Strategy traffic allocation method and device, electronic equipment and readable storage medium

Abstract

The invention relates to the field of data processing, and provides a strategy traffic allocation method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining an initial user behavior data set and an initial strategy execution data set; when the user click data is greater than the click threshold value, deleting the corresponding user click data; when the task click rate is greater than the click rate threshold, deleting the corresponding task click rate; performing feature extraction on the preprocessed user behavior data set and the preprocessed strategy execution data set to obtain user feature information and strategy feature information; performing scoring processing according to the user feature information and the strategy feature information to obtain task scoring information; and adjusting preset strategy traffic according to the task scoring information. According to the technical scheme, the abnormal information can be deleted, so that strategy traffic distribution can be more reasonable and accurate.

Description

Technical Field

[0001] The embodiments of the present application relate to, but are not limited to, the field of data processing, and in particular, to a method, device, electronic device, and computer-readable storage medium for policy traffic allocation. Background Art

[0002] With the continuous development of the social economy and the continuous progress of technology, people's living standards have also been continuously improved; in order to bring more guarantees to people's lives, various insurance businesses have also been well promoted and developed; in order to manage and process a large amount of insurance business data, currently, an insurance operation system is generally used to manage relevant data; with the development of business, operation strategies will also continue to increase. In order to better improve the click-through rate and conversion rate of operation strategies, the current operation strategy traffic allocation is often based on simple user behavior analysis, which will make the operation strategy traffic allocation unreasonable and inaccurate. Summary of the Invention

[0003] The following is an overview of the subject matter described in detail in this document. This overview is not intended to limit the scope of protection of the claims.

[0004] To solve the problems mentioned in the above background art, the embodiments of the present application provide a method, device, electronic device, and computer-readable storage medium for policy traffic allocation, which can delete abnormal information and make the policy traffic allocation more reasonable and accurate.

[0005] In a first aspect, the embodiments of the present application provide a method for policy traffic allocation, including:

[0006] Obtain an initial user behavior data set and an initial policy execution data set, where the initial user behavior data set includes multiple user click data, the initial policy execution data set includes multiple task click-through rates, and each user click data and the task click-through rate correspond to user marking information;

[0007] When the user click data corresponding to the user marking information is greater than a preset click threshold, perform a deletion process on the corresponding user click data to obtain a preprocessed user behavior data set;

[0008] When the task click-through rate corresponding to the user marking information is greater than a preset click-through rate threshold, perform a deletion process on the corresponding task click-through rate to obtain a preprocessed policy execution data set;

[0009] Extract features from the preprocessed user behavior data set and the preprocessed policy execution data set respectively to obtain user feature information corresponding to the preprocessed user behavior data set and policy feature information corresponding to the preprocessed policy execution data set;

[0010] Perform a scoring process based on the user characteristic information and the policy characteristic information to obtain task scoring information;

[0011] Adjust the preset policy traffic according to the task scoring information.

[0012] In a second aspect, an embodiment of the present application provides a policy traffic allocation device, including:

[0013] An acquisition unit, configured to acquire an initial user behavior data set and an initial policy execution data set, where the initial user behavior data set includes a plurality of user click data, the initial policy execution data set includes a plurality of task click-through rates, and each of the user click data and the task click-through rate corresponds to user marking information;

[0014] A deletion unit, configured to perform a deletion process on the corresponding user click data to obtain a preprocessed user behavior data set when the user click data corresponding to the user marking information is greater than a preset click threshold; and perform a deletion process on the corresponding task click-through rate to obtain a preprocessed policy execution data set when the task click-through rate corresponding to the user marking information is greater than a preset click-through rate threshold;

[0015] An extraction unit, configured to perform feature extraction on the preprocessed user behavior data set and the preprocessed policy execution data set respectively to obtain user characteristic information corresponding to the preprocessed user behavior data set and policy characteristic information corresponding to the preprocessed policy execution data set;

[0016] A scoring unit, configured to perform a scoring process based on the user characteristic information and the policy characteristic information to obtain task scoring information;

[0017] An adjustment unit, configured to adjust the preset policy traffic according to the task scoring information.

[0018] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the above-mentioned policy traffic allocation method is implemented.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, storing computer-executable instructions, where the computer-executable instructions are used to execute the above-mentioned policy traffic allocation method.

