Service scheme generation method and device based on cross-ecological collaboration, equipment and medium

Abstract

The invention relates to the technical field of data processing, and particularly discloses a service scheme generation method and device based on cross-ecological collaboration, equipment and a medium. When the active service is triggered, fusion analysis is performed on the user data through the target causal atlas, the potential demand of the user is accurately pre-judged, and cooperative processing is performed through the service nodes corresponding to the businesses to obtain the target service scheme, so that passive response is converted into the active service, user consultation is not needed, the service scheme can be actively provided for the user, and the user experience is improved. And cross-domain service nodes are automatically scheduled to work cooperatively through the smart contract, and finally the target service scheme is integrated and generated, so that a data island is broken, data transmission in different source databases is not needed, and the accuracy and the generation efficiency of the service scheme are improved. When the method is applied to a service system of a financial insurance service, potential requirements of a user can be actively analyzed, an accurate service scheme is timely and actively provided for the user, and the user experience is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a service scheme generation method and device based on cross-ecological collaboration, equipment and medium. BACKGROUND

[0002] With the rapid development of digital economy, financial services are gradually moving online and intelligent. In the traditional service mode, each financial institution (such as banks and insurance companies) is usually in a state of data fragmentation, forming obvious data islands. This fragmentation results in the inability to obtain comprehensive user data, making the final service scheme unable to meet user needs. For example, when an insurance company recommends deposit insurance, property insurance and other businesses, it cannot obtain the user's property information, resulting in the final financial service scheme failing to meet user needs. In order to improve the accuracy of the scheme, when providing insurance recommendation services, data requests need to be sent to banks or other related institutions, and the final service scheme is generated after the returned data is obtained, resulting in low efficiency of service scheme generation. Therefore, how to improve the accuracy and generation efficiency of the service scheme has become a problem to be solved. SUMMARY

[0003] The present application provides a service scheme generation method and device based on cross-ecological collaboration, equipment and medium to improve the accuracy and generation efficiency of the service scheme.

[0004] In a first aspect, the present application provides a service scheme generation method based on cross-ecological collaboration, which comprises: When the active service is triggered, the user data is obtained, and the user data is analyzed based on a preset target causal graph to obtain the user's potential demand; Based on the user's potential demand, an intelligent contract is matched, and the user's potential demand is allocated to at least one service node based on the intelligent contract; Based on the analysis of the user's potential demand by each service node according to the cooperation rules in the intelligent contract, a sub-service scheme is generated, and each sub-service scheme is integrated through the intelligent contract to obtain a target service scheme.

[0005] In a second aspect, the present application also provides a service scheme generation device based on cross-ecological collaboration, which comprises: A potential demand obtaining module is configured to obtain user data when the active service is triggered, and analyze the user data based on a preset target causal graph to obtain the user's potential demand; A service node matching module is configured to match an intelligent contract based on the user's potential demand, and allocate the user's potential demand to at least one service node based on the intelligent contract; a service scheme obtaining module configured to analyze the potential demand of the user by each service node according to the cooperation rule in the smart contract, generate a sub-service scheme, and integrate each sub-service scheme through the smart contract to obtain a target service scheme.

[0006] In a third aspect, the present application also provides a computer device, which comprises a memory and a processor; the memory is configured to store a computer program; the processor is configured to execute the computer program and realize the cross-ecological collaboration based service scheme generation method as described above when executing the computer program.

[0007] In a fourth aspect, the present application also provides a computer readable storage medium, which stores a computer program; the computer program is configured to make the processor realize the cross-ecological collaboration based service scheme generation method as described above when executed by the processor.

[0008] The present application discloses a cross-ecological collaboration based service scheme generation method, device, equipment and medium. When active service is triggered, user data is obtained, and the user data is analyzed based on a preset target causal graph to obtain potential demand of the user. The potential demand of the user is matched with a smart contract, and the potential demand of the user is allocated to at least one service node based on the smart contract. The potential demand of the user is analyzed by each service node according to the cooperation rule in the smart contract to generate a sub-service scheme, and each sub-service scheme is integrated through the smart contract to obtain a target service scheme. When active service is triggered, the present application fuses and analyzes user data through a target causal graph, accurately predicts potential demand of the user, and then collaboratively processes each service corresponding to the service node to obtain a target service scheme. The passive response is converted into active service, the user does not need to consult, the service scheme can be actively provided to the user, the service nodes in different fields are automatically scheduled to work collaboratively through the smart contract, the target service scheme is finally integrated and generated, the data island is broken, data transmission in different source databases is not needed, and the accuracy and generation efficiency of the service scheme are improved. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0010] Figure 1 is a first schematic flow chart of a cross-ecological collaboration based service scheme generation method provided by an embodiment of the present application; Figure 2 is a second schematic flowchart of a service scheme generation method based on cross-ecological collaboration provided by an embodiment of the present application; Figure 3 is a third schematic flowchart of a service scheme generation method based on cross-ecological collaboration provided by an embodiment of the present application; Figure 4 is a schematic block diagram of a service scheme generation apparatus based on cross-ecological collaboration provided by an embodiment of the present application; Figure 5 is a schematic block diagram of a computer device structure provided by an embodiment of the present application. DETAILED DESCRIPTION

[0011] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0012] The flowcharts shown in the drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor do they have to be executed in the order described. For example, some operations / steps can be further decomposed, combined or partially merged, so the actual execution order may be changed according to the actual situation.

