Combination service generation method and apparatus, device, and storage medium

Abstract

Embodiments of the present application disclose a combined service generation method and device, equipment and storage medium. In response to receiving user input information of a target user, the user input information is parsed to determine at least one user intention. At least one user demand service and a standard handling process corresponding to each user demand service are determined according to the at least one user intention. The user demand service corresponding to the target user is determined as a target demand service if the user information corresponding to the target user meets the corresponding precondition. A combined service handling process of the target user is generated according to the standard handling process corresponding to each target demand service and the corresponding atomic capability set. The present application can automatically and accurately parse the user intention through the user input information, intelligently obtain at least one user demand service, and automatically, real-time and flexibly generate a combined service handling process based on atomic capabilities, thereby improving the efficiency of generating a combined service and the quality of automatically generated results.

Description

Technical Field

[0001] This application relates to the field of business processing, and includes, but is not limited to, a method, apparatus, device, and storage medium for generating combined business processes. Background Technology

[0002] Currently, business transactions in sectors such as securities and finance, smart healthcare, and government services can be conducted online. This online process requires users to submit data item by item according to the business category, which is then approved by a centralized operations center. However, due to the dependencies between different business processes and the repetitive input of identical data across different processes, the current online process is redundant, cumbersome, and inefficient. Currently, combined business processes primarily rely on rule-based engine-based methods, which cannot handle requests with mixed intents, lack flexibility, and are difficult to adapt to diverse user interaction scenarios. Summary of the Invention

[0003] In view of this, the combined service generation method, apparatus, device, and storage medium provided in the embodiments of this application can realize flexible, accurate, and efficient generation of combined service processes.

[0004] The combined service generation method, apparatus, device, and storage medium provided in this application embodiment are implemented as follows: One aspect of this application provides a method for generating combined services, the method comprising: In response to receiving user input information from a target user, the user input information is parsed to determine at least one user intent; Based on the at least one user intent, at least one user demand service is determined, as well as the standard processing procedure corresponding to each user demand service; The user demand service that meets the corresponding prerequisite conditions and is identified as the target demand service; Based on the standard processing procedures and corresponding atomic capability sets corresponding to each target demand service, a combined service processing procedure for the target user is generated. The atomic capability set includes at least one atomic capability corresponding to the target demand service, and the atomic capability represents a standardized functional unit that cannot be further divided in the service.

[0005] In one possible implementation, the step of parsing the user input information to determine at least one user intent in response to receiving user input information from a target user includes: In response to receiving user input information from the target user, the user input information is preprocessed to obtain a standardized request text; The standardized request text is parsed based on preset domain constraints to obtain the corresponding structured intent; At least one user intent is obtained by performing multi-dimensional judgment on the structured intent.

[0006] In one possible implementation, obtaining at least one user intent by performing multi-dimensional judgment on the structured intent includes: The structured intent is split according to the preset business priority rules to obtain at least one candidate intent with a priority order; If no other candidate intents with the same priority order exist among the candidate intents, the candidate intent is determined to be a user intent. If there are other candidate intents with the same priority order among the candidate intents, at least one round of dialogue is conducted with the target user through a large language model to determine one candidate intent as the user intent from among the candidate intents with the same priority order.

[0007] In one possible implementation, determining at least one user-required service based on the at least one user intent, and the standard processing procedure corresponding to each user-required service, includes: Determine the corresponding first demand service for each user intent; Match relevant second demand services based on each of the first demand services and the target user's historical service information; The second requirement business is filtered according to a predefined set of exclusive standard processes to remove the second requirement business that cannot be combined with the first requirement business. Based on the first required service and the filtered second required service, at least one user required service is determined; the standard processing procedure corresponding to each user required service is obtained by searching in the predefined business process template library.

[0008] In one possible implementation, determining at least one user demand service based on the first demand service and the filtered second demand service includes: Display each of the first demand services and each of the second demand services; In response to receiving selection information for at least one of the first demand services and / or the second demand services, the first demand service and / or the second demand service selected in the selection information are determined to be user demand services.

[0009] In one possible implementation, the user demand service that determines whether the user information corresponding to the target user meets the corresponding preconditions is the target demand service, including: Determine the prerequisites for each of the aforementioned user demand services; Based on the user information corresponding to the target user, determine whether the preconditions corresponding to each user demand service are met; If the prerequisites for the user demand service are met, the user demand service is determined to be the target demand service.

[0010] In one possible implementation, the user demand service that determines whether the user information corresponding to the target user meets the corresponding preconditions is the target demand service, including: If the prerequisites for the user's service request are not met, corresponding supplementary information prompts will be generated based on the unmet content of the prerequisites. In response to receiving supplementary information from the user regarding the supplementary information prompt, the system re-evaluates whether the unmet preconditions have been met.

