Business promotion monitoring method and device and electronic equipment

Abstract

The invention discloses a monitoring method and device for a promoted service and electronic equipment. Relates to the field of artificial intelligence, and the method comprises the steps: obtaining the operation state information of M stage nodes, and judging whether there is an abnormal step in P promotion steps included in a promotion process of a target promotion service according to the operation state information, the M stage nodes being arranged in the promotion process, and the stage nodes being arranged between adjacent promotion steps; under the condition that the abnormal step exists, a first abnormal reason of the abnormal step is identified, an association step is determined from the P promotion steps according to the first abnormal reason, and the association step and the abnormal step have an association relationship; and identifying a second exception reason of the association step, and determining the exception step, the association step, the first exception reason and the second exception reason as monitoring results of the promotion business. According to the application, the problem of low timeliness and accuracy of monitoring the promotion business in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and more specifically, to a monitoring method, device, and electronic device for promoting business. Background Art

[0002] Financial institutions' business promotion efforts, whether focused on launching new products, promoting discounts, or maintaining customer relationships, require the design and execution of a complex series of processes. These often involve the collaboration of multiple departments, including market research, business planning, customer communication, data collection and analysis, and other steps. Because anomalies in business promotion operations directly impact customer satisfaction and product promotion efficiency, monitoring and management of business promotion results is crucial to identify any anomalies.

[0003] Traditional business promotion monitoring often focuses on post-event performance evaluation, such as final metrics like number of participants and conversion rates. While this approach can intuitively reflect overall business performance, it lacks real-time monitoring during execution and the timely detection of anomalies in intermediate links. Once a problem arises at any point in the business process, such as delayed information transmission, data processing errors, or improper resource allocation, these anomalies may persist throughout the entire business cycle and remain undetected until the end of the business. Adjustments and optimizations at this point often have little effect, and the optimal opportunity for intervention has already been missed.

[0004] Therefore, existing technologies have significant limitations in monitoring business promotion and cannot effectively ensure the timeliness and accuracy of the entire closed-loop process from planning to execution to evaluation.

[0005] Currently, no effective solution has been proposed to address the issues of low timeliness and accuracy in monitoring promotion services in related technologies. Summary of the Invention

[0006] The main purpose of this application is to provide a monitoring method, device and electronic equipment for promotion services, so as to solve the problems of low timeliness and accuracy in monitoring promotion services in related technologies.

[0007] To achieve the above-mentioned objectives, according to one aspect of the present application, a method for monitoring a promotion service is provided. The method comprises: obtaining operating status information of M stage nodes, and determining whether there is an abnormal step among P promotion steps included in a promotion process of a target promotion service based on the operating status information, wherein the promotion process is provided with M stage nodes, the stage nodes are provided between adjacent promotion steps, and M and P are positive integers; if there is an abnormal step, identifying a first abnormality cause of the abnormal step, and determining an associated step from the P promotion steps based on the first abnormality cause, wherein the associated step has an associated relationship with the abnormal step; identifying a second abnormality cause of the associated step, and determining the abnormal step, the associated step, the first abnormality cause, and the second abnormality cause as a monitoring result of the promotion service.

[0008] Optionally, M stage nodes are set in the promotion process, including: obtaining the importance of each promotion step to obtain P first importances; calculating the sum of the first importances of every two adjacent promotion steps to obtain T second importances, where T is a positive integer; obtaining the second importance greater than the importance threshold among the T second importances to obtain M third importances, and setting a stage node between the two promotion steps corresponding to each third importance to obtain M stage nodes, and setting the data collection frequency of each stage node according to the third importance.

[0009] Optionally, judging whether there are abnormal steps in the P promotion steps included in the promotion process of the target promotion business based on the running status information includes: for any stage node, obtaining each status data in the running status information, and obtaining the status threshold corresponding to each status data; comparing each status data with the corresponding status threshold in turn to obtain N comparison results, where N is a positive integer; judging whether there are abnormal results in the N comparison results, and if there are abnormal results, determining that the completed promotion step corresponding to the stage node is an abnormal step.

[0010] Optionally, identifying the first abnormal cause of the abnormal step includes: inputting the step name and operation status information of the abnormal step into a first abnormal identification model to obtain a first identification result, wherein the first identification result includes multiple abnormal causes and a first probability of each abnormal cause; obtaining the operation log of the server that executes the abnormal step, and inputting the operation log into a second abnormal identification model to obtain a second identification result, wherein the second identification result includes multiple abnormal causes and a second probability of each abnormal cause; combining the first identification result and the second identification result to obtain a target identification result, and determining the abnormal cause with the largest probability value in the target identification result as the first abnormal cause.

[0011] Optionally, the first abnormality recognition model is trained in the following manner: obtaining historical operation status information of historical stage nodes in the historical process, obtaining Q historical operation status information, and obtaining the abnormal cause of the historical step corresponding to each historical stage node, where Q is a positive integer; determining each historical operation status information and the corresponding abnormal cause as a set of sample data, obtaining Q groups of first sample data, and using the Q groups of first sample data to train the initial recognition model to obtain the first abnormality recognition model: the second abnormality recognition model is trained in the following manner: obtaining historical operation logs on the server to which the historical steps in the historical process belong, obtaining H historical operation logs, and obtaining the abnormal cause of each historical step, where H is a positive integer; determining each historical operation log and the corresponding abnormal cause as a set of sample data, obtaining H groups of second sample data, and using the H groups of second sample data to train the initial recognition model to obtain the second abnormality recognition model.

[0012] Optionally, determining the associated step from P promotion steps according to the first abnormal cause includes: determining the abnormal step and abnormal server indicated by the first abnormal cause; determining the abnormal step indicated by the first abnormal cause as the associated step, and determining the promotion step executed on the abnormal server as the associated step.

[0013] Optionally, the method also includes: determining a first optimization method for the abnormal step based on the first abnormal cause; determining a second optimization method for the associated step based on the second abnormal cause; generating a third optimization method for the promotion process based on the first optimization method and the second optimization method, and optimizing the promotion process through the third optimization method to obtain an updated promotion process.

