An insurance electric pin multilevel strategy real-time management and closed-loop verification system and method

Abstract

The application discloses an insurance electric sales multi-level strategy real-time management and control and closed-loop verification system and method, which pre-buries strategy trigger points at key operation nodes of an electric sales system, constructs a multi-level label system and a strategy configuration architecture covering customers, agents, institutions and centers, supports differentiated rule configuration and effective range setting based on multi-dimensional labels, solves the problems of single solidification of strategy rules in a traditional electric sales system, disconnection between execution nodes and business operations, lack of real-time of strategy matching and difficulty in quantifying tracking of strategy effect, realizes real-time label calculation and accurate strategy matching in multiple associated tables after triggering request reporting, improves the response speed of strategy triggering and the accuracy of action execution according to priority, improves the timeliness and execution consistency of sales node strategy intervention, reduces the information delay between strategy configuration and execution, and supports automatic effect analysis and dynamic rule adjustment based on execution instructions and context information.

Description

Technical Field

[0001] This invention relates to the fields of artificial intelligence and insurance data management technology, and in particular to a real-time control and closed-loop verification system and method for multi-level strategies in insurance telemarketing. Background Technology

[0002] In property insurance telemarketing, the formulation and execution of sales strategies have long relied on traditional manual management models. Core behavioral norms such as initial calls, early releases, and scheduled calls are mainly conveyed verbally or through electronic or paper materials, lacking systematic online management tools. Corrections and guidance for sales behavior are also mostly completed offline after the fact, making it difficult to achieve timely and effective process control.

[0003] At the level of scripts and rules, business departments typically pre-define standardized scripts and sales rules, applying the same strategy to all customers and agents, failing to differentiate based on individual customer characteristics, agent levels, and organizational differences. Regarding quality monitoring, currently, coaches primarily conduct random checks on call recordings through manual sampling. However, due to limited manpower, the sampling coverage is low, making it impossible to comprehensively and promptly assess the script quality of every call. Furthermore, existing marketing campaign configuration platforms have limited functionality, only supporting standard campaign rule configurations and lacking deep integration with telemarketing system operation nodes. This prevents real-time strategy intervention when agents perform critical operations such as making calls, saving end codes, and generating insurance policies.

[0004] The above methods have significant shortcomings in actual operation. Existing strategy configurations only support uniform rules or simple audience selection, failing to support differentiated configurations at multiple levels such as centers, institutions, agents, and customer tags. This results in inconsistent sales strategy execution standards across different centers and institutions, making it difficult to standardize and replicate best management practices. Furthermore, strategy recommendations and reminders are disconnected from the actual operating systems of telemarketing agents, lacking system-level strategy intervention capabilities at core operational nodes. This prevents real-time blocking effects of forced execution or reminders, leaving strategy execution entirely dependent on agent self-discipline. In addition, after strategy configuration, there is a lack of systematic tracking and verification capabilities for execution and effectiveness, failing to form a complete closed loop of configuration, execution, recording, analysis, and optimization. Strategy effectiveness evaluation relies on manual review, which is inefficient and leads to vague attributions. Moreover, existing strategy triggering methods are relatively simple, not pre-embedded in multiple key operational nodes of the telemarketing system, failing to achieve a coordinated effect of one-time configuration and multi-point triggering. Agents need to remember and execute different strategy requirements at different operational nodes, making omissions easy.

[0005] Therefore, there is an urgent need to provide a technical solution to address the above problems. Summary of the Invention

[0006] To address the aforementioned technical problems, this invention provides a real-time management and closed-loop verification system and method for multi-level strategies in insurance telemarketing.

[0007] In a first aspect, the present invention provides a real-time control and closed-loop verification system for multi-level strategies in insurance telemarketing, the technical solution of which is as follows: The strategy configuration module is used to configure the effective scope and effective rules of the strategy decision according to the tag dimensions required for matching the insurance telemarketing strategy. The effective rules include the trigger nodes, execution action classifications and execution actions in the insurance telemarketing business scenario. The strategy matching engine is used to calculate customer tag values ​​in real time from multiple related tables based on the trigger request reported by the telemarketing system at the trigger node, and match the effective strategy with the effective scope and the effective rules to obtain the matching result; The strategy triggering and execution module is used to sort the matching results according to the priority corresponding to the execution action category, and return an execution instruction containing the execution action to the telemarketing system according to the sorted matching results, so that the telemarketing system executes the execution action at the triggering node; The strategy execution record module is used to record the execution instructions and context information corresponding to each insurance telemarketing strategy trigger. The strategy effect analysis module is used to perform effect analysis based on the context information, obtain analysis results, and dynamically adjust the effective rules based on the analysis results.

[0008] The beneficial effects of the multi-level strategy real-time control and closed-loop verification system for insurance telemarketing of the present invention are as follows: The system of this invention pre-embeds strategy trigger points at key operational nodes in the telemarketing system, constructing a multi-level tag system and strategy configuration architecture covering customers, agents, institutions, and centers. It supports differentiated rule configuration and effective scope setting based on multi-dimensional tags, solving the problems of single and fixed strategy rules, disconnect between execution nodes and business operations, lack of real-time strategy matching, and difficulty in quantifying and tracking strategy effects in traditional telemarketing systems. It realizes real-time tag calculation and accurate strategy matching in multiple related tables after the trigger request is reported, improving the response speed of strategy triggering and the accuracy of priority-based issuance of execution actions, enhancing the timeliness and consistency of sales node strategy intervention, reducing information delay between strategy configuration and execution, and supporting automated effect analysis and dynamic rule adjustment based on execution instructions and context information.

[0009] Based on the above solution, the real-time control and closed-loop verification system for multi-level insurance telemarketing strategies of the present invention can be further improved as follows.

[0010] In one alternative approach, the tag dimensions include customer tags and organizational level tags, the customer tags including multiple dimensions for describing insurance customer attributes and sales process status, and the organizational level tags including applicable centers and applicable institutions.

[0011] The beneficial effects of adopting the above optional approach are as follows: the tag dimension is further divided into customer tags and organizational level tags. Customer tags cover insurance customer attributes and sales process status, while organizational level tags cover applicable centers and applicable institutions. This enables the strategy rules to be configured differently according to the characteristics of different levels, thereby improving the precision of strategy adaptation.

[0012] In one alternative approach, the strategy matching engine is specifically used for: Based on the trigger request, the customer tag value is calculated in real time from the sales data table, contact record table, and quotation record table. The calculated customer tag value is compared with the tag dimension defined in the strategy configuration module to determine whether it matches the effective rule.

[0013] The advantages of adopting the above optional method are: by further extracting data in real time from the sales data table, contact record table and quotation record table and calculating customer tag values, the calculation results are compared with the configured tag dimensions to determine whether the effective rules are met, so that the strategy matching is based on multi-source real-time data.

[0014] In one alternative approach, the triggering nodes include a sales click-to-dial node, a first-call click-to-dial node, a save-end-code node, a generate-insurance-application-form node, and an open-sales-strategy-window node. The triggering request carries a serial number and an operation type. When each of the triggering nodes is operated, the telemarketing system reports the triggering request to the strategy matching engine.

[0015] The advantages of adopting the above optional method are: further embedding trigger points in key operation nodes such as sales click-to-dial, first-call click-to-dial, saving end code, generating insurance policy and opening sales strategy window, and triggering requests carrying serial number and operation type, realizing multi-point coverage of strategy triggering and accurate identification of operation behavior.

[0016] In one alternative approach, the execution action categories include pop-up reminders, forced execution, forced execution with reminders, and sales strategy window reminders. The execution actions include setting prompts, disallowing the selection of end codes, disallowing dialing, and adding red text reminders to stage goals. The strategy triggering and execution module is specifically used for: Extract the action category and the action corresponding to each matching strategy from the matching results; The execution actions are sorted according to the priority, and the execution order of each matching strategy is determined based on the sorted execution action categories. The execution actions corresponding to each matching strategy are concatenated according to the execution order to generate the execution instruction; The execution instruction is returned to the telemarketing system so that the telemarketing system performs the corresponding operation at the trigger node according to the execution action in the execution instruction.

[0017] The beneficial effects of adopting the above optional method are as follows: further setting up four types of execution actions, namely pop-up reminders, forced execution, forced execution with reminders, and sales strategy window reminders, and sorting the execution actions according to priority, and concatenating the sorting results to generate execution instructions, so that the execution actions of different strategies can be issued in an orderly manner according to their importance.