[0020] The policy traffic allocation method according to the embodiments provided in this application has at least the following beneficial effects: During the process of policy traffic allocation, first obtain the initial user behavior data set and the initial policy execution data set. Among them, the initial user behavior data set includes multiple user click data, the initial policy execution data set includes multiple task click-through rates, and each user click data and task click-through rate correspond to user marking information; when the user click data corresponding to the user marking information is greater than the preset click threshold, perform deletion processing on the corresponding user click data, and then a preprocessed user behavior data set can be obtained; when the task click-through rate corresponding to the user marking information is greater than the preset click-through rate threshold, perform deletion processing on the corresponding task click-through rate, and then a preprocessed policy execution data set can be obtained; then perform feature extraction on the preprocessed user behavior data set and the preprocessed policy execution data set respectively, and user feature information corresponding to the preprocessed user behavior data set and policy feature information corresponding to the preprocessed policy execution data set can be obtained; then perform scoring processing according to the user feature information and the policy feature information to obtain task scoring information; finally, the preset policy traffic can be adjusted according to the task scoring information. Through the above method, when the user click data corresponding to the user marking information is greater than the preset click threshold, perform deletion processing on the corresponding user click data, and when the task click-through rate corresponding to the user marking information is greater than the preset click-through rate threshold, perform deletion processing on the corresponding task click-through rate, which can well eliminate abnormal information, make the basis for subsequent policy traffic allocation more reasonable, and then make the allocation more accurate, and dynamic policy traffic allocation processing can be realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings are used to provide a further understanding of the technical solutions of this application, and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application, and do not constitute a limitation to the technical solutions of this application.

[0022] Figure 1 is a schematic flowchart of the policy traffic allocation method provided by an embodiment of this application;

[0023] Figure 2 is Figure 1 a schematic flowchart of a specific implementation manner of step S400 in

[0024] Figure 3 is Figure 1 a schematic flowchart of a specific implementation manner of step S500 in

[0025] Figure 4 is Figure 1 a schematic flowchart of a specific implementation manner of step S600 in

[0026] Figure 5 is Figure 1 A schematic flowchart of a specific implementation manner after step S600 in

[0027] Figure 6 is Figure 1 A schematic flowchart of a specific implementation manner after step S300 in

[0028] Figure 7 is Figure 1 Another schematic flowchart of a specific implementation manner after step S600 in

[0029] Figure 8 A schematic diagram of a policy traffic allocation device provided by an embodiment of the present application;

[0030] Figure 9 A schematic diagram of an electronic device provided by an embodiment of the present application. Specific implementation manner

[0031] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0032] It should be noted that although functional module division is performed in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different module division in the device or a different order in the flowchart. Terms such as "first" and "second" in the specification, claims and the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence.

[0033] It should be noted that unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0034] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is a 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 obtain the best results.

[0035] AI is a new technological science that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence; artificial intelligence is a branch of computer science. Artificial intelligence attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence. The research in this field includes robots, speech recognition, image recognition, natural language processing, and expert systems, etc. Artificial intelligence can simulate the information processes of human consciousness and thinking. Artificial intelligence also refers to the theory, method, technology, and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0036] The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0037] Artificial intelligence is AI. AI is the theory, method, technology, and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0038] The server involved in artificial intelligence technology can be an independent server or 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, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0039] The present application provides a method, apparatus, electronic device, and computer-readable storage medium for policy traffic allocation. In the process of policy traffic allocation, first, an initial user behavior data set and an initial policy execution data set are obtained. The initial user behavior data set includes multiple user click data, and the initial policy execution data set includes multiple task click-through rates. Each user click data and task click-through rate corresponds to user marking information. When the user click data corresponding to the user marking information is greater than a preset click threshold, the corresponding user click data is deleted, and then a preprocessed user behavior data set can be obtained. When the task click-through rate corresponding to the user marking information is greater than a preset click-through rate threshold, the corresponding task click-through rate is deleted, and then a preprocessed policy execution data set can be obtained. Then, feature extraction is respectively performed on the preprocessed user behavior data set and the preprocessed policy execution data set, and user feature information corresponding to the preprocessed user behavior data set and policy feature information corresponding to the preprocessed policy execution data set can be obtained. Then, scoring processing is performed according to the user feature information and the policy feature information to obtain task scoring information. Finally, the preset policy traffic can be adjusted according to the task scoring information. Through the above method, when the user click data corresponding to the user marking information is greater than a preset click threshold, the corresponding user click data is deleted, and when the task click-through rate corresponding to the user marking information is greater than a preset click-through rate threshold, the corresponding task click-through rate is deleted, which can well eliminate abnormal information, make the basis for subsequent policy traffic allocation more reasonable, and thus make the allocation more accurate. Moreover, dynamic policy traffic allocation processing can be realized.

[0040] The policy traffic allocation method provided by the embodiments of the present application relates to the field of data processing. The policy traffic allocation method provided by the embodiments of the present application can be applied to a terminal, or to a server side, or can be software running on a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, or can be configured as a cloud server providing 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 for implementing the policy traffic allocation method, etc., but is not limited to the above forms.