[0014] To achieve the above-mentioned objectives, according to another aspect of the present application, a monitoring device for a promotion service is provided. The device includes: a first acquisition unit, configured to acquire operating status information of M stage nodes, and determine, based on the operating status information, whether there is an abnormal step among P promotion steps included in a promotion process of a target promotion service, wherein the promotion process is provided with M stage nodes, and the stage nodes are provided between adjacent promotion steps; an identification unit, configured to, if an abnormal step exists, identify a first abnormal cause of the abnormal step, and determine, based on the first abnormal cause, an associated step from the P promotion steps, wherein the associated step has an associated relationship with the abnormal step; and a first determination unit, configured to identify a second abnormal cause of the associated step, and determine the abnormal step, the associated step, the first abnormal cause, and the second abnormal cause as a monitoring result of the promotion service.

[0015] Optionally, the first acquisition unit includes: a first acquisition module, used to acquire the importance of each promotion step, and obtain P first importances; a calculation module, used to calculate the sum of the first importances of each two adjacent promotion steps, and obtain T second importances, where T is a positive integer; a second acquisition module, used to acquire the second importances greater than the importance threshold among the T second importances, and obtain M third importances, and set a stage node between the two promotion steps corresponding to each third importance, and obtain M stage nodes, and set the data collection frequency of each stage node according to the third importance.

[0016] Optionally, the first acquisition unit includes: a third acquisition module, used to obtain each status data in the running status information for any stage node, and obtain the status threshold corresponding to each status data; a comparison module, used to compare each status data with the corresponding status threshold in turn to obtain N comparison results, where N is a positive integer; a judgment module, used to judge whether there are abnormal results in the N comparison results, and if there are abnormal results, determine that the completed promotion step corresponding to the stage node is an abnormal step.

[0017] Optionally, the identification unit includes: a first identification module, used to input the step name and operation status information of the abnormal step into a first abnormal identification model to obtain a first identification result, wherein the first identification result includes multiple abnormal causes and a first probability of each abnormal cause; a second identification module, used to obtain the operation log of the server that executes the abnormal step, and input the operation log into a second abnormal identification model to obtain a second identification result, wherein the second identification result includes multiple abnormal causes and a second probability of each abnormal cause; a combination module, used to combine the first identification result and the second identification result to obtain a target identification result, and determine the abnormal cause with the largest probability value in the target identification result as the first abnormal cause.

[0018] Optionally, the device also includes: the first abnormality recognition model is trained in the following manner: a second acquisition unit is used to obtain historical operation status information of historical stage nodes in the historical process, obtain Q historical operation status information, and obtain the abnormal cause of the historical step corresponding to each historical stage node, where Q is a positive integer; a second determination unit is used to determine each historical operation status information and the corresponding abnormal cause as a group of sample data, obtain Q groups of first sample data, and use the Q groups of first sample data to train the initial recognition model to obtain the first abnormality recognition model: the second abnormality recognition model is trained in the following manner: a third acquisition unit is used to obtain historical operation logs on the server to which the historical steps in the historical process belong, obtain H historical operation logs, and obtain the abnormal cause of each historical step; the third determination unit is used to determine each historical operation log and the corresponding abnormal cause as a group of sample data, obtain H groups of second sample data, and use the H groups of second sample data to train the initial recognition model to obtain the second abnormality recognition model.

[0019] Optionally, the identification unit includes: a first determination module, used to determine the abnormal step and abnormal server indicated by the first abnormal cause; a second determination module, used to determine the abnormal step indicated by the first abnormal cause as an associated step, and determine the promotion step executed on the abnormal server as an associated step.

[0020] Optionally, the device also includes: a fourth determination unit, used to determine a first optimization method for the abnormal step based on the first abnormal cause; a fifth determination unit, used to determine a second optimization method for the associated step based on the second abnormal cause; a generation unit, used to generate a third optimization method for the promotion process based on the first optimization method and the second optimization method, and optimize the promotion process through the third optimization method to obtain an updated promotion process.

[0021] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided, which includes a memory storing an executable program; and a processor for running the program, wherein the above-mentioned monitoring method for promotion services is executed when the program is running.

[0022] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer program product is provided, comprising computer instructions, which implement the steps of the above-mentioned promotion service monitoring method when executed by a processor.

[0023] In an embodiment of the present application, operating status information of M stage nodes is obtained, and based on the operating status information, it is determined whether there is an abnormal step in P promotion steps included in the promotion process of the target promotion business. M stage nodes are set in the promotion process, and the stage nodes are set between adjacent promotion steps. When an abnormal step exists, a first abnormal cause of the abnormal step is identified, and an associated step is determined from the P promotion steps based on the first abnormal cause, wherein the associated step has an associated relationship with the abnormal step. A second abnormal cause of the associated step is identified, and the abnormal step, the associated step, the first abnormal cause, and the second abnormal cause are determined as monitoring results of the promotion business. By adding stage nodes for monitoring in the promotion process and identifying operating status information of the stage nodes, the abnormal step and the abnormal cause are determined, and the associated steps having an associated relationship with the abnormal step are determined. This achieves the purpose of accurately identifying abnormal steps in each step of the promotion process. By acquiring and processing the abnormal steps in the steps in real time, the effect of monitoring the process of the promotion process is achieved, thereby achieving the technical effect of improving the timeliness and accuracy of monitoring the promotion business, thereby solving the technical problem of low timeliness and accuracy of monitoring the promotion business in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0025] Figure 1 A hardware structure block diagram of a computer terminal for implementing a monitoring method for promoting business is shown;

[0026] Figure 2 This is a flow chart of a method for monitoring promotion services provided in Example 1 of the present application;

[0027] Figure 3 2 is a schematic diagram of a monitoring device for promoting services provided in Example 2 of the present application;

[0028] Figure 4 This is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0030] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims 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 a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising 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.

[0032] It should be noted that the monitoring method, device and electronic device for the promotion business determined in this disclosure can be used in the field of artificial intelligence, and can also be used in any field other than the field of artificial intelligence. The application field of the monitoring method, device and electronic device for the promotion business determined in this disclosure is not limited.

[0033] It should be noted that the collected information, user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) used in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize use or refuse use. If the user chooses to refuse, the expert decision-making process will be entered. For example, an interface is set up between this system and relevant users or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or institution through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or institution.

[0034] The embodiments or examples of the present disclosure are not exhaustive, but are merely illustrations of some embodiments or examples, and are not intended to be specific limitations on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment or example can be implemented as an independent example, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be arbitrarily combined; in addition, the various embodiments or examples can be arbitrarily combined. For example, some or all steps of different embodiments or examples can be arbitrarily combined, and a certain embodiment or example can be arbitrarily combined with the optional methods or optional examples of other embodiments or examples.

[0035] For ease of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0036] RPA robot: Robotic Process Automation, robotic process automation.

