Bill processing method, device, electronic device and storage medium

Abstract

The present application is applicable to the field of big data technology, and provides a method, device, electronic device and storage medium for processing bills, the method comprising: extracting any target bill from a database of bills to be processed; the management information of the target bill includes module identifiers of multiple preset management dimensions; selecting target submodules corresponding to the module identifiers from the submodule libraries associated with each of the management dimensions; encapsulating the target submodules of all the management dimensions to generate a target management algorithm corresponding to the target bill; importing the target bill into the target management algorithm, and outputting the bill processing result corresponding to the target bill. By adopting the above method, it is possible to realize that submodules between different management dimensions can be reused with each other, which greatly reduces the difficulty of developing the bill management algorithm and thereby improves the efficiency of bill management.

Description

Technical Field

[0001] The present application belongs to the field of big data technology, and in particular relates to a bill processing method, device, electronic device and storage medium. Background Art

[0002] With the increasing use of electronic technology, large amounts of information, bills, and other data can be stored and managed electronically. In particular, the emergence of electronic bills has greatly improved the efficiency of account reconciliation. As social activities continue to diversify and inter-business communication becomes more frequent, the number of electronic bills is also increasing. How to effectively reconcile and archive this vast array of bills has become a pressing issue.

[0003] With existing bill processing technology, the same transaction object will generate different types of bills in different transaction scenarios. The bill management system needs to configure corresponding management modules for different scenarios and verify and archive the bills through the management modules. With the increasing number of transaction scenarios, a transaction object may have hundreds or even thousands of management modules, which greatly increases the module development volume of the bill management process and also increases the code complexity of the management system. Summary of the Invention

[0004] The embodiments of the present application provide a bill processing method, apparatus, electronic device, and storage medium, which can solve the problem of existing bill processing technology. With the increasing trend of transaction scenarios, a transaction object may have hundreds or thousands of management modules, which greatly increases the module development volume of the bill management process and also increases the code complexity of the management system.

[0005] In a first aspect, an embodiment of the present application provides a method for processing a bill, comprising:

[0006] Extract any target bill from the bill database to be processed; the management information of the target bill includes module identifiers of multiple preset management dimensions;

[0007] Selecting target submodules corresponding to the module identifiers from the submodule libraries associated with each of the management dimensions;

[0008] According to the input and output relationship between each of the target sub-modules, encapsulate each of the target sub-modules and generate a target management algorithm corresponding to the target bill;

[0009] The target bill is processed by the target management algorithm, and a bill processing result is output.

[0010] In a possible implementation of the first aspect, before selecting the target sub-module corresponding to the module identifier from the sub-module libraries associated with each of the management dimensions, the method further includes:

[0011] If a configuration instruction initiated by a user is received, a visual interface for configuring the target submodule is generated;

[0012] In response to a configuration operation initiated by the user in the visual interface, obtaining a module configuration segment corresponding to the configuration operation; the configuration operation is further used to determine the management dimension;

[0013] Performing semantic analysis on the module configuration segment to determine at least one function keyword and a characteristic parameter associated with the function keyword;

[0014] Extracting a target function template associated with the function keyword from a preset function template library, and configuring custom parameters in the target function template based on the characteristic parameters to generate a target function corresponding to the function keyword;

[0015] Based on all the target functions, a target sub-module corresponding to the configuration operation is generated, and the generated target sub-module is added to the sub-module library of the management dimension specified by the configuration operation.

[0016] In a possible implementation of the first aspect, the method further includes:

[0017] If a new submodule is created in any of the submodule libraries, a training bill associated with the new submodule is obtained, and first training data corresponding to the training bill is output through the new submodule;

[0018] Importing the training bill into each existing submodule created in the submodule library to obtain second training data;

[0019] Calculating the processing similarity between the newly added submodule and each existing submodule based on the first training data and the second training data;

[0020] Obtaining historical configuration information of the existing submodule and newly added configuration information of the newly added submodule, and calculating configuration similarity between the newly added submodule and each of the existing submodules;

[0021] Determining a module overlap between the newly added submodule and the existing submodule based on the processing similarity and the configuration similarity;

[0022] If the overlap degree of any of the modules is greater than a preset overlap threshold, redundant prompt information about the newly added sub-module is generated.

[0023] In a possible implementation of the first aspect, obtaining the historical configuration information of the existing submodule and the newly added configuration information of the newly added submodule, and calculating the configuration similarity between the newly added submodule and each of the existing submodules includes:

[0024] Performing semantic analysis on the historical configuration information to determine a first keyword of the historical configuration information and a first characteristic parameter associated with the first keyword;

[0025] Performing semantic analysis on the newly added configuration information to determine a second keyword of the historical configuration information and a second characteristic parameter associated with the second keyword;

[0026] Selecting associated keywords matching the second keyword from all the first keywords, and calculating a parameter coverage ratio between a first feature parameter of the associated keyword and the second feature parameter;

[0027] The configuration similarity between the newly added submodule and the existing submodule is obtained according to the parameter coverage corresponding to all the second feature parameters.

[0028] In a possible implementation of the first aspect, extracting any target bill from the to-be-processed bill database includes:

[0029] Determine the transaction object of the target bill; the transaction object includes the payee and the recipient;

[0030] Selecting a processed archived bill that matches the transaction object from the historical bill library;

[0031] According to the association management algorithm used when managing each archived bill, all the archived bills are divided into multiple algorithm classes; the archived bills in each algorithm class use the same association management algorithm;

[0032] Calculate the matching confidence between the target bill and each algorithm class respectively; the matching confidence is specifically:

[0033]

[0034] Among them, ConfidenceLv(Bill t ,[Class i ] j ) is the matching confidence between the target bill and the jth algorithm class; Num([Class i ] j) is the total number of archived bills included in the jth algorithm class; CurrentTime is the generation time of the target bill; DealTime i Bill is the generation time of the i-th archived bill in the j-th algorithm class; t The transaction amount of the target bill; Class i is the transaction amount of the i-th archived bill in the j-th algorithm class; ξ and ω are the preset adjustment coefficients;

[0035] According to the association management algorithm corresponding to the algorithm class with the highest matching confidence, the module identifier corresponding to each management dimension of the target bill is configured to generate the management information.