[0013] It should be understood that the terms used in the present application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the present application specification and the appended claims, unless otherwise clearly indicated by the context, the singular forms “a”, “an” and “the” are intended to include the plural forms.

[0014] It should also be understood that the term “and / or” used in the present application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0015] Embodiments of the present application provide a cross-ecological collaboration-based service scheme generation method, device, equipment and medium. The cross-ecological collaboration-based service scheme generation method can be applied to a server, user data is analyzed by a target causal graph, potential user needs are accurately predicted, and then each service corresponding service node is collaboratively processed to obtain a target service scheme, passive response is converted into active service, the user does not need to consult, the service scheme can be actively provided to the user, cross-domain service nodes are collaboratively scheduled by an intelligent contract, and finally a target service scheme is integrated and generated, data islands are broken, data transmission in different source databases is not needed, and the accuracy and generation efficiency of the service scheme are improved. The server can be a stand-alone server or a server cluster.

[0016] Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The following embodiments and features in the embodiments can be combined with each other without conflict.

[0017] Please refer to Figure 1 , Figure 1 is a schematic flowchart of a cross-ecological collaboration-based service scheme generation method provided by an embodiment of the present application. The cross-ecological collaboration-based service scheme generation method can be applied to a server, is used for analyzing user data by a target causal graph, accurately predicting potential user needs, then collaboratively processing each service corresponding service node to obtain a target service scheme, converting passive response into active service, actively providing a service scheme to the user without user consultation, and finally integrating and generating a target service scheme by an intelligent contract to collaboratively work cross-domain service nodes, breaking data islands, and improving the accuracy and generation efficiency of the service scheme without data transmission in different source databases.

[0018] As shown in Figure 1 , the cross-ecological collaboration-based service scheme generation method specifically includes steps S101 to S103.

[0019] S101, when active service is triggered, user data is obtained, and the user data is analyzed based on a preset target causal graph to obtain potential user needs; In an embodiment, when the trigger condition of active service is reached, a data acquisition process is automatically started, user data is acquired, potential demand analysis is performed, and potential user needs are obtained.

[0020] In one embodiment, the active service trigger condition includes but is not limited to the compliance adaptive hub receiving a new rule (such as 30 years old or above without serious illness insurance population needs to be prompted), triggering data scanning of the target user group; user behavior / state change, such as monitoring user key behavior (such as buying a new car, abnormal physical examination data, exceeding the standard of violation times).

[0021] In a specific embodiment, user authorization needs to be obtained through a data authorization management interface before data monitoring, and one-key authorization withdrawal is supported, and the user can view which structure calls his / her data through the data authorization management interface. After obtaining the user authorization, the data is integrated across agencies through federated learning and differential privacy technology, including but not limited to behavior data such as navigation software mountainous area commuting route, vehicle registration information of vehicle management department, violation record; financial data such as bank flow, insurance record, risk assessment result.

[0022] In one embodiment, the original data is stored locally, and only feature labels (such as 5 times of violation in the past 3 months, no serious illness insurance) are obtained as user data to avoid data leakage.

[0023] In one embodiment, the target causal graph is a cross-scene causal relationship network formed by aggregating multi-agency local causal graphs through federated learning. The obtained user data (such as user Xiao Zhang buying a certain type of SUV) is matched with the target causal graph. The graph infers a set of potential demands that have strong causal correlation with it, obtains a structured list of user potential demands, i.e. user potential demands. For example, the potential demand list for Xiao Zhang may be: [demand 1: commercial vehicle insurance scheme, demand 2: vehicle loan scheme, demand 3: vehicle maintenance service].

[0024] In another embodiment, the data acquisition process can also be started when a user-initiated service request is received, user data is acquired, and potential demand analysis is performed to obtain user potential demands.

[0025] Further, before the active service trigger, the user data is acquired, and the user potential demands are obtained by analyzing the user data based on the preset target causal graph, it further includes: performing local inference on at least one local business history data corresponding to the user based on a preset causal inference model to obtain a local causal graph; aggregating each local causal graph to obtain the target causal graph.

[0026] In one embodiment, the local business history data refers to the user data stored in each cooperative agency (such as bank, insurance company, hospital, e-commerce platform) and not directly shared with the outside world. For example, bank loan records, insurance company claim records, and e-commerce platform consumption records.

[0027] The local causal graph refers to a local node (such as a vehicle management office, a navigation platform, etc.) where user data is located, reasoning on user business historical data through a preset causal inference model, identifying a strong correlation between "behavior-demand", and forming a local causal relationship network.

[0028] In specific embodiments, after user authorization, the local node (such as a physical examination center, a vehicle management office) collects user business historical data, including but not limited to behavior data such as navigation software mountainous area commuting route, vehicle registration information, and illegal record of the vehicle management office; financial data such as bank flow, insurance record, and risk assessment result.

[0029] The local node uses differential privacy technology to desensitize the original data, only retaining feature labels (such as 5 illegal records in the last 3 months, no serious illness insurance), and avoiding original data leakage.