[0037] Example 1

[0038] According to an embodiment of the present application, an embodiment of a monitoring method for promoting business is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0039] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal for implementing a monitoring method for promoting business is shown in FIG. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (illustrated as 102a, 102b, ..., 102n in the figure) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0040] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0041] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the promotion business monitoring method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the above-mentioned promotion business monitoring method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0042] The transmission device 106 is configured to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0043] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0044] Under the above operating environment, this application provides Figure 2 The monitoring method of the promotion business shown. Figure 2 Flowchart of the monitoring method for promotion services provided in Example 1 of the present application. Figure 2 As shown, the method includes:

[0045] Step S201, obtain the operating status information of M stage nodes, and determine whether there are abnormal steps in the P promotion steps included in the promotion process of the target promotion business based on the operating status information, wherein M stage nodes are set in the promotion process, and the stage nodes are set between adjacent promotion steps.

[0046] It should be noted that stage nodes are monitoring points set at key stages of a financial institution's promotion process. These nodes are distributed across P promotion steps and are used to collect the operational status of each step. Operational status information, which represents various performance indicators in the business process, such as task execution time and participant response data, can be used to assess the health of each step. Promotion steps are components of the entire promotion process and form the fundamental unit of the entire promotion closed loop. Abnormal steps are promotion steps whose operational status information displays behavior or performance that is inconsistent with expectations. This may be due to technical failures, operational errors, external interference, and other factors.

[0047] Specifically, the execution entity of this embodiment can be a business monitoring system, and an RPA robot can be deployed in the business monitoring system to perform node monitoring operations. First, it is necessary to determine the promotion steps included in the business promotion process and set stage nodes between adjacent steps for monitoring. The stage node can obtain information related to the execution result of the previous step, such as the time information of the end of execution, the result data obtained by execution, etc., as well as the execution information of the next execution step, such as whether to start execution, the time to start execution, etc., so that the information of the previous step and the information of the next step are combined into the operation status information of the stage node.

[0048] Furthermore, after setting the stage nodes, RPA robots can be used to monitor the operating status information of each stage node. The RPA robots can perform data capture and performance testing to obtain accurate operating status information. The obtained operating status information can be stored in the central database for subsequent analysis. The RPA robot can compare each indicator one by one according to the preset operating status information standards. Once it is found that a certain indicator deviates from the normal range, the anomaly detection mechanism is activated. Through multi-dimensional data analysis, it is determined whether the deviation is sufficient to constitute an abnormal step, thereby ensuring the accuracy of anomaly detection.

[0049] For example, a financial institution held a product launch event. The promotion process included five steps: planning, pre-launch, main promotion, follow-up, and evaluation, with a total of four phases. An RPA robot was deployed to collect operational status information at each of these phases, such as social media engagement rates and email open rates. If the monitored email open rate was significantly lower than the historical average, it would be marked as an abnormal step, indicating that the pre-launch step may have had poor email promotion effectiveness, and thus the pre-launch step was identified as an abnormal step.

[0050] Step S202: in the case where an abnormal step exists, identifying a first abnormal cause of the abnormal step, and determining a related step from the P generalized steps according to the first abnormal cause, wherein the related step has an association relationship with the abnormal step.

[0051] It should be noted that related steps are other generalized steps that have a causal relationship or mutual dependence with the abnormal steps. Problems with the abnormal steps may indirectly affect the normal operation of these steps.

[0052] Specifically, after confirming that a promotion step is abnormal, the primary cause of the abnormal step can be identified through the operational status information of the stage node, by tracing back system logs, comparing historical data, executing model predictions, and other methods. At the same time, based on the specific content of the primary cause of the abnormality, the scope and extent of its impact on the preceding and following steps can be analyzed to determine which steps are directly or indirectly related to it, namely the associated steps. This not only enables an immediate response to the current abnormal situation, but also allows the screening and processing of associated steps that have a correlation with the abnormal step, thereby preventing the abnormal step from affecting the associated steps and reducing the scope of the abnormal step's impact.

[0053] For example, if the warm-up step is determined to be an abnormal step, further analysis can determine that the first abnormal cause is that the email template design is too complex, resulting in a long loading time. At this time, since the email fails to convey information in a timely and effective manner, it may affect the user participation in the next step of promotion business. Therefore, the main promotion step can be marked as an associated step to complete the identification and judgment of the associated steps.

[0054] Step S203 , identifying the second abnormal reason of the associated step, and determining the abnormal step, the associated step, the first abnormal reason and the second abnormal reason as the monitoring result of the promotion business.

[0055] It should be noted that, since there may also be abnormalities in the associated steps, it is possible to identify whether there are abnormalities in the associated steps, and when there are abnormalities in the associated steps, identify the second abnormal cause of the associated steps, such as identifying the second abnormal cause that causes the performance of the associated steps to degrade or the risk to increase. After determining the second abnormal cause, the information obtained in the above steps can be integrated into the monitoring results and displayed together with the abnormal steps and their first abnormal causes to form a complete promotion process health report, thereby completing the monitoring of each step of the promotion business. It can not only instantly discover and identify abnormal steps in the business promotion process, but also determine the abnormal causes of the abnormal steps and the associated steps within the affected range, and then promptly discover abnormal phenomena in the promotion process when there are no abnormalities in the results of the business promotion operations, so that the abnormal steps with abnormal phenomena can be promptly handled to ensure the normal progress of the promotion process.

[0056] The monitoring method for promotion services provided in an embodiment of the present application obtains operating status information of M stage nodes and determines whether there is an abnormal step in P promotion steps included in a promotion process of a target promotion service based on the operating status information, wherein M stage nodes are provided in the promotion process and are provided between adjacent promotion steps. When an abnormal step exists, a first abnormal cause of the abnormal step is identified and, based on the first abnormal cause, an associated step is determined from the P promotion steps, wherein the associated step has an associated relationship with the abnormal step. A second abnormal cause of the associated step is identified and the abnormal step, the associated step, the first abnormal cause, and the second abnormal cause are determined as monitoring results of the promotion service. By adding stage nodes for monitoring in the promotion process and identifying operating status information of the stage nodes, the abnormal step and the abnormal cause are determined, and the associated steps having an associated relationship with the abnormal step are determined. This achieves the purpose of accurately identifying abnormal steps in each step of the promotion process. By acquiring and processing abnormal steps in the steps in real time, the effect of monitoring the promotion process is achieved, thereby achieving the technical effect of improving the timeliness and accuracy of monitoring the promotion service, thereby solving the technical problem of low timeliness and accuracy of monitoring the promotion service in the related art.