[0036] In a possible implementation of the first aspect, the management dimension includes a dimension hierarchy;

[0037] The selecting the target submodule corresponding to the module identifier from the submodule library associated with each management dimension includes:

[0038] Selecting a target submodule of the Nth dimensional level identified by a module associated with the Nth dimensional level from the submodule library of the management dimension of the Nth dimensional level; the initial value of N is 1;

[0039] If the value of N is less than the preset total number of levels, based on the module identifier associated with the Nth dimensional level, the sub-module library of the management dimension of the N+1th dimensional level is adjusted;

[0040] Increase the value of N and return to execute the operation of selecting the target sub-module of the Nth dimensional level identified by the module associated with the Nth dimensional level from the sub-module library of the management dimension of the Nth dimensional level until the value of N is greater than or equal to the total number of levels.

[0041] In a possible implementation of the first aspect, the management dimension includes a reconciliation trigger dimension;

[0042] The processing of the target bill by the target management algorithm and outputting a bill processing result includes:

[0043] Determining the reconciliation triggering timing of the target bill through the target submodule associated with the reconciliation triggering dimension;

[0044] If any bill status of the target bill does not meet the reconciliation trigger timing, the target bill is returned to the bill database;

[0045] If all the bill statuses of the target bill meet the reconciliation trigger timing, the bill processing result is generated.

[0046] In a second aspect, an embodiment of the present application provides a bill processing device, comprising:

[0047] A target bill extraction unit is configured to extract any target bill from the bill database to be processed; the management information of the target bill includes module identifiers of multiple preset management dimensions;

[0048] a target submodule selection unit, configured to select a target submodule corresponding to the module identifier from the submodule library associated with each management dimension;

[0049] A target management algorithm generating unit, configured to encapsulate each target submodule according to the input and output relationship between each target submodule, and generate a target management algorithm corresponding to the target bill;

[0050] The bill processing result generating unit is used to process the target bill through the target management algorithm and output the bill processing result.

[0051] In a third aspect, an embodiment of the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in any one of the first aspects above is implemented.

[0052] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the first aspects above is implemented.

[0053] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on an electronic device, enables the electronic device to execute any one of the methods described in the first aspect above.

[0054] Compared with the prior art, the embodiments of the present application have the following advantages: by storing all target bills to be processed in a bill database, when the target bill needs to be managed, it is extracted from the bill database, and according to the management information of the target bill, the target submodule matching the module identifier recorded in the management information is extracted from the submodule library of different management dimensions, by encapsulating the target submodules of all management dimensions, generating a target management algorithm for managing the target bill, and generating the bill processing result of the target bill through the target management algorithm, thereby realizing automatic management of the bill. Compared with the existing bill management technology, the embodiments of the present application do not need to configure corresponding bill management algorithms for different transaction objects. Since the bill processing algorithms for different transaction objects in the same transaction scenario are similar or even the same, the present application decouples the bill management algorithm from the transaction object and divides the bill management algorithm by preset management dimensions, so that the submodules between different management dimensions can be reused, which greatly reduces the difficulty of developing the bill management algorithm and thus improves the efficiency of bill management; on the other hand, thanks to the mutual decoupling between different management dimensions, the code complexity of the entire algorithm library is also reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0056] Figure 1 This is a flowchart of a method for processing bills provided in one embodiment of the present application;

[0057] Figure 2 This is a schematic diagram of an implementation method of a bill processing method provided in one embodiment of the present application;

[0058] Figure 3 is a schematic diagram of a visualization interface provided by an embodiment of the present application;

[0059] Figure 4 This is a schematic diagram of an implementation method of a bill processing method provided in one embodiment of the present application;

[0060] Figure 5 This is a schematic diagram of an implementation of S101 of a bill processing method provided in one embodiment of the present application;

[0061] Figure 6 This is a schematic diagram of an implementation method of S102 of a bill processing method provided in one embodiment of the present application;

[0062] Figure 7 This is a schematic diagram of an implementation of a bill processing method S104 provided in one embodiment of the present application;

[0063] Figure 8 This is a schematic diagram of the structure of a bill processing device provided in an embodiment of the present application;

[0064] Figure 9 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0065] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0066] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0067] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0068] The bill processing method provided in the embodiments of the present application can be applied to electronic devices such as smartphones, servers, tablet computers, laptops, ultra-mobile personal computers (UMPCs), and netbooks. The embodiments of the present application do not impose any restrictions on the specific type of electronic device. In particular, the electronic device can also be a big data-based bill management server that can manage received bills, including verifying, archiving, and providing result feedback, and generating bill processing results.

[0069] See also Figure 1 , Figure 1 A flowchart illustrating a method for processing a bill provided in an embodiment of the present application is shown. The method includes the following steps:

[0070] In S101, any target bill is extracted from a database of bills to be processed; the management information of the target bill includes module identifiers of multiple preset management dimensions.

[0071] In this embodiment, the electronic device can receive bills that require management from various transaction partners and store all bills in a bill pool, namely, the aforementioned pending bill database. The electronic device can then extract any target bill from the pending bill database and manage the target bill. This management can include reconciling the target bill, namely, verifying the accuracy of each item in the bill and generating corresponding verification results. The verification results for each item serve as the subsequent bill processing results.

[0072] In one possible implementation, the electronic device may be configured with a corresponding bill management cycle, and the electronic device may extract the corresponding target bill from the bill database for management according to the bill management cycle. For example, if the bill management cycle is 10 seconds, the electronic device will extract a target bill to be processed from the bill database every 10 seconds for reconciliation. The order of extraction may be determined by the order in which the target bills to be processed are added to the bill database, or by the processing priority of the target bills to be processed. The electronic device may be configured with different bill management cycles according to different time periods. For example, during busy time periods, the electronic device may be configured with a longer bill management cycle. Since the electronic device may need to allocate some resources to handle other tasks, such as bill reception and storage, the corresponding resources available for bill reconciliation are less. In this case, the time interval between processing each target bill can be extended. Conversely, during idle time periods, when there are more resources available for reconciliation, the electronic device may be configured with a shorter bill management cycle, so that the reconciliation interval can be dynamically adjusted to improve the utilization of device resources.

[0073] In one possible implementation, if different target bills have different processing priorities, when an electronic device receives the target bill and adds it to a bill database, it can automatically set the processing priority associated with the target bill. Specifically, the processing priority can be set by: obtaining management information of the target bill, determining the transaction object and transaction scenario based on the management information; determining the priority range associated with the transaction object based on the preset correspondence between the processing priority and the transaction object, and determining the associated correction coefficient based on the above transaction scenario; and determining the processing priority of the target bill based on the priority range and the above correction coefficient. This can automatically identify the priority of the target bill, thereby improving the flexibility and efficiency of bill management.

[0074] In one possible implementation, the electronic device can also receive a reconciliation request initiated by the user, which carries the account identifier of the target account to be reconciled. The electronic device can extract the corresponding target bill from the bill database based on the account identifier and perform reconciliation operations on the account.