[0011] Another aspect of the embodiments of this application provides a combined service generation apparatus, the apparatus comprising: The intent parsing module is used to parse the user input information received from the target user to determine at least one user intent; The intelligent recommendation module is used to determine at least one user demand service and the standard processing procedure corresponding to each user demand service based on the at least one user intent. The intelligent pre-detection module is used to determine the target user's user information that meets the corresponding preconditions as the target user's user demand service; The combined service processing module is used to generate a combined service processing flow for the target user based on the standard processing flow and the corresponding atomic capability set for each target demand service. The atomic capability set includes at least one atomic capability corresponding to the target demand service, and the atomic capability represents a standardized functional unit that cannot be further divided in the service.

[0012] In one possible implementation, the intent parsing module is further configured to: In response to receiving user input information from the target user, the user input information is preprocessed to obtain a standardized request text; The standardized request text is parsed based on preset domain constraints to obtain the corresponding structured intent; At least one user intent is obtained by performing multi-dimensional judgment on the structured intent.

[0013] In one possible implementation, the intent parsing module is further configured to: The structured intent is split according to the preset business priority rules to obtain at least one candidate intent with a priority order; If no other candidate intents with the same priority order exist among the candidate intents, the candidate intent is determined to be a user intent. If there are other candidate intents with the same priority order among the candidate intents, at least one round of dialogue is conducted with the target user through a large language model to determine one candidate intent as the user intent from among the candidate intents with the same priority order.

[0014] In one possible implementation, the intelligent recommendation module is further configured to: Determine the corresponding first demand service for each user intent; Match relevant second demand services based on each of the first demand services and the target user's historical service information; The second requirement business is filtered according to a predefined set of exclusive standard processes to remove the second requirement business that cannot be combined with the first requirement business. At least one user demand service is determined based on the first demand service and the filtered second demand service; The standard processing procedures corresponding to each user's required business are obtained by searching the predefined business process template library.

[0015] In one possible implementation, the intelligent recommendation module is further configured to: Display each of the first demand services and each of the second demand services; In response to receiving selection information for at least one of the first demand services and / or the second demand services, the first demand service and / or the second demand service selected in the selection information are determined to be user demand services.

[0016] In one possible implementation, the intelligent pre-detection module is further configured to: Determine the prerequisites for each of the aforementioned user demand services; Based on the user information corresponding to the target user, determine whether the preconditions corresponding to each user demand service are met; If the prerequisites for the user demand service are met, the user demand service is determined to be the target demand service.

[0017] In one possible implementation, the intelligent pre-detection module is further configured to: If the prerequisites for the user's service request are not met, corresponding supplementary information prompts will be generated based on the unmet content of the prerequisites. In response to receiving supplementary information from the user regarding the supplementary information prompt, the system re-evaluates whether the unmet preconditions have been met.

[0018] The electronic device provided in this application includes a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the program, it implements the method described in this application.

[0019] The computer-readable storage medium provided in this application embodiment stores a computer program thereon, which, when executed by a processor, implements the method provided in this application embodiment.

[0020] The combined service generation method, apparatus, device, and storage medium provided in this application, in response to receiving user input information from a target user, parses the user input information to determine at least one user intent. Based on the at least one user intent, it determines at least one user-required service and the corresponding standard processing procedure for each user-required service. User-required services whose user information for the target user meets the corresponding preconditions are identified as target-required services. Based on the standard processing procedure and corresponding atomic capability set for each target-required service, a combined service processing procedure for the target user is generated. This application can automatically and accurately parse user intent from user input information to intelligently obtain at least one user-required service and automatically, in real-time, and flexibly generate combined service processing procedures based on atomic capabilities, improving the efficiency of generating combined services and the quality of automatically generated results. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating a combined service generation method according to an embodiment of this application is shown; Figure 2 This diagram illustrates a combined service generation system according to an embodiment of the present application. Figure 3 A schematic diagram of a combined service generation apparatus according to an embodiment of this application is shown; Figure 4 A schematic diagram of an electronic device according to an embodiment of this application is shown. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the specific technical solutions of this application will be further described in detail below with reference to the accompanying drawings of the embodiments of this application. The following embodiments are used to illustrate this application, but are not intended to limit the scope of this application.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0025] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0026] It should be noted that the terms "first, second, third" used in the embodiments of this application are used to distinguish similar or different objects and do not represent a specific order of objects. It can be understood that "first, second, third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0027] The combined service generation method of this application embodiment can be executed by any electronic device, including but not limited to mobile phones, wearable devices (such as smartwatches, smart bracelets, smart glasses, etc.), tablet computers, laptops, vehicle terminals, PCs (Personal Computers), etc. The functions implemented by this method can be achieved by a processor in the electronic device calling program code. Of course, the program code can be stored in a computer storage medium. Therefore, the electronic device includes at least a processor and a storage medium.