[0057] In order to accurately set the stage nodes and reduce the workload of monitoring operations while ensuring the monitoring accuracy, optionally, in the monitoring method of the promotion business provided in the embodiment of the present application, M stage nodes are set in the promotion process, including: obtaining the importance of each promotion step to obtain P first importances; calculating the sum of the first importances of each two adjacent promotion steps to obtain T second importances, where T is a positive integer; obtaining the second importance greater than the importance threshold among the T second importances to obtain M third importances, and setting a stage node between the two promotion steps corresponding to each third importance to obtain M stage nodes, and setting the data collection frequency of each stage node according to the third importance.

[0058] Specifically, when monitoring the business promotion process, you first need to set the stage nodes. When setting the stage nodes, you first need to evaluate the importance of each individual promotion step in the entire promotion process, so as to express the degree of influence of each step on the final promotion goal in a quantitative form, that is, to obtain the importance of each promotion step, and finally obtain the first importance of each promotion step, and then distinguish the importance of each promotion step according to the first importance.

[0059] Furthermore, in order to ensure that the set stage nodes are all located between important steps, it is necessary to calculate the comprehensive importance of each pair of adjacent promotion steps, that is, add the first importance of each pair of adjacent promotion steps to obtain the second importance, and then use the value of the second importance to identify the importance superposition between adjacent steps in the process, and then identify the steps that will have a significant impact on the entire process, so as to determine the points where stage nodes need to be set.

[0060] Furthermore, after obtaining the second importance of each pair of adjacent promotion steps, it is necessary to screen the node setting positions by setting the importance threshold, retain the setting points with higher importance, and then determine the positions of the M stage nodes. In this way, while ensuring the monitoring accuracy, the workload required for the monitoring operation can be significantly reduced, avoiding the waste of resources caused by monitoring all steps with the same intensity.

[0061] It should be noted that after determining the stage nodes, the data collection frequency of each stage node can be dynamically adjusted according to the size of the third importance to ensure more intensive monitoring of the most critical links, while the monitoring frequency of relatively minor links can be appropriately reduced, thereby ensuring the rationality of the operation data monitoring operation.

[0062] Through this embodiment, by accurately identifying the most noteworthy stages in the business promotion process and flexibly adjusting the monitoring strategy according to the importance of the stage, the comprehensiveness of monitoring and the economy of resources are effectively balanced, the efficiency and accuracy of financial institutions in the business promotion process are improved, ineffective work is reduced, and the rational allocation of resources is ensured.

[0063] For example, a financial institution held a business promotion event. The promotion process consisted of six steps: market research, event planning, customer invitation, online registration, gift distribution, and performance evaluation. First, through qualitative and quantitative analysis, the importance of each step was determined. Online registration and gift distribution were assigned a higher first importance. Next, the sum of the importance of each adjacent step was calculated to obtain five second importances: market research + event planning, event planning + customer invitation, customer invitation + online registration, online registration + gift distribution, and gift distribution + performance evaluation. By setting importance thresholds, it was determined that the second importance of the "online registration + gift distribution" and "customer invitation + online registration" stages exceeded the threshold. Therefore, a stage node was set for each of these stages. Furthermore, the frequency of data collection was determined based on the importance of each stage, ensuring immediate response to any anomalies that might arise between steps. This mechanism enables financial institutions to accurately capture the operational status of key links during the business promotion process, promptly identify problems, and rapidly implement adjustments. This significantly improves the sophistication and flexibility of the business promotion process, while also reducing unnecessary monitoring operations and lowering business promotion costs.

[0064] In order to accurately determine the abnormal steps, optionally, in the monitoring method of the promotion business provided in the embodiment of the present application, judging whether there are abnormal steps in the P promotion steps included in the promotion process of the target promotion business based on the operation status information includes: for any stage node, obtaining each status data in the operation status information, and obtaining the status threshold corresponding to each status data; comparing each status data with the corresponding status threshold in turn to obtain N comparison results, where N is a positive integer; judging whether there are abnormal results in the N comparison results, and if there are abnormal results, determining that the completed promotion step corresponding to the stage node is an abnormal step.

[0065] Specifically, when identifying abnormal steps, the operating status information of each stage node can be obtained, and status data can be obtained from this information. The status data can cover various aspects of business execution at the stage node, such as response time, error rate, resource consumption level, data transmission rate, etc. By obtaining the performance indicators in the status data, the health status of the promotion step at the stage node can be evaluated based on the performance indicators and the thresholds corresponding to each performance indicator.

[0066] After obtaining all the status data of the stage nodes and their corresponding thresholds, the system will compare the differences between each status data and the threshold one by one, and then determine whether it exceeds the normal range based on the comparison results. Among them, the comparison results not only include the judgment of whether it is abnormal, but also provide quantitative information on the degree of abnormality, such as the percentage or absolute value exceeding the threshold, thereby further guiding the subsequent abnormal cause analysis steps.

[0067] Finally, the system analyzes the N comparison results to determine if any data exceeds the corresponding status threshold, which is considered an abnormal comparison result. If an abnormal comparison result exists, the completed promotion step corresponding to the stage node can be determined as an abnormal step, thus completing the rapid and accurate identification of abnormal steps.

[0068] For example, in a certain promotional campaign, the process consists of six steps: market research, product design, advertising, user registration, review and approval, and loan disbursement. A stage M1 node is set between user registration and review and approval to monitor the smooth transition between these two steps. The system automatically obtains operational status information for the M1 node, which may include the response time of the user registration page (represented as status data A) and the review and approval pass rate for registered users (represented as status data B). For status data A, the system sets a status threshold, such as 1 second, and for status data B, a threshold of 90%, indicating that a review and approval pass rate below 90% is also considered abnormal. The system compares status data A with the 1-second threshold and finds an average response time of 1.2 seconds. It then compares status data B with the 90% threshold and finds an review and approval pass rate of 88%. In this case, since both status data A and status data B exceed their respective thresholds, the system determines that the M1 node has an abnormal result and thus classifies the user registration step as an abnormal step.

[0069] This embodiment achieves the technical effect of accurately detecting promotion steps by monitoring and comparing status data with preset thresholds in real time at key stage nodes of the promotion process, accurately and efficiently identifying abnormal steps that lead to process abnormalities.

