Breakpoint behavior processing method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a breakpoint behavior processing method and device, electronic equipment and a storage medium, belongs to the technical field of data processing, and is suitable for the field of finance. The method comprises the following steps: acquiring a breakpoint behavior event of a target user; wherein the breakpoint behavior event has a breakpoint timestamp; obtaining original user information, original insurance records and original browsing records of the target user; performing feature extraction according to the breakpoint behavior event, the original user information, the original insurance record, the original browsing record and the breakpoint timestamp to obtain breakpoint clue features; performing conversion probability prediction according to the breakpoint clue features to obtain a breakpoint conversion rate; wherein the breakpoint conversion rate represents the success rate of promoting the insurance process of the target user; writing the breakpoint behavior event into a preset user breakpoint time wheel according to the breakpoint conversion rate; and performing flow promotion on the breakpoint behavior event in the breakpoint time wheel of the user through a preset seat queue. According to the embodiment of the invention, the processing conversion rate of the breakpoint behavior can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, is applicable to the financial field, and particularly relates to a breakpoint behavior processing method and device, an electronic device, and a storage medium. Background Art

[0002] Breakpoint behavior refers to users interrupting an action during a workflow. For example, a user might exit an insurance product details page after entering it, or fail to complete the payment process after clicking the Apply Now button. Breakpoint behavior is characterized by diverse triggering factors, fragmented behavioral paths, and unclear conversion intent. This makes it difficult to accurately identify and respond to breakpoint behavior using a single rule, resulting in generally low conversion rates. Therefore, improving the conversion rate of breakpoint behavior has become a pressing technical challenge. Summary of the Invention

[0003] The main purpose of the embodiments of the present application is to provide a breakpoint behavior processing method and device, an electronic device and a storage medium, aiming to improve the processing conversion rate of breakpoint behavior.

[0004] To achieve the above objectives, a first aspect of an embodiment of the present application provides a breakpoint behavior processing method, the method comprising:

[0005] Obtaining a breakpoint behavior event of the target user; wherein the breakpoint behavior event is a behavior event generated when the target user triggers an interrupt operation in the insurance application process, and the breakpoint behavior event includes a breakpoint timestamp;

[0006] Obtaining the original user information, original insurance record, and original browsing record of the target user;

[0007] Perform feature extraction based on the breakpoint behavior event, the original user information, the original insurance record, the original browsing record, and the breakpoint timestamp to obtain a breakpoint clue feature;

[0008] Perform conversion probability prediction based on the breakpoint clue features to obtain a breakpoint conversion rate; wherein the breakpoint conversion rate represents the success rate of promoting the insurance application process of the target user;

[0009] Writing the breakpoint behavior event into a preset user breakpoint time wheel according to the breakpoint conversion rate;

[0010] The process of the breakpoint behavior event in the user breakpoint time wheel is promoted through the preset seat queue.

[0011] In some embodiments, writing the breakpoint behavior event into a preset user breakpoint time wheel according to the breakpoint conversion rate includes:

[0012] Comparing the breakpoint conversion rate with a preset threshold, and determining a target conversion rate greater than the preset threshold from the breakpoint conversion rate;

[0013] Determining a target behavior event of the target conversion rate from the breakpoint behavior events;

[0014] The target behavior event is written into the user breakpoint time wheel according to the target conversion rate.

[0015] In some embodiments, writing the target behavior event into the user breakpoint time wheel according to the target conversion rate includes:

[0016] Mapping the target conversion rate according to a preset priority mapping rule to obtain a target breakpoint level;

[0017] Mapping the target breakpoint level according to a preset waiting time mapping rule to obtain a target waiting time;

[0018] Obtaining a target time slot from the user breakpoint time wheel according to the target waiting time;

[0019] The target behavior event is written into the target time slot.

[0020] In some embodiments, the user breakpoint time wheel has a target time slot, the target time slot has a target timestamp and the breakpoint behavior event; and the process of pushing the breakpoint behavior event in the user breakpoint time wheel through a preset agent queue includes:

[0021] Obtaining a current timestamp through a preset thread lock polling until the current timestamp is the same as the target timestamp, and reading the breakpoint behavior event from the target timestamp;

[0022] Perform idle state polling on the seat queue through the thread lock to obtain a target seat in an idle state;

[0023] Changing the target agent from the idle state to the busy state through the thread lock;

[0024] The process of the breakpoint behavior event is promoted through the target agent.

[0025] In some embodiments, extracting features based on the breakpoint behavior event, the original user information, the original insurance record, the original browsing record, and the breakpoint timestamp to obtain the breakpoint clue features includes:

[0026] Calculate the target time stamp based on the breakpoint time stamp and the preset target time period to obtain the target time stamp;

[0027] Acquire the insurance records between the breakpoint timestamp and the target timestamp from the original insurance records to obtain the target insurance records;

[0028] Obtaining the browsing records between the breakpoint timestamp and the target timestamp from the original browsing records to obtain the target browsing records;

[0029] Feature extraction is performed based on the breakpoint behavior event, the original user information, the target insurance record and the target browsing record to obtain the breakpoint clue feature.

