Operation management method, system and equipment based on user behaviors and medium

Abstract

The invention relates to the technical field of operation management, in particular to an operation management method, system and device based on user behaviors and a medium. The method comprises the steps of obtaining user behavior data and historical activity data, wherein the user behavior data comprises online behavior data of each user on a platform and activity participation data for historical activities; based on the historical activity data, the online behavior data of the target user and the activity participation data, a preference portrait of the target user is generated, and the target user is any user on the platform; platform content pushing is carried out on the target user based on the preference portrait of the target user; determining the user activity preference degree of the platform based on the preference portrait of each user on the platform; and formulating a current platform activity based on the historical activity data and the user activity preference degree, and issuing the current platform activity to a platform. According to the invention, customer requirements can be accurately met, and the platform operation management level is improved.

Description

Technical Field

[0001] The present application relates to the field of operation management technology, and in particular to an operation management method, system, device and medium based on user behavior. Background Art

[0002] With the rapid development of Internet technology and the sharp increase in the number of users, the core of operational management in the fields of insurance, automobile companies, banks, finance, etc. has gradually shifted to user-centricity, aiming to improve user experience and achieve precision marketing through in-depth analysis of user behavior data.

[0003] Related operational management methods often rely on manual experience and simple data analysis, and are unable to fully and accurately grasp user needs and behavioral habits. Summary of the invention

[0004] In order to solve the problem that the existing technology cannot accurately meet user needs, the present application provides an operation management method, system, device and medium based on user behavior.

[0005] In the first aspect, the present application provides an operation management method based on user behavior, which adopts the following technical solutions: An operation management method based on user behavior, comprising: Obtaining user behavior data and historical activity data, wherein the user behavior data includes online behavior data of each user on the platform and activity participation data for historical activities; Based on the historical activity data, the online behavior data and activity participation data of the target user, a preference profile of the target user is generated, where the target user is any user on the platform; Pushing platform content to the target user based on the preference profile of the target user; Determining the user activity preference of the platform based on the preference profile of each user on the platform; A current platform activity is formulated based on the historical activity data and the user activity preference, and the current platform activity is published to the platform.

[0006] By adopting the above technical solution, collecting users' online behavior data on the platform and activity participation data of historical activities, it is helpful to more accurately understand users' behavior patterns and interests. Combining historical activity data, target users' online behavior data and activity participation data, it is possible to carefully portray the personalized preference portrait of the target users, which not only includes users' preferences for different pages, products or services, but also covers users' participation in and feedback on historical activities. By using the preference portrait of the target users, the platform can push content that is more in line with users' interests, thereby improving user experience and satisfaction. By analyzing the preference portrait of each user on the platform, the user activity preference of the platform can be summarized, which helps the platform understand the overall interest trend of the user group. Based on historical activity data and user activity preference, the platform can formulate activities that are more attractive to users and have higher participation. By publishing activities, it can not only accurately meet customer needs, but also effectively promote social interaction between users and enhance the community atmosphere of the platform.

[0007] In a preferred example, the present application may be further configured as follows: generating a preference profile of the target user based on the historical activity data, the online behavior data and the activity participation data of the target user, including: Determine the behavior type and behavior object of each operation of the target user based on the online behavior data of the target user, wherein the behavior type includes browsing, clicking, purchasing and consulting, and the behavior object represents a page keyword, service or product name; Based on the preset score of each behavior type, the behavior type and behavior object of each operation, the behavior preference score of the target user for each behavior object is calculated, and the behavior preference score of the target user for each behavior object is stored as an online behavior profile; Based on the historical activity data and the activity participation data of the target user, an activity participation portrait of the target user is generated, and the online behavior portrait and the activity participation portrait constitute a preference portrait of the target user.

[0008] By adopting the above technical solution, we analyze the online behavior data of target users (including browsing, clicking, purchasing, consulting and other behavior types and their corresponding page keywords, service or product names), and calculate the behavior preference score based on the preset score to construct an online behavior portrait. At the same time, we integrate historical activity data and activity participation data to generate an activity participation portrait, and finally integrate to form a complete preference portrait of the target user, which can accurately capture the user's personalized preferences and interests, provide strong data support for subsequent personalized content push and activity customization, and effectively improve user experience and platform operation efficiency.