[0075] In this embodiment, each target bill is associated with corresponding management information, and the management information records the module identifiers of different management dimensions, so that the electronic device can automatically generate a target management algorithm that matches the target bill. Exemplarily, the above-mentioned management dimensions include but are not limited to: the above-mentioned preset management dimensions include: enterprise name, business scenario, split time and expense type four management dimensions, then the bill management information corresponding to the target bill can include the identifiers corresponding to the above four dimensions, that is, the management information corresponding to a certain target bill can specifically be: enterprise identifier: enterprise A, business scenario: air ticket, split time: settlement upon completion of charging, expense type: VIP1 level, thereby limiting the module identifiers corresponding to different management dimensions.

[0076] In S102, target sub-modules corresponding to the module identifiers are selected from the sub-module libraries associated with the management dimensions.

[0077] In this embodiment, the electronic device can configure corresponding sub-module libraries for different management dimensions. The sub-module library associated with each management dimension stores sub-modules related to the management dimension, and all sub-modules in the sub-module library contain management algorithms associated with the management dimension. For example, for Enterprise A and Enterprise B, when processing bills for air tickets in a business scenario, they both need to verify the air ticket amount, departure place, destination, and refund and change records, that is, the management content and verification method are the same. Therefore, the enterprise and the transaction scenario can be decoupled, and corresponding sub-modules can be generated for different management algorithms for air tickets in a business scenario, and stored in the sub-module library corresponding to the management dimension for air tickets in a business scenario, and corresponding module identifiers are configured for different management algorithms, such as Air Ticket 2, which means that the management dimension is business scenario-air tickets, and the corresponding sub-module is the sub-module numbered 2 in the management dimension.

[0078] In this embodiment, different reconciliation rules are encapsulated into multiple submodules in the aforementioned manner, and corresponding module identifiers are assigned to the different submodules. The electronic device can identify the module identifier in the management information of the target bill and extract the associated submodule from the corresponding management submodule library as the target submodule corresponding to the target bill when processing the target bill.

[0079] In S103, according to the input and output relationship between each of the target sub-modules, each of the target sub-modules is encapsulated to generate a target management algorithm corresponding to the target bill.

[0080] In this embodiment, after the electronic device determines the target sub-modules corresponding to different management dimensions, it can encapsulate and merge the various target sub-modules. Since different target sub-modules are only used to limit the reconciliation rules corresponding to specific management dimensions, and not the reconciliation rules corresponding to the entire target bill, all target sub-modules need to be merged to generate a target management algorithm corresponding to the target bill.

[0081] In one possible implementation, each management dimension can be associated with a corresponding dimension serial number. The electronic device can splice each target sub-module in sequence according to the above dimension serial number, and the output of the target sub-module of the previous dimension is the input of the target sub-module of the next dimension. Therefore, according to the relationship between input and output, each target sub-module can be spliced ​​in sequence, thereby generating a target management algorithm based on the preset dimension sorting.

[0082] In S104, the target bill is processed by the target management algorithm and a bill processing result is output.

[0083] In this embodiment, after obtaining and determining the target management algorithm corresponding to the target bill, the electronic device can process the above-mentioned target bill through the target management algorithm. Taking reconciliation as an example, the electronic device can determine the items that need to be checked for the target bill according to the above-mentioned target management algorithm, and obtain the standard data corresponding to each item, compare the standard data with the bill data recorded for the item in the target bill, determine the audit result corresponding to the item based on the comparison result, and generate the bill processing result corresponding to the target bill based on the audit results of all items.

[0084] In one possible implementation, if the audit results of any item fail the audit, the target bill is identified as an abnormal bill; conversely, if the audit results of all items pass the audit, the target bill is identified as a legal bill, archived (for example, stored in an archived database), and removed from the above-mentioned pending bill database.

[0085] As can be seen from the above, the bill processing method provided by the embodiment of the present application stores all target bills to be processed in the bill database. When the target bill needs to be managed, it is extracted from the bill database, and according to the management information of the target bill, the target submodule matching the module identifier recorded in the management information is extracted from the submodule library of different management dimensions. By encapsulating the target submodules of all management dimensions, a target management algorithm for managing the target bill is generated, and the bill processing result of the target bill is generated by the target management algorithm, thereby realizing automatic management of the bill. Compared with the existing bill management technology, the embodiment of the present application does not need to configure corresponding bill management algorithms for different transaction objects. Since the bill processing algorithms for different transaction objects in the same transaction scenario are similar or even the same, the present application decouples the bill management algorithm from the transaction object and divides the bill management algorithm by the preset management dimension, so that the submodules between different management dimensions can be reused with each other, which greatly reduces the difficulty of developing the bill management algorithm and thus improves the efficiency of bill management. On the other hand, thanks to the mutual decoupling between different management dimensions, the code complexity of the entire algorithm library is also reduced.

[0086] Figure 2 The following is a flowchart showing a specific implementation of a bill processing method provided by the second embodiment of the present invention. Figure 2 , relative to Figure 1 In the embodiment, the bill processing method provided by this embodiment further includes, before selecting the target submodule corresponding to the module identifier from the submodule library associated with each management dimension, S201 to S205, which are described in detail as follows:

[0087] Furthermore, before selecting the target submodule corresponding to the module identifier from the submodule libraries associated with each management dimension, the method further includes:

[0088] In S201 , if a configuration instruction initiated by a user is received, a visual interface for configuring the target submodule is generated.

[0089] In this embodiment, the electronic device can generate a target submodule based on the user's configuration operation. The user can send a configuration instruction to the electronic device through the user terminal, or initiate the above configuration instruction locally in the electronic device. When the electronic device receives the configuration instruction, it can generate a visual interface for configuring the target submodule. In order to improve the generation efficiency of the target submodule, the electronic device hides the code segment corresponding to the module and generates a visual interface containing multiple setting items. The user can enter the corresponding setting parameters in the visual interface, or select the preset configuration options in the project to create the target submodule. The above visual interface is divided into three types: module creation, module modification, and module deletion according to the different ways of managing the modules.

[0090] In S202, in response to a configuration operation initiated by the user in the visual interface, a module configuration segment corresponding to the configuration operation is obtained; the configuration operation is also used to determine the management dimension.

[0091] In this embodiment, for a module creation type configuration operation, there may be multiple items to be configured in the visual interface. For example, Figure 3 A schematic diagram of a visualization interface provided by an embodiment of the present application is shown. The visualization interface includes multiple setting items, namely module identification, dimension type, audit item, and parameter setting. Based on the visualization interface, the user can enter the corresponding parameters in the associated items. After all parameters are configured, the user can click the Done button in the visualization interface. The electronic device then collects the user-entered data for each setting item, thereby obtaining the module setting section.