[0030] In some embodiments, extracting features based on the breakpoint behavior event, the original user information, the target insurance record, and the target browsing record to obtain the breakpoint clue features includes:

[0031] Construct a user portrait based on the original user information to obtain a target user portrait vector;

[0032] Create an insurance profile based on the target insurance record to obtain a target insurance profile vector;

[0033] Extract interactive behavior features based on the target browsing records to obtain a target interactive behavior vector;

[0034] Constructing breakpoint attribute features according to the breakpoint behavior event to obtain a target breakpoint attribute vector;

[0035] The target user portrait vector, the target insurance portrait vector, the target interactive behavior vector and the target breakpoint attribute vector are vector-concatenated to obtain the breakpoint clue feature.

[0036] In some embodiments, obtaining a breakpoint behavior event of a target user includes:

[0037] Acquire the original breakpoint behavior of the target user; wherein the original breakpoint behavior is provided with an original timestamp;

[0038] Determine a time determination interval according to the original timestamp and a preset time window;

[0039] If the target user has other breakpoint behaviors within the time determination interval, the other breakpoint behaviors are associated with the original breakpoint behavior to obtain the breakpoint behavior event;

[0040] If the target user does not have any other breakpoint behaviors within the time determination interval, the original breakpoint behavior is used as the breakpoint behavior event.

[0041] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a breakpoint behavior processing device, the device comprising:

[0042] A first acquisition module is configured to acquire a breakpoint behavior event of a target user; wherein the breakpoint behavior event is a behavior event generated when the target user triggers an interrupt operation in the insurance application process, and the breakpoint behavior event includes a breakpoint timestamp;

[0043] The second acquisition module is used to obtain the original user information, original insurance record and original browsing record of the target user;

[0044] A feature extraction module is used to extract features based on the breakpoint behavior event, the original user information, the original insurance record, the original browsing record and the breakpoint timestamp to obtain breakpoint clue features;

[0045] A probability prediction module is used to predict the conversion probability based on the breakpoint clue characteristics to obtain a breakpoint conversion rate; wherein the breakpoint conversion rate represents the success rate of promoting the insurance application process of the target user;

[0046] A data writing module, configured to write the breakpoint behavior event into a preset user breakpoint time wheel according to the breakpoint conversion rate;

[0047] The breakpoint pushing module is used to push the process of the breakpoint behavior event in the user breakpoint time wheel through a preset seat queue.

[0048] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described in the first aspect when executing the computer program.

[0049] To achieve the above-mentioned purpose, the fourth aspect of the embodiments of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method described in the first aspect.

[0050] The present application proposes a breakpoint behavior processing method and device, electronic device, and storage medium. The method obtains the breakpoint behavior events of the target user in the insurance process, and combines the original user information, original insurance record, original browsing record, and breakpoint timestamp to perform feature extraction to form breakpoint clue features. The method then predicts the conversion probability based on the breakpoint clue features to obtain a breakpoint conversion rate representing the likelihood of success of the insurance process. The method then writes the corresponding breakpoint behavior event into the user breakpoint time wheel based on the breakpoint conversion rate, and finally promotes the process of the breakpoint behavior event through a preset agent queue. In this way, the embodiment of the present application improves the judgment accuracy through multi-source data fusion modeling and prediction, and manages the breakpoint events in an orderly manner with the help of the time wheel mechanism, thereby effectively improving the conversion success rate of the breakpoint behavior and solving the problems of difficult identification and response to breakpoint behavior and low conversion rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a flowchart of a breakpoint behavior processing method provided by an embodiment of the present application;

[0052] Figure 2 yes Figure 1 Flowchart of step S101 in FIG.

[0053] Figure 3 yes Figure 1 Flowchart of step S103 in FIG.

[0054] Figure 4 yes Figure 3 Flowchart of step S304 in FIG.

[0055] Figure 5 yes Figure 1 Flowchart of step S105 in FIG.

[0056] Figure 6 yes Figure 5 Flowchart of step S503 in FIG.

[0057] Figure 7 yes Figure 1 Flowchart of step S106 in FIG.

[0058] Figure 8 Schematic diagram of the structure of the breakpoint behavior processing device provided in an embodiment of the present application;

[0059] Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0061] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0063] First, let’s analyze some of the terms used in this application:

[0064] LightGBM (Light Gradient Boosting Machine): is an efficient distributed machine learning algorithm based on the Gradient Boosting Decision Tree (GBDT) framework, designed to improve training efficiency and prediction accuracy in large-scale data environments. The core idea of ​​LightGBM is to introduce mechanisms such as Gradient-based One-Side Sampling (GOSS) and Exclusive Feature Bundling (EFB) on the basis of the traditional gradient boosting tree algorithm to achieve efficient dimensionality reduction and sample optimization of training data, thereby improving training speed and reducing memory consumption. LightGBM supports a variety of learning tasks such as classification, regression, and sorting, and has high concurrent computing capabilities and strong generalization capabilities. It has been widely deployed in practical applications such as advertising click-through rate prediction, credit risk assessment, and search ranking optimization. As a typical ensemble learning method, LightGBM has good scalability in data processing, model training, and feature importance evaluation. It is one of the commonly used modeling tools in machine learning model engineering practice.