[0030] The local node loads a preset causal inference model, inputs the local business historical data features of the user (such as new car purchase, mountainous area commuting), identifies the time sequence causality (such as purchasing a new car triggering car insurance demand) and feature correlation (such as frequent mountainous area commuting requiring car damage insurance with additional non-counting deductible insurance) in the local business historical data features, obtains the causal relationship, and generates a local causal graph according to the causal relationship, that is, a behavior-demand causal relationship network in a local scenario, for example: the vehicle management office node outputs: "new car registration as cause, and compulsory insurance and commercial vehicle insurance demand as effect".

[0031] In one embodiment, the target causal graph is a global user demand causal network formed by aggregating the causal graph features of multiple local nodes through federated learning technology, realizing comprehensive prediction of cross-ecological demand. Specifically, each local node encrypts (or adds differential privacy noise for desensitization) the generated local causal graph, and then uploads it to the central server. After the central server collects all encrypted local causal graphs, it performs a secure aggregation algorithm. The local causal graphs from different data sources are fused to generate a target causal graph containing causal knowledge from multiple ecologies.

[0032] In one embodiment, the target causal graph is iteratively updated based on new local data features every day.

[0033] In another embodiment, the causal inference model is also trained through a federated learning method. Specifically, first, each local node trains the model according to the local data, and uploads the model parameters obtained after training to the central server. The central server aggregates the model parameters uploaded by each node to generate the final causal inference model, and returns the causal inference model to each local node for causal relationship identification according to the causal inference model.

[0034] In the above embodiments, a local causal graph is generated at a single institution local node through a preset causal inference model, and a global causal network across ecologies is formed through federated learning to aggregate multi-node feature parameters, thereby realizing data privacy protection, cross-domain data fusion, breaking data silos, and providing a data basis for subsequent potential demand identification and scheme generation.

[0035] Further, before the acquiring user data and analyzing the user data based on a preset target causal graph to obtain potential demands of the user, the method further includes: monitoring target data, analyzing new data when the new data is detected, and obtaining an analysis result, wherein the target data includes the user data or a compliance database; and triggering the active service when the analysis result meets a preset triggering condition.

[0036] In one embodiment, the target data includes but is not limited to user data and a compliance database. The user data refers to dynamic and user-related information such as behavior data and financial data, which is not raw data but authorized and desensitized data stream or feature update. The compliance database interfaces with the supervision system of the China Banking and Insurance Regulatory Commission and the traffic management office to obtain policy updates in the first time.

[0037] The monitoring mechanism of the user data can be a dual-mode of real-time collection and timing update to achieve full coverage. Specifically, cross-institution data sources are accessed through federated learning technology, including but not limited to behavior data and financial data. Real-time collection triggers the active service immediately when a key change in user behavior occurs (such as purchasing a new car or reaching the standard number of violations). Timing scanning updates the user data in full at dawn every day (or other time points set by the user according to actual needs) to identify long-term trends (such as continuous 3-month consumption degradation or annual physical examination index changes), and triggers the active service when the long-term trend meets the preset triggering condition.

[0038] The monitoring mechanism of the compliance database can be to automatically capture incremental information of the compliance database every hour (or other time period set by the user according to actual needs).

[0039] In one embodiment, the new data (user behavior change or compliance data update) is analyzed, and the analysis result is compared with the triggering condition of the active service. If the triggering condition is met, a structured triggering instruction is generated to trigger the active service.

[0040] The triggering condition is a configurable and quantifiable business rule that determines whether the active service is started. The triggering condition includes but is not limited to a threshold condition, such as more than 5 times of violations in the last 3 months, which triggers the car insurance risk prompt service.

[0041] In the above embodiments, target data monitoring covers user behavior and policy changes through real-time scanning and regular updates, and new data analysis relies on causal inference models and compliance hubs to accurately locate demand and determine the trigger for proactive services, achieving an upgrade from passive response to proactive services and providing timely service solutions for users.

[0042] S102, match the smart contract based on the user potential demand, and distribute the user potential demand to at least one service node based on the smart contract; In one embodiment, the smart contract is pre-deployed on the alliance chain, and each contract has a metadata tag to describe its function. The user potential demand is matched with the metadata tag to obtain the smart contract matched with the user potential demand.

[0043] In one embodiment, the cooperation rules of each service node corresponding to each service scenario are preset in the smart contract template, such as a bank car loan split that needs to feedback the loan approval result within 2 hours, and an insurance car insurance split that needs to adjust the premium calculation method based on the loan amount.

[0044] In one embodiment, the service node (digital person) is an intelligent collaboration entity deployed by financial institutions, vehicle management offices and other entity institutions in the cross-ecological digital alliance network, has a unique digital identity certificate (generated through blockchain qualification audit), and can perform tasks based on preset rules and cross-agency service nodes.

[0045] In one embodiment, according to the demand type (such as car insurance, critical illness insurance, and car loan) of the user potential demand, the service node of the corresponding business type in the cross-ecological service node alliance is matched. And verify whether the service node passes the compliance audit of the blockchain alliance chain, if it passes the compliance audit, the subtask corresponding to the user potential demand is assigned to the corresponding service node.

[0046] Further, the matching of the smart contract based on the user potential demand comprises: matching a preset smart contract template according to the user potential demand; extracting key variables from the user data based on the user potential demand, and adjusting parameters in the smart contract template based on the key variables to obtain the smart contract.

[0047] In one embodiment, the cross-ecological service node alliance pre-sets standardized smart contract templates corresponding to each service scenario, including but not limited to car insurance, car loan, critical illness insurance and other scenarios, and locates the corresponding template through the type of user potential demand.