[0018] In one alternative approach, the policy execution recording module is specifically used for: The node name corresponding to the triggering node, the serial number carried in the triggering request, the decision identifier and decision name corresponding to the matching result, the execution action category and execution action in the execution instruction, the prompt information corresponding to the execution action, and the unique operation identifier are written into the strategy triggering information table as the context information.

[0019] The advantages of adopting the above optional method are as follows: the node name, serial number, decision identifier, decision name, execution action category, execution action, prompt information and operation unique identifier are further written into the policy trigger information table as context information, forming a complete record of the policy execution process, which is convenient for subsequent traceability and verification.

[0020] In one alternative approach, the strategy effect analysis module is specifically used for: Based on the context information in the strategy trigger information table, the actual number of times the strategy is triggered and the total number of scenarios that should be triggered are statistically analyzed, and the strategy trigger rate is calculated. The strategy trigger rate is the ratio of the actual number of times the strategy is triggered to the total number of scenarios that should be triggered. Based on the context information, the number of times the agent operates according to the policy requirements is counted, and the policy execution rate is calculated. The policy execution rate is the ratio of the number of times the agent operates according to the policy requirements to the actual number of times the policy is triggered. A strategy optimization metric is generated based on the strategy trigger rate and the strategy execution rate. The strategy optimization metric is used to instruct the strategy configuration module to adjust the effective rules.

[0021] The advantages of adopting the above optional method are as follows: the strategy trigger rate is calculated by statistically analyzing the actual number of times the strategy is triggered and the total number of scenarios that should be triggered, the strategy execution rate is calculated by statistically analyzing the number of times agents operate according to the strategy requirements, and strategy optimization indicators are generated based on the two indicators, providing a quantitative reference for adjusting the effective rules.

[0022] Secondly, this invention provides a method for real-time management and closed-loop verification of multi-level strategies in insurance telemarketing. The method employs the real-time management and closed-loop verification system for multi-level strategies in insurance telemarketing provided by this invention. The technical solution of this method is as follows: Based on the tag dimensions required for matching insurance telemarketing strategies, configure the scope and rules for the effectiveness of strategy decisions. The rules include triggering nodes, action classifications, and actions to be performed in the insurance telemarketing business scenario. Based on the trigger request reported by the telemarketing system at the trigger node, customer tag values ​​are calculated in real time from multiple related tables, and the effective strategy is matched with the effective scope and the effective rules to obtain the matching result; Based on the matching results, the matching results are sorted according to the priority corresponding to the category of the execution action. Based on the sorted matching results, an execution instruction containing the execution action is returned to the telemarketing system so that the telemarketing system executes the execution action at the trigger node. Record the execution instructions and context information corresponding to each trigger of the insurance telemarketing strategy; The effect analysis is performed based on the context information to obtain the analysis results, and the effective rules are dynamically adjusted based on the analysis results.

[0023] The beneficial effects of the multi-level strategy real-time control and closed-loop verification method for insurance telemarketing of the present invention are as follows: The method of this invention pre-embeds strategy trigger points at key operational nodes in the telemarketing system, constructing a multi-level tag system and strategy configuration architecture covering customers, agents, institutions, and centers. It supports differentiated rule configuration and effective scope setting based on multi-dimensional tags, solving the problems of single and fixed strategy rules, disconnect between execution nodes and business operations, lack of real-time strategy matching, and difficulty in quantifying and tracking strategy effects in traditional telemarketing systems. It realizes real-time tag calculation and accurate strategy matching in multiple related tables after the trigger request is reported, improving the response speed of strategy triggering and the accuracy of priority-based issuance of execution actions. It enhances the timeliness and consistency of sales node strategy intervention, reduces the information delay between strategy configuration and execution, and supports automated effect analysis and dynamic rule adjustment based on execution instructions and context information.

[0024] Thirdly, the technical solution of an electronic device according to the present invention is as follows: It includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, it implements the steps of the real-time control and closed-loop verification method for multi-level insurance telemarketing strategies as described in this invention.

[0025] Fourthly, the technical solution of a computer-readable storage medium provided by the present invention is as follows: The computer-readable storage medium stores instructions that, when read, cause the computer-readable storage medium to perform the steps of the real-time control and closed-loop verification method for multi-level insurance telemarketing strategies as described in this invention.

[0026] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other objects, features and advantages of the present invention more obvious and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0027] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a schematic diagram of an embodiment of the real-time control and closed-loop verification system for multi-level strategies in insurance telemarketing according to the present invention. Figure 2 This is a schematic diagram of the overall system architecture; Figure 3 This is a flowchart illustrating the strategy matching and trigger execution logic. Figure 4 A schematic diagram illustrating the structure of an insurance telemarketing customer tagging system; Figure 5 This is a flowchart illustrating the strategy closed-loop verification and effect analysis process. Figure 6 This is a flowchart illustrating an embodiment of a multi-level strategy real-time control and closed-loop verification method for insurance telemarketing according to the present invention. Figure 7 This is a schematic diagram of an embodiment of an electronic device according to the present invention. Detailed Implementation

[0028] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0029] Figure 1 This diagram illustrates the structure of an embodiment of a real-time control and closed-loop verification system 100 for multi-level insurance telemarketing strategies provided by the present invention. Figure 1 As shown, the insurance telemarketing multi-level strategy real-time control and closed-loop verification system 100 includes: The strategy configuration module 101 is used to configure the effective scope and effective rules of the strategy decision according to the tag dimensions required for matching the insurance telemarketing strategy. The effective rules include the trigger nodes, execution action classifications and execution actions in the insurance telemarketing business scenario.

[0030] In insurance telemarketing, a strategy refers to a set of pre-defined rules designed to guide agents in performing standardized operations within specific sales scenarios. For example, Insurance Company A's auto insurance telemarketing department might develop a strategy requiring agents to select "No Quote" in the end code when making the first call to a customer whose auto insurance is about to expire, if the customer hasn't completed a quote that day. This set of rules constitutes the insurance telemarketing strategy. Tag dimensions refer to classification fields used to characterize customer attributes, sales process status, and organizational hierarchy, serving as the basis for strategy matching. For example, in the first-call quote control strategy, determining whether to trigger the strategy depends on whether the customer's "business mode" is auto insurance, whether the customer's "connection status" is connected, and whether the agent's "applicable institution" is Branch B. "Business mode," "connection status," and "applicable institution" are the tag dimensions.

[0031] Among them, a strategic decision refers to a complete strategic plan configured around a sales control objective, including basic information, scope of effect, rules of effect, and approval status. For example, a complete plan configured for the control of first-time quotes for customers whose auto insurance is expiring includes the decision name "Control of First-Time Quotes for Expiring Auto Insurance," the applicable center "Center A," the applicable agency "Branch B," and specific rules. This complete plan is the strategic decision. Scope of effect refers to the applicable boundaries of the strategic decision at the organizational level, used to limit the strategy to be effective only at the specified center level, agency level, or agent level. For example, the strategic decision of controlling first-time quotes for expiring auto insurance is only effective for all agents of "Branch B" under "Center A." This limitation is the scope of effect. An effective rule refers to the mapping relationship between the triggering conditions and the execution actions defined in the strategy decision. It includes three elements: triggering node, execution action category, and execution action. For example, an effective rule for the strategy decision of controlling the first call quote upon expiration of auto insurance is: when the triggering node is "first call click node", the execution action category is "mandatory execution plus reminder", the execution action is "do not allow selection of end code" and the prompt message "The customer is an auto insurance customer whose insurance has expired, please complete the quote first". This mapping relationship is the effective rule.

[0032] In this context, the insurance telemarketing business scenario refers to the set of customer states, sales stages, and operating environments faced by insurance telemarketing agents during the sales process, used to define the business context in which the strategy applies. For example, "first call" is an insurance telemarketing business scenario where the customer's car insurance is about to expire, and the agent makes the first outbound call to the customer. Trigger nodes are pre-embedded points in the telemarketing system used to trigger strategy matching when an agent performs a specific operation. For example, the "sales click to call node" when the agent clicks the call button to prepare for the outbound call, and the "save end code node" when the agent clicks to save the end code, are both trigger nodes. Execution action classification refers to the categorization of execution actions according to the intensity and presentation method of the strategy intervention. For example, the "forced execution plus reminder" category used for the first call pricing control strategy is an execution action classification, indicating that this strategy needs to both block the agent's operation and display a reminder message when blocking. The execution action refers to the specific operation instructions issued by the system to the telemarketing system after the strategy matching is successful; for example, the prompts "Do not select end code" and "The customer is a car insurance customer whose insurance has expired, please complete the quote first" returned by the system to the telemarketing system are execution actions.