[0028] The combined service generation method of this application embodiment can be used in any application scenario that requires online business processing, such as application scenarios in the government and public service fields that require business establishment, second-hand housing transfer, and talent settlement, application scenarios in the telecommunications and digital life services fields that require processing integrated packages, and application scenarios in the financial securities fields that require opening accounts, etc.

[0029] Currently, in scenarios involving the generation of combined business processes, related technologies typically employ LLM (Large Language Model) based on user input. However, this technology suffers from drawbacks such as susceptibility to parsing illusions, low flexibility of rule engines, and inefficient resolution of multi-intent ambiguity. The process of generating combined business processes is inefficient and inflexible, and the resulting combined business processes are not accurate enough. Therefore, this application aims to propose an efficient, flexible, and accurate combined business generation solution.

[0030] The combined service generation scheme of this application embodiment will be described in detail below with reference to the accompanying drawings.

[0031] Figure 1 A flowchart illustrating a combined service generation method according to an embodiment of this application is shown. Figure 1 As shown, the combined service generation method of this application embodiment may include the following steps S10-S40.

[0032] For ease of description, the combined service generation method of the embodiments of this application is described using an electronic device as the execution subject. It should be understood that the execution subject of the embodiments of this application may also be a processor or chip in an electronic device, and the embodiments of this application do not impose any limitations.

[0033] Step S10: In response to receiving user input information from the target user, parse the user input information to determine at least one user intent.

[0034] In one possible implementation, after receiving user input information, the electronic device parses the user input information to determine at least one user intent. The user input information is a service request represented by the user in natural language, used to record the service the user needs to perform. The user intent is information that the electronic device identifies to accurately instruct the user to perform the service.

[0035] Optionally, after receiving user input information, the electronic device can first perform data preprocessing to obtain standardized request text, and then parse the standardized request text to obtain the accurate user intent. That is, in response to receiving user input information from the target user, the device preprocesses the user input information to obtain standardized request text. Then, based on preset domain constraints, it parses the standardized request text to obtain the corresponding structured intent. Finally, it performs multi-dimensional judgments on the structured intent to obtain at least one user intent.

[0036] For example, after receiving user input information, an electronic device can perform text cleaning and standardization on the natural language service request to achieve preprocessing, obtaining standardized request text. Then, a Large Language Model (LLM) is invoked to perform intent parsing on the standardized request text, obtaining structured intent to further determine at least one user intent. The LLM can determine the structured intent by limiting the corresponding domain service list and predefined domain constraints on the output format.

[0037] After determining the structured intent, the electronic device can determine whether the intent represented by the user input information is ambiguous, i.e., whether it can accurately determine the service the user needs to perform. Further, the electronic device can directly determine the user intent based on the structured intent if there is no ambiguity; if there is ambiguity, it can clarify the ambiguity through multi-turn dialogue with the user using a large language model to obtain the accurate user intent. Optionally, the electronic device can first decompose the structured intent according to preset service priority rules to obtain at least one candidate intent with a priority order. Then, it can determine whether there is an ambiguous user intent based on the priority order of each candidate intent. For example, if no other candidate intents with the same priority order exist, the candidate intent is determined as the user intent. If other candidate intents with the same priority order exist, at least one round of dialogue is conducted with the target user using a large language model to determine one candidate intent from those with the same priority order as the user intent.

[0038] For example, the electronic device can first determine the structured intent. If it contains multiple intents, i.e., can match multiple service types simultaneously, it can initially split the intents according to a preset service priority, resulting in multiple candidate intents with a priority order. If at least two candidate intents have the same priority, the electronic device can determine that the split candidate intents are still ambiguous. Based on the ambiguous candidate intents, it can generate contextual clarification questions using a large language model. After receiving supplementary input information from the user, it can then combine the historical conversation context to perform intent matching and parsing again until the ambiguity is resolved. If all candidate intents are unambiguous, the candidate intents are directly determined as the user intents.

[0039] In some embodiments, the algorithm for parsing user intent can be integrated into an intent parsing module. This module receives user input information in natural language representation, performs text cleaning, denoising, and standardization on the user input information, and generates standardized request text. Then, a large language model (LLM) is invoked to perform intent parsing through domain constraints to obtain the structured intent corresponding to the user input information. Next, this structured intent is synchronized to the Skills layer of the core support module, where the Skills layer collaboratively performs multi-dimensional judgment. If multiple candidate intents are detected (i.e., matching multiple securities business types simultaneously), a preliminary split is performed according to preset business priority rules to obtain multiple candidate intents with priority order. Further, ambiguity among the multiple candidate intents is identified. If ambiguity still exists after splitting, a scenario-based clarifying question is generated through the large language model. After receiving supplementary input from the user, the historical conversation context is automatically concatenated for dialogue memory, and intent matching and parsing operations are performed again until the ambiguity is completely resolved. During the processing / query process, if the user is unfamiliar with the rules, simplified guidance is automatically provided to ensure zero intent bias, providing a reliable foundation for subsequent recommendations, pre-screening, and processing.