[0048] Specifically, the core scene keywords are identified from the user potential demand list, and the matching smart contract template is determined according to the similarity matching result of the core scene keywords and the metadata tags of each smart contract template.

[0049] In one embodiment, after template matching, contract parameters are adjusted based on user data characteristics (such as financial status) to achieve personalized adaptation.

[0050] Specifically, key variables related to services corresponding to users' potential needs are extracted from user data. For example, key variables for car insurance scenarios include vehicle value, loan amount, and commuting route.

[0051] The extracted key variables are written into a smart contract to form a smart contract that meets the current potential needs of users. The generated smart contract is then subject to compliance verification by a compliance adaptive hub. Once the verification is passed, the smart contract can be executed.

[0052] In the above embodiments, a preset smart contract template is matched and parameters are dynamically adjusted based on user data to generate a smart contract that meets the current needs, so as to achieve precise service and improve the accuracy and generation efficiency of service solutions.

[0053] S103. Based on the collaboration rules in the smart contract, each service node analyzes the potential needs of the user, generates sub-service solutions, and integrates the sub-service solutions through the smart contract to obtain the target service solution.

[0054] In one embodiment, each called service node generates a sub-service plan within its own business scope based on preset collaboration rules and the permissions granted by the smart contract. For example, the car insurance service node generates an insurance plan that combines vehicle damage insurance and deductible waiver insurance based on vehicle characteristics (commuting in mountainous areas).

[0055] In one embodiment, compliance verification of each sub-service plan is performed through a compliance adaptive hub, including verifying the matching degree of users' risk tolerance, confirming that users understand the product terms and risks, and recording and storing the sales process as evidence.

[0056] The smart contract logically integrates the verified sub-service solutions according to the rules to obtain the target service solution.

[0057] Furthermore, the step of analyzing the user's potential needs based on the collaboration rules in the smart contract by each service node, generating sub-service solutions, and integrating the sub-service solutions through the smart contract to obtain the target service solution includes: processing the business processing sub-tasks by each service node according to the collaboration rules to obtain the sub-service solutions; performing logical verification and conflict resolution on each sub-service solution based on the smart contract, and integrating the verified and conflict-resolved sub-service solutions through solution integration rules to obtain the target service solution.

[0058] In one embodiment, each service node, according to the collaboration rules, invokes its internal professional model to process the business processing sub-tasks and generates corresponding sub-service solutions.

[0059] In one embodiment, logical validation includes data consistency validation: checking whether the underlying data referenced in different schemes is consistent. For example, whether the vehicle valuation in the bank's scheme matches the vehicle valuation in the insurance scheme. If the difference is too large, a conflict is triggered. It also includes logical reasonableness validation, checking whether the logical relationships between the schemes are reasonable. For example, whether the sum of the total loan amount and the down payment equals the total vehicle price. If the sum of the loan amount and the down payment is less than the total vehicle price, it means the user has insufficient funds, and the scheme is not feasible.

[0060] In one embodiment, when conflicts arise between sub-service plans, the smart contract automatically resolves the conflicts according to preset conflict resolution rules. These rules include priority rules, such as stipulating that "the loan amount is based on the bank's approval, and the insurance plan must be adjusted accordingly." If the insurance plan is calculated based on a total vehicle price of 300,000, but the bank only approves a loan of 250,000, the smart contract will require the insurance service node to generate a new premium plan based on the 250,000 loan (i.e., the total vehicle price may be 300,000, with a down payment of 50,000). Other user-defined rules are also included, such as default value rules. For conflicts that cannot be resolved automatically, the smart contract can pause the process and notify a human to make a decision.

[0061] In one embodiment, after ensuring that all sub-solutions are logically consistent, the smart contract invokes the scheme integration rules to perform the final integration and generate the target service scheme.

[0062] In the above embodiments, when an active service is triggered, user data is fused and analyzed through a target causal graph to accurately predict potential user needs. Then, the service nodes corresponding to each business are collaboratively processed to obtain a target service solution. This transforms passive response into active service, providing a service solution to users proactively without requiring user consultation. Furthermore, smart contracts automatically schedule cross-domain service nodes to work collaboratively, ultimately integrating and generating the target service solution. This breaks down data silos and eliminates the need for data transmission between different source databases, improving the accuracy and efficiency of service solution generation.

[0063] Please see Figure 2 , Figure 2This is a schematic flowchart illustrating a service solution generation method based on cross-ecosystem collaboration, provided in an embodiment of this application. This method can be applied to a server to simulate solutions using virtual scenarios and modify the solutions based on user feedback. It combines standardized recommendations with personalized modifications, addressing user misunderstandings of the product while ensuring a high degree of match between the solution and actual needs through a feedback loop. This approach improves the accuracy of solutions while maintaining efficiency in their generation.

[0064] like Figure 2 As shown, after step S103 of the service solution generation method based on cross-ecological collaboration, it further includes steps S201 to S203.

[0065] S201. Process the target service plan to construct a virtual decision-making scenario; S202. Receive the user's interaction command, interact with the virtual decision-making scenario based on the interaction command, and obtain the virtual decision-making result; S203. Receive the solution feedback information input by the user based on the virtual decision result, and modify the target service solution based on the solution feedback information, and use the modified solution as the target service solution.