[0070] In order to accurately identify the abnormal cause of the abnormal step, optionally, in the monitoring method for promoting business provided in an embodiment of the present application, identifying the first abnormal cause of the abnormal step includes: inputting the step name and operation status information of the abnormal step into a first abnormal identification model to obtain a first identification result, wherein the first identification result includes multiple abnormal causes and a first probability of each abnormal cause; obtaining the operation log of the server that executes the abnormal step, and inputting the operation log into a second abnormal identification model to obtain a second identification result, wherein the second identification result includes multiple abnormal causes and a second probability of each abnormal cause; combining the first identification result and the second identification result to obtain a target identification result, and determining the abnormal cause with the largest probability value in the target identification result as the first abnormal cause.

[0071] It should be noted that the first anomaly identification model is a machine learning-based model that predicts possible anomaly causes and their likelihood based on the operational status information of the generalization step, and outputs multiple anomaly causes and their corresponding first probabilities. The second anomaly identification model is a machine learning-based model that takes server operation logs as input and outputs multiple anomaly causes and their corresponding second probabilities, used to analyze the anomaly causes at the underlying system level.

[0072] Specifically, after identifying the abnormal steps, it is necessary to analyze the abnormal causes of each abnormal step. First, the step name and operation status information of the abnormal step are passed as input to the first abnormal recognition model, where the operation status information includes but is not limited to task execution time, resource usage, etc. These data reflect the performance of the step during the actual execution process, thereby obtaining the first recognition result. The first abnormal recognition model is trained based on historical data and can predict multiple possible causes of abnormal steps and their respective first probabilities, that is, the first recognition result, by analyzing this information.

[0073] Furthermore, after obtaining the first probability, the system also needs to obtain the operation log from the server responsible for executing the abnormal step, where the operation log contains detailed operation records of the server within a specific time period, including but not limited to system calls, error messages, resource allocation and consumption data, etc., and input the log data into the second abnormality recognition model. The model analyzes the possible causes of the abnormality from the perspective of the underlying hardware and software, and gives the second probability of each abnormal cause.

[0074] After obtaining the first recognition result and the second recognition result, the first recognition result and the second recognition result can be combined to form a target recognition result, and then the first abnormal cause of the abnormal step can be determined based on the target recognition result. When the first recognition result and the second recognition result are combined to form the target recognition result, the probabilities of the same abnormal cause in the two recognition results can be added to obtain the final probability of the abnormal cause, and the final probabilities of each abnormal cause can be used to sort them, so as to determine the abnormal cause with the largest probability value as the first abnormal cause, so as to ensure that the first abnormal cause finally determined is the most likely abnormal cause, and then by combining the analysis at the business level and the system level, and the predictive ability of the machine learning model, the accuracy and credibility of the abnormal cause identification are improved.

[0075] This embodiment analyzes the operation information collected by the node and the operation log of the operation server respectively, and synthesizes the analysis results to obtain the abnormal cause of the abnormal step, thereby ensuring accurate identification of the abnormal cause.

[0076] In order to ensure the accuracy of the model, optionally, in the monitoring method for promotion services provided in an embodiment of the present application, the first abnormality recognition model is trained in the following manner: obtaining historical operation status information of historical stage nodes in the historical process, obtaining Q historical operation status information, and obtaining the abnormal cause of the historical step corresponding to each historical stage node, where Q is a positive integer; determining each historical operation status information and the corresponding abnormal cause as a group of sample data, obtaining Q groups of first sample data, and using the Q groups of first sample data to train the initial recognition model to obtain the first abnormality recognition model: the second abnormality recognition model is trained in the following manner: obtaining historical operation logs on the server to which the historical steps in the historical process belong, obtaining H historical operation logs, and obtaining the abnormal cause of each historical step; determining each historical operation log and the corresponding abnormal cause as a group of sample data, obtaining H groups of second sample data, and using the H groups of second sample data to train the initial recognition model to obtain the second abnormality recognition model.

[0077] It should be noted that historical operation status information refers to the operational data and indicators collected by nodes at various stages of past promotion activities, including but not limited to task execution time, resource usage, and error rates. Historical operation logs record the detailed operation history of the server during the promotion process, covering system calls, exception information, resource allocation changes, and more.

[0078] Specifically, when using the first anomaly identification model to identify anomaly causes, the system extracts operational status information recorded at each stage node of each historical promotion business from historical promotion operations. This information is used to record the execution status of past promotion steps. At the same time, the system collects anomalies and their specific causes that occurred during the promotion steps corresponding to each historical stage node, providing actual anomaly cases for model training. This allows the model to learn the relationship between operational status indicators and anomaly causes, thereby improving the accuracy of the model's prediction of anomaly causes.

[0079] After acquiring multiple historical operational status information and its corresponding anomaly causes, the system pairs each set of historical operational status information with the anomaly cause, generating multiple sets of first sample data. This sample data is then used to train an initial anomaly recognition model. By learning from the historical data, the model learns how to predict the possible anomaly causes and probabilities of abnormal steps based on the current operational status information. Through this training process, the model can more accurately identify potential anomalies in the promotion process based on historical experience, providing technical support for rapid response and resolution.

[0080] Furthermore, the second anomaly recognition model also needs to be trained, and it is also necessary to obtain the historical operation logs on the server to which the historical steps in the historical process belong, as well as the abnormal reasons for each historical step, so as to associate the historical operation logs corresponding to each step with the abnormal reasons, obtain multiple second sample data, and then use the second sample data to train the model to obtain the second anomaly recognition model.

[0081] This embodiment obtains historical data at historical moments to form sample data, and uses the sample data to train the first anomaly recognition model and the second anomaly recognition model, thereby ensuring that the model can obtain accurate anomaly cause recognition results based on different inputs.

[0082] Optionally, in the monitoring method for promoting services provided in an embodiment of the present application, determining the associated step from P promotion steps according to the first abnormal cause includes: determining the abnormal step and the abnormal server indicated by the first abnormal cause; determining the abnormal step indicated by the first abnormal cause as the associated step, and determining the promotion step executed on the abnormal server as the associated step.

[0083] Specifically, after determining the first abnormal cause of the abnormal step, it is necessary to analyze the first abnormal cause so as to analyze whether there are related steps based on the first abnormal cause, that is, whether the abnormal cause of the abnormal step is related to other steps. When it is determined that the abnormal cause of the abnormal step is related to other steps based on the first abnormal cause, it is necessary to determine the related steps that cause the abnormal step to be abnormal based on the first abnormal cause, so as to determine the related steps in the business promotion process that also have abnormalities.