[0009] In a preferred example, the present application may be further configured as follows: generating the activity participation portrait of the target user based on the historical activity data and the activity participation data of the target user includes: Based on the activity participation data of the target user, taking the historical activities in which the target user has participated as target historical activities; Extracting the target user's activity feedback on the target historical activity from the activity participation data; extracting activity features of the target historical activity from the historical activity data; Based on the activity feedback and the activity features, a feature preference score of the target user for each activity feature in the target historical activities is determined, and the feature preference score of each activity feature constitutes an activity participation profile of the target user.

[0010] By adopting the above technical solution, analyzing the historical activities that the target user has participated in and their feedback, and combining the characteristics of the historical activity data, this technology can accurately calculate the characteristic preference scores of the target user for different activity features, thereby generating a detailed activity participation portrait, which helps to deeply understand the user's activity preferences.

[0011] In a preferred example, the present application may be further configured as follows: determining the user activity preference of the platform based on the preference portrait of each user on the platform includes: Extracting an activity participation profile from the preference profile of each user on the platform; Based on the activity participation portrait of each user, the sum of the feature preference scores of each user corresponding to each activity feature is calculated to obtain a comprehensive feature preference score of each activity feature on the platform; the comprehensive feature preference score of each activity feature on the platform constitutes the user activity preference.

[0012] By adopting the above technical solution, summarizing the activity participation portrait of each user on the platform and calculating the comprehensive feature preference score of each activity feature, it is possible to accurately measure the overall preference of platform users for various activity features, that is, user activity preference, which provides strong data support for the platform to optimize activity design and improve user participation and satisfaction.

[0013] In a preferred example, the present application may be further configured as follows: formulating the current platform activity based on the historical activity data and the user activity preference includes: Based on the historical activity data and the user activity preference, the sum of the comprehensive feature preference scores of the various activity features included in each historical activity is calculated to obtain a total activity preference score for each historical activity; Selecting a historical activity with the largest total score of the activity preference from various historical activities as a recommended activity; Determining new activity features based on the user activity preference and the activity features included in the recommended activity; The recommended activities and the newly added activity features are recommended to the platform administrator, and the current platform activities input by the platform administrator are received.

[0014] By adopting the above technical solution, historical activity data and user activity preferences are combined to calculate the total activity preference score, the most popular recommended activities are selected, and new activity features are introduced based on user preferences. This can intelligently assist platform managers in formulating activity plans that are more in line with user interests, thereby effectively improving the attractiveness and participation of activities and optimizing platform operating results.

[0015] In a preferred example, the present application may be further configured as follows: the platform content push for the target user based on the preference profile of the target user includes: Determine the behavior objects included in each content to be pushed on the platform, and calculate the sum of the behavior preference scores of each behavior object included in each content to be pushed to obtain the push recommendation value of each content to be pushed; Each content to be pushed on the platform is pushed to the display interface of the target user according to the corresponding push recommendation value from large to small.

[0016] By adopting the above technical solution, based on the preference portrait of the target user, the push recommendation value is determined by calculating the sum of the behavioral preference scores of each content to be pushed on the platform, and the content is displayed to the user from high to low according to this value. This technology can accurately match user interests, improve the personalization and relevance of content push, thereby enhancing the user experience and user stickiness of the platform.

[0017] In a preferred example, the present application can be further configured as follows: the method further includes: When there is a new user on the platform, obtain the new user information and the user information of each historical user on the platform; Matching the newly added user information with the user information of each historical user to determine a target historical user that best matches the newly added user information; The preference portrait of the target historical user is retrieved, and platform content is pushed to the newly added user based on the preference portrait of the target historical user.

[0018] By adopting the above technical solution, when a new user appears on the platform, the most similar target historical user is determined by matching the new user information with the historical user information, and content is pushed to the new user based on the preference profile of the target historical user. This strategy can quickly provide personalized content for the new user, effectively shorten the adaptation period of the new user, and improve the user experience and the user appeal of the platform.