[0033] The strategy matching engine 102 is used to calculate customer tag values ​​in real time from multiple related tables based on the trigger request reported by the telemarketing system at the trigger node, and match the effective strategy with the effective scope and the effective rules to obtain the matching result.

[0034] The telemarketing system refers to the terminal software system used by agents to perform telephone sales operations. It provides a dialing interface, an end-of-call code saving interface, and an insurance application generation interface, and interacts with the strategy matching engine 102. For example, the client software used by the agent, which includes customer list display, dialing, end-of-call code selection, and insurance application entry functions, is the telemarketing system. A trigger request refers to the data message sent by the telemarketing system to the strategy matching engine 102 when a trigger node is operated by an agent, requesting matching of the effective strategy for the current scenario. For example, when an agent clicks to save the end-of-call code, the telemarketing system encapsulates the transaction number "S20260816001", the operation type "3", and the current customer's sales transaction number into a message and sends it to the strategy matching engine 102; this message is the trigger request.

[0035] The associated tables refer to database tables that store business data such as sales data, contact records, and quotation records. The strategy matching engine 102 extracts data from these tables to calculate tag values. For example, after receiving a trigger request, the strategy matching engine 102 reads customer information, historical contact records, and quotation records from the three associated tables: the "Sales Master Table," the "Contact Record Table," and the "Quotation Trajectory Table," respectively, to calculate the current customer's tag value. The customer tag value refers to the specific value calculated in real time for each tag dimension for the customer. For example, based on the customer identifier carried in the trigger request, the associated tables calculate the customer's business mode as "car insurance," the connection status as "connected," and the number of outbound calls as 3. These specific values ​​are the customer tag values.

[0036] The effective strategy refers to the rule in the strategy decision that needs to be executed after the strategy matching engine 102 determines it in the current triggering scenario. For example, the strategy matching engine 102 determines, based on the calculated customer tag value "business model = auto insurance" and the agency to which the agent belongs, "Branch B", that the agent needs to execute one rule in the "auto insurance expiration first-time quote control" strategy in the current scenario. This rule is the effective strategy. The matching result refers to the structured data output by the strategy matching engine 102 after completing the matching determination, which contains the effective strategy and its corresponding execution action information. For example, the data returned by the strategy matching engine 102 to the strategy triggering and execution module 103 includes the decision identifier "D20260816001" of the matched effective strategy, the decision name "auto insurance expiration first-time quote control", the execution action category "mandatory execution plus reminder type" and the execution action "do not allow selection end code". This set of data is the matching result.

[0037] The strategy triggering and execution module 103 is used to sort the matching results according to the priority corresponding to the execution action category, and return an execution instruction containing the execution action to the telemarketing system according to the sorted matching results, so that the telemarketing system executes the execution action at the triggering node.

[0038] Priority refers to the sorting criteria used to determine the execution order of multiple matching results when multiple matching results exist simultaneously. For example, if two strategies are matched simultaneously in the current triggering scenario, one action is classified as "forced execution plus reminder" and the other action is classified as "pop-up reminder". The priority of "forced execution plus reminder" is higher than that of "pop-up reminder". The agent will execute the action corresponding to "forced execution plus reminder" first.

[0039] The sorted matching result refers to the ordered sequence obtained by arranging all matching results in descending order of priority. For example, when there are two matching results, the matching result corresponding to "forced execution with reminder" is arranged before the matching result corresponding to "pop-up reminder". The ordered sequence obtained after sorting is the sorted matching result. The execution instruction refers to the operable command generated by the strategy triggering and execution module 103 based on the sorted matching result and executed by the telemarketing system. For example, the strategy triggering and execution module 103 concatenates "Do not allow selection of end code" and "The customer is a car insurance expiring customer, please complete the quotation first" into an execution instruction and returns it to the telemarketing system. Based on this, the telemarketing system disables all end code options except "no quotation" in the pop-up window where the end code is saved and displays a prompt. This command is the execution instruction.

[0040] The strategy execution record module 104 is used to record the execution instructions and context information corresponding to each insurance telemarketing strategy trigger.

[0041] The context information refers to all relevant data recorded during a single policy trigger, including trigger node information, request data, matching result data, and execution instruction data. For example, the context information recorded during a single policy trigger includes the trigger node name "Save End Code Node", serial number "S20260816001", decision identifier "D20260816001", decision name "Auto Insurance Expiration First Quotation Control", execution action category "Mandatory Execution with Reminder", execution action "Do Not Allow Selection of End Code", prompt message "The customer is an auto insurance expiring customer, please complete the quotation first", and operation unique identifier "UUID-20260816-001". All of this data constitutes the context information.

[0042] The strategy effect analysis module 105 is used to perform effect analysis based on the context information, obtain analysis results, and dynamically adjust the effective rules based on the analysis results.

[0043] The analysis results refer to the quantitative evaluation data output by the strategy effect analysis module 105 after performing statistical calculations on the context information. For example, the strategy effect analysis module 105 statistically shows that the strategy trigger rate of the first-time quote control strategy for car insurance expiration was 80% and the strategy execution rate was 75% during the period from July 1, 2026 to July 15, 2026. These statistical data are the analysis results.

[0044] The technical solution of this embodiment pre-embeds strategy trigger points at key operation nodes in the telemarketing system, constructs a multi-level tag system and strategy configuration architecture covering customers, agents, institutions, and centers, supports differentiated rule configuration and effective scope setting based on multi-dimensional tags, and solves the problems of single and fixed strategy rules, disconnect between execution nodes and business operations, lack of real-time strategy matching, and difficulty in quantifying and tracking strategy effects in traditional telemarketing systems. It realizes real-time tag calculation and accurate strategy matching in multiple related tables after the trigger request is reported, improves the response speed of strategy triggering and the accuracy of priority-based issuance of execution actions, enhances the timeliness and consistency of sales node strategy intervention, reduces information delay between strategy configuration and execution, and supports automated effect analysis and dynamic rule adjustment based on execution instructions and context information.

[0045] In one alternative approach, the tag dimensions include customer tags and organizational level tags, the customer tags including multiple dimensions for describing insurance customer attributes and sales process status, and the organizational level tags including applicable centers and applicable institutions.

[0046] Customer tags refer to the collective term for tag dimensions used to describe the attributes of insurance customers and the status of the sales process. For example, the "Business Model" tag identifies whether the customer belongs to a product line of auto insurance or non-auto insurance, the "Connection Status" tag identifies whether the most recent outbound call was connected, and the "Number of Outbound Calls" tag identifies the total number of times the customer has been called. These tags together constitute customer tags. Organizational level tags refer to the tag dimensions used to describe the organizational structure level to which the agent belongs, and are used to limit the scope of application of the strategy within the organization. For example, the "Applicable Center" tag identifies which telemarketing center the strategy applies to, and the "Applicable Institution" tag identifies which branch under that center the strategy applies to. These tags together constitute organizational level tags.

[0047] The "applicable center" refers to the highest-level unit at the organizational level to which the strategy decision applies, which is the center-level organization for telemarketing operations. For example, the applicable center for the strategy decision regarding the control of the first-time quote upon expiration of auto insurance is "Center A," meaning this strategy is only effective within Center A. The "applicable institution" refers to the grassroots business unit at the organizational level to which the strategy decision applies, which is the city-level or regional branch office belonging to the center. For example, the applicable institution for the strategy decision regarding the control of the first-time quote upon expiration of auto insurance is "Branch B," meaning this strategy is effective within Branch B under Center A.

[0048] Among the above optional methods, the tag dimension is further divided into customer tags and organizational level tags. Customer tags cover insurance customer attributes and sales process status, while organizational level tags cover applicable centers and applicable institutions. This allows the strategy rules to be configured differently according to different level characteristics, improving the precision of strategy adaptation.

[0049] In an alternative embodiment, the strategy matching engine 102 is specifically used for: Based on the trigger request, the customer tag value is calculated in real time from the sales data table, contact record table, and quotation record table. The calculated customer tag value is compared with the tag dimension defined in the strategy configuration module 101 to determine whether it matches the effective rule.