[0066] In one embodiment, after obtaining the target service plan, the plan is pushed to the user. Upon receiving the user's viewing instruction, the most suitable virtual scenario template is matched according to the plan type, and the template is modified based on key parameters in the plan to generate a customized virtual decision-making scenario based on real plan data. For example, a car insurance plan corresponds to a traffic accident simulation scenario, and a pension insurance plan corresponds to a retirement life simulation scenario.

[0067] Specifically, key parameters from the solution are embedded into the virtual scene template, making them variable. For example, parameters such as car insurance coverage and deductible are set as core variables in the scene; loan interest rates and repayment periods are linked to changes in the virtual character's assets.

[0068] External random variables can also be introduced to simulate real-world uncertainty. For example, in car insurance scenarios, different accident severity levels and repair costs for the other party's vehicle can be set.

[0069] Using VR / AR or advanced visualization technologies, an immersive or semi-immersive environment can be generated that users can access through devices such as VR headsets or tablets.

[0070] For example, the "car insurance decision-making scenario" built for user Xiao Zhang might be a virtual traffic accident scene. His vehicle model is displayed on the screen, and next to it is a panel showing the coverage and premium of two insurance plans, A and B, which he is considering. The scenario prompts: Please choose a plan and then experience the claims process for a rear-end collision.

[0071] In one embodiment, the interactive instructions are instructions made by the user in a virtual scene, including but not limited to: selecting a plan, such as switching between plan A and plan B; adjusting parameters, such as manually adjusting the insured amount, loan term, etc.; and clicking the button corresponding to an event such as simulating a rainstorm flooding accident.

[0072] It supports receiving multimodal interaction commands, including but not limited to VR controller operation, voice commands, touch screen clicks and other interaction methods.

[0073] Upon receiving user interaction commands, actuarial and financial models calculate the virtual decision outcome in real time, such as the expected claim settlement in insurance. This virtual decision result is immediately fed back into the virtual scenario and presented to the user in a visual format. This intuitive presentation reduces the user's understanding cost and improves the user experience.

[0074] For example, in a virtual scenario, a user selects Plan A (low premium, but high deductible) and triggers a minor collision. The virtual result shows: you need to pay 1500 yuan for repairs. Then, the user switches to Plan B (high premium, but low deductible) and triggers the same accident. The virtual result changes to: the insurance company will fully reimburse you, and you will pay 0 yuan.

[0075] In one embodiment, solution feedback includes explicit and implicit feedback. Explicit feedback: Direct evaluations or choices by the user. For example, after experiencing the solution, a user clicks or enters "I prefer Solution B" or "I want to increase the coverage of Solution A to 500,000." Implicit feedback: Preferences inferred through analysis of user behavior. For example: a user spends the longest time on a particular solution; a user repeatedly simulates a specific risk (such as water damage), indicating strong interest in this coverage; the user ultimately selects a solution in a virtual environment for confirmation.

[0076] User feedback is categorized and processed, triggering corresponding correction logic. The service plan is then modified according to the corresponding correction logic to obtain the final target service plan.

[0077] In one embodiment, the revised target service plan undergoes a compliance audit. Once the audit is passed, the revised plan is pushed to the user, supporting secondary virtual experience verification. The user can re-enter the virtual scene to test the revised plan until they are satisfied, at which point the final version of the target service plan is generated.

[0078] In one embodiment, after the solution is confirmed, the correction process is recorded through the Hyperledger Fabric consortium blockchain to ensure that each round of adjustments is auditable and tamper-proof, serving as a basis for subsequent service traceability.

[0079] In the above embodiments, a virtual scenario is used to simulate the solution, and the solution is modified based on user feedback. This combines standardized recommendations with personalized modifications, which not only solves the user's misunderstanding of the product, but also ensures that the solution is highly matched with actual needs through a feedback loop, thereby improving the accuracy of the solution while ensuring the efficiency of solution generation.

[0080] In one embodiment, after obtaining the target service plan and confirming the user's choice, services are provided to the user according to the target service plan, and compliance monitoring is conducted during the service process. For example, during the user's insurance application process, for high-risk insurance products (such as unit-linked insurance), a three-pronged compliance verification process is automatically initiated: verifying whether the user's risk tolerance matches the policy, confirming that the user has fully understood the product terms and risks, and recording the sales process for evidence. For low-risk products such as accident insurance, the process is simplified to improve application efficiency. This not only reduces the compliance risks for insurance institutions but also protects the legitimate rights and interests of users.

