Artificial intelligence-based financial service processing method, apparatus, device, and medium

Abstract

The application discloses an artificial intelligence-based financial service processing method and device, equipment and medium, relates to the technical field of artificial intelligence, and comprises the following steps: obtaining a target financial service use case, and determining a financial service completion condition set and a financial service state space based on the target financial service use case; constructing a target action model and a target constraint model according to the target financial service use case; combining the financial service completion condition set, the financial service state space, the target action model and the target constraint model to obtain a target service rule set, and processing a to-be-processed financial service by using a financial service processing model under the constraint of the target service rule set. Through the combination of the completion condition, the state space, the action model and the target constraint model for limiting reasoning, a system-level comprehensive constraint and controllable execution basis is provided for a preset financial service processing model based on an agent-based artificial intelligence system.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to methods, apparatus, equipment and media for financial business processing based on artificial intelligence. Background Technology

[0002] With the development of artificial intelligence technology, especially the increasing demand for the application of Agentic AI (Artificial Intelligence) with autonomous planning capabilities in business systems, AI not only needs to complete information processing tasks, but also needs to participate in business decision-making and trigger actual business operations.

[0003] In application systems that incorporate artificial intelligence to automate business processes, existing technologies typically rely on fixed processes, rule engines, or API calls to control the order of business execution. This approach makes it difficult to ensure the controllability and verifiability of the execution behavior while maintaining the flexibility of the AI ​​system. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a method, apparatus, device, and medium for financial business processing based on artificial intelligence, which can provide a system-level comprehensive constraint and controllable execution basis for subsequent preset financial business processing models based on agent-based artificial intelligence systems by combining completion conditions, state space, action models, and target constraint models for restrictive reasoning. The specific solution is as follows:

[0005] Firstly, this application provides a financial business processing method based on artificial intelligence, including:

[0006] Obtain the target financial business use case corresponding to the financial business to be processed, wherein the target financial business use case is a structured description of the financial business objective, financial business boundary and applicable conditions of the business;

[0007] Based on the target financial business use case, a set of financial business completion conditions and a financial business state space are determined; the set of financial business completion conditions is a set of conditions used to determine whether the business objective has been achieved, and the financial business state space includes several financial business states.

[0008] Based on the target financial business use case, a target action model and a target constraint model are constructed; wherein, the target action model is a structured description of the smallest granularity business operation of the artificial intelligence system, and the target constraint model is a set of rules used to restrict the reasoning path and reasoning behavior of the artificial intelligence system;

[0009] The set of conditions for completing the financial business, the state space of the financial business, the target action model, and the target constraint model are combined to obtain the set of target business rules.

[0010] Under the constraints of the target business rule set, the financial business to be processed is processed using a preset financial business processing model; the preset financial business processing model is an artificial intelligence model built based on an agent-based artificial intelligence system.

[0011] Optionally, determining the set of financial transaction completion conditions and the financial transaction state space based on the target financial transaction use case includes:

[0012] Several business completion conditions are extracted from the target financial business use case, and the financial business completion condition set is constructed based on each of the business completion conditions;

[0013] Several business objects are identified from the target financial business use cases, and the financial business state space is constructed based on the stable state of each business object during its life cycle.

[0014] Optionally, constructing the target action model based on the target financial business use case includes:

[0015] The task preconditions and task execution effects are determined based on the target financial business use case, and the target action model is constructed based on the task preconditions and task execution effects; wherein, the task preconditions represent the business state conditions that the target action model must meet when it is executed, and the task execution effects represent the impact of the target action model on the financial business state space after it is executed.

[0016] Optionally, the target constraint model includes sequence constraints, dependency constraints, and prohibition constraints; the sequence constraints are used to constrain the execution order of operations of the artificial intelligence model, the dependency constraints are used to constrain the dependency relationships between operations of the artificial intelligence model, and the prohibition constraints are used to prohibit operations of the artificial intelligence model.

[0017] Optionally, the artificial intelligence-based financial transaction processing method further includes:

[0018] Assign a unique identifier to the target business rule set and perform version management on the target business rule set so as to update and reuse the target business rule set.