[0040] Step S20: Determine at least one user demand service and the standard processing procedure corresponding to each user demand service based on the at least one user intent.

[0041] In one possible implementation, after determining at least one user intent corresponding to the user input information, the electronic device can determine at least one matching user-required service based on the at least one user intent, and simultaneously obtain the standard processing procedure corresponding to each user-required service. Optionally, the user-required services determined in this application embodiment may include user services explicitly indicated by the user intent, and services that the user may need to process automatically based on the user's situation.

[0042] Optionally, after determining at least one user intent, the electronic device can determine the corresponding first required service for each user intent. Based on each first required service and the target user's historical service information, relevant second required services are matched. The second required services are then filtered according to a predefined set of proprietary standard processes to remove those that cannot be combined with the first required services. At least one user required service is determined based on the first required services and the filtered second required services. The standard processing procedure corresponding to each user required service is then retrieved from a predefined service process template library.

[0043] The predefined set of dedicated standard processes includes at least one set of business processes that match standard processing procedures. This set can be used to restrict and control the combination of business processes within the standard process template library. Specifically, it can restrict the combination of second-needed business processes that have a first-needed business process that matches a standard processing procedure, while preventing the combination of second-needed business processes that do not have a first-needed business process that matches a standard processing procedure. For example, within the scope of authority, business processes related to the Science and Technology Innovation Board and the Growth Enterprise Market can be combined, while business processes related to standardized accounts and business processes within the scope of authority cannot be combined.

[0044] Electronic devices can determine the user's final service needs through human-computer interaction, that is, they can display each first service need and each second service need. In response to receiving selection information for at least one first service need and / or second service need, the selected first service need and / or second service need in the selection information is determined to be the user's service need.

[0045] For example, the process of determining user needs can be integrated into an intelligent recommendation module in an electronic device. This module maps various securities services to a predefined business process template library, which covers standard processing procedures for all relevant business areas. Simultaneously, in conjunction with the RuleAgent, and linked to the Skills layer of the core support module, it strictly adheres to securities industry regulatory requirements and executes verification rules to conduct preliminary compliance checks on the processing conditions and user qualifications of recommended services, ensuring that the recommended services are compliant, controllable, and user-suitable. After a user enters the business processing page, the electronic device can display the first required service as well as a second service that the user might need to process (such as renewal reminders, a re-processing entry for rejected services, and related service recommendations). If the user selects at least one of the first or second required services, the selected service is determined as the user's required service, and the standard processing procedure corresponding to each user's required service is automatically retrieved from the business process template library. Furthermore, the electronic device can also perform qualification verification for each user's required service after determining it. Upon successful verification, the standard processing procedure for each user's required service is obtained, resulting in a customer-specific standard process set and directly executable business processes for quick user operation. If the verification fails, the electronic device can return a clear verification failure message and automatically generate an easy-to-understand natural language explanation, effectively improving the user experience.

[0046] For example, in this embodiment, the electronic device can map the user's required business to a predefined business process template library after determining the user's required business to obtain the corresponding standard business process. For example, the STAR Market access activation process = risk assessment → asset threshold verification → transaction experience verification → signing agreement → activation submission. Furthermore, parameters corresponding to the rule engine (such as user risk level, asset size, and transaction experience) can be used to verify whether the target user is capable of handling the business. The verification rules conform to industry requirements (such as STAR Market access requiring 2 years of transaction experience + a 500,000 RMB asset threshold). If all verifications pass, a customer business standard process set consisting of multiple standard business processes corresponding to the user's required business is generated to further generate an executable business process for the user to execute. If the verification fails, a verification failure message is returned, and a natural language explanation is generated through LLM (such as "Your assets do not meet the 500,000 RMB threshold for STAR Market access; please supplement your assets and try again").

[0047] Based on the aforementioned technical features, the process of determining user-demanded services in this embodiment can rely on user profile data, historical transaction records, business status, and securities business preferences, combined with the logical reasoning capabilities of a large model, to accurately match core user needs. This process of determining user-demanded services can proactively recommend suitable related services, realizing the transformation of network services from "passive response" to "proactive service."

[0048] Step S30: Determine the user demand service that meets the corresponding prerequisite conditions for the user information corresponding to the target user as the target demand service.