[0041] This application can be used in numerous general - purpose or special - purpose 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 so on. This 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, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0042] It should be noted that in each specific embodiment of this application, when it comes to performing relevant processing based on data related to user 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. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when this application embodiment needs to obtain sensitive personal information of the user, the user's separate permission or separate consent will be obtained through methods such as pop - up windows or redirecting to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user - related data for the normal operation of this application embodiment will be obtained.

[0043] The following further elaborates on the embodiments of this application with reference to the accompanying drawings.

[0044] As Figure 1 shown, Figure 1 is a flowchart of a policy traffic allocation method provided by an embodiment of this application. The policy traffic allocation method includes the following steps:

[0045] Step S100: Obtain an initial user behavior data set and an initial policy execution data set. Among them, the initial user behavior data set includes multiple user click data, and the initial policy execution data set includes multiple task click - through rates. Each user click data and task click - through rate corresponds to user - marked information.

[0046] The policy traffic allocation method provided by the embodiments of this application first obtains an initial user behavior data set and an initial policy execution data set. Among them, the initial user behavior data set includes multiple user click data, and the initial policy execution data set includes multiple task click-through rates. Moreover, each piece of user click data and task click-through rate corresponds to user marking information. Obtaining the initial user behavior data set and the initial policy execution data set can provide a basis for subsequent policy traffic allocation.

[0047] It should be noted that before obtaining the initial user behavior data set and the initial policy execution data set, the user's permission or consent will be obtained first. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiments of this application need to obtain the user's sensitive personal information, the user's separate permission or separate consent will be obtained through methods such as pop-up windows or jumping to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for the normal operation of the embodiments of this application will be obtained.

[0048] Exemplarily, in a property insurance business system, the initial user behavior data set may include user click data, browsing behavior data, and interaction behavior data, etc. User click data is a record triggered by the user clicking on an option in the property insurance business system, such as clicking on "purchase insurance" or "apply for claims"; browsing behavior data is a record of the user browsing a certain page in the property insurance business system, such as browsing the insurance product page, terms page, or case page; interaction behavior data is a record of the user interacting with the interaction platform of the property insurance business system, such as online consultation or customer service feedback, etc. The initial policy execution data set may include task click-through rate, push reach rate, and task completion rate. The task click-through rate refers to the proportion of users who click into the task page after receiving the push task. For example, when the user interface receives "Introduction to the adjustment of insurance preferential policies", the user can choose to click or ignore it. Finally, the system can obtain the proportion of users who choose to click; the push reach rate is the proportion of push messages sent by the system that successfully reach the user device. For example, if there are a total of 100 user devices and the insurance sales push message can be successfully delivered to 80 of them, the push reach rate at this time is 80%; the task completion rate refers to the proportion of users who actually complete the task after clicking into the task. For example, the system pushes a task of winning a lottery by playing a quiz game to users. A total of 100 users click into the quiz game, and finally only 60 people complete the quiz game to participate in the lottery. At this time, the task completion rate is 60%.

[0049] It should be noted that the strategy in the embodiments of the present application is the business policy pushed to users in the system. For example, in the vehicle insurance business system, when the vehicle insurance renewal is approaching, the system can recommend the currently optimal vehicle insurance business to users for selection.

[0050] It should be noted that each user click data and task click-through rate correspond to user marking information, which is used to mark the uniqueness of registered users in the system. Exemplarily, in the endowment insurance business system, when a user registers an account in the system, a sequential code will be generated to mark the uniqueness of the user, and subsequently, different users can be distinguished through this sequential code.

[0051] Step S200: When the user click data corresponding to the user marking information is greater than a preset click threshold, perform deletion processing on the corresponding user click data to obtain a preprocessed user behavior data set.

[0052] For the strategy traffic allocation method provided by the embodiments of the present application, after obtaining the initial user behavior data set, when the user click data corresponding to the user marking information is greater than the preset click threshold, it is determined that this part of the user click data is formed by malicious clicks of users. Therefore, deletion processing needs to be performed on the corresponding user click data to obtain a preprocessed user behavior data set, making the subsequent strategy traffic allocation more reasonable and accurate.

[0053] Exemplarily, in the property insurance business system, user A maliciously clicks on "household property insurance" in the system interface multiple times. At this time, the user click data corresponding to user A's user marking information will be greater than the preset click threshold. Before subsequent strategy traffic adjustment, the user click data corresponding to user A will be deleted first, which can well prevent some extreme data from having an adverse impact on the strategy traffic adjustment and improve the accuracy of the strategy traffic allocation. Among them, the preset click threshold can be set according to the actual situation. For example, it can be set to 30, and user A clicks on "household property insurance" in the system interface 40 times within the set time. In this case, it is determined that the user click data corresponding to user A is extreme data and needs to be deleted to improve the accuracy of subsequent strategy traffic allocation.