[0019] Optionally, the step of processing the financial business to be processed using a preset financial business processing model under the constraints of the target business rule set includes:

[0020] Using the preset financial business processing model and the current business state corresponding to the financial task to be processed, the initial candidate operation corresponding to the current business state is determined from the target business rule set;

[0021] The initial candidate operations are validated using the constraints in the target business rule set, and candidate operations that violate the constraints are removed to obtain the target candidate operations;

[0022] The preset financial business processing model is used to generate the target operation sequence corresponding to the target candidate operation, and the target operation sequence is used to process the financial business to be processed.

[0023] Optionally, the artificial intelligence-based financial transaction processing method further includes:

[0024] If any operation in the target operation sequence fails, the execution of the target operation sequence is stopped, and a rollback mechanism is triggered according to the rollback attribute corresponding to any operation.

[0025] Secondly, this application provides a financial transaction processing device based on artificial intelligence, comprising:

[0026] The use case acquisition module is used to acquire the target financial business use cases corresponding to the financial business to be processed, wherein the target financial business use cases are a structured description of the financial business objectives, financial business boundaries and applicable conditions of the business.

[0027] The determination module is used to determine a set of financial business completion conditions and a financial business state space based on the target financial business use case; the set of financial business completion conditions is a set of conditions used to determine whether the business objective has been achieved, and the financial business state space includes several financial business states;

[0028] The model building module is used to build a target action model and a target constraint model based on the target financial business use case; wherein, the target action model is a structured description of the smallest granularity business operation of the artificial intelligence system, and the target constraint model is a set of rules used to restrict the reasoning path and reasoning behavior of the artificial intelligence system;

[0029] The combination module is used to combine the set of conditions for completing the financial business, the state space of the financial business, the target action model, and the target constraint model to obtain the set of target business rules.

[0030] The business processing module is used to process the financial business to be processed using a preset financial business processing model under the constraints of the target business rule set; the preset financial business processing model is an artificial intelligence model built based on an agent-based artificial intelligence system.

[0031] Thirdly, this application provides an electronic device, comprising:

[0032] Memory, used to store computer programs;

[0033] A processor is used to execute the computer program to implement the aforementioned artificial intelligence-based financial business processing method.

[0034] Fourthly, this application provides a computer-readable storage medium for storing a computer program, which, when executed by a processor, implements the aforementioned artificial intelligence-based financial business processing method.

[0035] This application first obtains the target financial business use case corresponding to the financial business to be processed. The target financial business use case is a structured description of the financial business objective, financial business boundary, and applicable conditions. Then, based on the target financial business use case, a set of financial business completion conditions and a financial business state space are determined. The set of financial business completion conditions is a set of conditions used to determine whether the business objective has been achieved. The financial business state space includes several financial business states. Next, a target action model and a target constraint model are constructed based on the target financial business use case. The target action model is a structured description of the smallest-granularity business operation of the artificial intelligence system. The target constraint model is a set of rules used to restrict the reasoning path and reasoning behavior of the artificial intelligence system. Then, the set of financial business completion conditions, the financial business state space, the target action model, and the target constraint model are combined to obtain a target business rule set. Finally, under the constraints of the target business rule set, the financial business to be processed is processed using a preset financial business processing model. The preset financial business processing model is an artificial intelligence model built based on a proxy-based artificial intelligence system. Therefore, this application achieves a clear stateful expression of business objectives by defining a set of automatically determineable financial business completion conditions using structured business use cases; it defines the perceptible boundaries of the artificial intelligence system by constructing a financial business state space containing several business states; it standardizes the executable behavioral semantics of the artificial intelligence system by establishing a target action model describing the smallest granularity of business operations; and it forms a unified set of target business rules by combining completion conditions, state space, action model, and target constraint model used for limiting reasoning, thereby providing a system-level comprehensive constraint and controllable execution basis for the subsequent pre-set financial business processing model based on the agent-based artificial intelligence system. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0037] Figure 1This is a schematic diagram of a financial business processing method based on artificial intelligence disclosed in this application;

[0038] Figure 2 This is a schematic diagram of the structure of a financial business processing device based on artificial intelligence disclosed in this application;

[0039] Figure 3 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0040] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] In application systems that incorporate artificial intelligence (AI) to automate business processes, existing technologies struggle to ensure both the flexibility of the AI ​​system and the controllability and verifiability of its execution. To address this, this application provides an AI-based financial business processing method. By combining completion conditions, state space, action models, and target constraint models for restrictive reasoning, it provides a system-level comprehensive constraint and controllable execution basis for subsequent pre-set financial business processing models based on agent-based AI systems.

