with the second bill occurrence dates in the second description content corresponding to the candidate bill details to determine a target bill detail in the candidate bill details that matches the first bill occurrence date in the first description content; Among them, the difference between the second bill occurrence date of the target bill details and the first bill occurrence date is less than or equal to a set threshold value.

3. The method according to claim 1, wherein Controlling the RPA robot to perform bill value matching between any bill record and the target bill details includes: Controlling the RPA robot to obtain a first bill value corresponding to any bill record and a second bill value corresponding to the target bill details based on the natural language processing technology NLP; Controlling the RPA robot to compare the first bill value with the second bill value to determine whether any bill record matches the target bill details.

4. The method according to claim 3, wherein, The method further includes: When it is determined that any bill record matches the target bill details, controlling the RPA robot to select and save any bill record and the target bill details in the bill matching interface.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: When the bill matching interface does not display the bill record information and bill details information corresponding to the target account in response to the selected target unit and target account, or when it is determined whether the bill record information corresponding to the target account matches the bill details information, controlling the RPA robot to update the target unit or target account.

6. A bill information processing device based on artificial intelligence AI and robotic process automation RPA, characterized in that, It includes: A login module, configured to control the RPA robot to log in to the bill system whenever a processing cycle arrives; A selection module, configured to control the RPA robot to select a target unit and a target account corresponding to the target unit in the bill matching interface of the bill system; A matching module, configured to, when the bill matching interface displays the bill record information and bill details information corresponding to the target account in response to the selected target unit and target account, control the RPA robot to match the bill record information with the bill details information; An acquisition module, configured to control the RPA robot to perform content extraction on each bill record in the bill record information based on the natural language processing technology NLP to obtain a first description content corresponding to each bill record; Controlling the RPA robot to perform content extraction on each bill detail in the bill details information based on the natural language processing technology NLP to obtain a second description content corresponding to each bill detail; among them, the first description content includes the occurrence date, bill type, and bill value of the bill record, and the second description content includes the occurrence date, bill type, and bill value of the bill detail; The matching module is further configured to, for any bill record in the bill record information, control the RPA robot to determine, according to the first description content corresponding to any bill record and the second description content corresponding to each bill detail in the bill details information, a target bill detail in the bill details information whose second description content matches the first description content corresponding to any bill record; Controlling the RPA robot to perform bill value matching between any bill record and the target bill details.

7. The device according to claim 6, characterized in that, The first description content includes the corresponding first bill type and the first bill occurrence date. The second description content includes the corresponding second bill type and the second bill occurrence date. The matching module is further configured to: Control the RPA robot to match the first bill type in the first description content with the second bill types in the second description content corresponding to each bill detail, so as to determine candidate bill details that match the first bill type in the first description content from the bill detail information; Control the RPA robot to match the first bill occurrence date in the first description content with the second bill occurrence dates in the second description content corresponding to the candidate bill details, so as to determine target bill details that match the first bill occurrence date in the first description content from the candidate bill details; Wherein, the difference between the second bill occurrence date of the target bill detail and the first bill occurrence date is less than or equal to a set threshold.

8. The device according to claim 6, wherein The matching module is further configured to: Control the RPA robot to obtain the first bill value corresponding to any bill record and the second bill value corresponding to the target bill detail based on the natural language processing technology NLP; Control the RPA robot to compare the first bill value with the second bill value to determine whether any bill record matches the target bill detail.

9. An electronic device, characterized in that, It includes: A processor and a memory. Instructions are stored in the memory, and the instructions are loaded and executed by the processor to implement the method according to any one of claims 1 to 5.

10. A computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the method according to any one of claims 1-5 is implemented.

Images