[0065] The Timing Wheel is a data structure and time control mechanism used to efficiently manage and schedule scheduled tasks. It is often used to handle large numbers of delayed or time-triggered tasks. The basic principle of the Timing Wheel is to divide the entire timeline into multiple time slots at a fixed granularity, with each time slot storing task events that will be triggered at a corresponding time point. The Timing Wheel's pointer moves clockwise at a fixed period, and each movement triggers the task mounted in the current time slot, thereby achieving precise control and orderly scheduling of scheduled tasks. The Timing Wheel can be divided into single-layer and multi-layer timing wheel structures. The multi-layer timing wheel is suitable for scheduled scheduling tasks with larger time spans and higher precision requirements. The Timing Wheel is widely used in task scheduling in operating system kernels, connection management in network frameworks, and task triggering control in distributed systems. It has technical advantages such as low time complexity, low resource overhead, and high scheduling efficiency. It is an important basic component for building real-time scheduling mechanisms in high-concurrency environments.

[0066] Time Slot: It is the basic time unit used to carry scheduled tasks and is the core logical component of the time wheel structure. Time slots are arranged in order according to fixed time granularity, and each time slot is used to store task events or operation instructions that will be triggered at the corresponding time point. The system periodically moves to each time slot through the pointer and triggers all tasks mounted in the current time slot, thereby realizing the orderly processing of delayed tasks or timed events. The design of time slots has structural characteristics such as queuing and bucketing, which can support multi-threaded safe access and dynamic task mounting. It is often used in task scheduling systems, network connection management, cache cleaning mechanisms, distributed processing frameworks and other fields. Time slots and time wheels together construct a low-latency, high-performance time-driven scheduling mechanism with the advantages of simple implementation, high triggering efficiency, and low resource overhead. It is an important structural foundation for scheduled task management in a high-concurrency environment.

[0067] Agent Queue: It is a data structure and resource control mechanism used to manage the status and scheduling order of multiple service agents. It is widely used in scenarios such as customer service systems, call centers, and process execution systems. The agent queue is used to dynamically maintain the operating status of each agent (such as idle, busy, offline, etc.) and the allocation priority of agent resources. It supports concurrent access control, status polling, task scheduling and other operational logic. When the system receives a pending task (such as a user request or a breakpoint behavior event), it traverses the agent queue to identify the target agent in the idle state, assigns the task to the agent for execution, and updates the corresponding agent status to busy. The agent queue is usually combined with a thread lock mechanism for concurrent security management to ensure the mutual exclusion and consistency of resource scheduling in a high-concurrency environment. The agent queue has the characteristics of clear structure, strong scalability, and flexible scheduling strategy. It is an important basic component for realizing the linkage between task resource distribution and process response in the process promotion system.

[0068] Breakpoint behavior refers to users interrupting an action during a workflow. For example, a user might exit an insurance product details page after entering it, or fail to complete the payment process after clicking the Apply Now button. Breakpoint behavior is characterized by diverse triggering factors, fragmented behavioral paths, and unclear conversion intent. This makes it difficult to accurately identify and respond to breakpoint behavior using a single rule, resulting in generally low conversion rates. Therefore, improving the conversion rate of breakpoint behavior has become a pressing technical challenge.

[0069] Based on this, embodiments of the present application provide a breakpoint behavior processing method and device, an electronic device, and a storage medium, aiming to improve the processing conversion rate of breakpoint behaviors.

[0070] The embodiments of the present application provide a breakpoint behavior processing method and device, an electronic device, and a storage medium, which are specifically described through the following embodiments. First, the breakpoint behavior processing method in the embodiments of the present application is described.

[0071] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0072] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0073] The breakpoint behavior processing method provided in the embodiment of the present application relates to the field of data processing technology and is applicable to the financial field. The breakpoint behavior processing method provided in the embodiment of the present application can be applied in a terminal, can be applied in a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the breakpoint behavior processing method, etc., but is not limited to the above forms.

[0074] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0075] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0076] Figure 1 This is an optional flowchart of the breakpoint behavior processing method provided in the embodiment of the present application. Figure 1The method may include but is not limited to steps S101 to S106.

[0077] Step S101: Obtain a breakpoint behavior event of a target user; wherein the breakpoint behavior event is a behavior event generated when the target user triggers an interrupt operation in the insurance application process, and the breakpoint behavior event includes a breakpoint timestamp;

[0078] Step S102, obtaining the original user information, original insurance record and original browsing record of the target user;

[0079] Step S103, extracting features based on the breakpoint behavior event, original user information, original insurance record, original browsing record and breakpoint timestamp to obtain breakpoint clue features;

[0080] Step S104: predicting the conversion probability based on the breakpoint clue characteristics to obtain the breakpoint conversion rate; wherein the breakpoint conversion rate represents the success rate of promoting the target user's insurance application process;

[0081] Step S105, writing the breakpoint behavior event into a preset user breakpoint time wheel according to the breakpoint conversion rate;

[0082] Step S106: Push the process of the breakpoint behavior event in the user breakpoint time wheel through the preset agent queue.

[0083] Steps S101 to S106 shown in the embodiment of the present application obtain the breakpoint behavior events of the target user in the insurance process, and combine the original user information, original insurance records, original browsing records and breakpoint timestamps to perform feature extraction to form breakpoint clue features, and then perform conversion probability prediction based on the breakpoint clue features to obtain the breakpoint conversion rate representing the possibility of success of the insurance process, and then write the corresponding breakpoint behavior events into the user breakpoint time wheel according to the breakpoint conversion rate, and finally promote the process of breakpoint behavior events through the preset seat queue. In this way, the embodiment of the present application improves the judgment accuracy through multi-source data fusion modeling and prediction, and manages breakpoint events in an orderly manner with the help of the time wheel mechanism, thereby effectively improving the conversion success rate of breakpoint behavior and solving the problems of difficult identification and response of breakpoint behavior and low conversion rate.