[0042] See Figure 1 As shown in the figure, an embodiment of the present invention discloses a financial business processing method based on artificial intelligence, including:

[0043] Step S11: Obtain the target financial business use case corresponding to the financial business to be processed, wherein the target financial business use case is a structured description of the financial business objective, financial business boundary and applicable conditions of the business.

[0044] In this embodiment, the first step is to obtain the target financial business use case corresponding to the financial business. The aforementioned target financial business use case refers to a structured description model of the business objectives, business boundaries, and applicable conditions, used to express the business results that users expect the system to complete and their applicable semantic constraints, rather than specific operational steps.

[0045] By acquiring the business use cases corresponding to financial transactions, a data foundation is provided for the creation of subsequent business rule sets.

[0046] Step S12: Determine the financial business completion condition set and the financial business state space based on the target financial business use case; the financial business completion condition set is a set of conditions used to determine whether the business objective has been achieved, and the financial business state space includes several financial business states.

[0047] In this embodiment, the process of determining the set of financial business completion conditions and the financial business state space based on the target financial business use case includes: extracting several business completion conditions from the target financial business use case and constructing a set of financial business completion conditions based on each business completion condition; identifying several business objects from the target financial business use case and constructing a financial business state space based on the stable state of each business object in its life cycle.

[0048] Specifically, based on the business completion conditions described in the user use case, at least one target state (i.e., a set of financial business completion conditions) is defined that can be directly determined by the system state. The target state is represented in the form of a set of state conditions, and whether the target state is satisfied or not is determined by the combination of state variables in the business state space, without relying on the specific execution process or the subjective judgment of artificial intelligence.

[0049] The states of business objects involved in user use cases are abstracted to construct a business state space (i.e., a financial business state space). This business state space includes multiple discrete business states, which describe the stable states that a business object may be in during its lifecycle and serve as the basis for determining the preconditions and execution results of executable actions. The business states do not include user interface states, intermediate technical states, or temporary process states.

[0050] In other words, the target state refers to a set of objective conditions that can be automatically identified by the system state to determine whether a business objective has been achieved. This target state is independent of the specific execution path. The state space refers to the structured set of all stable business states that a business object may be in during its lifecycle, used to limit the range of business states that AI can identify and reason about. By transforming business objectives into target states that can be determined by the system state, the AI's planning process has clear termination conditions, avoiding invalid or abnormal reasoning due to the lack of an objective determination mechanism.

[0051] Step S13: Construct a target action model and a target constraint model based on the target financial business use case; wherein, the target action model is a structured description of the smallest granularity business operation of the artificial intelligence system, and the target constraint model is a set of rules used to restrict the reasoning path and reasoning behavior of the artificial intelligence system.

[0052] This embodiment constructs AI-triggered action models based on the business capability breakdown results. Each action model includes at least:

[0053] Preconditions are used to limit the business conditions under which an action can be performed;

[0054] Execution effect, used to describe the deterministic state changes that occur in the business state space after the action is executed;

[0055] The mapping execution unit is used to map actions to controlled actual execution implementations;

[0056] The rollback attribute indicates whether the action can be undone or compensated for.

[0057] Action models serve as the basic execution units that can be selected during the planning and reasoning process of artificial intelligence. Artificial intelligence can only select and execute corresponding actions if the preconditions are met.

[0058] Accordingly, the process of constructing a target action model based on the target financial business use case may specifically include: determining the task preconditions and task execution effects based on the target financial business use case, and constructing the target action model based on the task preconditions and task execution effects; wherein, the task preconditions represent the business state conditions that the target action model must meet when it is executed, and the task execution effects represent the impact of the target action model on the financial business state space after it is executed.