[0019] In the second aspect, the present application provides an operation management system based on user behavior, which adopts the following technical solutions: An operation management system based on user behavior, comprising: An acquisition module, used to acquire user behavior data and historical activity data, wherein the user behavior data includes online behavior data of each user on the platform and activity participation data for historical activities; A generation module, used to generate a preference profile of the target user based on the historical activity data, the online behavior data and activity participation data of the target user, where the target user is any user on the platform; A push module, used to push platform content to the target user based on the preference profile of the target user; A determination module, configured to determine a user activity preference of the platform based on a preference profile of each user on the platform; A formulation module is used to formulate current platform activities based on the historical activity data and the user activity preference, and publish the current platform activities to the platform.

[0020] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: one or more processors; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the user behavior-based operation management method as described in any one of the first aspects.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute the user behavior-based operation management method as described in any one of the first aspects.

[0022] In a fifth aspect, the present application provides a computer program product, which adopts the following technical solution: A computer program product includes a computer program. When the computer program is executed by a processor, it implements the user behavior-based operation management method as described in any one of the first aspects.

[0023] In summary, this application includes the following beneficial technical effects: This application helps to more accurately understand users' behavior patterns and interests by collecting users' online behavior data on the platform and activity participation data of historical activities. Combining historical activity data, target users' online behavior data and activity participation data can carefully portray the target users' personalized preference portraits, which not only include users' preferences for different pages, products or services, but also cover users' participation in and feedback on historical activities. By using the target users' preference portraits, the platform can push content that is more in line with users' interests, thereby improving user experience and satisfaction. By analyzing the preference portraits of each user on the platform, the platform's user activity preferences can be summarized, which helps the platform understand the overall interest trends of the user group. Based on historical activity data and user activity preferences, the platform can formulate activities that are more attractive to users and have higher participation. By publishing activities, it can not only accurately meet customer needs, but also effectively promote social interaction between users and enhance the community atmosphere of the platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flowchart of an operation management method based on user behavior provided in an embodiment of the present application; Figure 2 It is a structural diagram of an operation management system based on user behavior provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following is combined with Figure 1 -Attached Figure 3 This application is described in further detail.

[0026] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make modifications to the present embodiment without any creative contribution as needed, but such modifications are protected by the patent law as long as they are within the scope of the claims of the present application.

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0029] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0030] The present application embodiment provides an operation management method based on user behavior, such as Figure 1 As shown, the method provided in the embodiment of the present application is performed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes steps S101 to S105, wherein: S101. Obtain user behavior data and historical activity data, where the user behavior data includes online behavior data of each user on the platform and activity participation data for historical activities.

[0031] Specifically, the types of platforms for operation and management include: insurance, car companies, banks, etc. The platform log recording system is used to capture and record the online behavior data of users on the platform in real time, including: browsing, clicking, purchasing, consulting, comments, etc. A database is set up in the electronic device, and the database stores historical activity data. The historical activity data includes detailed information of each historical activity, including: activity theme, time, participating users, user feedback, etc. The historical activities can be online or offline activities. For any user, the user's activity participation data includes which specific activities the user has participated in and the activity feedback after participating in the activities.

[0032] S102. Generate a preference profile of the target user based on historical activity data, the target user's online behavior data and activity participation data. The target user is any user on the platform.

[0033] Specifically, determine the preference profile of each user on the platform. Taking the target user as an example, the preference profile of the target user includes online behavior profile and activity participation profile. The online behavior profile represents the target user's online operation preferences or habits, and the activity participation profile represents the target user's preferences or habits for activities.

[0034] S103: Push platform content to target users based on their preference profiles.

[0035] Specifically, the online behavior profile in the target user's preference profile includes the content that the target user is interested in. For all the content to be pushed on the platform, the target user's estimated preference value for each content to be pushed is calculated according to the target user's online behavior profile as the push recommendation value. The various content to be pushed on the platform are arranged from large to small according to the corresponding push recommendation value, and the determined sorting result is pushed to the display interface of the target user's terminal device.