[0049] In one possible implementation, after identifying at least one user-required service for a target user, the electronic device can further determine whether the preconditions for each user-required service are met based on the user information corresponding to the target user. These preconditions indicate the procedures or materials required before processing the corresponding user-required service. If the preconditions for a user-required service are not met, the electronic device can compile all the necessary supplementary user information at once to prompt the user to supplement the materials or procedures. Conversely, if the preconditions for a user-required service are met, the device can be directly identified as the target service to further generate the corresponding service processing flow.

[0050] Optionally, after determining at least one user-demanded service, the electronic device can determine the preconditions corresponding to each user-demanded service. Based on the user information corresponding to the target user, it can determine whether the preconditions corresponding to each user-demanded service are met. If the preconditions of a user-demanded service are met, the user-demanded service is determined as the target demand service. If the preconditions of a user-demanded service are not met, corresponding supplementary information prompts are generated based on the unmet preconditions. In response to receiving supplementary information from the user regarding the supplementary information prompts, the device can re-determine whether the unmet preconditions are met.

[0051] For example, this pre-condition verification process can be integrated into an intelligent pre-inspection module. This module, through the precheckAgent intelligent agent linked with the Skills layer, completes a one-stop, full-dimensional condition verification before processing, ensuring a smooth process and that users are clearly aware of the processing requirements. The specific process may include receiving the business processing requests from the intent parsing module and the intelligent recommendation module to obtain the pre-conditions for each user's requested business, and then calling data from the customer management system to comprehensively verify whether all pre-conditions for each user's requested business are met. These pre-conditions may include document validity, mobile phone number authentication status, qualification thresholds, etc. Furthermore, if at least one pre-condition is not met, all unmet conditions are summarized at once to generate a clear information supplement prompt, clearly informing the user of the missing items, the supplementation path, and the estimated time, avoiding multiple pop-up redirects. Simultaneously, for user requests requiring supplementary information (such as mobile phone number authentication and document renewal), electronic devices can also provide a one-stop combined business processing entry point to avoid user confusion, ensure a smooth and seamless processing flow, and reduce complaints related to account cancellation from the source.

[0052] Step S40: Generate the combined service processing flow for the target user based on the standard processing flow and the corresponding set of atomic capabilities for each target service requirement.

[0053] In one possible implementation, after determining that all preconditions are met and the user has identified the target service they need to handle, the electronic device can generate a combined service processing flow for simultaneously handling the aforementioned target services, based on the standard processing flow and corresponding atomic capability set for each target service. The atomic capability set includes at least one atomic capability corresponding to each target service, and each atomic capability represents a standardized functional unit that cannot be further divided within the service. That is, the standard service flow in this embodiment is uniformly based on the same set of atomic capabilities. The electronic device can obtain and merge the atomic capability sets of each target service to generate a combined service atomic capability set. Based on the actual atomic capability set of the combined service, the combined service processing flow is dynamically generated in real time for the user to execute.

[0054] In this embodiment, the electronic device can integrate the algorithm for generating the combined business processing flow into a combined business processing module. This module, based on the atomic encapsulation of related domain businesses, enables real-time construction and one-stop processing of combined businesses. This module, in conjunction with the intelligent recommendation module generating a standard business process set for the target user and the verification results from the intelligent pre-inspection module, works with the workflow agent and links the Skills layer of the core support module to acquire and merge the atomic capability sets of each target requirement business, generating a combined business atomic capability set adapted to the user's needs. Subsequently, based on the standard processing flow of each target requirement business, the optimal combined business processing flow is dynamically generated in real time, clarifying the execution order and data transmission requirements of each atomic capability, ensuring that the resulting combined business processing flow is highly efficient and does not violate the standard processing flow of any target requirement business. This combined business processing flow ensures that the user does not need to manually switch or repeatedly submit materials throughout the entire process. Simultaneously, the progress of the entire business processing process is synchronized to the core support module in real time, ensuring that the user can monitor the processing status in real time and achieve smooth one-stop processing of multiple businesses.

[0055] For example, the electronic device can also call the rule engine to perform compliance verification on the parameters (such as user risk level, asset size, and transaction experience) corresponding to the standard processing procedures of each target demand business during the process of generating the combined business processing procedure. After all verifications pass, a set of standard processes for customer business is generated; the atomic capability sets corresponding to each standard business process are extracted and merged to generate a set of combined business atomic capabilities, and then the combined business processing procedure is generated dynamically in real time; if the verification fails, verification failure information is generated and pushed to the execution feedback module.

[0056] In some embodiments, the generated combined business processing flow can also be verified. For example, the verification can be performed by dynamically generating the combined business processing flow and obtaining the business execution results for customers to process combined business transactions. If the verification fails, a large language model is invoked to generate a natural language explanation of the verification failure and push it to the user. Simultaneously, the entire business log is recorded and uploaded to the data storage module to complete the feedback loop.