[0084] See also Figure 2 In some embodiments, step S101 may include but is not limited to steps S201 to S204:

[0085] Step S201, obtaining the original breakpoint behavior of the target user; wherein the original breakpoint behavior is provided with an original timestamp;

[0086] Step S202, determining a time determination interval based on the original timestamp and a preset time window;

[0087] Step S203: If the target user has other breakpoint behaviors within the time determination interval, the other breakpoint behaviors are associated with the original breakpoint behavior to obtain a breakpoint behavior event;

[0088] Step S204: If the target user does not have any other breakpoint behaviors within the time determination interval, the original breakpoint behavior is taken as a breakpoint behavior event.

[0089] In steps S201 to S204 shown in the embodiment of the present application, the original breakpoint behavior of the target user is obtained, the original timestamp corresponding to the original breakpoint behavior is determined, and the time determination interval is determined based on the original timestamp and the preset time window, and whether there are other breakpoint behaviors within the time determination interval. If there are other breakpoint behaviors, the original breakpoint behavior is associated with the other breakpoint behaviors to generate a comprehensive breakpoint behavior event; if there are no other breakpoint behaviors, the original breakpoint behavior is directly used as the breakpoint behavior event. In this way, the embodiment of the present application improves the ability to recognize the continuity of the behavior sequence by introducing the aggregation of breakpoint behaviors through time windows, which helps to restore the interruption logic of the user in the insurance process, thereby providing a more valuable reference behavior basis for subsequent conversion prediction and personalized reach.

[0090] In step S201 of some embodiments, the original breakpoint behavior is an interruption operation performed by the target user during the insurance application process, including but not limited to exiting the insurance product details page, not completing the payment after clicking the Apply Now button, closing the page midway through filling in the insurance application information, returning to the previous page during the payment process, and other operations. The original timestamp is the time information of the interruption operation behavior, which is used to indicate the specific time when the original breakpoint behavior occurred in the time series.

[0091] In step S202 of some embodiments, the process of determining the time determination interval based on the original timestamp and the preset time window is specifically as follows: using the original timestamp as a reference, extending a certain length of time into the past to form a continuous time interval, namely the time determination interval. The preset time window can be set to different lengths such as 5 minutes, 10 minutes, 30 minutes, etc. according to the business scenario requirements. For example, if the original timestamp is 10:00:00 on May 1, 2024, and the preset time window is 10 minutes, then the time determination interval is from 09:50:00 on May 1, 2024 to 10:10:00 on May 1, 2024. By setting the time determination interval, it can be used to filter other behavior information that is continuous or close in time to the original breakpoint behavior.

[0092] In step S203 of some embodiments, the remaining breakpoint behaviors are interruption operations generated by the same target user within the time determination interval and occurring at the same or similar process stage as the original breakpoint behavior. For example, a user may exit the insurance product details page twice in a row, or attempt to pay twice in a row but fail. If such remaining breakpoint behaviors exist, the original breakpoint behavior and the remaining breakpoint behaviors are integrated through association processing.

[0093] Association processing involves merging the behavioral data of multiple breakpoints into a unified data structure. A breakpoint behavior event is a set of interruption operation behaviors of a target user within a specific time period, which is used to describe and characterize the user's behavior pattern and possible conversion intention.

[0094] In step S102 of some embodiments, the original user information refers to basic attribute information related to the target user, including but not limited to static data such as gender, age, geographic location, account registration information, historical operation device type, etc.

[0095] The original insurance record refers to the insurance behavior data, including completed or uncompleted insurance documents, filling status, product selection, payment status, etc.

[0096] Original browsing history refers to the target user's page access behavior, including access time, visited pages, page dwell time, click behavior, jump path and other data.

[0097] See also Figure 3 In some embodiments, step S103 may include but is not limited to steps S301 to S304:

[0098] Step S301, calculating based on the breakpoint timestamp and the preset target time period to obtain a target timestamp;

[0099] Step S302: Obtain the insurance records between the breakpoint timestamp and the target timestamp from the original insurance records to obtain the target insurance records;

[0100] Step S303, obtaining the browsing records between the breakpoint timestamp and the target timestamp from the original browsing records to obtain the target browsing records;

[0101] Step S304 , performing feature extraction based on the breakpoint behavior event, original user information, target insurance record, and target browsing record to obtain breakpoint clue features.

[0102] In steps S301 to S304 shown in the embodiment of the present application, the target timestamp is determined by calculating based on the breakpoint timestamp and the preset target time period. Then, between the breakpoint timestamp and the target timestamp, the corresponding target insurance records are extracted from the original insurance records, and the corresponding target browsing records are extracted from the original browsing records. Then, the breakpoint behavior events and the original user information are combined to perform multi-dimensional data fusion processing to obtain breakpoint clue features that can characterize the breakpoint background and behavior logic. In this way, the embodiment of the present application extracts recent insurance records and browsing records by introducing time period constraints, and fuses user information with breakpoint behavior to characterize the target user's recent insurance intentions and breakpoint behavior.