[0084] It should be noted that the reason for the abnormality of the abnormal step is not only the influence of other steps, but also the influence of other servers on the abnormal step. At this time, it is also possible to analyze whether there is an abnormal server based on the first abnormal cause. At this time, if it is determined that the server is abnormal, the steps running on the server may also be abnormal. At this time, it is necessary to determine the promotion steps executed on the abnormal server as related steps, so as to ensure accurate and comprehensive identification of the related steps.

[0085] This embodiment identifies associated steps that may have abnormalities based on the content contained in the first abnormality cause, so that the associated steps can be processed in advance when no obvious abnormalities occur in the associated steps, thereby reducing the probability of abnormalities in the business promotion process and improving the accuracy of the process operation.

[0086] Optionally, in the monitoring method for promotion services provided in the embodiment of the present application, the method also includes: determining a first optimization method for the abnormal step based on the first abnormal cause; determining a second optimization method for the associated step based on the second abnormal cause; generating a third optimization method for the promotion process based on the first optimization method and the second optimization method, and optimizing the promotion process through the third optimization method to obtain an updated promotion process.

[0087] Specifically, after obtaining the first exception cause, it is necessary to determine the first optimization method for the abnormal step based on the first exception cause. Similarly, it is necessary to determine the second optimization method for the related steps based on the second exception cause. The first optimization method may involve modifying a part of the business process, adjusting resource allocation, optimizing algorithms or code logic, etc. The second optimization method focuses more on preventing the potential impact of the abnormal cause on the related steps and ensuring the continuity and stability of the overall process. This forward-looking optimization can include strengthening the monitoring of specific steps, increasing redundant resources, optimizing the data exchange mechanism across steps, etc., with the aim of building a more robust process framework and improving the system's resistance to abnormalities.

[0088] It should be noted that the process of determining the optimization method based on the cause of the abnormality can be determined through a model or a comparison table. For example, the optimization method of the cause of the abnormality can be determined through a model, or the optimization method can be determined based on a comparison table of preset causes of abnormality and optimization methods. This embodiment does not limit the process of determining the optimization method based on the cause of the abnormality.

[0089] Afterward, the first and second optimization methods can be combined to form a complete third optimization method. For example, the third optimization method can be formed by removing the common processes in the first and second optimization methods and taking the union of the two methods as the third optimization method, or by superimposing the first and second optimization methods to form a more comprehensive third optimization method. This third optimization method not only fixes the current abnormal steps but also strengthens the risk resistance of the entire process. By implementing optimization operations, the promotion process is updated, thereby improving the long-term efficiency and security of the business promotion process.

[0090] For example, during a business promotion, a financial institution encountered unusually slow loading speeds on its product display page. Through monitoring by RPA robots and analysis using the first anomaly recognition model, the primary cause of the anomaly was determined to be slow loading of image resources. To address this issue, the first optimization approach was designed: optimizing the image resource loading strategy. For example, using methods like image compression and asynchronous loading directly resolved the product display page loading speed issue.

[0091] However, further analysis identified a secondary cause of the anomaly: uneven server resource allocation. This not only impacted the "Product Display Page" but also potentially caused delays or freezes in related steps like "Online Consultation" and "User Registration" during peak hours. To address this, the system implemented a secondary optimization approach, including dynamically adjusting server resource allocation, optimizing traffic scheduling mechanisms, and enhancing load balancing between servers, to ensure these related steps continued to run smoothly even in the face of high concurrency.

[0092] Finally, by combining the first and second optimization methods, a third optimization method was formed, which included adjustments to the "product display page" loading strategy and overall optimization of server resource allocation. The system automatically performed resource configuration adjustments and guided the operation and maintenance team to optimize the network architecture and load balancing strategy, effectively improving the response speed and user experience of the entire promotion process.

[0093] This example uses intelligent methods to identify anomaly causes and design targeted optimization strategies to effectively prevent and resolve anomalies. This approach not only reduces troubleshooting time but also improves the reliability of future promotional campaigns through preventative optimization, reducing process interruptions caused by technical issues.

[0094] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0095] Example 2

[0096] The embodiment of the present application further provides a monitoring device for promotion services. It should be noted that the monitoring device for promotion services in the embodiment of the present application can be used to execute the monitoring method for promotion services provided in the above embodiment. The monitoring device for promotion services provided in the embodiment of the present application is introduced below.

[0097] According to an embodiment of the present application, a device for implementing the above-mentioned monitoring method for promotion services is also provided. Figure 3 Schematic diagram of a monitoring device for promoting services provided in Example 2 of the present application. Figure 3 As shown, the device includes:

[0098] The first acquisition unit 31 is used to obtain the operating status information of M stage nodes, and determine whether there is an abnormal step in the P promotion steps included in the promotion process of the target promotion business based on the operating status information, wherein M stage nodes are set in the promotion process, and the stage nodes are set between adjacent promotion steps.

[0099] The identification unit 32 is used to identify a first abnormal cause of the abnormal step when there is an abnormal step, and determine a related step from the P generalized steps according to the first abnormal cause, wherein the related step has an association relationship with the abnormal step.

[0100] The first determining unit 33 is configured to identify the second abnormal reason of the associated step, and determine the abnormal step, the associated step, the first abnormal reason and the second abnormal reason as monitoring results of the promotion service.

[0101] The monitoring device for promotion services provided in the embodiment of the present application obtains the operating status information of M stage nodes through the first acquisition unit 31, and determines whether there is an abnormal step in the P promotion steps included in the promotion process of the target promotion service based on the operating status information, wherein M stage nodes are set in the promotion process, and the stage nodes are set between adjacent promotion steps; the identification unit 32 identifies the first abnormal cause of the abnormal step when there is an abnormal step, and determines the associated step from the P promotion steps based on the first abnormal cause, wherein the associated step has an associated relationship with the abnormal step; the first determination unit 33 identifies the second abnormal cause of the associated step, and determines the abnormal step, the associated step, the first abnormal cause, and the second abnormal cause as the monitoring result of the promotion service. By adding stage nodes for monitoring in the promotion process and identifying the operating status information of the stage nodes, the abnormal steps and the causes of the abnormalities are determined, and the associated steps with the abnormal steps are determined. The purpose of accurately identifying the abnormal steps in each step of the promotion process is achieved. By obtaining the abnormal steps in the steps in real time and processing them, the effect of monitoring the process of the promotion process is achieved, thereby achieving the technical effect of improving the timeliness and accuracy of monitoring the promotion business, and thus solving the technical problem of low timeliness and accuracy of monitoring the promotion business in related technologies.