[0050] The sales data table stores basic customer information and sales master records, including fields for customer identifier, business model, and policy expiration date. For example, after receiving a trigger request, the strategy matching engine 102 reads the "Business Model" field of the record with customer identifier "C202608001" from the sales data table and sets its value to "Auto Insurance." The sales data table is the source table for reading this information. The contact record table stores records of each contact between the agent and the customer, including fields for connection status, ringing duration, call duration, and end code. For example, the strategy matching engine 102 queries the contact record table for the latest contact record with customer identifier "C202608001," sets the "Connection Status" field to "Connected" and the "Call Duration" field to 125 seconds. The contact record table is the data source table for querying contact records. The quotation record table refers to a data table that stores the historical trajectory of the quotation operations performed by agents for customers, including fields such as quotation time, quotation amount, and insurance type. For example, the strategy matching engine 102 counts the number of quotation records for customer with the identifier "C202608001" from the quotation record table as 2. The quotation record table is the data source table for counting the number of quotations.

[0051] In the above optional methods, further steps are taken to extract data from the sales data table, contact record table, and quotation record table in real time and calculate customer tag values. The calculation results are then compared with the configured tag dimensions to determine whether the effective rules are met, so that the strategy matching is based on multi-source real-time data.

[0052] In one alternative approach, the triggering nodes include a sales click-to-dial node, a first-call click-to-dial node, a save-end-code node, a generate-insurance-application-form node, and an open-sales-strategy-window node. The triggering request carries a serial number and an operation type. When each of the triggering nodes is operated, the telemarketing system reports the triggering request to the strategy matching engine 102.

[0053] The "Sales Click-to-Dial" node refers to the trigger point when an agent clicks the "Dial" button in the telemarketing system to initiate an outbound call. For example, when an agent opens the customer list page and clicks the dial button next to the customer record, the telemarketing system reports a trigger request at that moment, and this operation point is the "Sales Click-to-Dial" node. The "First-Call Click-to-Dial" node refers to the trigger point when an agent clicks the "Dial" button to initiate the first outbound call to a customer. For example, when an agent makes the first outbound call to a customer identified as "C202608001" and clicks the dial button, the telemarketing system reports a trigger request, and this operation point is the "First-Call Click-to-Dial" node. The "Save End-of-Call Code" node refers to the trigger point when an agent clicks to save the end-of-call code after completing a call. For example, after ending a call with a customer, when an agent selects "No Quote" in the end-of-call code selection interface and clicks the save button, the telemarketing system reports a trigger request, and this operation point is the "Save End-of-Call Code" node.

[0054] The "Generate Application Policy" node refers to the trigger point when an agent clicks the "Generate Application Policy" button to generate an application policy for a customer. There are three types of application policy generation: single commercial insurance application policy generation, single compulsory traffic accident liability insurance application policy generation, and combined insurance application policy generation. For example, when an agent clicks the "Generate Application Policy" button after reaching an agreement with a customer, the telemarketing system reports a trigger request; this operation point is the "Generate Application Policy" node. The "Open Sales Strategy Window" node refers to the trigger point when an agent opens the sales auxiliary strategy window in the telemarketing system. For example, when an agent clicks to open the sales strategy window during a call to view system-recommended sales scripts and strategy prompts, the telemarketing system reports a trigger request; this operation point is the "Open Sales Strategy Window" node.

[0055] The serial number refers to a unique business transaction number that identifies a single sales transaction. It is generated by the telemarketing system when an agent begins processing a customer. For example, when an agent begins processing a sales task for a customer identified as "C202608001", the telemarketing system generates a serial number "S20260816001". This number remains unchanged in all subsequent related operations; the serial number is "S20260816001". The operation type refers to a numeric code that identifies the type of operation performed by the agent at the current trigger node. For example, when an agent clicks to save the end code, the trigger request reported by the telemarketing system carries an operation type code of "3", indicating that the current trigger node is the save end code node; the numeric code "3" is the operation type.

[0056] Among the above optional methods, trigger points are further embedded in key operation nodes such as sales click-to-dial, first-call click-to-dial, saving the end code, generating the insurance policy, and opening the sales strategy window. The trigger request carries the serial number and operation type, realizing multi-point coverage of strategy triggering and accurate identification of operation behavior.

[0057] In one alternative approach, the execution actions are categorized into pop-up reminders, forced execution, forced execution with reminders, and sales strategy window reminders. The execution actions include configuring prompts, disallowing the selection of end codes, disallowing dialing, and adding red text reminders to stage goals.

[0058] Among them, the pop-up reminder category refers to actions that only display a prompt message to the agent and do not block the agent's subsequent operations. For example, after a successful policy match, the system pops up a prompt message "Please confirm whether the customer is the person answering the call" when the agent clicks to dial. After the agent clicks "OK," the pop-up closes and the agent can continue dialing. This action belongs to the pop-up reminder category. The forced execution category refers to actions that directly block the agent's current operation and prevent the agent from continuing to perform subsequent actions. For example, after a successful policy match, the system blocks the save operation when the agent clicks to save the end code. The agent cannot complete the end code saving until the policy conditions are met. This action belongs to the forced execution category.

[0059] The "Forced Execution with Reminder" category refers to actions that interrupt the agent's current operation while displaying a prompt message. For example, after a successful strategy match, the system interrupts the save operation when the agent clicks to save the end code, and simultaneously displays a pop-up message: "The customer's car insurance is expiring; please complete the quote first." Even after the agent clicks "OK," the pop-up closes, but the operation is still interrupted. This action falls under the "Forced Execution with Reminder" category. The "Sales Strategy Window Reminder" category refers to actions that display strategy prompts within the sales strategy window without interrupting the pop-up. For example, after a successful strategy match, the system displays a prompt: "Recommendation of 1 million RMB third-party liability insurance" in the agent's already opened sales strategy window. The agent can view this independently without affecting the current operation process. This action falls under the "Sales Strategy Window Reminder" category.

[0060] The "prompt message configuration" refers to configuring the specific text content displayed to the agent when the strategy is triggered, as part of the execution action. For example, the prompt message in the strategy configuration might be "The customer's car insurance is expiring; please complete the quote first." This text content constitutes the prompt message configuration. "Disallowing selection of end codes" means that the system disables the execution action of specified end code options at the end code saving node, preventing the agent from selecting the disabled end code. For example, if the system disables the "Unreachable" and "Customer Do Not Call" end code options at the end code saving node, the agent cannot select these two options; this restriction is "disallowing selection of end codes."

[0061] "Disallowing click-to-dial" means that the system disables the dial button's execution action at the dialing node, preventing agents from initiating outbound calls. For example, if the system determines that the current customer is outside the dialing time range, it disables the dial button in the sales click-to-dial node, preventing agents from clicking to call the customer. This restriction is "disallowing click-to-dial." "Adding red text reminders to stage goals" means that the system adds a strategy prompt in red font to the agent's sales stage goal display area. For example, after a successful strategy match, the system adds a red text reminder in red font to the agent's daily stage goal display area: "Customers with expiring car insurance should complete 3 quotes today." This red text reminder is an example of adding red text reminders to stage goals.

[0062] The strategy triggering and execution module 103 is specifically used for: Extract the action category and the action corresponding to each matching strategy from the matching results.

[0063] The execution actions are sorted according to the priority, and the execution order of each matching strategy is determined based on the sorted execution action categories.

[0064] The execution order refers to the order in which the actions corresponding to each matching result are executed when there are multiple matching results. For example, when two strategies are matched at the same time, the action corresponding to the "forced execution with reminder" strategy is executed first, and the action corresponding to the "pop-up reminder" strategy is executed later. This order of executing "forced execution with reminder" first and then "pop-up reminder" is the execution order.

[0065] The execution actions corresponding to each matching strategy are concatenated according to the execution order to generate the execution instruction.

[0066] The execution instruction is returned to the telemarketing system so that the telemarketing system performs the corresponding operation at the trigger node according to the execution action in the execution instruction.

[0067] Among the above optional methods, four types of execution actions are further set: pop-up reminder, forced execution, forced execution plus reminder, and sales strategy window reminder. The execution actions are sorted according to priority, and the execution instructions are generated by splicing the sorting results, so that the execution actions of different strategies can be issued in an orderly manner according to their importance.

[0068] In an alternative embodiment, the policy execution recording module 104 is specifically used for: The node name corresponding to the triggering node, the serial number carried in the triggering request, the decision identifier and decision name corresponding to the matching result, the execution action category and execution action in the execution instruction, the prompt information corresponding to the execution action, and the unique operation identifier are written into the strategy triggering information table as the context information.