[0103] In step S301 of some embodiments, the target time period is used to limit the scope of behaviors that require retrospective analysis. For example, the target time period can be preset to the past 30 days. If the breakpoint timestamp is 10:00:00 on May 1, 2022, the corresponding target timestamp is 10:00:00 on April 1, 2022.

[0104] In step S302 of some embodiments, the target insurance record is the insurance behavior data between the target timestamp and the breakpoint timestamp, for example, it can be the car insurance premium, insurance period, insurance status of various non-car insurance types, etc.

[0105] In step S303 of some embodiments, the target browsing record is the page access behavior information generated by the target user between the target timestamp and the breakpoint timestamp. Specifically, it may include fields such as the browsed page identifier, dwell time, click behavior, and jump path. For example, the browsing time, number of views, number of clicks to apply for insurance immediately, and the browsing time of each module on the same product line in the past 30 days up to the time of the current view can indicate the depth of customer interaction.

[0106] See also Figure 4 In some embodiments, step S304 may include but is not limited to steps S401 to S405:

[0107] Step S401: construct a user portrait based on the original user information to obtain a target user portrait vector;

[0108] Step S402: Create an insurance profile based on the target insurance record to obtain a target insurance profile vector;

[0109] Step S403, extracting interactive behavior features based on the target browsing history to obtain a target interactive behavior vector;

[0110] Step S404: constructing breakpoint attribute features based on the breakpoint behavior event to obtain a target breakpoint attribute vector;

[0111] Step S405: perform vector concatenation on the target user portrait vector, the target insurance portrait vector, the target interactive behavior vector, and the target breakpoint attribute vector to obtain the breakpoint clue feature.

[0112] In steps S401 to S405 shown in the embodiment of the present application, by processing the original user information, a target user portrait vector is constructed to characterize the basic attributes and behavioral preferences of the target user; by processing the target insurance record, a target insurance portrait vector is constructed to characterize the historical behavior pattern and operation tendency of the target user in the insurance process; by processing the target browsing record, a target interactive behavior vector is extracted to characterize the interaction trajectory and activity level between the target user and the system interface; further, a target breakpoint attribute vector is constructed based on the breakpoint behavior event to describe the contextual features and abnormal performance when the breakpoint occurs. Finally, the target user portrait vector, the target insurance portrait vector, the target interactive behavior vector and the target breakpoint attribute vector are vector spliced ​​to generate a breakpoint clue feature. In this way, the embodiment of the present application integrates key information at the user level, the behavior level and the abnormal event level through multi-dimensional feature modeling and vector splicing.

[0113] In step S401 of some embodiments, user profile construction involves parsing and vectorizing the static attributes and stable preference information generated by the target user during their historical insurance application process. This raw user information includes, but is not limited to, indicators such as gender, age, region, commonly used device type, historical insurance product category preferences, and long-term behavioral stability. Taking age and region as an example, age can be discretized into multiple age groups and one-hot encoded. Region can be encoded using geographic tags, and category preference characteristics can be extracted based on the user's distribution of insurance products over a period of time.

[0114] In step S402 of some embodiments, the insurance profile is constructed by categorizing and coding the insurance application data generated by the target user within a target time period, including information such as the risk type, price range, coverage amount, coverage period, frequency of insurance application, completeness of application, and payment behavior of the insured product. Taking the frequency of insurance application as an example, the number of successful insurance application attempts initiated within the target time period is counted, and the strength of insurance application intention is evaluated in combination with the interruption rate of application application and the payment failure rate.

[0115] In step S403 of some embodiments, interactive behavior feature extraction involves analyzing the target user's page browsing behavior on the insurance platform during a target time period, including indicators such as page visit sequence, page dwell time, click density, function button usage, and jump path complexity. Taking click density as an example, the number of clicks per unit time is counted to determine whether there is high-frequency interaction, thereby assessing the user's active exploration level and operational intent.

[0116] In step S404 of some embodiments, the breakpoint attribute feature is constructed as follows: extracting and encoding the key information associated with the target user in the breakpoint behavior event, including the breakpoint type, breakpoint source, breakpoint product line, breakpoint premium, etc. The breakpoint type is used to indicate the process node where the breakpoint behavior is located, such as information filling interruption, payment interruption, insurance confirmation interruption, etc.; the breakpoint source is used to identify the entry channel that triggers the breakpoint behavior, such as self-access, recommended link jump, activity guidance, etc.; the breakpoint product line is used to reflect the insurance product category associated with the current breakpoint operation, such as health insurance, accident insurance, car insurance, etc.; the breakpoint premium is used to characterize the cost level of the product involved in the current breakpoint behavior. The above information is encoded to obtain the target breakpoint attribute vector.

[0117] In step S104 of some embodiments, the breakpoint conversion rate is used to quantify the possibility of redirecting the target user back to the insurance process and completing the insurance through operational means or intervention after the breakpoint behavior occurs, reflecting the probability level of converting the breakpoint behavior to the insurance completion state.

[0118] For example, if a target user closes the page after filling in the insurance information, and the breakpoint conversion rate is 72%, it means that after the current breakpoint behavior occurs, the probability of the user completing the insurance process after receiving a contact reminder or discount prompt for the user is 72%.