[0102] Optionally, in the monitoring device for the promotion business provided in the embodiment of the present application, the first acquisition unit 31 includes: a first acquisition module, used to acquire the importance of each promotion step, and obtain P first importances; a calculation module, used to calculate the sum of the first importances of each two adjacent promotion steps, and obtain T second importances, where T is a positive integer; a second acquisition module, used to acquire the second importance greater than the importance threshold among the T second importances, and obtain M third importances, and set a stage node between the two promotion steps corresponding to each third importance, and obtain M stage nodes, and set the data collection frequency of each stage node according to the third importance.

[0103] Optionally, in the monitoring device for promotion services provided in the embodiment of the present application, the first acquisition unit 31 includes: a third acquisition module, used to obtain, for any stage node, each status data in the running status information, and obtain the status threshold corresponding to each status data; a comparison module, used to compare each status data with the corresponding status threshold in turn to obtain N comparison results, where N is a positive integer; a judgment module, used to judge whether there are abnormal results in the N comparison results, and if there are abnormal results, determine that the completed promotion step corresponding to the stage node is an abnormal step.

[0104] Optionally, in the monitoring device for promoting business provided in the embodiment of the present application, the identification unit 32 includes: a first identification module, used to input the step name and operation status information of the abnormal step into a first abnormal identification model to obtain a first identification result, wherein the first identification result includes multiple abnormal causes and a first probability of each abnormal cause; a second identification module, used to obtain the operation log of the server that executes the abnormal step, and input the operation log into a second abnormal identification model to obtain a second identification result, wherein the second identification result includes multiple abnormal causes and a second probability of each abnormal cause; a combination module, used to combine the first identification result and the second identification result to obtain a target identification result, and determine the abnormal cause with the largest probability value in the target identification result as the first abnormal cause.

[0105] Optionally, in the monitoring device for promoting services provided in an embodiment of the present application, the first abnormality recognition model is trained in the following manner: a second acquisition unit is used to acquire historical operating status information of historical stage nodes in the historical process, obtain Q historical operating status information, and obtain the abnormal cause of the historical step corresponding to each historical stage node, where Q is a positive integer; a second determination unit is used to determine each historical operating status information and the corresponding abnormal cause as a group of sample data, obtain Q groups of first sample data, and use the Q groups of first sample data to train the initial recognition model to obtain the first abnormality recognition model: the second abnormality recognition model is trained in the following manner: a third acquisition unit is used to acquire historical operating logs on the server to which the historical steps in the historical process belong, obtain H historical operating logs, and obtain the abnormal cause of each historical step; a third determination unit is used to determine each historical operating log and the corresponding abnormal cause as a group of sample data, obtain H groups of second sample data, and use the H groups of second sample data to train the initial recognition model to obtain the second abnormality recognition model.

[0106] Optionally, in the monitoring device for promoting services provided in an embodiment of the present application, the identification unit 32 includes: a first determination module for determining the abnormal step and abnormal server indicated by the first abnormal cause; a second determination module for determining the abnormal step indicated by the first abnormal cause as an associated step, and determining the promotion step executed on the abnormal server as an associated step.

[0107] Optionally, in the monitoring device for promotion services provided in the embodiment of the present application, the device also includes: a fourth determination unit, used to determine a first optimization method for the abnormal step based on the first abnormal cause; a fifth determination unit, used to determine a second optimization method for the associated step based on the second abnormal cause; a generation unit, used to generate a third optimization method for the promotion process based on the first optimization method and the second optimization method, and optimize the promotion process through the third optimization method to obtain an updated promotion process.

[0108] It should be noted that the first acquisition unit 31, identification unit 32, and first determination unit 33 correspond to steps S201 to S203 in Example 1. The examples and application scenarios implemented by the above-mentioned units and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the above-mentioned modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above-mentioned modules can also be part of the device and can be run in the computer terminal 10 provided in Example 1.

[0109] Example 3

[0110] An embodiment of the present application may provide an electronic device, Figure 4 This is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 Only one is shown) processor 1002, memory 1004, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0111] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implementing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal 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 a combination thereof.

[0112] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtain the operating status information of M stage nodes, and determine whether there is an abnormal step in the P promotion steps included in the promotion process of the target promotion business based on the operating status information, wherein M stage nodes are set in the promotion process, and the stage nodes are set between adjacent promotion steps; in the case of an abnormal step, identify the first abnormal cause of the abnormal step, and determine the associated step from the P promotion steps based on the first abnormal cause, wherein the associated step has an associated relationship with the abnormal step; identify the second abnormal cause of the associated step, and determine the abnormal step, the associated step, the first abnormal cause and the second abnormal cause as the monitoring result of the promotion business.

[0113] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the importance of each promotion step to obtain P first importances; calculate the sum of the first importances of each two adjacent promotion steps to obtain T second importances, where T is a positive integer; obtain the second importance greater than the importance threshold among the T second importances to obtain M third importances, and set a stage node between the two promotion steps corresponding to each third importance to obtain M stage nodes, and set the data collection frequency of each stage node according to the third importance.

[0114] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: for any stage node, obtain each status data in the running status information, and obtain the status threshold corresponding to each status data; compare each status data with the corresponding status threshold in turn to obtain N comparison results, where N is a positive integer; determine whether there are abnormal results in the N comparison results, and if there are abnormal results, determine that the completed promotion step corresponding to the stage node is an abnormal step.

[0115] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: input the step name and operation status information of the abnormal step into the first abnormal recognition model to obtain a first recognition result, wherein the first recognition result includes multiple abnormal causes and a first probability of each abnormal cause; obtain the operation log of the server that executes the abnormal step, and input the operation log into the second abnormal recognition model to obtain a second recognition result, wherein the second recognition result includes multiple abnormal causes and a second probability of each abnormal cause; combine the first recognition result and the second recognition result to obtain a target recognition result, and determine the abnormal cause with the largest probability value in the target recognition result as the first abnormal cause.