[0069] The decision identifier refers to a unique number that identifies a strategy decision, automatically generated by the system when the strategy is created. For example, when the "Auto Insurance Expiration First-Time Quotation Control" strategy is created, the system generates a unique number "D20260816001". This number is used to associate all triggering events in strategy execution records and effect analysis; "D20260816001" is the decision identifier. The decision name refers to the Chinese name of the strategy decision, filled in by the strategy configuration personnel when creating the strategy, used to identify and distinguish different strategies. For example, when the strategy configuration personnel create the "Auto Insurance Expiration First-Time Quotation Control" strategy, they fill in the name "Auto Insurance Expiration First-Time Quotation Control," and this name is the decision name.

[0070] The "prompt message" refers to the text displayed to the agent when the strategy is triggered, corresponding to the prompt configuration in the action execution. For example, the text "The customer's car insurance is expiring; please complete the quote first" displayed in the pop-up window after successful strategy matching is the prompt message. The "unique operation identifier" refers to a globally unique identifier generated during a single strategy trigger, used to associate all records within the same trigger operation. For example, a strategy trigger process generates a UUID value of "550e8400-e29b-41d4-a716-446655440000". This UUID is used to uniquely identify this trigger in the strategy trigger information table; the UUID value "550e8400-e29b-41d4-a716-446655440000" is the unique operation identifier.

[0071] The strategy trigger information table refers to a data table stored in the database that records the complete context information for each strategy trigger. For example, a record in the strategy trigger information table contains the operation unique identifier "550e8400-e29b-41d4-a716-446655440000", serial number "S20260816001", trigger node name "Save End Code Node", decision identifier "D20260816001", and decision name "Auto Insurance Expiration First Quotation Control". This table is the strategy trigger information table.

[0072] In the above optional methods, the node name, serial number, decision identifier, decision name, action category, action, prompt information, and unique operation identifier are further written into the policy trigger information table as context information, forming a complete record of the policy execution process, which is convenient for subsequent traceability and verification.

[0073] In an alternative embodiment, the strategy effect analysis module 105 is specifically used for: Based on the context information in the strategy trigger information table, the actual number of times the strategy is triggered and the total number of scenarios that should be triggered are statistically analyzed, and the strategy trigger rate is calculated. The strategy trigger rate is the ratio of the actual number of times the strategy is triggered to the total number of scenarios that should be triggered.

[0074] The actual number of times the strategy is triggered refers to the total number of times the strategy decision is determined to be a successful match and executed by the strategy matching engine 102 within the statistical period. For example, from July 1, 2026 to July 15, 2026, the strategy matching engine 102 triggered the "Auto Insurance Expiration First Quotation Control" strategy a total of 100 times and recorded them all. The value of 100 is the actual number of times the strategy is triggered within the statistical period.

[0075] The total number of scenarios to be triggered refers to the total number of times all agents within the effective scope of the strategy decision perform operations at the trigger node of the strategy within the statistical period. For example, from July 1, 2026 to July 15, 2026, within the effective scope of the auto insurance expiration first call quotation control strategy "Center A - Branch B", all agents performed the call operation 125 times at the first call click node. The value 125 is the total number of scenarios to be triggered.

[0076] The strategy trigger rate refers to the ratio of the actual number of times a strategy is triggered to the total number of scenarios that should be triggered, used to measure the completeness of strategy coverage. For example, the auto insurance expiration first-time quote control strategy was actually triggered 100 times within the statistical period, while the total number of scenarios that should be triggered was 125. The strategy trigger rate is... The calculation formula is: ; Indicates the policy trigger rate. Indicates the actual number of times the strategy is triggered. This indicates the total number of scenarios that should be triggered; a policy trigger rate of 80% means that the policy covers 80% of the scenarios that should be triggered.

[0077] Based on the context information, the number of times the agent operates according to the policy requirements is counted, and the policy execution rate is calculated. The policy execution rate is the ratio of the number of times the agent operates according to the policy requirements to the actual number of times the policy is triggered.

[0078] The number of times an agent operates according to the policy requirements refers to the number of times an agent completes the corresponding operation according to the policy execution instructions after the policy is triggered within the statistical period. For example, the first round of quote control policy for car insurance upon expiration was triggered 100 times. After 75 of these triggers, the agent selected the "no quote" end code as required by the system instead of the disabled end code option. The value 75 is the number of times the agent operates according to the policy requirements.

[0079] The strategy execution rate refers to the ratio of the number of times an agent performs actions according to the strategy requirements to the number of times the strategy is actually triggered. It measures the degree to which agents comply with the strategy requirements. For example, the actual number of triggers for the first-time quote control strategy upon expiration of auto insurance within the statistical period is 100, of which agents correctly execute the actions according to the strategy requirements 75 times. The strategy execution rate is... The calculation formula is: ; Indicates the strategy execution rate. This indicates the number of times the agent needs to operate according to the policy requirements. This indicates the actual number of times the strategy was triggered; a strategy execution rate of 75% indicates a seat compliance rate of 75%.

[0080] The number of times an agent operates according to the policy requirements refers to the number of times an agent completes the corresponding operation according to the policy execution instructions after the policy is triggered within the statistical period. For example, the first round of quote control policy for car insurance upon expiration was triggered 100 times. Among them, after 75 triggers, the agent selected the "no quote" end code as required by the system instead of the disabled end code option. The value 75 is the number of times the agent operates according to the policy requirements.

[0081] A strategy optimization metric is generated based on the strategy trigger rate and the strategy execution rate. The strategy optimization metric is used to instruct the strategy configuration module 101 to adjust the effective rules.

[0082] Among them, the strategy optimization index refers to comprehensive quantitative data generated based on the strategy trigger rate and strategy execution rate, used to instruct the strategy configuration module 101 to adjust the effective rules; the strategy effect analysis module 105 compares the strategy trigger rate with a preset trigger rate threshold and the strategy execution rate with a preset execution rate threshold. When the strategy trigger rate is lower than the preset trigger rate threshold and the strategy execution rate is lower than the preset execution rate threshold, the generated strategy optimization index is a first type of adjustment instruction, which is used to instruct the strategy configuration module 101 to expand the scope of applicable institutions in the effective scope; when the strategy trigger rate is not lower than the preset trigger rate threshold and the strategy execution rate is lower than the preset execution rate threshold, the generated strategy optimization index is a second type of adjustment instruction, which is used to instruct the strategy configuration module 101 to adjust the effective rules. The action classification has been changed from pop-up reminder to mandatory execution plus reminder; when the strategy trigger rate is lower than the preset trigger rate threshold and the strategy execution rate is not lower than the preset execution rate threshold, the generated strategy optimization indicator is the third type of adjustment instruction. The third type of adjustment instruction is used to instruct the strategy configuration module 101 to adjust the trigger node from the current trigger node to other trigger nodes; for example, the strategy trigger rate of the car insurance expiration first-time quotation control strategy is 80%, the strategy execution rate is 75%, the preset trigger rate threshold is 90%, and the preset execution rate threshold is 90%. When the strategy trigger rate is lower than the preset trigger rate threshold and the strategy execution rate is lower than the preset execution rate threshold, the generated strategy optimization indicator is the first type of adjustment instruction. The first type of adjustment instruction instructs the strategy configuration module 101 to expand the effective scope from "Branch B" to "Branch C".

[0083] In the above-mentioned optional methods, the strategy trigger rate is further calculated by statistically analyzing the actual number of times the strategy is triggered and the total number of scenarios that should be triggered, and the strategy execution rate is calculated by statistically analyzing the number of times agents operate according to the strategy requirements. Based on these two indicators, strategy optimization indicators are generated, providing a quantitative reference for adjusting the effective rules.

[0084] Figure 2 The overall architecture of the technical solution in this embodiment is shown. For example... Figure 2As shown, the system includes a strategy configuration module, a strategy matching engine 102, a telemarketing system agent terminal, and a strategy execution record and effect analysis module. In the strategy configuration module, the strategy tag management module maintains all tag dimensions required for strategy matching, the strategy configuration module 101 converts business strategies into executable configurations, and the strategy approval module approves the configured strategy decisions. After the strategy configuration is completed, the effective rules are sent to the strategy matching engine 102. The strategy matching engine 102 receives trigger requests reported by the telemarketing system agent terminal at the sales click-to-dial node, first-call click-to-dial node, end-code saving node, insurance application generation node, and strategy window opening node, performs tag calculation, rule matching, and priority processing, and returns the matching results to the telemarketing system agent terminal for execution. The strategy execution record and effect analysis module receives strategy trigger records and call quality records, and generates an effect analysis report including trigger rate, execution rate, and conversion contribution.