[0057] In other embodiments, the electronic device's data storage module stores a business process template library, a rule engine keyword library and regular expressions, dialogue memory data, full-link business logs, user interaction data, and atomic capability set-related data throughout the entire combined business generation process. This supports data querying and traceability, providing data support for business auditing and process optimization. Furthermore, this module can dynamically update the rule engine's keyword library, regular expressions, compliance verification rules, business process template library, and atomic capability set based on the generation of the combined business process and subsequent combined business processing. This adapts to changes in securities industry regulatory policies and business iteration needs without modifying the system's core code, reducing maintenance costs.

[0058] Figure 2 A schematic diagram of a combined service generation system according to an embodiment of this application is shown. Figure 2 As shown, the combined business generation scheme of this application embodiment can realize one-stop processing of customer business through an intent parsing module, an intelligent recommendation module, an intelligent pre-inspection module, and a combined business processing module. Specifically, users can initiate business requests / queries through the intent parsing module. After parsing and disambiguation, the module outputs a structured intent. The Skills layer of the core support module completes business judgment, boundary verification, and matching to confirm that the request is compliant and within the service scope, thus obtaining the user's intent. Based on this accurate user intent and user profile, the intelligent recommendation module pushes suitable securities businesses and standard processes, and collaborates with the Skills layer to complete compliance verification. The intelligent pre-inspection module can complete pre-condition verification and account type screening, generating a clear business list to determine target business needs and other information. After user confirmation, the combined business processing module collaborates with the core support module, using the Skills layer to complete the merging of atomic capabilities and the generation of combined processes.

[0059] Throughout the entire combined business processing flow, the Skills layer enables business collaboration and data interoperability among various modules, providing a solid guarantee for the entire service loop. The Skills layer undertakes four core responsibilities: First, it collaborates with the intent parsing module, conducting multi-dimensional analysis, boundary verification, and secondary precise matching of the structured intent output by the model to obtain user intent. Second, it cooperates with the intelligent recommendation module to meet compliance verification requirements, executing system interaction rules and rigorously reviewing parameters throughout the entire business processing flow to ensure all business operations comply with industry regulatory requirements and company compliance standards. Third, it handles the capability invocation requirements of the combined business processing module, responsible for the integration and invocation of atomic capabilities. Fourth, it supports data retrieval for the intelligent pre-inspection module, synchronizing core data such as customer qualifications, business status, and account type to ensure accurate and real-time pre-inspection results, providing data support for process guidance. This module adopts a lightweight integration solution, eliminating the need for large-scale modifications to existing business systems, effectively reducing project implementation costs and landing risks.

[0060] Furthermore, relying on the Skills layer, the system calls upon existing business system resources to perform end-to-end compliance verification and data synchronization to complete business processing. Ultimately, the processing results are fed back to the user in real time, while simultaneously updating data in relevant modules, forming a complete closed-loop business processing service encompassing "interaction-analysis-recommendation-pre-check-processing-feedback." The Skills layer, as the core support for the entire process, runs through the entire collaborative processing of combined businesses, coordinating and managing four core tasks: business judgment and matching, compliance verification, atomic capability integration, and system integration and adaptation. It precisely connects the five functional modules, ensuring collaborative operation and data interoperability, achieving efficient, compliant, and convenient business processing.

[0061] Based on the aforementioned technical features, this application embodiment constructs a collaborative architecture of "LLM-led parsing + rule engine hard verification + dynamic assembly of atomic capabilities," achieving an organic unity between the extremely high flexibility of intent parsing and the absolute compliance of business execution. This not only completely solves the pain points of rigid processes, repeated submissions, and frequent breakpoints in traditional solutions, but also allows users to complete combined business transactions in one stop through natural dialogue without manual switching, upgrading the online service hall from passive response to proactive intelligent recommendation, greatly improving user experience and processing efficiency. At the same time, the reuse mechanism of atomic capabilities and the hot update capability of rules enable this application embodiment to call atomic capabilities in real time to provide customer processing processes. The addition of new businesses only requires modification of the business process template library and the exclusive standard process set to achieve rapid online support for customer processing. This enables low-cost and rapid adaptation to new businesses and changes in regulatory policies. The lightweight integration solution also significantly reduces the risk of modifying existing systems, providing a "AI + compliance" business generation solution with intelligence, high scalability, and high feasibility for implementation in highly regulated industries such as healthcare, government affairs, and securities.

[0062] It should be understood that although the steps in the above flowcharts are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the above flowcharts may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0063] Based on the foregoing embodiments, this application provides a combined service generation device, which includes various modules and units included in each module, and can be implemented by a processor; of course, it can also be implemented by specific logic circuits; in the implementation process, the processor can be a central processing unit (CPU), microprocessor (MPU), digital signal processor (DSP) or field programmable gate array (FPGA), etc.