[0116] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: The first abnormality recognition model is trained in the following manner: the historical operation status information of the historical stage node in the historical process is obtained to obtain Q historical operation status information, and the abnormal cause of the historical step corresponding to each historical stage node is obtained, where Q is a positive integer; each historical operation status information and the corresponding abnormal cause are determined as a group of sample data to obtain Q groups of first sample data, and the Q groups of first sample data are used to train the initial recognition model to obtain the first abnormality recognition model: The second abnormality recognition model is trained in the following manner: the historical operation log on the server to which the historical step in the historical process belongs is obtained to obtain H historical operation logs, and the abnormal cause of each historical step is obtained; each historical operation log and the corresponding abnormal cause are determined as a group of sample data to obtain H groups of second sample data, and the initial recognition model is trained using the H groups of second sample data to obtain the second abnormality recognition model.

[0117] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: determine the abnormal step and abnormal server indicated by the first abnormal cause; determine the abnormal step indicated by the first abnormal cause as an associated step, and determine the promotion step executed on the abnormal server as an associated step.

[0118] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: determine the first optimization method of the abnormal step based on the first abnormal cause; determine the second optimization method of the associated step based on the second abnormal cause; generate a third optimization method for the promotion process based on the first optimization method and the second optimization method, and optimize the promotion process through the third optimization method to obtain an updated promotion process.

[0119] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, or other terminal devices. Figure 4 It does not limit the structure of the above electronic device. For example, the electronic device may also include Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 4 Different configurations shown.

[0120] A person skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0121] Example 4

[0122] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the promotion service monitoring method provided in the first embodiment.

[0123] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0124] An embodiment of the present application further provides a computer program product, which, when executed on a data processing device, is suitable for executing the steps of the monitoring method for promoting a service.

[0125] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program. When the executable program runs, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned monitoring method for promotion services.

[0126] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0127] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the 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 units or modules, which can be electrical or other forms.

[0129] The units described 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 to achieve the purpose of this embodiment according to actual needs.

[0130] 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.

[0131] 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, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0132] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A monitoring method for promoting a business, characterized in that: include: Obtaining operation status information of M stage nodes, and determining whether there are any abnormal steps in P promotion steps included in the promotion process of the target promotion business based on the operation status information, wherein the promotion process is provided with the M stage nodes, the stage nodes are provided between adjacent promotion steps, and M and P are positive integers; In the case where the abnormal step exists, identifying a first abnormal cause of the abnormal step, and determining a related step from the P generalized steps according to the first abnormal cause, wherein the related step has an associated relationship with the abnormal step; A second abnormal reason of the association step is identified, and the abnormal step, the association step, the first abnormal reason, and the second abnormal reason are determined as monitoring results of the promotion business.

2. The method according to claim 1, characterized in that The M stage nodes provided in the promotion process include: Obtain the importance of each promotion step and obtain P first importances; Calculate the sum of the first importance of each two adjacent generalization steps to obtain T second importances, where T is a positive integer; Obtain the second importance greater than the importance threshold among the T second importances, obtain M third importances, and set a stage node between the two promotion steps corresponding to each third importance to obtain M stage nodes, and set the data collection frequency of each stage node according to the third importance.

3. The method according to claim 1, characterized in that Judging whether there is an abnormal step in the P promotion steps included in the promotion process of the target promotion business according to the operation status information includes: For any stage node, obtain each state data in the running state information, and obtain the state threshold corresponding to each state data; Compare each state data with the corresponding state threshold in turn to obtain N comparison results, where N is a positive integer; It is determined whether there is an abnormal result in the N comparison results, and if there is an abnormal result, the completed promotion step corresponding to the stage node is determined to be the abnormal step.

4. The method according to claim 1, wherein The first abnormal cause of the abnormal step of identifying the abnormal step includes: Inputting the step name of the abnormal step and the operation status information into a first abnormality recognition model to obtain a first recognition result, wherein the first recognition result includes multiple abnormal causes and a first probability of each abnormal cause; Obtaining an operation log of the server that executes the abnormal step, and inputting the operation log into a second abnormality recognition model to obtain a second recognition result, wherein the second recognition result includes multiple abnormal causes and a second probability of each abnormal cause; The first recognition result and the second recognition result are combined to obtain a target recognition result, and the abnormal cause with the largest probability value in the target recognition result is determined as the first abnormal cause.

5. The method according to claim 4, characterized in that The first anomaly recognition model is trained in the following way: Obtain the historical running status information of the historical stage nodes in the historical process, obtain Q historical running status information, and obtain the abnormal cause of the historical step corresponding to each historical stage node, where Q is a positive integer; Each historical operation status information and the corresponding abnormal cause are determined as a set of sample data to obtain Q sets of first sample data, and the Q sets of first sample data are used to train the initial recognition model to obtain the first abnormality recognition model: The second anomaly recognition model is trained in the following way: Obtain the historical operation logs on the server to which the historical steps in the historical process belong, obtain H historical operation logs, and obtain the exception cause of each historical step, where H is a positive integer; Each historical operation log and the corresponding abnormal cause are determined as a group of sample data to obtain H groups of second sample data, and the H groups of second sample data are used to train the initial recognition model to obtain the second abnormality recognition model.

6. The method according to claim 1, characterized in that Determining an associated step from the P generalization steps according to the first abnormality cause includes: Determining the abnormal step and abnormal server indicated by the first abnormal cause; The abnormal step indicated by the first abnormal cause is determined as the associated step, and the promotion step executed on the abnormal server is determined as the associated step.

7. The method according to claim 1, characterized in that The method further comprises: determining a first optimization method for the abnormal step according to the first abnormal cause; determining a second optimization method of the association step according to the second abnormality cause; A third optimization method for the promotion process is generated according to the first optimization method and the second optimization method, and the promotion process is optimized by the third optimization method to obtain an updated promotion process.

8. A monitoring device for promoting business, characterized in that: include: a first acquiring unit, configured to acquire operating status information of M stage nodes, and determine whether there is an abnormal step in P promotion steps included in a promotion process of a target promotion business based on the operating status information, wherein the promotion process is provided with the M stage nodes, the stage nodes are provided between adjacent promotion steps, and M and P are positive integers; an identification unit, configured to, when the abnormal step exists, identify a first abnormal cause of the abnormal step, and determine a related step from the P generalized steps based on the first abnormal cause, wherein the related step has an associated relationship with the abnormal step; The first determining unit is configured to identify a second abnormal reason of the associating step, and determine the abnormal step, the associating step, the first abnormal reason, and the second abnormal reason as a monitoring result of the promotion business.

9. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the steps of the promotion service monitoring method according to any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: a memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the monitoring method for promotion services according to any one of claims 1 to 7.

Images