[0092] In this embodiment, when the user initiates a configuration operation corresponding to a target submodule, the user may limit the management dimension associated with the target submodule, for example, by checking, clicking, or inputting to determine the management dimension associated with the configured target submodule.

[0093] In S203, semantic analysis is performed on the module configuration paragraph to determine at least one function keyword and a characteristic parameter associated with the function keyword.

[0094] In this embodiment, after receiving the module configuration paragraph input by the user, the electronic device can perform semantic analysis on the module configuration paragraph. Since the user can use natural language input when configuring the target submodule, that is, not a standard code configuration paragraph, the electronic device can perform semantic understanding of the natural language, identify the function keyword contained in the module configuration paragraph, and determine the character type corresponding to the function keyword based on the function keyword. The electronic device then checks whether the sentence corresponding to the function keyword in the module configuration paragraph contains an associated character corresponding to the above character type. If so, the associated character is identified as a characteristic parameter associated with the function keyword.

[0095] In S204, a target function template associated with the function keyword is extracted from a preset function template library, and the custom parameters in the target function template are configured based on the characteristic parameters to generate a target function corresponding to the function keyword.

[0096] In this embodiment, the electronic device may store a function template library containing all function templates related to the management dimension. The electronic device may extract a target function template corresponding to the identified function keyword from the corresponding function template library based on the management dimension specified by the configuration operation. The target function template contains corresponding custom parameters, and the electronic device may assign values ​​to the custom parameters based on the characteristic parameters corresponding to the function keyword, thereby generating a target function corresponding to the function keyword.

[0097] In S205 , based on all the target functions, a target sub-module corresponding to the configuration operation is generated, and the generated target sub-module is added to the sub-module library of the management dimension specified by the configuration operation.

[0098] In this embodiment, after the electronic device configures corresponding target functions for all function keywords, it can encapsulate all target functions to generate a target sub-module corresponding to the configuration operation, thereby realizing the task of creating the target sub-module, and adding the created target sub-module to the sub-module library corresponding to the management dimension for subsequent calls.

[0099] In an embodiment of the present application, a visual interface is generated and configuration operations initiated by the user in the visual interface are received, thereby generating a corresponding target sub-module, thereby enabling the creation operation of the target sub-module to be implemented. Since a visual interface is generated, the difficulty of module creation can be reduced, and the input language is not a code language, but can be described in natural language and converted into a standard code function through semantic analysis and keyword matching, which further reduces the difficulty of module creation.

[0100] Figure 4 The following is a flowchart showing a specific implementation of a bill processing method provided by the third embodiment of the present invention. Figure 4 , relative to Figure 1 The embodiment provides a bill processing method further comprising: S401 to S406, which are described in detail as follows:

[0101] In S401, if a new sub-module is created in any of the sub-module libraries, a training bill associated with the new sub-module is obtained, and first training data corresponding to the training bill is output through the new sub-module.

[0102] In this embodiment, when the electronic device detects the addition of a new submodule to the submodule library of any management dimension, i.e., the newly added submodule, it can perform module redundancy identification on the newly added submodule to determine whether similar submodules exist within the existing submodule library, thereby reducing the code complexity of the entire code database. Based on this, the electronic device can obtain a training bill corresponding to the newly added submodule and process the training bill through the newly added submodule to generate first training data corresponding to the newly added submodule.

[0103] In S402, the training bill is imported into each existing sub-module created in the sub-module library to obtain second training data.

[0104] In this embodiment, in order to compare the module overlap between the newly added submodule and each existing submodule, the electronic device can also process the above training bill through each existing submodule respectively, so as to obtain the second training data corresponding to each existing submodule.

[0105] In S403 , the processing similarity between the newly added submodule and each existing submodule is calculated based on the first training data and the second training data.

[0106] In this embodiment, after determining the first training data corresponding to the newly added sub-module and the second training data corresponding to the existing sub-module, the electronic device can determine the number of identical data between the two and the processing similarity between the newly added sub-module and the existing sub-module based on the number of first training data and second training data corresponding to the same training bill. Since the processing results of the two are the same for the same training bill, it is highly likely that the audit items and corresponding processing logic corresponding to the two sub-modules are the same or similar. Therefore, whether the two modules belong to the same module can be identified by whether the processing results are the same.

[0107] In S404, historical configuration information of the existing submodule and newly added configuration information of the newly added submodule are obtained, and configuration similarities between the newly added submodule and each of the existing submodules are calculated.

[0108] In this embodiment, the electronic device can also obtain configuration information corresponding to the newly added submodule, that is, the above-mentioned newly added configuration information, and compare the newly added configuration information with the historical configuration information corresponding to the existing submodule, so as to determine the configuration similarity related to the module configuration.

[0109] Furthermore, as another embodiment of the present application, the above S404 specifically includes the following steps:

[0110] In S404.1, semantic analysis is performed on the historical configuration information to determine a first keyword of the historical configuration information and a first characteristic parameter associated with the first keyword.

[0111] In S404.2, semantic analysis is performed on the newly added configuration information to determine a second keyword of the historical configuration information and a second characteristic parameter associated with the second keyword.

[0112] In S404.3, associated keywords matching the second keyword are selected from all the first keywords, and a parameter coverage ratio between the first characteristic parameter of the associated keyword and the second characteristic parameter is calculated.

[0113] In S404.4, the configuration similarity between the newly added submodule and the existing submodule is obtained based on the parameter coverage corresponding to all the second characteristic parameters.

[0114] In this embodiment, when configuring a submodule, the user can enter the corresponding module configuration paragraph. Each module configuration paragraph can include a corresponding function keyword and a characteristic parameter corresponding to the function keyword. The electronic device can respectively determine the function keyword (i.e., the first keyword) corresponding to the newly added submodule and the characteristic parameter (i.e., the first characteristic parameter) corresponding to the function keyword. Correspondingly, the above operation can also be performed on the existing submodule to determine the second keyword and the second characteristic parameter corresponding to the second keyword.

[0115] In this embodiment, after the electronic device extracts the function keywords and corresponding feature parameters of the newly added submodule and the existing submodule, it can compare whether the corresponding feature parameters are the same between the same function keywords, thereby calculating the corresponding parameter coverage. For example, the newly added submodule contains the keyword "air ticket amount" and the corresponding feature parameter is "greater than 10,000", while the existing submodule also contains the keyword "air ticket amount" and the corresponding feature parameter is "greater than 8,000", then the above two keywords can be identified as having an associated relationship, and the parameter coverage between the two feature parameters can be compared. The coverage between the above two parameters is 80%. After determining the parameter coverage between all the keywords that have an associated relationship, the electronic device can determine the configuration similarity between the two modules.