[0059] The aforementioned target action model is a structured description model of AI-executable business behaviors, used to define the smallest business execution unit (i.e. the smallest granular business operation) that AI can trigger during planning and execution, and its state change semantics.

[0060] Furthermore, this embodiment constructs a constraint model based on the business rules, compliance requirements, and governance requirements implicit in user use cases. The constraint model is used to limit the sequence of actions that artificial intelligence can generate during planning, reasoning, and execution. The constraints include at least one or more of the following: sequence constraints, dependency constraints, and prohibition constraints, and constraint priorities can be set.

[0061] In other words, the aforementioned constraint model refers to a set of rules used to restrict the AI's inference path and execution behavior, including sequence constraints, dependency constraints, prohibition rules, and their priority control logic. Specifically, the goal constraint model includes sequence constraints, dependency constraints, and prohibition constraints; sequence constraints are used to constrain the execution order of operations of the AI ​​model, dependency constraints are used to constrain the dependency relationships between operations of the AI ​​model, and prohibition constraints are used to prohibit operations of the AI ​​model.

[0062] Step S14: Combine the set of conditions for completing the financial business, the state space of the financial business, the target action model, and the target constraint model to obtain the set of target business rules.

[0063] This embodiment combines the business target state, business state space, action model, and constraint model to generate a planning domain model (i.e., target business rule set) for the corresponding user use case.

[0064] The planning domain model has a unique identifier and supports version management, and is used as an input model for AI planning reasoning and runtime execution.

[0065] Accordingly, the AI-based financial business processing method in this embodiment further includes: assigning a unique identifier to the target business rule set and performing version management on the target business rule set so as to update and reuse the target business rule set.

[0066] Step S15: Under the constraints of the target business rule set, process the financial business to be processed using a preset financial business processing model; the preset financial business processing model is an artificial intelligence model built based on an agent-based artificial intelligence system.

[0067] In this embodiment, the process of processing the financial business to be processed using a preset financial business processing model under the constraints of the target business rule set includes: determining the initial candidate operation corresponding to the current business state from the target business rule set using the preset financial business processing model and the current business state corresponding to the financial task to be processed; verifying the initial candidate operation using the constraints in the target business rule set and removing candidate operations that violate the constraints to obtain the target candidate operation; generating the target operation sequence corresponding to the target candidate operation using the preset financial business processing model, and processing the financial business to be processed using the target operation sequence.

[0068] Specifically, during runtime, the AI ​​planning engine (i.e., the preset financial business processing model) performs a planning reasoning process based on the current business state and the planning domain model, generating an action sequence that satisfies the target state. During the planning process, the planning engine can only select candidate actions from the action model and verifies the constraint model before each planning and execution step to ensure that the generated action sequence does not violate business rules and compliance constraints. After an action is executed, the system updates the current business state based on the action's execution effect and repeats the planning and execution process until the target state is met or the planning termination condition is triggered.

[0069] By using action models to structurally define the executable behaviors of AI, we can prevent AI from directly manipulating the underlying system interfaces. By using constraint models to restrict the AI's reasoning path, we can enable AI to generate legal action sequences even in non-fixed processes.

[0070] It should be noted that the aforementioned pre-set financial business processing model refers to an artificial intelligence system with the ability to understand objectives, reason autonomously, plan and make decisions, and execute. It can autonomously select and execute action sequences under constraints based on a structured business model to achieve business objectives.

[0071] Additionally, it should be noted that in this embodiment, each action that contributes to the financial task is bound to a rollback mechanism, which can restore the consistency of the system state when execution fails, thereby avoiding abnormal business data.

[0072] That is, if any operation in the target operation sequence fails, the execution process of the target operation sequence is stopped, and a rollback mechanism is triggered according to the rollback attribute corresponding to any operation.

[0073] Therefore, this application achieves a clear stateful expression of business objectives by defining a set of automatically determineable financial business completion conditions using structured business use cases; it defines the perceptible boundaries of the artificial intelligence system by constructing a financial business state space containing several business states; it standardizes the executable behavioral semantics of the artificial intelligence system by establishing a target action model describing the smallest granularity of business operations; and it forms a unified set of target business rules by combining completion conditions, state space, action model, and target constraint model used for limiting reasoning, thereby providing a system-level comprehensive constraint and controllable execution basis for the subsequent pre-set financial business processing model based on the agent-based artificial intelligence system.