[0036] S104: Determine the user activity preference of the platform based on the preference profile of each user on the platform.

[0037] Specifically, the activity participation profiles in the preference profiles of all users on the platform are summarized, and the activity characteristics and preference levels of the platform users are extracted as the user activity preference.

[0038] S105: Formulate current platform activities based on historical activity data and user activity preferences, and publish the current platform activities to the platform.

[0039] Specifically, a historical activity with the highest degree of preference among platform users is determined from historical activities as a recommended activity, and new activity features are determined based on user activity preferences and activity features included in the recommended activity. The recommended activity and the new activity features are recommended to platform managers, so that the platform managers can formulate current platform activities and input them into electronic devices based on the received recommended activities and the new activity features.

[0040] This embodiment collects the user's online behavior data on the platform and the activity participation data of historical activities, which helps to more accurately understand the user's behavior patterns and interests. Combining the historical activity data, the target user's online behavior data and activity participation data can carefully portray the target user's personalized preference portrait, which not only includes the user's preferences for different pages, products or services, but also covers the user's participation in and feedback on historical activities. Using the target user's preference portrait, the platform can push content that is more in line with the user's interests, thereby improving user experience and satisfaction. By analyzing the preference portrait of each user on the platform, the platform's user activity preference can be summarized to obtain the platform's user activity preference, which helps the platform understand the overall interest trend of the user group. Based on historical activity data and user activity preference, the platform can formulate activities that are more attractive to users and have higher participation. By publishing activities, it can not only accurately meet customer needs, but also effectively promote social interaction between users and enhance the community atmosphere of the platform.

[0041] A possible implementation of the embodiment of the present application generates a preference profile of a target user based on historical activity data, online behavior data of the target user, and activity participation data, including: Determine the behavior type and behavior object of each operation of the target user based on the online behavior data of the target user. The behavior types include browsing, clicking, purchasing and consulting. The behavior object represents the page keywords, service or product names. Based on the preset score of each behavior type, the behavior type and behavior object of each operation, the behavior preference score of the target user for each behavior object is calculated, and the behavior preference score of the target user for each behavior object is stored as an online behavior profile; Based on historical activity data and the target user's activity participation data, an activity participation profile of the target user is generated. The online behavior profile and activity participation profile constitute the target user's preference profile.

[0042] In this embodiment, the online behavior data of the target user includes multiple operation data, each operation data includes: timestamp, behavior type (such as browsing, clicking, purchasing and consulting, etc.) and behavior object (such as the page keyword, service or product name, etc. of the operation). One operation includes a behavior type and a corresponding behavior object. For example, when browsing a certain page, the behavior object is the keyword of the page. It can also be when clicking on a certain service or product, and the behavior object is the service or product name. Among them, the behavior type and behavior object can be flexibly set by the platform administrator according to the platform type, and this embodiment does not limit it.

[0043] Taking any behavior object as an example, any behavior object is used as the target behavior object, and calculating the behavior preference score of the target user for the target behavior object includes: based on the behavior type and behavior object of each operation of the target user, determining that the behavior object is the behavior type of several operations of the target user, and calculating the sum of the preset scores corresponding to the behavior types of the several operations as the behavior preference score of the target user for the target behavior object. Referring to the above process, the behavior preference score of the target user for each behavior object is determined according to the online behavior data of the target user, and the behavior preference score of the target user for each behavior object constitutes the online behavior profile of the target object.

[0044] The preset score for each behavior type is set in advance by the platform administrator according to business needs. For example, the preset score for the purchase behavior type is higher than that for the click behavior type.

[0045] This embodiment analyzes the online behavior data of the target user (including browsing, clicking, purchasing, consulting and other behavior types and their corresponding page keywords, service or product names), and calculates the behavior preference score based on the preset score to build an online behavior portrait. At the same time, it integrates the historical activity data and activity participation data to generate an activity participation portrait, and finally integrates to form a complete preference portrait of the target user, which can accurately capture the user's personalized preferences and interests, provide strong data support for subsequent personalized content push and activity customization, and effectively improve user experience and platform operation efficiency.