[0116] In an embodiment of the present application, by respectively determining the function keywords contained in the two sub-modules and the characteristic parameters corresponding to the function keywords, the degree of repetition of the parameters between the two sub-modules is compared, and the degree of parameter overlap is used as the configuration similarity between the two configuration information. This can achieve parameter quantification of the configuration similarity and improve the accuracy of configuration similarity identification.

[0117] In S405 , the module overlap between the newly added submodule and the existing submodule is determined based on the processing similarity and the configuration similarity.

[0118] In this embodiment, the electronic device can determine the degree of module overlap between the newly added sub-module and the existing sub-module based on the processing similarity and configuration similarity. For example, the electronic device can set corresponding weights for the processing dimension and the configuration dimension, perform a weighted superposition of the processing similarity and the configuration similarity based on the weights of the two dimensions, and calculate the module overlap between the two modules.

[0119] In S406 , if the overlap degree of any of the modules is greater than a preset overlap threshold, redundant prompt information about the newly added sub-module is generated.

[0120] In this embodiment, if there is an existing sub-module in the sub-module library whose module overlap with the newly added sub-module is greater than the overlap threshold, the electronic device can generate corresponding redundant prompt information to prompt the user that a corresponding sub-module has been created in the sub-module library, and add the module identifier of the existing sub-module whose module overlap with the newly added sub-module is greater than the overlap threshold to the above redundant prompt information so that the user can perform redundant confirmation.

[0121] In an embodiment of the present application, after receiving a newly added sub-module, it can be compared with the existing sub-modules, and when it is detected that there is an existing sub-module with a high degree of overlap with it, redundant prompt information is generated to prompt that the same sub-module already exists in the sub-module library, avoiding users from repeatedly creating the same or similar sub-modules, thereby reducing the code redundancy of the sub-module library.

[0122] Figure 5 The flowchart of the specific implementation of the bill processing method S101 provided by the fourth embodiment of the present invention is shown. Figure 5 , relative to Figure 1 In the embodiment, the bill processing method provided in this embodiment includes S1011 to S1015, which are described in detail as follows:

[0123] In S1011, the transaction object of the target bill is determined; the transaction object includes a payee and a payee.

[0124] In this embodiment, in addition to being user-configurable, the target bill management information can also be automatically configured by the electronic device based on the target bill's transaction recipient. Based on this, the electronic device can identify the target bill's contents and determine the transaction recipient corresponding to the target bill. This transaction recipient includes the payee and recipient of the target bill. Optionally, if other intermediary transaction recipients exist, these intermediary transaction recipients may also be included within the transaction recipient, with the specific determination based on actual circumstances.

[0125] In S1012, a processed archived bill that matches the transaction object is selected from the historical bill library.

[0126] In this embodiment, the electronic device's historical bill library stores all archived bills (i.e., bills that have been reconciled through a management algorithm), and each archived bill is also associated with a corresponding transaction object. Based on this, the electronic device can select an archived bill from the historical bill library whose transaction object is the same as the transaction object of the target bill, and determine the management information of the target bill based on the archived bill selected above.

[0127] In S1013, all the archived bills are divided into multiple algorithm classes according to the association management algorithm used when managing each archived bill; the archived bills in each algorithm class use the same association management algorithm.

[0128] In this embodiment, since each archived bill is a reconciled bill, i.e., it has been processed by a corresponding management algorithm, the electronic device can identify the management algorithm used when reconciling each archived bill, i.e., the aforementioned association management algorithm, and classify all archived bills based on whether the association management algorithms are the same, thereby obtaining multiple algorithm classes. The archived bills in each algorithm class use the same association management algorithm when reconciling.

[0129] In S1014, the matching confidence between the target bill and each algorithm class is calculated respectively; the matching confidence is specifically:

[0130]

[0131] Among them, ConfidenceLv(Bill t ,[Class i ] j ) is the matching confidence between the target bill and the jth algorithm class; Num([Class i ] j ) is the total number of archived bills included in the jth algorithm class; CurrentTime is the generation time of the target bill; DealTime i Bill is the generation time of the i-th archived bill in the j-th algorithm class; t The transaction amount of the target bill; Class i is the transaction amount of the i-th archived bill in the j-th algorithm class; ξ and ω are the preset adjustment coefficients

[0132] In this embodiment, after the electronic device has been divided into multiple algorithm classes, it can calculate the similarity between the archived bills and the target bills within each algorithm class, thereby determining the matching confidence level of the target bill belonging to the algorithm class based on the similarity between the archived bills and the target bills. The similarity between the archived bills and the target bills is mainly related to the generation time and transaction amount of the bills. The closer the similarity between the two, the higher the corresponding similarity, and the higher the confidence level between the target bill and the algorithm class.

[0133] In S1015, according to the association management algorithm corresponding to the algorithm class with the highest matching confidence, the module identifier corresponding to each management dimension of the target bill is configured to generate the management information.

[0134] In this embodiment, after calculating the matching confidence corresponding to each algorithm class, the electronic device can select the associated management algorithm corresponding to the algorithm class with the highest value as the target management algorithm corresponding to the target bill, and based on the target sub-modules used in each management dimension in the target management algorithm, determine the module identifier associated with the target bill in each management dimension, thereby obtaining the management information of the target bill and realizing automatic configuration of the management information.

[0135] In an embodiment of the present application, by determining the archived bill that matches the target bill from the archived bills and automatically configuring the management information of the target bill based on the association management algorithm used by the archived bills, the flexibility of the management information configuration can be further improved and the efficiency of bill management can be improved.

[0136] Figure 6 The flowchart of the specific implementation of the bill processing method S102 provided by the fifth embodiment of the present invention is shown. Figure 6 , relative to Figure 1-5 In any of the above embodiments, in a bill processing method provided in this embodiment, S102 includes: S1021 to S1023, which are described in detail as follows:

[0137] Furthermore, the management dimension includes a dimension hierarchy;

[0138] The selecting the target submodule corresponding to the module identifier from the submodule library associated with each management dimension includes:

[0139] In S1021 , a target submodule of the Nth dimensional level identified by a module associated with the Nth dimensional level is selected from the submodule library of the management dimension of the Nth dimensional level; the initial value of N is 1.

[0140] In S1022 , if the value of N is less than the preset total number of levels, the sub-module library of the management dimension of the N+1 th dimensional level is adjusted based on the module identifier associated with the N th dimensional level.