[0074] See Figure 2 As shown in the figure, an embodiment of the present invention discloses a financial business processing device based on artificial intelligence, comprising:

[0075] The use case acquisition module 11 is used to acquire the target financial business use case corresponding to the financial business to be processed, wherein the target financial business use case is a structured description of the financial business objective, financial business boundary and applicable conditions of the business.

[0076] The state space determination module 12 is used to determine the financial business completion condition set and the financial business state space based on the target financial business use case; the financial business completion condition set is a set of conditions used to determine whether the business objective has been achieved, and the financial business state space includes several financial business states.

[0077] The model building module 13 is used to build a target action model and a target constraint model based on the target financial business use case; wherein, the target action model is a structured description of the smallest granularity business operation of the artificial intelligence system, and the target constraint model is a set of rules used to restrict the reasoning path and reasoning behavior of the artificial intelligence system;

[0078] Data combination module 14 is used to combine the financial business completion condition set, the financial business state space, the target action model and the target constraint model to obtain the target business rule set;

[0079] The business processing module 15 is used to process the financial business to be processed using a preset financial business processing model under the constraints of the target business rule set; the preset financial business processing model is an artificial intelligence model built based on an agent-based artificial intelligence system.

[0080] In some specific embodiments, the state space determination module 12 may specifically include:

[0081] A set construction unit is used to extract several business completion conditions from the target financial business use case, and construct the financial business completion condition set based on each of the business completion conditions;

[0082] The state space construction unit is used to identify several business objects from the target financial business use case and construct the financial business state space according to the stable state of each business object in its life cycle.

[0083] In some specific embodiments, the model building module 13 may specifically include:

[0084] The model building unit is used to determine the preconditions and execution effects of the task based on the target financial business use case, and to build the target action model based on the preconditions and execution effects; wherein, the preconditions represent the business state conditions that the target action model must meet when it is executed, and the execution effects represent the impact of the target action model on the financial business state space after it is executed.

[0085] In some specific embodiments, the artificial intelligence-based financial transaction processing device further includes:

[0086] The identifier allocation module is used to assign a unique identifier to the target business rule set and to manage the version of the target business rule set so as to update and reuse the target business rule set.

[0087] In some specific embodiments, the service processing module 15 may specifically include:

[0088] An operation determination unit is used to determine the initial candidate operation corresponding to the current business state from the target business rule set using the preset financial business processing model and the current business state corresponding to the financial task to be processed.

[0089] The business processing unit is used to generate a target operation sequence corresponding to the target candidate operation using the preset financial business processing model, and to process the financial business to be processed using the target operation sequence.

[0090] In some specific embodiments, the artificial intelligence-based financial transaction processing device further includes:

[0091] The rollback trigger module is used to stop the execution of the target operation sequence if any operation in the target operation sequence fails, and to trigger a rollback mechanism according to the rollback attribute corresponding to any operation.

[0092] Furthermore, embodiments of this application also disclose an electronic device, Figure 3 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0093] Figure 3 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the artificial intelligence-based financial business processing method disclosed in any of the foregoing embodiments. Alternatively, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0094] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0095] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0096] The operating system 221 is used to manage and control the various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, Netware, Unix, Linux, etc. In addition to including computer programs capable of performing the AI-based financial business processing method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks.