[0085] The strategy tag management module maintains all tag dimensions required for strategy matching, including customer tags and organizational level tags. Customer tags comprise 17 dimensions, as shown in Table 1, covering business model, outbound call count, consecutive missed calls, ringing duration, connection status, call duration, pricing status, pricing count, weekday appointment volume, appointment date, auto insurance main termination code, non-auto insurance main termination code, sales rhythm, first call time, service status, verified status, and transaction status. Each tag is configured as either an enumeration or a numerical type based on its business meaning. Organizational level tags include applicable centers and applicable institutions, both supporting multiple selections. The strategy tag management module reuses existing tag tables, distinguishing tag usage scenarios through tag roles. When the strategy matching engine 102 is invoked, it calculates the current customer's tag value in real time from more than ten related tables, including the sales data table, contact record table, and pricing record table, based on the serial number and operation type.

[0086] Table 1: The strategy configuration module 101 transforms business strategies into executable configurations, including basic information configuration and rule configuration. Basic decision information includes the decision name, applicable center, applicable organization, decision description, start time, and end time. Multiple selections are supported for both applicable center and applicable organization, and the end time cannot be earlier than the start time. Rule configuration is the core of strategy differentiation capabilities. Each decision can be configured with multiple rules. The configuration items for each rule are shown in Table 2, including trigger nodes, execution action categories, execution actions, and prompt content. Trigger nodes can be selected as sales click-to-dial nodes, first-call click-to-dial nodes, save end-of-call code nodes, generate insurance policy nodes, or open sales strategy window nodes. Execution action categories can be selected as pop-up reminders, forced execution, forced execution with reminders, or sales strategy window reminders. Execution actions can be configured with prompts, disallowing the selection of end-of-call codes, disallowing click-to-dial, or adding red text reminders to stage goals. The strategy configuration module 101 supports batch import and export of rules using Excel templates.

[0087] Table 2: The strategy matching engine 102 matches and applies strategies in real time based on the current context information when each operation node in the telemarketing system is triggered. The strategy triggering and execution module 103 embeds points at five key operation nodes in the telemarketing system to achieve real-time triggering of strategies, interception of execution actions, and display of reminders. The embedded points for the five trigger nodes are shown in Table 3: operation type code 1 for the sales click-to-call node, operation type code 2 for the first click-to-call node, operation type code 3 for the save-end-code node, operation type code 4 for the generate-application-form node, and operation type code 5 for the open-sales-strategy-window node.

[0088] Table 3: Figure 3 The complete process of policy matching and trigger execution is shown. For example... Figure 3As shown, after an agent triggers an operation in the telemarketing system, the system performs scenario switch judgment, center switch judgment, and team switch judgment. After the switch judgment is passed, the system calculates the tag value in real time from more than ten related tables such as the sales data table, contact record table, and quotation record table based on the serial number. The calculation logic of key tag fields is shown in Table 4. The number of consecutive missed calls is obtained by querying the total amount of data in the missed call table and comparing it with the time of the latest recorded contact. The number of outbound calls is the sum of the amount of data with recording identifiers and the total amount of missed calls. The ringing duration is the ringing duration recorded when a call is missed. The call duration is the maximum difference between the end time and the start time of the data with the recording number in the contact record table. The number of quotations is the number of records in the agent's quotation trajectory table. The number of workday appointments is the number of unprocessed data in the next workday appointment table for the current agent. The sales rhythm is determined by obtaining the number of days that can be underwritten in advance from the agency and combining the insurance expiration date, the current date, and the first call date to determine the stage.

[0089] Table 4: After the strategy matching engine 102 completes real-time calculation of tag values, it performs strategy matching according to the center level, organization level, and tag combination. After matching, it determines whether an effective strategy has been matched. If no effective strategy is matched, no action is taken, and the agent continues the original process. If an effective strategy is matched, it is summarized according to the execution action category. The summary containers for execution action categories are shown in Table 5. The summary container for pop-up reminders is alertRules, which only provides a reminder without blocking the operation; the summary container for forced execution is forceRules, which blocks the operation and prevents the agent from continuing; the summary container for forced execution plus reminders is forceAlertRules, which blocks the operation and displays a reminder; and the summary container for sales strategy window reminders is salesWindowRules, which displays the reminder content in the sales strategy window.

[0090] Table 5: After the aggregation is complete, the process enters the priority processing stage. The highest priority is the forced execution and alert strategy; when `forceAlertRules` is not empty, the alert message is extracted and concatenated, and the current operation is terminated. The second highest priority is the forced execution strategy; when `forceRules` is not empty, the execution action is extracted and concatenated, and the current operation is terminated. The third priority is the pop-up alert strategy; when `alertRules` is not empty, the alert message is extracted and concatenated, and the original operation continues after agent confirmation. The fourth priority is the sales strategy window alert strategy; when `salesWindowRules` is not empty, the alert message is extracted and concatenated and returned to the sales strategy window for display. When multiple matching results exist simultaneously, the alert messages corresponding to each matching result are concatenated and returned uniformly. After priority processing is complete, the process enters the front-end execution action processing stage. The front-end processing methods for each return scenario are shown in Table 6. In pop-up notification return scenarios, a prompt message is displayed in the pop-up; the agent clicks "OK" to close the pop-up and continue with subsequent operations. In forced execution return scenarios, the action to be executed is displayed in the pop-up; the agent clicks "OK" to close the pop-up and terminate the operation. In forced execution plus reminder return scenarios, a prompt message is displayed in the pop-up; the agent clicks "OK" to close the pop-up and terminate the operation. In sales strategy window reminder return scenarios, the system retrieves the prompt message content and displays it in the sales strategy window. Once the execution record is stored, the strategy triggering process ends.

[0091] Table 6: The strategy execution record module 104 records the complete context of each strategy trigger, providing a data foundation for strategy effect analysis and closed-loop verification. The system creates a strategy trigger information table, with the fields shown in Table 7, including: unique operation identifier, sales serial number, page trigger location, trigger node name, action category, action, prompt message, decision identifier, decision name, start time, and end time. The unique operation identifier uses the same value within a single trigger operation, and the numeric codes 1 to 5 for the page trigger location correspond to the five trigger nodes.

[0092] Table 7: Figure 4 The structure of the customer tagging system is shown. For example... Figure 4 As shown in Table 1, the customer tagging system includes 17 dimensions of real-time calculated tags. The business meaning and value type of each tag are shown in Table 1, covering the key states and attributes of customers throughout the entire sales lifecycle from first contact to transaction.

[0093] Figure 5 The complete process of closed-loop verification and effect analysis is shown. For example... Figure 5As shown, closed-loop verification comprises five stages: strategy configuration, strategy execution, strategy recording, strategy analysis, and strategy optimization. In the strategy configuration stage, strategy tag management, strategy configuration, and strategy approval are performed. After approval, the strategy execution stage begins. In the strategy execution stage, the telemarketing system triggers strategy requests at five trigger nodes. The strategy matching engine 102 performs real-time tag calculation and strategy matching, and executes actions based on the matching results. In the strategy recording stage, the strategy trigger information table records the complete context of the strategy trigger, and the call quality table records call quality data. In the strategy analysis stage, the strategy effectiveness analysis engine calculates strategy effectiveness metrics based on the data in the strategy trigger information table and the call quality table. The formula for calculating the strategy trigger rate is: in, Indicates the policy trigger rate. Indicates the actual number of times the strategy is triggered. This represents the total number of scenarios that should be triggered. The formula for calculating the strategy execution rate is: in, Indicates the strategy execution rate. This indicates the number of times the agent needs to operate according to the policy requirements. This indicates the actual number of times the strategy was triggered. Conversion contribution is calculated as the difference between the policy conversion rate of policies triggered by the strategy and the policy conversion rate of policies not triggered. The strategy performance analysis engine also supports strategy suitability analysis by time period, institution, and agent. During the strategy optimization phase, inefficient strategies with low trigger and execution rates are identified based on the results of the strategy analysis phase. Strategy configuration parameters are adjusted, including adjustments to the effective scope, trigger conditions, and execution actions. After adjustment, the optimized strategy is redeployed to take effect, forming a continuous improvement loop from strategy configuration to strategy optimization.