[0141] In S1023, the value of N is increased, and the operation of selecting the target sub-module of the Nth dimensional level identified by the module associated with the Nth dimensional level from the sub-module library of the management dimension of the Nth dimensional level is returned to be executed until the value of N is greater than or equal to the total number of levels.

[0142] In this embodiment, there is a certain cascade relationship between each management dimension. The management dimension of the upper level can be associated with a specific target submodule in the management dimension of the lower level, thereby greatly improving the search efficiency of the target submodule. For example, the cascade relationship of each management dimension in a certain management system is: transaction object (first dimension level) → transaction scenario (second dimension level) → payment method (third dimension level). If the transaction object is user A and the specific transaction scenario associated with it is the air ticket scenario and the train ticket scenario, then when the management dimension of the transaction object of a certain target bill is identified as user A, it is only necessary to select the corresponding target submodule in the air ticket scenario and the train ticket scenario, without extracting the target submodule from the submodules of all transaction scenarios, thereby improving the extraction efficiency of the target submodule and performing batch filtering of the submodules through the cascade relationship. That is, the submodule library of the next level is determined by the module identifier of the target submodule of the previous level, until the target submodule of the last management level is selected, that is, the identification has been completed.

[0143] In an embodiment of the present application, by configuring the cascade relationship between different management dimensions, the purpose of batch filtering invalid sub-modules is achieved, thereby greatly improving the extraction efficiency of the target sub-module and then improving the processing efficiency of the target bill.

[0144] Figure 7 The flowchart of the specific implementation of the bill processing method S104 provided by the sixth embodiment of the present invention is shown. Figure 7 , relative to Figure 1-5 In any of the embodiments, in the bill processing method provided in this embodiment, step S104 includes: S1041 to S1043, which are described in detail as follows:

[0145] Furthermore, the management dimension includes a reconciliation trigger dimension;

[0146] The processing of the target bill by the target management algorithm and outputting a bill processing result includes:

[0147] In S1041 , the reconciliation triggering timing of the target bill is determined through the target submodule associated with the reconciliation triggering dimension.

[0148] In S1042, if any bill status of the target bill does not meet the reconciliation triggering timing, the target bill is returned to the bill database.

[0149] In S1043, if all the bill statuses of the target bill meet the reconciliation triggering timing, the bill processing result is generated.

[0150] In this embodiment, the processing dimension of the target bill includes a reconciliation trigger dimension, which is used to determine the reconciliation timing corresponding to the target bill. Due to different transaction scenarios or different transaction objects, the timing of reconciliation may be different. For example, some bills are reconciled after expense splitting and reconciliation after reimbursement, while some bills are reconciled after expense splitting and reconciliation after consumption is completed. Therefore, in order to achieve diversified reconciliation settings, before checking whether the various items of the target bill are correct, the electronic device can first determine whether the current reconciliation trigger timing of the target bill is met, and when it is identified that the preset reconciliation trigger timing is not met, the target bill will be returned to the bill database to be processed; on the contrary, if all reconciliation trigger timings are met, the target bill will be processed through the target management algorithm to obtain the corresponding bill processing result.

[0151] In the embodiment of the present application, by identifying whether the reconciliation trigger timing of the target bill is currently met, the accuracy of the reconciliation timing can be improved to meet the personalized needs of different users for reconciliation timing.

[0152] Figure 8 The electronic device includes various units for executing Figure 1 Each step in the corresponding embodiment. Please refer to Figure 1 and Figure 1 For the sake of convenience, only the parts related to this embodiment are shown.

[0153] See also Figure 8 The bill processing method and device includes:

[0154] The target bill extraction unit 81 is used to extract any target bill from the bill database to be processed; the management information of the target bill includes module identifiers of multiple preset management dimensions;

[0155] A target submodule selection unit 82 is configured to select a target submodule corresponding to the module identifier from the submodule library associated with each management dimension;

[0156] The target management algorithm generating unit 83 is used to encapsulate each target submodule according to the input and output relationship between each target submodule, and generate a target management algorithm corresponding to the target bill;

[0157] The bill processing result generating unit 81 is configured to process the target bill using the target management algorithm and output a bill processing result.

[0158] Optionally, the bill processing device further includes:

[0159] a configuration instruction receiving unit, configured to generate a visual interface for configuring the target submodule upon receiving a configuration instruction initiated by a user;

[0160] a module configuration segment acquisition unit, configured to, in response to a configuration operation initiated by the user in the visual interface, acquire a module configuration segment corresponding to the configuration operation; the configuration operation is further used to determine the management dimension;

[0161] a characteristic parameter determination unit, configured to perform semantic analysis on the module configuration segment to determine at least one function keyword and a characteristic parameter associated with the function keyword;

[0162] An objective function generating unit is configured to extract an objective function template associated with the function keyword from a preset function template library, and configure custom parameters in the objective function template based on the characteristic parameters to generate an objective function corresponding to the function keyword;

[0163] The objective function encapsulation unit is used to generate the target sub-module corresponding to the configuration operation based on all the objective functions, and add the generated target sub-module to the sub-module library of the management dimension specified by the configuration operation.

[0164] Optionally, the bill processing device further includes:

[0165] A first training data generating unit is configured to obtain a training bill associated with a newly added submodule if a new submodule is created in any of the submodule libraries, and output first training data corresponding to the training bill through the newly added submodule;

[0166] A second training data unit is used to import the training bill into each existing sub-module created in the sub-module library to obtain second training data;

[0167] a processing similarity calculation unit, configured to calculate the processing similarity between the newly added submodule and each existing submodule based on the first training data and the second training data;

[0168] a configuration similarity calculation unit, configured to obtain historical configuration information of the existing submodule and newly added configuration information of the newly added submodule, and calculate configuration similarities between the newly added submodule and each of the existing submodules;

[0169] a module overlap calculation unit, configured to determine a module overlap between the newly added submodule and the existing submodule based on the processing similarity and the configuration similarity;

[0170] The redundant prompt unit is used to generate redundant prompt information about the newly added sub-module if the overlap degree of any of the modules is greater than a preset overlap threshold.

[0171] Optionally, the configuration similarity calculation unit includes:

[0172] a first characteristic parameter determining unit, configured to perform semantic analysis on the historical configuration information to determine a first keyword of the historical configuration information and a first characteristic parameter associated with the first keyword;

[0173] a second characteristic parameter determining unit, configured to perform semantic analysis on the newly added configuration information, and determine a second keyword of the historical configuration information and a second characteristic parameter associated with the second keyword;

[0174] a parameter coverage calculation unit, configured to select associated keywords matching the second keyword from all the first keywords, and calculate a parameter coverage between the first characteristic parameter of the associated keyword and the second characteristic parameter;

[0175] A parameter coverage comparison unit is used to obtain the configuration similarity between the newly added sub-module and the existing sub-module according to the parameter coverage corresponding to all the second feature parameters.