[0054] Step S300: When the task click-through rate corresponding to the user marking information is greater than a preset click-through rate threshold, perform deletion processing on the corresponding task click-through rate to obtain a preprocessed strategy execution data set.

[0055] After obtaining the initial policy execution data set, the policy traffic allocation method provided by the embodiment of the present application can, when the task click-through rate corresponding to the user marking information is greater than the preset task click-through rate, determine that this part of the task click-through rate is formed due to malicious clicks by the user. Therefore, it is necessary to delete the corresponding task click-through rate to obtain a preprocessed policy execution data set, so that subsequent policy traffic allocation can be more reasonable and accurate.

[0056] Exemplarily, in the endowment insurance business system, user B clicks to purchase commercial endowment insurance multiple times. At this time, the task click-through rate increases due to multiple abnormal click operations by user B. In order to make subsequent policy traffic allocation more reasonable, it is necessary to delete the task click-through rate corresponding to user B to improve the rationality of policy traffic allocation. Among them, the preset task click-through rate can be set according to the actual situation. For example, it can be set to 40%. User B clicks on commercial endowment insurance in the system interface multiple times within the set time, resulting in a task click-through rate of 48%. In this way, it will be determined that the task click-through rate corresponding to user B is extreme data and needs to be deleted to improve the accuracy of subsequent policy traffic allocation.

[0057] Step S400: Extract features from the preprocessed user behavior data set and the preprocessed policy execution data set respectively to obtain user feature information corresponding to the preprocessed user behavior data set and policy feature information corresponding to the preprocessed policy execution data set.

[0058] After obtaining the preprocessed user behavior data set and the preprocessed policy execution data set, the policy traffic allocation method provided by the embodiment of the present application can extract features from the preprocessed user behavior data set and the preprocessed policy execution data set respectively, and obtain user feature information corresponding to the preprocessed user behavior data set and policy feature information corresponding to the preprocessed policy execution data set, so as to prepare for subsequent scoring processing.

[0059] It should be noted that extracting features from the preprocessed user behavior data set and the preprocessed policy execution data set respectively can extract features that can effectively represent the data from the preprocessed user behavior data set and the preprocessed policy execution data set; based on the above method, the dimension of the data can be well reduced and the interpretability of the data can be improved.

[0060] As Figure 2 shown, in step S400, extracting features from the preprocessed user behavior data set and the preprocessed policy execution data set respectively to obtain user feature information corresponding to the preprocessed user behavior data set and policy feature information corresponding to the preprocessed policy execution data set may include the following steps:

[0061] Step S410: Filter the preprocessed user behavior dataset to obtain a filtered user behavior dataset, and perform feature vector construction processing on the filtered user behavior dataset to obtain user feature information;

[0062] Step S420: Filter the preprocessed policy execution dataset to obtain a filtered policy execution dataset, and perform feature vector construction processing on the filtered policy execution dataset to obtain policy feature information.

[0063] For steps S410 to S420, in the process of feature extraction from the preprocessed user behavior dataset and the preprocessed policy execution dataset, first filter the preprocessed user behavior dataset to obtain a filtered user behavior dataset, and perform feature vector construction processing on the filtered user behavior dataset to obtain user feature information; then filter the preprocessed policy execution dataset to obtain a filtered policy execution dataset, and then perform feature vector construction processing on the filtered policy execution dataset to obtain policy feature information. Subsequently, scoring processing can be performed based on the user feature information and the policy feature information to obtain corresponding task scoring information, preparing for subsequent policy traffic allocation.

[0064] It should be noted that filtering the preprocessed user behavior dataset obtains a filtered user behavior dataset; among them, the purpose of filtering the preprocessed user behavior dataset is to remove irrelevant or redundant preprocessed user behavior data and retain information meaningful for analysis. Similarly, filtering the preprocessed policy execution dataset obtains a filtered policy execution dataset; among them, the purpose of filtering the preprocessed policy execution dataset is to remove irrelevant or redundant preprocessed policy execution data.

[0065] Step S500: Perform scoring processing based on the user feature information and the policy feature information to obtain task scoring information.

[0066] For the policy traffic allocation method provided in the embodiments of this application, after obtaining the user feature information and the policy feature information, scoring processing can be performed based on the user feature information and the policy feature information to obtain task scoring information, and subsequently, the preset policy traffic can be adjusted according to the obtained task scoring information, making the allocation of policy traffic more reasonable.