[0064] Figure 3 A schematic diagram of a combined service generation apparatus according to an embodiment of this application is shown. Figure 3 As shown, the combined service generation apparatus of this application embodiment includes: The intent parsing module 30 is used to parse the user input information received from the target user to determine at least one user intent; The intelligent recommendation module 31 is used to determine at least one user demand service and the standard processing procedure corresponding to each user demand service based on the at least one user intent. The intelligent pre-detection module 32 is used to determine the user demand service that meets the corresponding preconditions of the user information corresponding to the target user as the target demand service; The combined business processing module 33 is used to generate a combined business processing process for the target user based on the standard processing process and the corresponding atomic capability set for each target demand business. The atomic capability set includes at least one atomic capability corresponding to the target demand business, and the atomic capability represents a standardized functional unit that cannot be further divided in the business.

[0065] In one possible implementation, the intent parsing module 30 is further configured to: In response to receiving user input information from the target user, the user input information is preprocessed to obtain a standardized request text; The standardized request text is parsed based on preset domain constraints to obtain the corresponding structured intent; At least one user intent is obtained by performing multi-dimensional judgment on the structured intent.

[0066] In one possible implementation, the intent parsing module 30 is further configured to: The structured intent is split according to the preset business priority rules to obtain at least one candidate intent with a priority order; If no other candidate intents with the same priority order exist among the candidate intents, the candidate intent is determined to be a user intent. If there are other candidate intents with the same priority order among the candidate intents, at least one round of dialogue is conducted with the target user through a large language model to determine one candidate intent as the user intent from among the candidate intents with the same priority order.

[0067] In one possible implementation, the intelligent recommendation module 31 is further configured to: Determine the corresponding first demand service for each user intent; Match relevant second demand services based on each of the first demand services and the target user's historical service information; The second requirement business is filtered according to a predefined set of exclusive standard processes to remove the second requirement business that cannot be combined with the first requirement business. Based on the first demand service and the filtered second demand service, at least one user demand service is determined. The standard processing procedures corresponding to each user's required business are obtained by searching the predefined business process template library.

[0068] In one possible implementation, the intelligent recommendation module 31 is further configured to: Display each of the first demand services and each of the second demand services; In response to receiving selection information for at least one of the first demand services and / or the second demand services, the first demand service and / or the second demand service selected in the selection information are determined to be user demand services.

[0069] In one possible implementation, the intelligent pre-detection module 32 is further configured to: Determine the prerequisites for each of the aforementioned user demand services; Based on the user information corresponding to the target user, determine whether the preconditions corresponding to each user demand service are met; If the prerequisites for the user demand service are met, the user demand service is determined to be the target demand service.

[0070] In one possible implementation, the intelligent pre-detection module 32 is further configured to: If the prerequisites for the user's service request are not met, corresponding supplementary information prompts will be generated based on the unmet content of the prerequisites. In response to receiving supplementary information from the user regarding the supplementary information prompt, the system re-evaluates whether the unmet preconditions have been met.

[0071] The descriptions of the above device embodiments are similar to those of the above method embodiments, and have similar beneficial effects. For technical details not disclosed in the device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0072] It should be noted that, in the embodiments of this application... Figure 3 The module division of the combined service generation device shown is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, exist as separate physical units, or be integrated into one unit by two or more units. The integrated units can be implemented in hardware, as software functional units, or a combination of both.

[0073] It should be noted that, in the embodiments of this application, if the above-described methods are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.

[0074] Figure 4 A schematic diagram of an electronic device according to an embodiment of this application is shown. For example... Figure 4 As shown in the figure, this application provides an electronic device, which can be a server, and its internal structure diagram can be as follows. Figure 4 As shown, the electronic device includes a processor 420, a memory, and a transceiver 440 connected via a system bus 410. The processor 420 provides computing and control capabilities. The memory includes a non-volatile storage medium 431 and internal memory 432. The non-volatile storage medium 431 stores an operating system, computer programs, and a database. The internal memory 432 provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium 431. The database stores data. The transceiver 440 communicates with external terminals via a network connection. The computer program is executed by the processor 420 to implement the aforementioned methods.

[0075] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor 420, implements the steps of the method provided in the above embodiments.

[0076] This application provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps in the method provided in the above-described method embodiments.

[0077] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0078] In one possible implementation, the apparatus provided in this application can be implemented as a computer program, which can be configured as follows: Figure 4 The device operates on the electronic device shown. The memory of the electronic device can store the various program modules that make up the above-described apparatus. The computer program composed of the various program modules causes the processor 420 to execute the steps of the methods in the various embodiments of this application described in this specification.