[0081] For example, at 2:00 AM, the compliance center receives a new regulatory rule: individuals over 30 years old without critical illness insurance should be given special attention. The federated learning node runs a model locally at the medical examination center, outputting the risk label "Xiao Zhang, 30 years old, high blood pressure, no critical illness insurance." The blockchain node immediately labels Xiao Zhang's digital identity as "high-priority push target." A pop-up window is proactively pushed to Xiao Zhang's phone (at 8:30 AM): "Good morning, Xiao Zhang! The system has detected that you currently lack critical illness insurance coverage and have high blood pressure. A VR trial insurance cabin has been prepared for you. You can watch the entire process of a 300,000 RMB coverage payout upon diagnosis in 3 minutes. Put on your VR glasses now to experience it, would you like to start?" The user requires zero input, only confirmation. Xiao Zhang clicks the confirmation button on his phone. The VR scene simulates "early-stage cancer diagnosis - 300,000 RMB lump sum payment - covering 3 years of income loss." The compliance center verifies in real time: screen recording and risk questionnaire automatically pop up - Xiao Zhang clicks to confirm. The blockchain records the experience completion time and risk matching pass in real time. In the instant of the virtual scenario experience, a "Decision Risk Assessment Report" pops up on the phone: Recommended coverage: 300,000; Recommended annual premium: ≤ 7% of salary. Xiao Zhang clicks the "Insure Now" button—the digital human automatically retrieves the blockchain-verified identity and risk results—a 10-second electronic signature—and the policy is generated. Simultaneously, the compliance center completes audio and video recording for evidence preservation and sends a "Compliant Sales" receipt back to the regulatory node.

[0082] Please see Figure 3 , Figure 3This is a schematic flowchart illustrating a service solution generation method based on cross-ecosystem collaboration, provided in an embodiment of this application. This method can be applied to servers to automate the decomposition of complex requirements and task allocation, replacing the traditional process that requires extensive manual communication and coordination, thus significantly improving solution generation efficiency. All collaboration rules are encoded in smart contracts, ensuring the standardization of the collaboration process and the reliability of the results, avoiding human error or bias, and improving the accuracy of the solutions.

[0083] like Figure 3 As shown, step S102 of the service solution generation method based on cross-ecological collaboration specifically includes steps S301 to S302.

[0084] S301. Based on the smart contract, analyze the potential needs of the user to obtain at least one business need, and generate business processing sub-tasks according to each of the business needs. S302. Match each of the business processing subtasks with the digital identity certificates of each of the service nodes to obtain the service nodes that match each of the business processing subtasks, and assign each of the business processing subtasks to the corresponding service nodes.

[0085] In one embodiment, the smart contract embeds rules for a deep understanding and deconstruction of a specific type of business scenario. For the "new car service smart contract," its internal logic predefines the essential steps required to complete "new car-related financial services."

[0086] After receiving a user's potential request, the smart contract parses it according to its built-in logic to identify at least one business requirement corresponding to the user's potential request. For each identified business requirement, a specific and well-defined business processing subtask is generated, and the input and output specifications for that task are defined.

[0087] In one embodiment, the most suitable service node authorized by the alliance is matched to execute each business processing subtask.

[0088] Specifically, by querying the cross-ecosystem service node alliance chain, a list of all service nodes holding valid digital identity certificates can be obtained. The certificates contain metadata such as the affiliated institution, business scope, and compliance qualifications. For example, the service node certificate of an insurance company is marked "Business scope: car insurance scheme design, critical illness insurance underwriting"; the service node certificate of a bank is marked "Business scope: car loan approval, transaction verification".

[0089] Intelligent matching is performed based on sub-task type (such as auto insurance underwriting) and service node certificate metadata, including exact matching and scenario-related matching. For example, the skill requirements of each business processing sub-task are matched with the business qualifications in the certificates of each service node. For example, exact matching: the auto loan approval sub-task is matched only with auto loan service nodes of banking institutions (certificates include auto loan authorization); scenario-related matching: the vehicle inspection appointment sub-task is matched with vehicle management office service nodes.

[0090] In one embodiment, when multiple service nodes meet the matching criteria (e.g., multiple bank service nodes can handle car loans), tasks are dynamically allocated based on historical response speed and success rate.

[0091] Once the matching is complete, the AssignTask() function is automatically executed based on the on-chain event triggering mechanism, which encrypts the task information using the certificate public key and sends it to the target service node.

[0092] For example, the smart contract analyzes a user's potential needs and generates three sub-tasks: car insurance quote, loan assessment, and vehicle registration guide. The car insurance quote task is matched to service nodes A and B of insurance companies. The loan assessment task is matched to service node C of a bank. The vehicle registration guide task is matched to service node D of the vehicle management office. The car insurance quote task is assigned to the service node with the faster response time and higher success rate between service nodes A and B, allowing the user to compare prices. The loan assessment task is assigned to service node C of the bank. The vehicle registration guide task is assigned to service node D of the vehicle management office.

[0093] In the above embodiments, the complex decomposition of requirements and task allocation are automated, replacing the traditional process that requires a large amount of manual communication and coordination, greatly improving the efficiency of solution generation. All collaboration rules are encoded in smart contracts, ensuring the standardization of the collaboration process and the reliability of the results, avoiding human error or bias, and improving the accuracy of the solution.

[0094] Please see Figure 4 , Figure 4 This application provides a schematic block diagram of a service solution generation apparatus based on cross-ecosystem collaboration, which is used to execute the aforementioned service solution generation method based on cross-ecosystem collaboration. The service solution generation apparatus based on cross-ecosystem collaboration can be configured on a server.

[0095] like Figure 4 As shown, the service solution generation device 400 based on cross-ecological collaboration includes: The potential demand acquisition module 401 is used to acquire user data when an active service is triggered, and to analyze the user data based on a preset target causal graph to obtain potential user demands. The service node matching module 402 is used to match smart contracts based on the user's potential needs, and to assign the user's potential needs to at least one service node based on the smart contracts. The service solution acquisition module 403 is used to analyze the potential needs of the user based on the collaboration rules in the smart contract of each service node, generate sub-service solutions, and integrate the sub-service solutions through the smart contract to obtain the target service solution.