[0067] Exemplarily, in a property insurance business system, scoring processing is performed based on the user feature information and the policy feature information to obtain corresponding task scoring information; for example, the click-through rate of business policy A in the property insurance business system is higher than that of business policy B in the property insurance business system, and subsequently, the traffic allocation ratio of business policy A will be increased, and the traffic allocation ratio of business policy B will be decreased.

[0068] As Figure 3 shown, in step S500, scoring processing is performed based on user characteristic information and policy characteristic information to obtain task scoring information, which may include the following steps:

[0069] Step S510, combining the user characteristic information and the policy characteristic information to obtain combined characteristic information;

[0070] Step S520, determining push reach rate information, task click-through rate information, and task completion rate information from the combined characteristic information;

[0071] Step S530, performing scoring processing based on the push reach rate information, task click-through rate information, and task completion rate information to obtain task scoring information.

[0072] For steps S510 to S530, in the process of obtaining task scoring information by performing scoring processing based on user characteristic information and policy characteristic information, first, the user characteristic information and the policy characteristic information are combined to obtain combined characteristic information; then, the push reach rate information, task click-through rate information, and task completion rate information are determined from the combined characteristic information; finally, scoring processing is performed based on the push reach rate information, task click-through rate information, and task completion rate information to obtain task scoring information. Subsequently, the preset policy traffic can be adjusted according to the task scoring information, so that the policy traffic adjustment can be more reasonable and accurate, and dynamic policy traffic adjustment processing can be achieved.

[0073] It should be noted that after obtaining the user characteristic information and the policy characteristic information, the user characteristic information and the policy characteristic information can be combined to fuse the user characteristic information and the policy characteristic information, which can better capture the relationship between user behavior and business policies, and improve the accuracy and robustness of subsequent operations.

[0074] Exemplarily, in the elderly care service business system, the task click-through rate refers to the proportion of users who click to enter the task page after receiving the push task. For example, when the user interface receives the "Introduction to Commercial Endowment Insurance Preferential Policies", the user can choose to click or ignore it, and finally the system can obtain the proportion of users who choose to click; the push reach rate is the proportion of push messages sent by the system that successfully reach the user devices. For example, if there are a total of 100 user devices and the endowment insurance sales push message can be successfully delivered to 60 of them, the push reach rate at this time is 60%; the task completion rate refers to the proportion of users who actually complete the task after clicking into the task. For example, the system pushes an endowment insurance problem feedback column to users. A total of 100 users click into the problem feedback, and finally only 50 people complete the relevant problem feedback of endowment insurance. At this time, the task completion rate is 50%.

[0075] Exemplarily, scoring processing is performed according to the push reach rate information, task click-through rate information, and task completion rate information to obtain task scoring information. Among them, the calculation formula used in the process of calculating the task score according to the push reach rate information can be as follows: task score = (current reach rate - lower limit of basic reach rate) / (upper limit of current reach rate - lower limit of basic reach rate) × (upper limit of interval score - lower limit of interval score) + lower limit of interval score. The task score corresponding to the push reach rate information is calculated through the above formula. Similarly, the task scores related to the task click-through rate information and task completion rate information can also be calculated in a similar manner. After obtaining the three task scores, the average value of the three can be calculated, and finally, the average value of the three is used as the final task scoring information. Subsequently, the policy traffic can be adjusted according to the obtained task scoring information.

[0076] Step S600: Adjust the preset policy traffic according to the task scoring information.

[0077] For the policy traffic allocation method provided in the embodiments of the present application, after obtaining the task scoring information, the preset policy traffic can be adjusted according to the task scoring information, so that the allocation of the policy traffic can be more reasonable.

[0078] Exemplarily, the task score of business policy A in the property insurance business system is higher than that of business policy B in the property insurance business system. Subsequently, the traffic allocation ratio of business policy A will be increased, and the traffic allocation ratio of business policy B will be decreased.

[0079] As Figure 4 shown, in step S600, adjusting the preset policy traffic according to the task scoring information may include the following steps:

[0080] Step S610: Adjust the preset traffic allocation ratio according to the task scoring information to obtain a traffic adjustment ratio;

[0081] Step S620: Re-allocate the policy traffic according to the traffic adjustment ratio.

[0082] For steps S610 to S620, in the process of adjusting the preset policy traffic according to the task scoring information, first, the preset traffic allocation ratio can be adjusted according to the task scoring information to obtain the traffic adjustment ratio, and finally, the policy traffic can be re-allocated according to the traffic adjustment ratio. Exemplarily, in an insurance business system, there are policies A, B, and C. The previous traffic ratio distribution is that policy A accounts for 20%, policy B accounts for 50%, and policy C accounts for 30%. However, in the process of traffic allocation, the task score corresponding to policy A is 80, the task score corresponding to policy B is 20, and the task score corresponding to policy C is 60. Therefore, in the subsequent traffic adjustment process, policy A is adjusted to account for 50%, policy B is adjusted to account for 15%, and policy C is adjusted to account for 35%, thereby reasonably realizing the traffic allocation process and improving the accuracy of traffic allocation.