[0094] The strategy effectiveness analysis module 105 supports quantitative evaluation and iterative optimization of strategy effectiveness based on strategy execution records. The module calculates the strategy trigger rate by statistically analyzing the actual number of times the strategy is triggered and the total number of scenarios that should be triggered, based on context information in the strategy trigger information table. The module also calculates the strategy execution rate by statistically analyzing the number of times agents perform operations according to the strategy requirements, based on context information. Finally, the module generates strategy optimization indicators based on the strategy trigger rate and strategy execution rate. These indicators are used to instruct the strategy configuration module 101 to adjust the effective rules.

[0095] In another embodiment of the insurance telemarketing multi-level strategy real-time control and closed-loop verification system of the present invention, it includes: The strategy configuration module 101 is used to match the required tag dimensions according to the insurance telemarketing strategy. It configures the customer tags in the tag dimensions as enumeration tags and numerical tags according to business model, number of outbound calls, number of consecutive unanswered calls, ringing duration, connection status, call duration, quotation status, quotation frequency, weekday appointment volume, appointment date type, car insurance main end code, non-car insurance main end code, sales rhythm, first call time, service sales status, verified status, and transaction status. It configures the organizational level tags in the tag dimensions as center level constraint tags and institution level constraint tags according to the applicable center and applicable institution. Based on the relationship between the tag dimensions, it generates the effective scope and effective rules of the strategy decision. The effective rules include the trigger nodes, execution action classification, and execution actions in the insurance telemarketing business scenario.

[0096] The strategy matching engine 102 is used to receive trigger requests reported by the telemarketing system at the trigger node, identify the current customer ID and agent ID based on the serial number carried in the trigger request, read the applicable center and applicable organization to which the agent belongs from the agent information table based on the agent ID, and read the customer's sales data, contact records and quotation records at different sales stages from the sales data table, contact record table and quotation record table based on the customer ID. It calculates the customer tag value for each tag dimension according to the configuration type of the tag dimension, and matches the effective strategy according to the effective scope and effective rules to obtain the matching result.

[0097] The strategy triggering and execution module 103 is used to receive matching results, sort the matching results according to the priority corresponding to the execution action category, and return an execution instruction containing the execution action to the telemarketing system based on the sorted matching results. When the execution action is classified as mandatory execution plus reminder or mandatory execution, the strategy triggering and execution module 103 calls the operation interception interface of the telemarketing system to block the agent's current operation at the trigger node. When the execution action is classified as pop-up reminder, the strategy triggering and execution module 103 calls the prompt display interface of the telemarketing system to pop up a prompt message on the telemarketing system interface and allow the agent to continue the current operation. When the execution action is classified as sales strategy window reminder, the strategy triggering and execution module 103 calls the window rendering interface of the telemarketing system to render the prompt message corresponding to the execution action to the sales strategy window area of ​​the telemarketing system.

[0098] The strategy execution record module 104 is used to record the execution instructions and context information corresponding to each insurance telemarketing strategy trigger. The context information includes the serial number carried by the trigger request, the operation type of the trigger node, the actual feedback operation record of the agent after the execution action is processed, and the response time from the agent reporting from the trigger node to the completion of the execution action.

[0099] The strategy effectiveness analysis module 105 is used to perform effectiveness analysis based on contextual information. The strategy effectiveness analysis module 105 generates a strategy intervention effectiveness score based on the contextual information. The formula for calculating the strategy intervention effectiveness score is as follows: in, This indicates the score for the effectiveness of the strategic intervention. This indicates the total number of times the strategy was triggered within the statistical period. Indicates the first The response time from when the agent reports from the triggering node to when the action is completed when the secondary strategy is triggered. This indicates the maximum response time triggered by all strategies within the statistical period. This represents the minimum response time for all strategies triggered within the statistical period. This represents a positive constant to prevent the denominator from being zero. The attenuation coefficient representing the response time effect. This represents the weighting coefficient of the response time dimension in the score of the effectiveness of the strategy intervention. Indicates the first When a policy is triggered, a matching flag is set between the agent's actual feedback operation record and the policy-required execution action. The value is 1 if there is a match, and 0 if there is no match. Indicates the first The conversion status indicator for the customer corresponding to this strategy trigger within a preset time period after the strategy is triggered: 1 for converted customers and 0 for non-converted customers. This represents the total number of customers who have converted within the statistical period, all of whom have triggered the strategy.

[0100] It should be noted that the calculation formula for the effectiveness score of strategy intervention incorporates three dimensions—the agent's response speed to strategy intervention, the degree of matching between the agent's operation and the strategy requirements, and the customer's conversion result after the strategy is triggered—into a unified scoring framework through a non-linear weighted fusion method. The response speed dimension is measured using normalized relative position combined with an exponential decay mechanism to reflect the characteristic that the faster the agent's response speed under strategy intervention, the higher the score. The operation matching dimension is based on a binary identifier and adds the customer conversion result as an adjustment factor so that strategy-triggered events that simultaneously meet the two conditions of operation matching and customer conversion receive a higher score contribution. The three dimensions are balanced through weight coefficients, so that the effectiveness score of strategy intervention can comprehensively measure the overall effect of each strategy-triggered event in terms of response timeliness, execution accuracy, and business conversion.

[0101] The above formula transforms the originally discrete and independent execution records into sortable and comparable continuous quantitative indicators by conducting multi-dimensional quantitative evaluation of strategy-triggered events. This provides a unified evaluation benchmark for strategy optimization, making the identification of inefficient strategies no longer dependent on human experience judgment, but based on the objective judgment of the scoring results automatically calculated by the system. At the same time, the introduction of the response time exponential decay mechanism makes the strategy intervention effectiveness score continuously and smoothly sensitive to changes in agent response speed, avoiding the problem of drastic score jumps caused by small fluctuations in response time.

[0102] The strategy effectiveness analysis module 105 is used to sort the effective rules according to the strategy intervention effectiveness score and generate strategy optimization indicators. The strategy optimization indicators are used to instruct the strategy configuration module 101 to adjust the effective rules.

[0103] The strategy configuration module 101 is also used to receive strategy optimization indicators, identify inefficient rules based on the strategy intervention effectiveness score in the strategy optimization indicators, mark rules that are classified as mandatory execution plus reminders and whose strategy intervention effectiveness score is lower than a preset threshold as rules to be optimized, extract the mismatch features between the actual feedback operation records of the agents and the execution actions required by the strategy from the rules to be optimized, and adjust the organizational level constraint label or trigger node or execution action classification or execution action in the effective scope of the rules to be optimized based on the mismatch features.

[0104] The technical solution of this embodiment uses the configuration of tag dimensions as an enumeration class and a numerical class and the establishment of an association relationship as the basis for strategy configuration. It identifies customer and agent identifiers through serial numbers and reads the organizational level to which the agent belongs. It calls the operation interception interface to block operations, or calls the prompt display interface to pop up prompt information, or calls the window rendering interface to render prompt information by executing action classification. By recording the response time and the actual feedback operation records of the agents, it adjusts the organizational level constraint tags or trigger nodes or execution action classifications or execution actions in the effective scope accordingly. This solves the problems of insufficient granularity of strategy configuration, inability to dynamically adjust strategy matching according to organizational level and customer stage, disconnect between strategy execution and agent operation interface, and lack of data basis for effect analysis on consistency between agent behavior and strategy requirements. It improves the flexibility of strategy configuration, the accuracy of strategy matching, the timeliness of strategy intervention, and the standardization of operation execution.

[0105] Figure 6 This diagram illustrates a flowchart of an embodiment of a real-time control and closed-loop verification method for multi-level insurance telemarketing strategies provided by the present invention. This method employs the real-time control and closed-loop verification system 100 for multi-level insurance telemarketing strategies provided by the present invention. Figure 6 As shown, the method includes the following steps: S1. Configure the effective scope and effective rules of the strategy decision according to the required tag dimensions for matching the insurance telemarketing strategy. The effective rules include the trigger nodes, action classifications and actions in the insurance telemarketing business scenario. S2. Based on the trigger request reported by the telemarketing system at the trigger node, calculate the customer tag value in real time from multiple related tables, and match the effective strategy with the effective scope and the effective rule to obtain the matching result; S3. Based on the matching results, sort the matching results according to the priority corresponding to the execution action category, and return an execution instruction containing the execution action to the telemarketing system according to the sorted matching results, so that the telemarketing system executes the execution action at the trigger node; S4. Record the execution instructions and context information corresponding to each insurance telemarketing strategy trigger; S5. Perform effect analysis based on the context information to obtain analysis results, and dynamically adjust the effective rules based on the analysis results.