[0046] A possible implementation of the embodiment of the present application generates an activity participation profile of a target user based on historical activity data and activity participation data of the target user, including: Based on the activity participation data of the target user, the historical activities in which the target user has participated are taken as the target historical activities; Extracting target users’ activity feedback on target historical activities from activity participation data; Extracting activity features of target historical activities from historical activity data; Based on activity feedback and activity features, the feature preference score of the target user for each activity feature in the target historical activities is determined, and the feature preference score of each activity feature constitutes the activity participation profile of the target user.

[0047] In this embodiment, the target user's activity participation data includes the activity name, participation time, user feedback, etc. The activity ID or activity name is extracted from the target user's activity participation data as the target historical activity, that is, the historical activity that the target user has participated in. The target user's feedback data on the target historical activity is extracted from the target user's activity participation data. The feedback data may include ratings, comments, likes, shares, questionnaires after activity participation, etc. The specific feedback type depends on the platform's activity feedback mechanism.

[0048] Relevant activity data of the target historical activities are extracted from the historical activity data. For any activity in the target historical activities, the activity features contained therein include one or more of the following: activity type, activity theme, activity prizes, participation conditions, activity form (online / offline), activity scale, etc. The specific feature type of each historical activity is determined by the specific activity content.

[0049] The target historical activities include several activities, each activity includes multiple activity features, and the same activity features in each activity feature of the target historical activities are divided into the same group to obtain multiple groups, each group includes one or more same activity features, and the feature number of the activity features in each group is recorded. For example, the feature of offline activities corresponding to a certain group has a corresponding feature number that is the number of offline activities in the target historical activities; the feature of activity prizes being vouchers corresponding to a certain group has a corresponding feature number that is the number of activities in the target historical activities where the activity prizes are vouchers.

[0050] Take any group of activity features as the target group, the features included in the target group are the target activity features, record the number of features in the target group as A, and calculate the feature preference score of the target user for the target activity features. Specifically, each feature in the target group comes from a historical activity, and the feedback data of the target user includes feedback data for each activity. The feedback data types include: comments, likes, shares, etc.

[0051] The same basic score is set for each activity feature in advance, and a scoring rule is set for each feedback data type. The scoring rules for comments include: counting the positive and negative emotions of each comment of the target user on a certain activity (this can be achieved through text analysis algorithms or pre-trained recognition models). If a comment is positive, the score of the comment is recorded as 1; if a comment is negative, the score of the comment is recorded as -1; if a comment has no obvious emotional tendency, the score of the comment is recorded as 0. The sum of the scores of each comment is calculated as the comment score. If the target user does not comment on the activity, the comment score is recorded as 0. The scoring rule for the number of likes is: the number of likes of the target user for a certain activity is recorded as the like score. The scoring rule for the number of shares is: the number of shares of the target user for a certain activity is recorded as the number of shares score.

[0052] For any feature in the target group, determine the activity to which the feature belongs, and calculate the comment score, like score, and share score based on the target user's feedback data on the activity, and use the sum of the comment score, like score, and share score as the target user's activity score for the activity. Referring to the above process, the target user's activity score for each activity in the target historical activities is calculated.

[0053] Then, find out whether the target user has participated in a questionnaire survey after participating in a certain activity. The feedback data also includes the questionnaires participated by the target user, and the questionnaire data contains the target user's score on the activity features. If the target user has not participated in any questionnaire survey, calculate the average activity score of the activities corresponding to the A features in the target group, and use the obtained average as the feature preference score of the target activity feature corresponding to the target group. Thus, the feature preference score of the target user for the features contained in each group of activity features is obtained.

[0054] If the target user has participated in the questionnaire survey, calculate the average activity score of the activities corresponding to each of the A features in the target group, and use the obtained average as the adjustment score of the target activity feature corresponding to the target group. The optional score of each activity feature in the questionnaire is a cardinality level, and the level represents satisfaction. The higher the level, the more satisfied the target user is with the feature. The levels from small to large correspond to different proportions. The score ratio of the level in the middle is 1, and the higher the level, the smaller the proportion. For the target group, the A features in the target group come from A activities. The number of activities in the A activities that the target user has participated in the questionnaire survey is recorded as B. The average of the B score ratios for the target activity features that the target user has participated in is calculated as the target ratio.