[0083] As Figure 5 shown, after adjusting the preset policy traffic according to the task scoring information, the following steps may be included:

[0084] Step S710, feedback the adjusted policy traffic information to a preset monitoring terminal;

[0085] Step S720, convert the policy traffic information into a traffic monitoring log based on the monitoring terminal.

[0086] For steps S710 to S720, after adjusting the preset policy traffic according to the task scoring information, the adjusted policy traffic information can be fed back to a preset monitoring terminal; then, based on the monitoring terminal, the policy traffic information is converted into a traffic monitoring log, which can facilitate the subsequent viewing and maintenance of system logs by maintenance personnel. Among them, the preset monitoring terminal can be a server. It should be noted that the policy traffic information in the embodiments of the present application is the policy traffic adjustment ratio.

[0087] As Figure 6 shown, after deleting the corresponding task click-through rate to obtain the preprocessed policy execution data set, the following steps may be included:

[0088] Step S310, perform data cleaning on the preprocessed user behavior data set and the preprocessed policy execution data set;

[0089] Step S320, format the preprocessed user behavior data set and the preprocessed policy execution data set after data cleaning.

[0090] For steps S310 to S320, performing data cleaning on the preprocessed user behavior dataset and the preprocessed policy execution dataset can effectively delete duplicate or redundant data, facilitating subsequent data processing. Then, formatting the preprocessed user behavior dataset and the preprocessed policy execution dataset after data cleaning is carried out to facilitate subsequent feature extraction.

[0091] As Figure 7 shown, after adjusting the preset policy traffic according to the task scoring information, the following steps may be included:

[0092] Step S810, after a preset time period, re-obtain a new initial user behavior dataset and an initial policy execution dataset;

[0093] Step S820, when the user click data corresponding to the user marking information is less than or equal to the click threshold, and the task click-through rate corresponding to the user marking information is less than or equal to the click-through rate threshold, use the adjusted policy traffic as the candidate traffic allocation plan.

[0094] For steps S810 to S820, after adjusting the preset policy traffic according to the task scoring information, after a preset time period, re-obtain a new initial user behavior dataset and an initial policy execution dataset; when the user click data corresponding to the user marking information is less than or equal to the click threshold, and the task click-through rate corresponding to the user marking information is less than or equal to the click-through rate threshold, use the adjusted policy traffic as the candidate traffic allocation plan, and then subsequent policy traffic allocation processing can be based on the candidate traffic allocation plan to quickly approach a better policy traffic allocation plan.

[0095] It should be noted that the preset time period can be set according to actual needs; for example, in a property insurance business system, there are policies A, B, and C. After adjustment, policy A is adjusted to account for 50%, policy B is adjusted to account for 15%, and policy C is adjusted to account for 35%. After 1 hour, re-obtain the initial user behavior dataset and the initial policy execution dataset in the property insurance business system; when the user click data corresponding to the user marking information is less than or equal to the click threshold, and the task click-through rate corresponding to the user marking information is less than or equal to the click-through rate threshold, the current policy traffic allocation plan will be used as the candidate traffic allocation plan and stored as a better traffic allocation plan. Subsequently, traffic allocation can be directly carried out according to the candidate traffic allocation plan, accelerating the process of rationalizing traffic allocation.

[0096] In addition, as Figure 8 shown, an embodiment of the present application further provides a policy traffic allocation device 10, including:

[0097] An acquisition unit 100, configured to acquire an initial user behavior data set and an initial policy execution data set, where the initial user behavior data set includes a plurality of user click data, the initial policy execution data set includes a plurality of task click-through rates, and each user click data and task click-through rate corresponds to user marking information;

[0098] A deletion unit 200, configured to, when the user click data corresponding to the user marking information is greater than a preset click threshold, perform a deletion process on the corresponding user click data to obtain a preprocessed user behavior data set; when the task click-through rate corresponding to the user marking information is greater than a preset click-through rate threshold, perform a deletion process on the corresponding task click-through rate to obtain a preprocessed policy execution data set;

[0099] An extraction unit 300, configured to respectively perform feature extraction on the preprocessed user behavior data set and the preprocessed policy execution data set to obtain user feature information corresponding to the preprocessed user behavior data set and policy feature information corresponding to the preprocessed policy execution data set;

[0100] A scoring unit 400, configured to perform a scoring process according to the user feature information and the policy feature information to obtain task scoring information;

[0101] An adjustment unit 500, configured to adjust a preset policy traffic according to the task scoring information.