[0176] Optionally, the target bill extraction unit 81 includes:

[0177] A transaction object determination unit, configured to determine the transaction object of the target bill; the transaction object includes a payee and a recipient;

[0178] an archived bill determining unit, configured to select a processed archived bill that matches the transaction object from a historical bill database;

[0179] an algorithm class division unit, configured to divide all archived bills into a plurality of algorithm classes according to an association management algorithm used when managing each archived bill; the archived bills in each algorithm class use the same association management algorithm;

[0180] A matching confidence calculation unit is used to calculate the matching confidence between the target bill and each of the algorithm classes; the matching confidence is specifically:

[0181]

[0182] Among them, ConfidenceLv(Bill t ,[Class i ] j ) is the matching confidence between the target bill and the jth algorithm class; Num([Classi ] j ) is the total number of archived bills included in the jth algorithm class; CurrentTime is the generation time of the target bill; DealTime i Bill is the generation time of the i-th archived bill in the j-th algorithm class; t The transaction amount of the target bill; Class i is the transaction amount of the i-th archived bill in the j-th algorithm class; ξ and ω are the preset adjustment coefficients;

[0183] A management information configuration unit is used to configure the module identifier corresponding to each management dimension of the target bill according to the association management algorithm corresponding to the algorithm class with the highest matching confidence, and generate the management information.

[0184] Optionally, the management dimension includes a dimension hierarchy;

[0185] The target submodule selection unit 82 includes:

[0186] A first cascade processing unit is configured to select a target submodule of the Nth dimensional level identified by a module associated with the Nth dimensional level from the submodule library of the management dimension of the Nth dimensional level; an initial value of N is 1;

[0187] A second cascade processing unit is configured to adjust the sub-module library of the management dimension of the N+1th dimensional level based on the module identifier associated with the Nth dimensional level if the value of N is less than the preset total number of levels;

[0188] A return unit is used to increase the value of N and return to execute the operation of selecting the target sub-module of the Nth dimensional level identified by the module associated with the Nth dimensional level from the sub-module library of the management dimension of the Nth dimensional level, until the value of N is greater than or equal to the total number of levels.

[0189] Optionally, the management dimension includes a reconciliation trigger dimension;

[0190] The bill processing result generating unit 84 includes:

[0191] a reconciliation trigger timing determination unit, configured to determine the reconciliation trigger timing of the target bill through the target submodule associated with the reconciliation trigger dimension;

[0192] a bill database returning unit, configured to return the target bill to the bill database if any bill status of the target bill does not meet the reconciliation triggering timing;

[0193] The reconciliation triggering unit is configured to generate the bill processing result if all the bill statuses of the target bill meet the reconciliation triggering timing.

[0194] Therefore, the bill processing method and device provided by the embodiment of the present invention can also store all target bills to be processed in the bill database, extract them from the bill database when it is necessary to manage the target bill, and extract the target submodule that matches the module identifier recorded in the management information from the submodule library of different management dimensions according to the management information of the target bill, and encapsulate the target submodules of all management dimensions to generate a target management algorithm for managing the target bill, and generate the bill processing result of the target bill through the target management algorithm, thereby realizing automatic management of the bill. Compared with the existing bill management technology, the embodiment of the present application does not need to configure corresponding bill management algorithms for different transaction objects. Since the bill processing algorithms for different transaction objects in the same transaction scenario are similar or even the same, the present application decouples the bill management algorithm from the transaction object and divides the bill management algorithm by the preset management dimension, so that the submodules between different management dimensions can be reused with each other, which greatly reduces the difficulty of developing the bill management algorithm and thus improves the efficiency of bill management; on the other hand, thanks to the mutual decoupling between different management dimensions, the code complexity of the entire algorithm library is also reduced.

[0195] It should be understood that Figure 8 In the structural diagram of the bill processing method shown, each module is used to execute Figures 1 to 7 The steps in the corresponding embodiment, and for Figures 1 to 7 Each step in the corresponding embodiment has been explained in detail in the above embodiment. Figures 1 to 7 as well as Figures 1 to 7 The relevant descriptions in the corresponding embodiments will not be repeated here.

[0196] Figure 9 This is a structural block diagram of an electronic device provided by another embodiment of the present application. Figure 9 As shown, the electronic device 900 of this embodiment includes: a processor 910, a memory 920, and a computer program 930 stored in the memory 920 and executable by the processor 910, such as a program for a bill processing method. When the processor 910 executes the computer program 930, the steps of each embodiment of the above-mentioned bill processing method are implemented, such as Figure 1 Alternatively, the processor 910 executes the computer program 930 to implement the above Figure 9 The functions of each module in the corresponding embodiment are, for example, Figure 8 For details on the functions of units 81 to 84, please refer to Figure 7 Related description in the corresponding embodiment.

[0197] Exemplarily, the computer program 930 may be divided into one or more modules, one or more of which are stored in the memory 920 and executed by the processor 910 to complete the present application. One or more modules may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 930 in the electronic device 900. For example, the computer program 930 may be divided into various unit modules, and the specific functions of each module are as described above.

[0198] The electronic device 900 may include, but is not limited to, a processor 910 and a memory 920. Those skilled in the art will appreciate that Figure 9 This is merely an example of the electronic device 900 and does not constitute a limitation of the electronic device 900 . The electronic device 900 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0199] The processor 910 may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0200] The memory 920 may be an internal storage unit of the electronic device 900, such as a hard disk or memory of the electronic device 900. The memory 920 may also be an external storage device of the electronic device 900, such as a plug-in hard disk, smart memory card, flash memory card, etc. equipped on the electronic device 900. Furthermore, the memory 920 may include both an internal storage unit of the electronic device 900 and an external storage device.