[0119] In one embodiment, conversion probability prediction is implemented using the LightGBM model. During the LightGBM model training process, cross-validation is used to evaluate the training dataset. Specifically, the dataset containing breakpoint clue features and historical insurance result labels is divided into multiple subsets. In each round of training, one subset is selected as the validation set, and the remaining subsets are used as the training set. Multiple rounds of training and validation are performed alternately to evaluate the model's stability and generalization ability under different data partitions.

[0120] See also Figure 5 In some embodiments, step S105 includes but is not limited to steps S501 to S503:

[0121] Step S501, comparing the breakpoint conversion rate with a preset threshold, and determining a target conversion rate greater than the preset threshold from the breakpoint conversion rate;

[0122] Step S502, determining a target behavior event with a target conversion rate from the breakpoint behavior events;

[0123] Step S503: Write the target behavior event into the user breakpoint time wheel according to the target conversion rate.

[0124] In steps S501 to S503, as shown in this embodiment of the application, the breakpoint conversion rate is compared with a preset threshold to identify a target conversion rate with high conversion potential. Based on the breakpoint behavior events corresponding to the target conversion rate, a target behavior event is determined and then written into the user breakpoint time wheel. In this way, this embodiment of the application screens breakpoint behavior events, intervening only in high-value breakpoint behaviors, thereby improving the accuracy and scheduling efficiency of breakpoint process intervention.

[0125] In some embodiments, in step S501, the preset threshold is a numerical value. For example, a preset threshold of 0.65 indicates that only when the breakpoint conversion rate is greater than 0.65 is the breakpoint behavior event considered to have high reflow potential and be worthy of process intervention. By comparing the breakpoint conversion rate with the preset threshold, target conversion rates with higher potential for conversion can be selected from all breakpoint behavior events, thereby improving the targetedness and effectiveness of process promotion.

[0126] The target conversion rate is a conversion rate greater than a preset threshold. For example, if the conversion rate of breakpoint behavior event A is 35%, the conversion rate of breakpoint behavior event B is 70%, and the preset threshold is 50%, then the target conversion rate is 70%.

[0127] In step S502 of some embodiments, a corresponding event, namely a target behavior event, is determined based on the target conversion rate.

[0128] See also Figure 6 In some embodiments, step S503 includes but is not limited to steps S601 to S604:

[0129] Step S601, mapping the target conversion rate according to a preset priority mapping rule to obtain a target breakpoint level;

[0130] Step S602, mapping the target breakpoint level according to a preset waiting time mapping rule to obtain a target waiting time;

[0131] Step S603, obtaining a target time slot from the user breakpoint time wheel according to the target waiting time;

[0132] Step S604: Write the target behavior event into the target time slot.

[0133] In the steps S601 to S604 shown in the embodiment of the present application, the target breakpoint level is obtained by mapping the target conversion rate according to the preset priority mapping rules, and then the target breakpoint level is mapped according to the preset waiting time mapping rules to obtain the target waiting time. The target time slot is further obtained from the user breakpoint time wheel according to the target waiting time, and the target behavior event is written into the target time slot. As a result, the embodiment of the present application realizes the hierarchical scheduling and orderly allocation of different target behavior events, so that when the target behavior events are subsequently processed, they can be processed in batches according to the time priority corresponding to the breakpoint level, effectively improving the timeliness of the breakpoint process promotion and the rationality of resource scheduling, avoiding the pressure brought by the centralized processing in high concurrency scenarios, and improving the overall operating efficiency of the breakpoint behavior processing.

[0134] In some embodiments, in step S601, the target conversion rate is mapped according to a preset priority mapping rule by assigning corresponding priority labels based on multiple conversion rate intervals, where the priority levels are used to measure the conversion urgency and process response priority of the breakpoint behavior event. The priority mapping rule can be preset to multiple segmented intervals. For example, when the target conversion rate is greater than 0.8, it is mapped to a first breakpoint level; when the target conversion rate is between 0.6 and 0.8, it is mapped to a second breakpoint level; and when the target conversion rate is less than 0.6, it is mapped to a third breakpoint level.

[0135] In some embodiments, in step S602, the target breakpoint level is mapped according to a preset wait time mapping rule by determining a corresponding target wait time based on the breakpoint level. The target wait time is used to control the delay period for pushing the breakpoint behavior event in the user breakpoint time wheel. The wait time mapping rule is a one-to-one correspondence. For example, a first-level breakpoint level corresponds to a wait time of 5 minutes, a second-level breakpoint level corresponds to a wait time of 15 minutes, and a third-level breakpoint level corresponds to a wait time of 30 minutes.

[0136] In step S603 of some embodiments, the actual processing time of the target behavior event is determined by adding the current time to the target waiting time, and then a matching target time slot is extracted from the user breakpoint time wheel structure based on the actual processing time. The target time slot is a time node container in the breakpoint time wheel for mounting behavior events.

[0137] See also Figure 7 In some embodiments, the user breakpoint time wheel has a target time slot, the target time slot has a target timestamp and a breakpoint behavior event, and step S106 may include but is not limited to steps S701 to S704:

[0138] Step S701: obtain the current timestamp through the preset thread lock polling until the current timestamp is the same as the target timestamp, and read the breakpoint behavior event from the target time slot;

[0139] Step S702: poll the idle state of the agent queue through the thread lock to obtain the target agent in the idle state;

[0140] Step S703: Change the target agent state from idle to busy through thread lock;

[0141] Step S704: Push the process of the breakpoint behavior event through the target agent.