[0102] It should be noted that in the process of policy traffic allocation, the initial user behavior dataset and the initial policy execution dataset are first obtained. Among them, the initial user behavior dataset includes multiple user click data, and the initial policy execution dataset includes multiple task click-through rates, and each user click data and task click-through rate correspond to user marking information. When the user click data corresponding to the user marking information is greater than the preset click threshold, the corresponding user click data is deleted, and then the preprocessed user behavior dataset can be obtained. When the task click-through rate corresponding to the user marking information is greater than the preset click-through rate threshold, the corresponding task click-through rate is deleted, and then the preprocessed policy execution dataset can be obtained. Then, feature extraction is performed on the preprocessed user behavior dataset and the preprocessed policy execution dataset respectively, and the user feature information corresponding to the preprocessed user behavior dataset and the policy feature information corresponding to the preprocessed policy execution dataset can be obtained. Then, scoring is performed according to the user feature information and the policy feature information to obtain task scoring information. Finally, the preset policy traffic can be adjusted according to the task scoring information. Through the above method, when the user click data corresponding to the user marking information is greater than the preset click threshold, the corresponding user click data is deleted, and when the task click-through rate corresponding to the user marking information is greater than the preset click-through rate threshold, the corresponding task click-through rate is deleted, which can well eliminate abnormal information, make the basis for subsequent policy traffic allocation more reasonable, and then make the allocation more accurate, and dynamic policy traffic allocation processing can be realized.

[0103] The specific implementation manner of the policy traffic allocation device 10 is basically the same as that of the above-mentioned specific embodiment of the policy traffic allocation method, and will not be elaborated here.

[0104] In addition, as Figure 9 shown, an embodiment of the present application further provides an electronic device 700, which includes: a memory 720, a processor 710, and a computer program stored on the memory 720 and executable on the processor 710.

[0105] The processor 710 and the memory 720 can be connected through a bus or other means.

[0106] The non-transitory software program and instructions required to implement the policy traffic allocation method of the above embodiment are stored in the memory 720, and when executed by the processor 710, they execute the policy traffic allocation method of the above embodiments.

[0107] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] In addition, an embodiment of the present application further provides a computer-readable storage medium storing computer-executable instructions, which are executed by a processor 710 or a controller, for example, executed by a processor 710 in the above device embodiment, enabling the processor 710 to execute the policy traffic allocation method in the above embodiment.

[0109] The above embodiments can be used in combination. The modules with the same name in different embodiments may be the same or different.

[0110] The specific embodiments of the present application are described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily have to be performed in the particular order or continuous order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0111] Each embodiment in the present application is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and computer-readable storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple. The relevant parts can be referred to the partial description of the method embodiments.

[0112] The device, equipment, and computer-readable storage medium provided by the embodiments of the present application correspond to the method. Therefore, the device, equipment, and non-volatile computer storage medium also have beneficial technical effects similar to the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding device, equipment, and computer storage medium will not be elaborated here.

[0113] In the 1990s, it was obvious to distinguish whether an improvement to a technology was a hardware improvement (e.g., improvement to circuit structures such as diodes, transistors, switches, etc.) or a software improvement (improvement to method processes). However, with the development of technology, many method process improvements today can be regarded as direct improvements to hardware circuit structures. Almost all designers obtain the corresponding hardware circuit structure by programming the improved method process into the hardware circuit. Therefore, it cannot be said that an improvement to a method process cannot be implemented with a hardware entity module. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program by themselves to "integrate" a digital system on a piece of PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL). And there is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. Currently, the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply making a little logical programming of the method process with the above-mentioned several hardware description languages and programming it into the integrated circuit, it is easy to obtain the hardware circuit that implements the logical method process.

[0114] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program the method steps to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0115] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0116] For the convenience of description, the above devices are described by dividing them into various units according to their functions. Of course, when implementing the embodiments of the present application, the functions of the various units can be implemented in the same or multiple software and / or hardware.

[0117] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the embodiments of the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0118] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0119] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0120] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0121] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0122] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (Flash RAM). The memory is an example of computer-readable media.

[0123] A computer-readable medium includes permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape disk storage or other magnetic storage devices, or any other non-transitory media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0124] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the said element.

[0125] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent the cases of A existing alone, A and B existing simultaneously, and B existing alone. Where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0126] Embodiments of the present application may 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, etc. that perform specific tasks or implement specific abstract data types. Embodiments of the present application may also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0127] Each embodiment in the present application is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and reference can be made to the corresponding parts of the method embodiments for the relevant content.