[0106] It should be noted that the beneficial effects of the real-time control and closed-loop verification method for multi-level insurance telemarketing strategies provided in the above embodiments are the same as those of the above-described real-time control and closed-loop verification system 100 for multi-level insurance telemarketing strategies, and will not be repeated here. Furthermore, the method and system embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the system embodiments, which will not be repeated here.

[0107] The insurance telemarketing multi-level strategy real-time control and closed-loop verification system 100 of the present invention can be a computer program (including program code) running on a computer device. For example, the insurance telemarketing multi-level strategy real-time control and closed-loop verification system 100 of the present invention is an application software that can be used to execute the corresponding steps in the insurance telemarketing multi-level strategy real-time control and closed-loop verification method of the present invention.

[0108] In some embodiments, the insurance telemarketing multi-level strategy real-time control and closed-loop verification system 100 of the present invention can be implemented in a combination of hardware and software. As an example, the insurance telemarketing multi-level strategy real-time control and closed-loop verification system 100 of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the insurance telemarketing multi-level strategy real-time control and closed-loop verification method of the present invention. For example, the processor in the form of a hardware decoding processor can be one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0109] The modules described in the embodiments of this invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0110] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-mentioned real-time control and closed-loop verification methods for multi-level insurance telemarketing strategies. That is, an electronic device according to an embodiment of the present invention may include, but is not limited to: a processor and a memory; the memory is used to store the computer program; the processor is used to execute the real-time control and closed-loop verification method for multi-level insurance telemarketing strategies shown in any embodiment of the present invention by calling the computer program.

[0111] In one alternative embodiment, an electronic device is provided, such as Figure 7 As shown, Figure 7 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0112] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0113] Bus 4002 may include a path for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The bus 4002 is represented by only one thick line, but this does not mean that there is only one bus or one type of bus.

[0114] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0115] The memory 4003 stores application code (computer program) for executing the present invention, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0116] Among them, electronic devices can also be terminal devices. A terminal device can be any terminal device that can install applications and access web pages through applications, including at least one of smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, smart TVs, and smart in-vehicle devices.

[0117] It should be noted that, Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0118] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the above-mentioned methods for real-time control and closed-loop verification of multi-level insurance telemarketing strategies.

[0119] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0120] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. The processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the aforementioned real-time control and closed-loop verification method for multi-level insurance telemarketing strategies.

[0121] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0122] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0123] The computer-readable storage medium provided in this invention can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0124] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0125] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0126] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0127] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this invention can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0128] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A real-time control and closed-loop verification system for multi-level strategies in insurance telemarketing, characterized in that, include: The strategy configuration module is used to configure the effective scope and effective rules of the strategy decision according to the tag dimensions required for matching the insurance telemarketing strategy. The effective rules include the trigger nodes, execution action classifications and execution actions in the insurance telemarketing business scenario. The strategy matching engine is used to calculate customer tag values ​​in real time from multiple related tables based on the trigger request reported by the telemarketing system at the trigger node, and match the effective strategy with the effective scope and the effective rules to obtain the matching result; The strategy triggering and execution module is used to sort the matching results according to the priority corresponding to the execution action category, and return an execution instruction containing the execution action to the telemarketing system according to the sorted matching results, so that the telemarketing system executes the execution action at the triggering node; The strategy execution record module is used to record the execution instructions and context information corresponding to each insurance telemarketing strategy trigger. The strategy effect analysis module is used to perform effect analysis based on the context information, obtain analysis results, and dynamically adjust the effective rules based on the analysis results.

2. The real-time control and closed-loop verification system for multi-level insurance telemarketing strategies according to claim 1, characterized in that, The tag dimensions include customer tags and organizational level tags. The customer tags include multiple dimensions used to describe insurance customer attributes and sales process status. The organizational level tags include applicable centers and applicable institutions.

3. The real-time control and closed-loop verification system for multi-level insurance telemarketing strategies according to claim 2, characterized in that, The strategy matching engine is specifically used for: Based on the trigger request, the customer tag value is calculated in real time from the sales data table, contact record table, and quotation record table. The calculated customer tag value is compared with the tag dimension defined in the strategy configuration module to determine whether it matches the effective rule.

4. The real-time control and closed-loop verification system for multi-level insurance telemarketing strategies according to claim 1, characterized in that, The triggering nodes include a sales click-to-dial node, a first-call click-to-dial node, a save-end-code node, a generate-insurance-application-form node, and an open-sales-strategy-window node. The triggering request carries a serial number and an operation type. When each of the triggering nodes is operated, the telemarketing system reports the triggering request to the strategy matching engine.

5. The real-time control and closed-loop verification system for multi-level insurance telemarketing strategies according to claim 4, characterized in that, The execution actions are categorized into pop-up reminders, forced execution, forced execution with reminders, and sales strategy window reminders. The execution actions include setting prompts, disallowing the selection of end codes, disallowing dialing, and adding red text reminders to stage goals. The strategy triggering and execution module is specifically used for: Extract the action category and the action corresponding to each matching strategy from the matching results; The execution actions are sorted according to the priority, and the execution order of each matching strategy is determined based on the sorted execution action categories. The execution actions corresponding to each matching strategy are concatenated according to the execution order to generate the execution instruction; The execution instruction is returned to the telemarketing system so that the telemarketing system performs the corresponding operation at the trigger node according to the execution action in the execution instruction.

6. The real-time control and closed-loop verification system for multi-level insurance telemarketing strategies according to claim 4, characterized in that, The strategy execution record module is specifically used for: The node name corresponding to the triggering node, the serial number carried in the triggering request, the decision identifier and decision name corresponding to the matching result, the execution action category and execution action in the execution instruction, the prompt information corresponding to the execution action, and the unique operation identifier are written into the strategy triggering information table as the context information.

7. The real-time control and closed-loop verification system for multi-level insurance telemarketing strategies according to claim 6, characterized in that, The strategy effectiveness analysis module is specifically used for: Based on the context information in the strategy trigger information table, the actual number of times the strategy is triggered and the total number of scenarios that should be triggered are statistically analyzed, and the strategy trigger rate is calculated. The strategy trigger rate is the ratio of the actual number of times the strategy is triggered to the total number of scenarios that should be triggered. Based on the context information, the number of times the agent operates according to the policy requirements is counted, and the policy execution rate is calculated. The policy execution rate is the ratio of the number of times the agent operates according to the policy requirements to the actual number of times the policy is triggered. A strategy optimization metric is generated based on the strategy trigger rate and the strategy execution rate. The strategy optimization metric is used to instruct the strategy configuration module to adjust the effective rules.

8. A method for real-time control and closed-loop verification of multi-level strategies in insurance telemarketing, characterized in that, The real-time control and closed-loop verification system for multi-level insurance telemarketing strategies as described in any one of claims 1 to 7, the method comprising: Based on the tag dimensions required for matching insurance telemarketing strategies, configure the scope and rules for the effectiveness of strategy decisions. The rules include triggering nodes, action classifications, and actions to be performed in the insurance telemarketing business scenario. Based on the trigger request reported by the telemarketing system at the trigger node, customer tag values ​​are calculated in real time from multiple related tables, and the effective strategy is matched with the effective scope and the effective rules to obtain the matching result; Based on the matching results, the matching results are sorted according to the priority corresponding to the category of the execution action. Based on the sorted matching results, an execution instruction containing the execution action is returned to the telemarketing system so that the telemarketing system executes the execution action at the trigger node. Record the execution instructions and context information corresponding to each trigger of the insurance telemarketing strategy; The effect analysis is performed based on the context information to obtain the analysis results, and the effective rules are dynamically adjusted based on the analysis results.

9. An electronic device, characterized in that, The electronic device includes a processor coupled to a memory, the memory storing at least one computer program, which is loaded and executed by the processor to enable the electronic device to implement the real-time control and closed-loop verification method for multi-level insurance telemarketing strategies as described in claim 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program, which, when executed by a processor, implements the real-time control and closed-loop verification method for multi-level insurance telemarketing strategies as described in claim 8.

Images