[0142] In steps S701 to S704 shown in the embodiment of the present application, the current timestamp is obtained through a preset thread lock polling mechanism until the current timestamp is consistent with the target timestamp, and the breakpoint behavior event is read from the target time slot; further, the idle state of the agent queue is polled through the thread lock to obtain the target agent in the idle state; then the target agent's state is updated from idle to busy through the thread lock, and the target agent is scheduled to push the breakpoint behavior event. Therefore, the embodiment of the present application realizes the synchronous control of time scheduling and agent resource status by introducing a thread lock mechanism. In the processing scenario with intensive breakpoint behavior events and high concurrency, it ensures the timeliness of event triggering and the orderliness of resource allocation, and effectively improves the response efficiency of process promotion.

[0143] In step S701 of some embodiments, the current system time is periodically obtained through a polling mechanism and compared with a target timestamp pre-programmed into the user breakpoint time wheel until the current timestamp matches the target timestamp. When the trigger condition is met, the pending breakpoint action event is read from the corresponding target time slot and accurately activated according to the time priority.

[0144] It should be noted that there are multiple time slots for mounting breakpoint behavior events in the user breakpoint time wheel. Each time slot is bound to an independent thread lock for controlling the polling and triggering of breakpoint behavior events in the time slot.

[0145] In step S702 of some embodiments, it is determined one by one whether each seat is in an idle state. When the seat state of a certain seat is an idle state, the seat is determined to be a target seat.

[0146] It should be noted that in the process of polling the idle state of the agent queue to obtain the target agent in the idle state, the thread lock is an independent global thread lock, that is, the entire agent queue is polled and state managed only by this thread lock, thereby avoiding resource competition and allocation conflicts caused by multiple threads accessing or modifying the agent state at the same time in high concurrency scenarios.

[0147] In step S703 of some embodiments, after the target agent is acquired, the agent status field is locked by a thread lock and atomically updated from the idle state to the busy state to prevent other concurrent threads from acquiring the same agent resource at the same time.

[0148] It should be noted that the thread lock in step S703 and the thread lock in step S702 are the same thread lock.

[0149] In step S704 of some embodiments, the target agent performs a process promotion operation, such as a user return visit, prompt message push, or manual assistance guidance.

[0150] See also Figure 8 The present application also provides a breakpoint behavior processing device that can implement the above breakpoint behavior processing method. The device includes:

[0151] The first acquisition module 801 is used to acquire a breakpoint behavior event of a target user; wherein the breakpoint behavior event is a behavior event generated when the target user triggers an interrupt operation in the insurance application process, and the breakpoint behavior event includes a breakpoint timestamp;

[0152] The second acquisition module 802 is used to obtain the original user information, original insurance record and original browsing record of the target user;

[0153] Feature extraction module 803, for extracting features based on breakpoint behavior events, original user information, original insurance records, original browsing records, and breakpoint timestamps to obtain breakpoint clue features;

[0154] The probability prediction module 804 is used to predict the conversion probability based on the breakpoint clue characteristics to obtain the breakpoint conversion rate; wherein the breakpoint conversion rate represents the success rate of promoting the insurance application process of the target user;

[0155] The data writing module 805 is used to write the breakpoint behavior event into the preset user breakpoint time wheel according to the breakpoint conversion rate;

[0156] The breakpoint pushing module 806 is used to push the process of the breakpoint behavior events in the user breakpoint time wheel through the preset seat queue.

[0157] The specific implementation of the breakpoint behavior processing device is basically the same as the specific embodiment of the breakpoint behavior processing method described above, and will not be repeated here.

[0158] The present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-described breakpoint behavior processing method when executing the computer program. The electronic device can be any smart terminal including a tablet computer, an in-vehicle computer, or the like.

[0159] See also Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0160] The processor 901 can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0161] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called by the processor 901 to execute the breakpoint behavior processing method of the embodiments of this application;

[0162] Input / output interface 903, used to implement information input and output;

[0163] Communication interface 904, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0164] Bus 905 , which transmits information between various components of the device (e.g., processor 901 , memory 902 , input / output interface 903 , and communication interface 904 );

[0165] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0166] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned breakpoint behavior processing method is implemented.

[0167] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0168] The breakpoint behavior processing method, breakpoint behavior processing device, electronic device and storage medium provided in the embodiment of the present application obtain the breakpoint behavior events of the target user in the insurance process, and combine the original user information, original insurance record, original browsing record and breakpoint timestamp to perform feature extraction to form breakpoint clue features, and then perform conversion probability prediction based on the breakpoint clue features to obtain the breakpoint conversion rate representing the possibility of success of the insurance process, and then write the corresponding breakpoint behavior event into the user breakpoint time wheel according to the breakpoint conversion rate, and finally promote the process of breakpoint behavior events through the preset seat queue. In this way, the embodiment of the present application improves the judgment accuracy through multi-source data fusion modeling and prediction, and manages breakpoint events in an orderly manner with the help of the time wheel mechanism, thereby effectively improving the conversion success rate of breakpoint behavior and solving the problems of difficult identification and response of breakpoint behavior and low conversion rate.

[0169] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0170] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0171] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0172] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0173] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0174] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0175] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0176] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0177] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0178] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store programs.