[0128] The above description is only for the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A strategic traffic allocation method, characterized in that: include: Acquire an initial user behavior data set and an initial policy execution data set, wherein the initial user behavior data set includes a plurality of user click data, the initial policy execution data set includes a plurality of task click rates, and each of the user click data and the task click rate corresponds to user tag information; When the user click data corresponding to the user mark information is greater than a preset click threshold, the corresponding user click data is deleted to obtain a pre-processed user behavior data set; When the task click rate corresponding to the user marking information is greater than a preset click rate threshold, the corresponding task click rate is deleted to obtain a preprocessing strategy execution data set; Performing feature extraction on the preprocessed user behavior data set and the preprocessed policy execution data set respectively to obtain user feature information corresponding to the preprocessed user behavior data set and policy feature information corresponding to the preprocessed policy execution data set; Performing scoring processing according to the user characteristic information and the strategy characteristic information to obtain task scoring information; The preset strategy flow is adjusted according to the task scoring information.

2. The strategic traffic allocation method according to claim 1, characterized in that: The extracting features of the pre-processed user behavior data set and the pre-processed policy execution data set respectively to obtain user feature information corresponding to the pre-processed user behavior data set and policy feature information corresponding to the pre-processed policy execution data set includes: Performing filtering processing on the pre-processed user behavior data set to obtain a filtered user behavior data set, and performing feature vector construction processing on the filtered user behavior data set to obtain the user feature information; The pre-processing strategy execution data set is filtered to obtain a filtering strategy execution data set, and the filtering strategy execution data set is subjected to feature vector construction to obtain the strategy feature information.

3. The strategic traffic allocation method according to claim 1, characterized in that: The step of performing scoring processing according to the user characteristic information and the strategy characteristic information to obtain task scoring information includes: Combining the user characteristic information and the policy characteristic information to obtain combined characteristic information; Determine push reach rate information, task click rate information and task completion rate information from the combined feature information; Scoring is performed based on the push reach rate information, the task click rate information and the task completion rate information to obtain the task scoring information.

4. The strategic traffic allocation method according to claim 1, characterized in that: The adjusting process of the preset strategy flow according to the task scoring information includes: Adjusting the preset flow distribution ratio according to the task scoring information to obtain a flow adjustment ratio; The policy traffic is redistributed according to the traffic adjustment ratio.

5. The strategic traffic allocation method according to claim 1, characterized in that: After adjusting the preset strategy flow according to the task scoring information, the method further includes: Feedback the adjusted policy traffic information to the preset monitoring terminal; The policy traffic information is converted into a traffic monitoring log based on the monitoring terminal.

6. The strategic traffic allocation method according to claim 1, characterized in that: After deleting the corresponding task click rate to obtain a preprocessing strategy execution data set, the method further includes: Performing data cleaning processing on the preprocessed user behavior data set and the preprocessed strategy execution data set; The pre-processed user behavior data set and the pre-processed strategy execution data set after data cleaning are formatted.

7. The strategic traffic allocation method according to claim 1, characterized in that: After adjusting the preset strategy flow according to the task scoring information, the method further includes: After a preset time period, reacquire the new initial user behavior data set and the initial policy execution data set; When the user click data corresponding to the user tag information is less than or equal to the click threshold, and the task click rate corresponding to the user tag information is less than or equal to the click rate threshold, the adjusted policy traffic is used as a candidate traffic allocation scheme.

8. A strategic traffic allocation device, characterized in that: include: An acquisition unit, used to acquire an initial user behavior data set and an initial policy execution data set, wherein the initial user behavior data set includes a plurality of user click data, the initial policy execution data set includes a plurality of task click rates, and each of the user click data and the task click rate corresponds to user tag information; A deleting unit, configured to delete the corresponding user click data when the user click data corresponding to the user mark information is greater than a preset click threshold, so as to obtain a preprocessed user behavior data set; and to delete the corresponding task click rate when the task click rate corresponding to the user mark information is greater than a preset click rate threshold, so as to obtain a preprocessed strategy execution data set; An extraction unit, used to perform feature extraction on the preprocessed user behavior data set and the preprocessed policy execution data set respectively, to obtain user feature information corresponding to the preprocessed user behavior data set and policy feature information corresponding to the preprocessed policy execution data set; A scoring unit, configured to perform scoring processing according to the user characteristic information and the strategy characteristic information to obtain task scoring information; The adjustment unit is used to adjust the preset strategy flow according to the task scoring information.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the policy traffic allocation method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing computer-executable instructions, characterized in that: The computer executable instructions are used to execute the policy traffic allocation method described in any one of claims 1 to 7.

Images