[0096] Furthermore, the service solution generation device 400 based on cross-ecological collaboration also includes a solution modification module, which includes: The virtual decision-making scenario construction unit is used to process the target service solution and construct a virtual decision-making scenario; The virtual decision result acquisition unit is used to receive user interaction instructions, interact with the virtual decision-making scenario based on the interaction instructions, and obtain virtual decision results; The service plan modification unit is used to receive the plan feedback information input by the user based on the virtual decision result, modify the target service plan based on the plan feedback information, and use the modified plan as the target service plan.

[0097] Furthermore, the service solution generation device 400 based on cross-ecological collaboration also includes a target causal graph generation module, which includes: The local causal graph generation unit is used to perform local inference on at least one local business historical data corresponding to the user based on a preset causal inference model to obtain a local causal graph. The target causal graph generation unit is used to aggregate the local causal graphs to obtain the target causal graph.

[0098] Furthermore, the service node matching module 402 includes: A smart contract template matching unit is used to match a preset smart contract template according to the user's potential needs; The smart contract parameter adjustment unit is used to extract key variables from the user data based on the user's potential needs, and adjust the parameters in the smart contract template based on the key variables to obtain the smart contract.

[0099] Furthermore, the service node matching module 402 includes: The subtask generation unit is used to analyze the potential needs of the user based on the smart contract, obtain at least one business need, and generate business processing subtasks according to each of the business needs. The subtask matching unit is used to match each of the business processing subtasks with the digital identity certificates of each of the service nodes, obtain the service nodes that match each of the business processing subtasks, and assign each of the business processing subtasks to the corresponding service nodes.

[0100] Furthermore, the service solution acquisition module 403 includes: The sub-service scheme acquisition unit is used to process the business processing sub-tasks according to the cooperation rules based on each of the service nodes to obtain the sub-service scheme; The sub-service scheme integration unit is used to perform logical verification and conflict resolution on each of the sub-service schemes based on the smart contract, and to integrate the sub-service schemes that have passed verification and resolved conflicts through scheme integration rules to obtain the target service scheme.

[0101] Furthermore, the service solution generation device 400 based on cross-ecological collaboration also includes a trigger detection module, which includes: The data analysis unit is used to monitor target data, analyze the new data when new data is detected, and obtain analysis results, wherein the target data includes the user data or compliance database; The service triggering unit is used to trigger the active service when the analysis results meet the preset triggering conditions.

[0102] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the above-described apparatus and modules can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0103] The aforementioned device can be implemented as a computer program, which can be used in, for example... Figure 5 It runs on the computer device shown.

[0104] Please see Figure 5 , Figure 5 This is a schematic block diagram illustrating the structure of a computer device according to an embodiment of this application. The computer device may be a server.

[0105] See Figure 5 The computer device includes a processor, memory, and network interface connected via a system bus, wherein the memory may include non-volatile storage media and internal memory.

[0106] Non-volatile storage media can store operating systems and computer programs. These computer programs include program instructions that, when executed, cause the processor to perform any method for generating service solutions based on cross-ecosystem collaboration.

[0107] The processor provides computing and control capabilities, supporting the operation of the entire computer device.

[0108] Internal memory provides an environment for the execution of computer programs in non-volatile storage media. When these computer programs are executed by a processor, the processor can execute any service solution generation method based on cross-ecosystem collaboration.

[0109] This network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 5 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 computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0110] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0111] In one embodiment, the processor is configured to run a computer program stored in memory to perform the following steps: When an active service is triggered, user data is acquired, and the user data is analyzed based on a preset target causal graph to obtain potential user needs. Based on the user's potential needs, a smart contract is matched, and based on the smart contract, the user's potential needs are assigned to at least one service node; Based on the collaboration rules in the smart contract, each service node analyzes the potential needs of the user, generates sub-service solutions, and integrates the sub-service solutions through the smart contract to obtain the target service solution.

[0112] In one embodiment, after the processor analyzes the user's potential needs based on the collaboration rules in the smart contract according to each of the service nodes, generates sub-service solutions, and integrates the sub-service solutions through the smart contract to obtain the target service solution, it is further configured to: The target service plan is processed to construct a virtual decision-making scenario; Receive user interaction commands, interact with the virtual decision-making scenario based on the interaction commands, and obtain virtual decision-making results; Receive solution feedback information from the user based on the virtual decision result, and revise the target service solution based on the solution feedback information, and use the revised solution as the target service solution.

[0113] In one embodiment, before the processor acquires user data upon triggering an active service and analyzes the user data based on a preset target causal graph to obtain potential user needs, it is also configured to: Based on a pre-defined causal inference model, local inference is performed on at least one local business historical data corresponding to the user to obtain a local causal graph. The local causal graphs are aggregated to obtain the target causal graph.

[0114] In one embodiment, the processor, when implementing a smart contract for matching based on the user's potential needs, is configured to: Match a preset smart contract template based on the user's potential needs; Based on the user's potential needs, key variables are extracted from the user data, and the parameters in the smart contract template are adjusted based on the key variables to obtain the smart contract.