[0179] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A breakpoint behavior processing method, characterized in that: The method comprises: Obtaining a breakpoint behavior event of the target user; wherein the breakpoint behavior event is a behavior event generated when the target user triggers an interrupt operation in the insurance application process, and the breakpoint behavior event includes a breakpoint timestamp; Obtaining the original user information, original insurance record, and original browsing record of the target user; Perform feature extraction based on the breakpoint behavior event, the original user information, the original insurance record, the original browsing record, and the breakpoint timestamp to obtain a breakpoint clue feature; Perform conversion probability prediction based on the breakpoint clue features to obtain a breakpoint conversion rate; wherein the breakpoint conversion rate represents the success rate of promoting the insurance application process of the target user; Writing the breakpoint behavior event into a preset user breakpoint time wheel according to the breakpoint conversion rate; The process of the breakpoint behavior event in the user breakpoint time wheel is promoted through the preset seat queue.

2. The method according to claim 1, characterized in that Writing the breakpoint behavior event into a preset user breakpoint time wheel according to the breakpoint conversion rate includes: Comparing the breakpoint conversion rate with a preset threshold, and determining a target conversion rate greater than the preset threshold from the breakpoint conversion rate; Determining a target behavior event of the target conversion rate from the breakpoint behavior events; The target behavior event is written into the user breakpoint time wheel according to the target conversion rate.

3. The method according to claim 2, characterized in that Writing the target behavior event into the user breakpoint time wheel according to the target conversion rate includes: Mapping the target conversion rate according to a preset priority mapping rule to obtain a target breakpoint level; Mapping the target breakpoint level according to a preset waiting time mapping rule to obtain a target waiting time; Obtaining a target time slot from the user breakpoint time wheel according to the target waiting time; The target behavior event is written into the target time slot.

4. The method according to claim 1, wherein The user breakpoint time wheel has a target time slot, and the target time slot has a target timestamp and the breakpoint behavior event; The process of pushing the breakpoint behavior event in the user breakpoint time wheel through the preset seat queue includes: Obtaining a current timestamp through a preset thread lock polling until the current timestamp is the same as the target timestamp, and reading the breakpoint behavior event from the target timestamp; Perform idle state polling on the seat queue through the thread lock to obtain a target seat in an idle state; Changing the target agent from the idle state to the busy state through the thread lock; The process of the breakpoint behavior event is promoted through the target agent.

5. The method according to claim 1, wherein The feature extraction is performed based on the breakpoint behavior event, the original user information, the original insurance record, the original browsing record and the breakpoint timestamp to obtain the breakpoint clue feature, including: Calculate the target time stamp based on the breakpoint time stamp and the preset target time period to obtain the target time stamp; Acquire the insurance records between the breakpoint timestamp and the target timestamp from the original insurance records to obtain the target insurance records; Obtaining the browsing records between the breakpoint timestamp and the target timestamp from the original browsing records to obtain the target browsing records; Feature extraction is performed based on the breakpoint behavior event, the original user information, the target insurance record and the target browsing record to obtain the breakpoint clue feature.

6. The method according to claim 5, characterized in that The feature extraction based on the breakpoint behavior event, the original user information, the target insurance record and the target browsing record to obtain the breakpoint clue feature includes: Construct a user portrait based on the original user information to obtain a target user portrait vector; Create an insurance profile based on the target insurance record to obtain a target insurance profile vector; Extract interactive behavior features based on the target browsing records to obtain a target interactive behavior vector; Constructing breakpoint attribute features according to the breakpoint behavior event to obtain a target breakpoint attribute vector; The target user portrait vector, the target insurance portrait vector, the target interactive behavior vector and the target breakpoint attribute vector are vector-concatenated to obtain the breakpoint clue feature.

7. The method according to any one of claims 1 to 6, characterized in that The step of obtaining the target user's breakpoint behavior event includes: Acquire the original breakpoint behavior of the target user; wherein the original breakpoint behavior is provided with an original timestamp; Determine a time determination interval according to the original timestamp and a preset time window; If the target user has other breakpoint behaviors within the time determination interval, the other breakpoint behaviors are associated with the original breakpoint behavior to obtain the breakpoint behavior event; If the target user does not have any other breakpoint behaviors within the time determination interval, the original breakpoint behavior is used as the breakpoint behavior event.

8. A breakpoint behavior processing device, characterized in that: The device comprises: A first acquisition module is configured to acquire a breakpoint behavior event of a target user; wherein the breakpoint behavior event is a behavior event generated when the target user triggers an interrupt operation in the insurance application process, and the breakpoint behavior event includes a breakpoint timestamp; The second acquisition module is used to obtain the original user information, original insurance record and original browsing record of the target user; A feature extraction module is used to extract features based on the breakpoint behavior event, the original user information, the original insurance record, the original browsing record and the breakpoint timestamp to obtain breakpoint clue features; A probability prediction module is used to predict the conversion probability based on the breakpoint clue characteristics to obtain a breakpoint conversion rate; wherein the breakpoint conversion rate represents the success rate of promoting the insurance application process of the target user; A data writing module, configured to write the breakpoint behavior event into a preset user breakpoint time wheel according to the breakpoint conversion rate; The breakpoint pushing module is used to push the process of the breakpoint behavior event in the user breakpoint time wheel through a preset seat queue.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the breakpoint behavior processing method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the breakpoint behavior processing method according to any one of claims 1 to 7 is implemented.

Images