[0201] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for processing bills, characterized in that: include: Extract any target bill from the bill database to be processed; The management information of the target bill includes module identifiers of multiple preset management dimensions; Selecting target submodules corresponding to the module identifiers from the submodule libraries associated with each of the management dimensions; According to the input and output relationship between each of the target sub-modules, encapsulate each of the target sub-modules and generate a target management algorithm corresponding to the target bill; Processing the target bill using the target management algorithm and outputting a bill processing result; The step of extracting any target bill from the bill database to be processed includes: Determine the transaction object of the target bill; the transaction object includes the payee and the recipient; Selecting a processed archived bill that matches the transaction object from the historical bill library; According to the association management algorithm used when managing each archived bill, all the archived bills are divided into multiple algorithm classes; the archived bills in each algorithm class use the same association management algorithm; Calculate the matching confidence between the target bill and each algorithm class respectively; the matching confidence is specifically: Among them, ConfidenceLv(Bill t ,[Class i ] j ) is the matching confidence between the target bill and the jth algorithm class; Num([Class i ] j ) is the total number of archived bills included in the jth algorithm class; CurrentTime is the generation time of the target bill; DealTime i Bill is the generation time of the i-th archived bill in the j-th algorithm class; t The transaction amount of the target bill; Class i is the transaction amount of the i-th archived bill in the j-th algorithm class; ξ and ω are the preset adjustment coefficients; According to the associated management algorithm corresponding to the algorithm class with the highest matching confidence, the module identifier corresponding to the target bill in each management dimension is configured to generate the management information, including: selecting the associated management algorithm corresponding to the algorithm class with the highest numerical value as the target management algorithm corresponding to the target bill, and based on the target sub-module used in each management dimension in the target management algorithm, determining the module identifier associated with the target bill in each management dimension.

2. The processing method according to claim 1, characterized in that Before selecting the target submodule corresponding to the module identifier from the submodule libraries associated with each of the management dimensions, the method further includes: If a configuration instruction initiated by a user is received, a visual interface for configuring the target submodule is generated; In response to a configuration operation initiated by the user in the visual interface, obtaining a module configuration segment corresponding to the configuration operation; the configuration operation is further used to determine the management dimension; Performing semantic analysis on the module configuration segment to determine at least one function keyword and a characteristic parameter associated with the function keyword; Extracting a target function template associated with the function keyword from a preset function template library, and configuring custom parameters in the target function template based on the characteristic parameters to generate a target function corresponding to the function keyword; Based on all the target functions, a target sub-module corresponding to the configuration operation is generated, and the generated target sub-module is added to the sub-module library of the management dimension specified by the configuration operation.

3. The processing method according to claim 1, characterized in that Also includes: If a new submodule is created in any of the submodule libraries, a training bill associated with the new submodule is obtained, and first training data corresponding to the training bill is output through the new submodule; Importing the training bill into each existing submodule created in the submodule library to obtain second training data; Calculating the processing similarity between the newly added submodule and each existing submodule based on the first training data and the second training data; Obtaining historical configuration information of the existing submodule and newly added configuration information of the newly added submodule, and calculating configuration similarity between the newly added submodule and each of the existing submodules; Determining a module overlap between the newly added submodule and the existing submodule based on the processing similarity and the configuration similarity; If the overlap degree of any of the modules is greater than a preset overlap threshold, redundant prompt information about the newly added sub-module is generated.

4. The processing method according to claim 3, characterized in that The obtaining of historical configuration information of the existing submodule and newly added configuration information of the newly added submodule, and calculating configuration similarity between the newly added submodule and each of the existing submodules, includes: Performing semantic analysis on the historical configuration information to determine a first keyword of the historical configuration information and a first characteristic parameter associated with the first keyword; Performing semantic analysis on the newly added configuration information to determine a second keyword of the historical configuration information and a second characteristic parameter associated with the second keyword; Selecting associated keywords matching the second keyword from all the first keywords, and calculating a parameter coverage ratio between a first feature parameter of the associated keyword and the second feature parameter; The configuration similarity between the newly added submodule and the existing submodule is obtained according to the parameter coverage corresponding to all the second feature parameters.

5. The processing method according to any one of claims 1 to 4, characterized in that: The management dimension includes a dimension hierarchy; The selecting the target submodule corresponding to the module identifier from the submodule library associated with each management dimension includes: Selecting a target submodule of the Nth dimensional level identified by a module associated with the Nth dimensional level from the submodule library of the management dimension of the Nth dimensional level; the initial value of N is 1; If the value of N is less than the preset total number of levels, based on the module identifier associated with the Nth dimensional level, the sub-module library of the management dimension of the N+1th dimensional level is adjusted; Increase the value of N and return to execute the operation of selecting the target sub-module of the Nth dimensional level identified by the module associated with the Nth dimensional level from the sub-module library of the management dimension of the Nth dimensional level until the value of N is greater than or equal to the total number of levels.

6. The processing method according to any one of claims 1 to 4, characterized in that: The management dimension includes a reconciliation trigger dimension; The processing of the target bill by the target management algorithm and outputting a bill processing result includes: Determining the reconciliation triggering timing of the target bill through the target submodule associated with the reconciliation triggering dimension; If any bill status of the target bill does not meet the reconciliation trigger timing, the target bill is returned to the bill database; If all the bill statuses of the target bill meet the reconciliation trigger timing, the bill processing result is generated.

7. A bill processing device, characterized in that: include: A target bill extraction unit, configured to extract any target bill from the bill database to be processed; The management information of the target bill includes module identifiers of multiple preset management dimensions; a target submodule selection unit, configured to select a target submodule corresponding to the module identifier from the submodule library associated with each management dimension; A target management algorithm generating unit, configured to encapsulate each target submodule according to the input and output relationship between each target submodule, and generate a target management algorithm corresponding to the target bill; a bill processing result generating unit, configured to process the target bill using the target management algorithm and output a bill processing result; The target bill extraction unit includes: A transaction object determination unit, configured to determine the transaction object of the target bill; the transaction object includes a payee and a recipient; an archived bill determining unit, configured to select a processed archived bill that matches the transaction object from a historical bill database; an algorithm class division unit, configured to divide all archived bills into a plurality of algorithm classes according to an association management algorithm used when managing each archived bill; the archived bills in each algorithm class use the same association management algorithm; A matching confidence calculation unit is used to calculate the matching confidence between the target bill and each of the algorithm classes; the matching confidence is specifically: Among them, ConfidenceLv(Bill t ,[Class i ] j ) is the matching confidence between the target bill and the jth algorithm class; Num([Class i ] j ) is the total number of archived bills contained in the jth algorithm class; CurrentTime is the generation time of the target bill; DealTime i Bill is the generation time of the i-th archived bill in the j-th algorithm class; t The transaction amount of the target bill; Class i is the transaction amount of the i-th archived bill in the j-th algorithm class; ξ and ω are the preset adjustment coefficients; A management information configuration unit is used to configure the module identifiers corresponding to the target bill in each of the management dimensions according to the associated management algorithm corresponding to the algorithm class with the highest matching confidence, and generate the management information, including: selecting the associated management algorithm corresponding to the algorithm class with the highest numerical value as the target management algorithm corresponding to the target bill, and determining the module identifiers associated with the target bill in each management dimension based on the target sub-modules used in each management dimension in the target management algorithm.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images