[0097] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned disclosed artificial intelligence-based financial business processing method. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0098] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0099] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0100] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0101] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0102] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A financial transaction processing method based on artificial intelligence, characterized in that, include: Obtain the target financial business use case corresponding to the financial business to be processed, wherein the target financial business use case is a structured description of the financial business objective, financial business boundary and applicable conditions of the business; Based on the target financial business use case, a set of financial business completion conditions and a financial business state space are determined; the set of financial business completion conditions is a set of conditions used to determine whether the business objective has been achieved, and the financial business state space includes several financial business states. Based on the target financial business use case, a target action model and a target constraint model are constructed; wherein, the target action model is a structured description of the smallest granularity business operation of the artificial intelligence system, and the target constraint model is a set of rules used to restrict the reasoning path and reasoning behavior of the artificial intelligence system; The set of conditions for completing the financial business, the state space of the financial business, the target action model, and the target constraint model are combined to obtain the set of target business rules. Under the constraints of the target business rule set, the financial business to be processed is processed using a preset financial business processing model; the preset financial business processing model is an artificial intelligence model built based on an agent-based artificial intelligence system.

2. The financial transaction processing method based on artificial intelligence according to claim 1, characterized in that, The process of determining the set of financial business completion conditions and the financial business state space based on the target financial business use case includes: Several business completion conditions are extracted from the target financial business use case, and the financial business completion condition set is constructed based on each of the business completion conditions; Several business objects are identified from the target financial business use cases, and the financial business state space is constructed based on the stable state of each business object during its life cycle.

3. The artificial intelligence-based financial transaction processing method according to claim 1, characterized in that, The step of constructing the target action model based on the target financial business use case includes: The task preconditions and task execution effects are determined based on the target financial business use case, and the target action model is constructed based on the task preconditions and task execution effects; wherein, the task preconditions represent the business state conditions that the target action model must meet when it is executed, and the task execution effects represent the impact of the target action model on the financial business state space after it is executed.

4. The financial transaction processing method based on artificial intelligence according to claim 1, characterized in that, The target constraint model includes sequence constraints, dependency constraints, and prohibition constraints; the sequence constraints are used to constrain the execution order of operations of the artificial intelligence model, the dependency constraints are used to constrain the dependency relationships between operations of the artificial intelligence model, and the prohibition constraints are used to prohibit operations of the artificial intelligence model.

5. The financial business processing method based on artificial intelligence according to claim 1, characterized in that, Also includes: Assign a unique identifier to the target business rule set and perform version management on the target business rule set so as to update and reuse the target business rule set.

6. The artificial intelligence-based financial transaction processing method according to any one of claims 1 to 5, characterized in that, The step of processing the financial business to be processed using a preset financial business processing model under the constraints of the target business rule set includes: Using the preset financial business processing model and the current business state corresponding to the financial task to be processed, the initial candidate operation corresponding to the current business state is determined from the target business rule set; The initial candidate operations are validated using the constraints in the target business rule set, and candidate operations that violate the constraints are removed to obtain the target candidate operations; The preset financial business processing model is used to generate the target operation sequence corresponding to the target candidate operation, and the target operation sequence is used to process the financial business to be processed.

7. The financial business processing method based on artificial intelligence according to claim 6, characterized in that, Also includes: If any operation in the target operation sequence fails, the execution of the target operation sequence is stopped, and a rollback mechanism is triggered according to the rollback attribute corresponding to any operation.

8. A financial transaction processing device based on artificial intelligence, characterized in that, include: The use case acquisition module is used to acquire the target financial business use cases corresponding to the financial business to be processed, wherein the target financial business use cases are a structured description of the financial business objectives, financial business boundaries and applicable conditions of the business. The state space determination module is used to determine the financial business completion condition set and the financial business state space based on the target financial business use case; the financial business completion condition set is a set of conditions used to determine whether the business objective has been achieved, and the financial business state space includes several financial business states. The model building module is used to build a target action model and a target constraint model based on the target financial business use case; wherein, the target action model is a structured description of the smallest granularity business operation of the artificial intelligence system, and the target constraint model is a set of rules used to restrict the reasoning path and reasoning behavior of the artificial intelligence system; The data combination module is used to combine the set of conditions for completing the financial business, the state space of the financial business, the target action model, and the target constraint model to obtain the set of target business rules. The business processing module is used to process the financial business to be processed using a preset financial business processing model under the constraints of the target business rule set; the preset financial business processing model is an artificial intelligence model built based on an agent-based artificial intelligence system.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the artificial intelligence-based financial business processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store computer programs, which, when executed by a processor, implement the artificial intelligence-based financial business processing method as described in any one of claims 1 to 7.

Images