[0055] Set the same basic score for different activity features in advance, and take the product of the basic score of the target activity feature corresponding to the target group and the target ratio as the intermediate score of the target activity feature. Adjust the intermediate score according to the adjustment score of the target activity feature to obtain the feature preference score of the target activity feature. Each activity feature in the target historical activity corresponds to an intermediate score and an adjustment score. Sort the adjustment scores of each activity feature from small to large, calculate the ratio of the maximum value to the basic score of the activity feature, and divide each adjustment score by the ratio to obtain the adjusted target adjustment score. The target adjustment score is normalized within the range of 0 to the basic score. For any feature, the sum of the intermediate score and the target adjustment score is used as the feature preference score.

[0056] This embodiment analyzes the historical activities in which the target user has participated and their feedback, and combines the characteristics of the historical activity data. This technology can accurately calculate the characteristic preference scores of the target user for different activity characteristics, thereby generating a detailed activity participation portrait, which helps to deeply understand the user's activity preferences.

[0057] A possible implementation of the embodiment of the present application is to determine the user activity preference of the platform based on the preference profile of each user on the platform, including: Extract activity participation profiles from the preference profiles of each user on the platform; Based on each user's activity participation portrait, the sum of the feature preference scores of each user corresponding to each activity feature is calculated to obtain the comprehensive feature preference score of each activity feature on the platform; the comprehensive feature preference score of each activity feature on the platform constitutes the user's activity preference.

[0058] In this embodiment, the activity participation portrait of the target user includes the feature preference score of the target user for each activity feature. Assuming that for a certain activity feature, there is a corresponding feature preference score in the activity participation portraits of B users, the sum of the B feature preference scores is calculated as the comprehensive feature preference score of the activity feature. The comprehensive preference score of the activity feature represents the degree of preference of the platform users for the activity feature. The larger the score, the more popular the activity feature is among the platform users.

[0059] This embodiment summarizes the activity participation portrait of each user on the platform and calculates the comprehensive feature preference score of each activity feature. It can accurately measure the overall preference of platform users for various activity features, that is, user activity preference, and provide strong data support for the platform to optimize activity design and improve user participation and satisfaction.

[0060] A possible implementation of the embodiment of the present application is to formulate current platform activities based on historical activity data and user activity preferences, including: Based on the historical activity data and the user activity preference, the sum of the comprehensive feature preference scores of each activity feature included in each historical activity is calculated to obtain the total activity preference score of each historical activity; Select the historical activity with the largest total activity preference score from all historical activities as the recommended activity; Determine new activity features based on user activity preferences and activity features included in recommended activities; Recommend recommended activities and new activity features to platform managers, and receive current platform activities input by platform managers.

[0061] In this embodiment, for each historical activity, all activity features contained therein are traversed, and the corresponding comprehensive feature preference scores in the user activity preference are accumulated to obtain the total activity preference score of the historical activity. The total activity preference score represents the comprehensive preference degree of the platform user for the historical activity. The larger the score, the higher the preference degree of the platform user.

[0062] Traverse the activity features and user activity preferences included in the recommended activities, determine multiple activity features with the highest comprehensive feature preference scores that are not included in the recommended activities as new activity features, and the new activity features can be a feature list arranged from large to small according to the comprehensive feature preference scores. Recommend the recommended activities and new activity features to the platform administrator, who can flexibly select the top features from the feature list and add them to the recommended activities to obtain the current platform activities.

[0063] This embodiment calculates the total activity preference score by integrating historical activity data and user activity preferences, selects the most popular recommended activities, and introduces new activity features based on user preferences. It can intelligently assist platform managers in formulating activity plans that are more in line with user interests, thereby effectively improving the attractiveness and participation of activities and optimizing platform operating results.