[0079] It should be noted that the descriptions of the storage medium and device embodiments above are similar to the descriptions of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the storage medium, storage medium, and device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0080] It should be understood that the phrases "one embodiment," "an embodiment," or "some embodiments" mentioned throughout the specification mean that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, phrases such as "in one possible implementation," "in one embodiment," or "in some embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. The descriptions of the various embodiments above tend to emphasize the differences between the various embodiments; their similarities or commonalities can be referred to mutually, and for the sake of brevity, they will not be repeated here.

[0081] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three kinds of relationships. For example, object A and / or object B can represent three situations: object A exists alone, object A and object B exist simultaneously, and object B exists alone.

[0082] It should be noted that, in this document, 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. Unless otherwise specified, 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 that element.

[0083] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple modules or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or modules can be electrical, mechanical, or other forms.

[0084] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules. They may be located in one place or distributed across multiple network units. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0085] In addition, each functional module in the various embodiments of this application can be integrated into one processing unit, or each module can be a separate unit, or two or more modules can be integrated into one unit; the integrated modules can be implemented in hardware or in the form of hardware plus software functional units.

[0086] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0087] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0088] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0089] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0090] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0091] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for generating combined services, characterized in that, The method includes: In response to receiving user input information from a target user, the user input information is parsed to determine at least one user intent; Based on the at least one user intent, at least one user demand service is determined, as well as the standard processing procedure corresponding to each user demand service; The user demand service that meets the corresponding prerequisite conditions and is identified as the target demand service; Based on the standard processing procedures and corresponding atomic capability sets corresponding to each target demand service, a combined service processing procedure for the target user is generated. The atomic capability set includes at least one atomic capability corresponding to the target demand service, and the atomic capability represents a standardized functional unit that cannot be further divided in the service.

2. The method according to claim 1, characterized in that, The step of responding to receiving user input information from a target user and parsing the user input information to determine at least one user intent includes: In response to receiving user input information from the target user, the user input information is preprocessed to obtain a standardized request text; The standardized request text is parsed based on preset domain constraints to obtain the corresponding structured intent; At least one user intent is obtained by performing multi-dimensional judgment on the structured intent.

3. The method according to claim 2, characterized in that, The step of obtaining at least one user intent by performing multi-dimensional judgment on the structured intent includes: The structured intent is split according to the preset business priority rules to obtain at least one candidate intent with a priority order; If no other candidate intents with the same priority order exist among the candidate intents, the candidate intent is determined to be a user intent. If there are other candidate intents with the same priority order among the candidate intents, at least one round of dialogue is conducted with the target user through a large language model to determine one candidate intent as the user intent from among the candidate intents with the same priority order.

4. The method according to claim 1, characterized in that, The step of determining at least one user-required service based on the at least one user intent, and the standard processing procedure corresponding to each user-required service, includes: Determine the corresponding first demand service for each user intent; Match relevant second demand services based on each of the first demand services and the target user's historical service information; The second requirement business is filtered according to a predefined set of exclusive standard processes to remove the second requirement business that cannot be combined with the first requirement business. At least one user demand service is determined based on the first demand service and the filtered second demand service; The standard processing procedures corresponding to each user's required business are obtained by searching the predefined business process template library.

5. The method according to claim 4, characterized in that, The step of determining at least one user demand service based on the first demand service and the filtered second demand service includes: Display each of the first demand services and each of the second demand services; In response to receiving selection information for at least one of the first demand services and / or the second demand services, the first demand service and / or the second demand service selected in the selection information are determined to be user demand services.

6. The method according to claim 1, characterized in that, The service of determining that the user information corresponding to the target user meets the corresponding preconditions is the target demand service, including: Determine the prerequisites for each of the aforementioned user demand services; Based on the user information corresponding to the target user, determine whether the preconditions corresponding to each user demand service are met; If the prerequisites for the user demand service are met, the user demand service is determined to be the target demand service.

7. The method according to claim 6, characterized in that, The service of determining that the user information corresponding to the target user meets the corresponding preconditions is the target demand service, including: If the prerequisites for the user's service request are not met, corresponding supplementary information prompts will be generated based on the unmet content of the prerequisites. In response to receiving supplementary information from the user regarding the supplementary information prompt, the system re-evaluates whether the unmet preconditions have been met.

8. A combined service generation device, characterized in that, The device includes: The intent parsing module is used to parse the user input information received from the target user to determine at least one user intent; The intelligent recommendation module is used to determine at least one user demand service and the standard processing procedure corresponding to each user demand service based on the at least one user intent. The intelligent pre-detection module is used to determine the target user's user information that meets the corresponding preconditions as the target user's user demand service; The combined service processing module is used to generate a combined service processing flow for the target user based on the standard processing flow and the corresponding atomic capability set for each target demand service. The atomic capability set includes at least one atomic capability corresponding to the target demand service, and the atomic capability represents a standardized functional unit that cannot be further divided in the service.

9. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images