[0115] In one embodiment, when the processor allocates the potential user demand to at least one service node based on the smart contract, it is configured to: Based on the smart contract, the user's potential needs are analyzed to obtain at least one business need, and business processing sub-tasks are generated according to each of the business needs. Each of the business processing subtasks is matched with the digital identity certificate of each of the service nodes to obtain the service nodes that match each of the business processing subtasks, and each of the business processing subtasks is assigned to the corresponding service node.

[0116] In one embodiment, when the processor analyzes the potential user needs based on the collaboration rules in the smart contract according to each of the service nodes, generates sub-service solutions, and integrates the sub-service solutions through the smart contract to obtain the target service solution, it is used to: Based on the processing of the business processing sub-tasks by each of the service nodes in accordance with the cooperation rules, the sub-service scheme is obtained; Based on the smart contract, the sub-service solutions are logically verified and conflict resolved. Then, through the solution integration rules, the sub-service solutions that have passed verification and resolved conflicts are integrated to obtain the target service solution.

[0117] In one embodiment, before the processor acquires user data upon triggering an active service and analyzes the user data based on a preset target causal graph to obtain potential user needs, it is also configured to: The target data is monitored, and when new data is detected, the new data is analyzed to obtain analysis results. The target data includes the user data or the compliance database. The active service is triggered when the analysis results meet the preset triggering conditions.

[0118] The embodiments of this application also provide a computer-readable storage medium storing a computer program, the computer program including program instructions, and the processor executing the program instructions to implement any of the service scheme generation methods based on cross-ecosystem collaboration provided in the embodiments of this application.

[0119] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0120] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A service plan generation method based on cross-ecosystem collaboration, characterized by, The application relates to a method for providing a target service scheme based on a user's potential demand. When active service triggering occurs, user data is acquired, and the user's potential demand is obtained by analyzing the user data based on a preset target causal graph. The user's potential demand is matched with an intelligent contract, and the user's potential demand is allocated to at least one service node based on the intelligent contract. Each service node analyzes the user's potential demand based on the cooperation rules in the intelligent contract, generates a sub-service scheme, and integrates each sub-service scheme through the intelligent contract to obtain a target service scheme.

2. The cross-ecosystem collaboration based service plan generation method according to claim 1, characterized in that, After the target service scheme is obtained, the target service scheme is processed to construct a virtual decision-making scene. An interactive instruction of a user is received, the virtual decision-making scene is interacted based on the interactive instruction, and a virtual decision-making result is obtained. Scheme feedback information input by the user based on the virtual decision-making result is received, and the target service scheme is modified based on the scheme feedback information, and the modified scheme is taken as the target service scheme. Before the user's potential demand is obtained, at least one local business history data corresponding to the user is locally inferred based on a preset causal inference model to obtain a local causal graph. 3.The cross-ecosystem collaboration based service plan generation method of claim 1, wherein, Each local causal graph is aggregated to obtain the target causal graph. The user's potential demand is matched with a preset intelligent contract template. Key variables are extracted from the user data based on the user's potential demand, and parameters in the intelligent contract template are adjusted based on the key variables to obtain the intelligent contract. 4.The cross-ecosystem collaboration based service plan generation method of claim 1, wherein, The user's potential demand is parsed based on the intelligent contract to obtain at least one business demand, and a business processing subtask is generated according to each business demand. Each business processing subtask is matched with a digital identity certificate of each service node to obtain a service node matched with each business processing subtask, and each business processing subtask is allocated to a corresponding service node. Each service node analyzes the user's potential demand based on the cooperation rules in the intelligent contract to generate a sub-service scheme, and each sub-service scheme is integrated through the intelligent contract to obtain a target service scheme. 5.The cross-ecosystem collaboration based service plan generation method of claim 1, wherein, Each service node processes the business processing subtask based on the cooperation rules to obtain the sub-service scheme. The intelligent contract is used for logical verification and conflict resolution of each sub-service scheme, and each sub-service scheme after the verification and conflict resolution is integrated through a scheme integration rule to obtain the target service scheme. ​ 6.The cross-ecosystem collaboration based service plan generation method of claim 5, wherein, ​ ​ ​ 7. The cross-ecosystem collaboration based service plan generation method according to any one of claims 1 to 6, characterized by, Before the obtaining of the potential demand of the user based on the preset target causal graph, the method further includes: monitoring target data, and analyzing new data to obtain an analysis result when the new data is detected, wherein the target data includes the user data or a compliance database; triggering the active service when the analysis result meets a preset triggering condition. 8.A service plan generation device based on cross-ecosystem collaboration, characterized by comprising: The method includes: a potential demand obtaining module, configured to obtain user data and analyze the user data based on a preset target causal graph to obtain a potential demand of the user when an active service is triggered; a service node matching module, configured to match an intelligent contract based on the potential demand of the user and allocate the potential demand of the user to at least one service node based on the intelligent contract; a service scheme obtaining module, configured to analyze the potential demand of the user according to a cooperation rule in the intelligent contract by each service node, generate a sub-service scheme, and integrate each sub-service scheme to obtain a target service scheme through the intelligent contract.

9. A computer device, comprising: The computer device includes a memory and a processor; the memory is configured to store a computer program; the processor is configured to execute the computer program and implement the cross-ecological collaboration-based service scheme generation method in any one of claims 1 to 7 when the computer program is executed.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to enable the processor to implement the cross-ecological collaboration-based service scheme generation method in any one of claims 1 to 7.

Images