[0064] A possible implementation of the embodiment of the present application is to push platform content to a target user based on a preference profile of the target user, including: Determine the behavior objects included in each content to be pushed on the platform, and calculate the sum of the behavior preference scores of each behavior object included in each content to be pushed to obtain the push recommendation value of each content to be pushed; Each content to be pushed on the platform is pushed to the display interface of the target user according to the corresponding push recommendation value from large to small.

[0065] In this embodiment, there will be a series of content to be pushed on the platform, which may include articles, videos, products, advertisements, etc. For each content to be pushed, the behavior objects used therein are identified and extracted. For text content, natural language processing technology is used for extraction, and for image content, image recognition algorithm is used for extraction.

[0066] After determining the push recommendation value of each content to be pushed, a push method is formulated, including the quantity, frequency, and display method of the pushed content. A larger recommendation quantity and frequency can be set for the content to be pushed with a large push recommendation value. The push quantity and frequency corresponding to different push recommendation values ​​can be pre-set, and the corresponding display method can be pre-set according to the form of the content to be pushed (text, video, product), which is not limited in this embodiment.

[0067] This embodiment is based on the preference portrait of the target user. It determines the push recommendation value by calculating the sum of the behavioral preference scores of each content to be pushed on the platform, and displays the content to the user from high to low according to this value. This technology can accurately match user interests, improve the personalization and relevance of content push, thereby enhancing the user experience and user stickiness of the platform.

[0068] A possible implementation of the embodiment of the present application is to obtain the new user information and the user information of each historical user on the platform when there is a new user on the platform; Match the newly added user information with the user information of each historical user to determine the target historical user that best matches the newly added user information; The preference profile of the target historical user is retrieved, and platform content is pushed to the new user based on the preference profile of the target historical user.

[0069] In this embodiment, the newly added user information includes the basic information of the newly added user, such as user name, registration time, gender, age, geographic location, etc. The historical user refers to the user who has registered on the platform and has a preference profile. The user information of each historical user is extracted from the database of the platform. This information should include the basic information of the historical user, historical behavior data, and the constructed preference profile. Use a suitable similarity calculation method (such as cosine similarity, Euclidean distance, Jaccard similarity coefficient, etc.) to match the new user information with the user information of each historical user, calculate the similarity between them, and select the historical user with the highest similarity to the new user as the target historical user according to the similarity calculation result. Referring to the above-mentioned step of pushing platform content to the target user based on the preference profile of the target user, the platform content is pushed to the new user based on the preference profile of the target historical user.

[0070] In this embodiment, when a new user appears on the platform, the most similar target historical user is determined by matching the new user information with the historical user information, and content is pushed to the new user based on the preference profile of the target historical user. This strategy can quickly provide personalized content for the new user, effectively shorten the new user's adaptation period, and improve the user experience and the user appeal of the platform.

[0071] The present application embodiment provides an operation management system based on user behavior, such as Figure 2 As shown, the system includes: an acquisition module 201, a generation module 202, a push module 203, a determination module 204 and a formulation module 205, wherein: An acquisition module 201 is used to acquire user behavior data and historical activity data, wherein the user behavior data includes online behavior data of each user on the platform and activity participation data for historical activities; A generation module 202 is used to generate a preference profile of a target user based on historical activity data, online behavior data of the target user, and activity participation data. The target user is any user on the platform; Push module 203, used to push platform content to target users based on their preference profiles; A determination module 204, configured to determine a user activity preference of the platform based on a preference profile of each user on the platform; The formulation module 205 is used to formulate the current platform activity based on the historical activity data and the user activity preference, and publish the current platform activity to the platform.

[0072] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0073] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0074] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0075] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0076] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above-mentioned embodiment of the operation management method based on user behavior.

[0077] Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0078] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer-readable storage medium is run on a computer, the computer can execute the contents shown in the aforementioned embodiment of the operation management method based on user behavior.

[0079] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0080] An embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the contents shown in the aforementioned embodiment of the operation management method based on user behavior are implemented.

[0081] The above are only some implementation methods 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. An operation management method based on user behavior, characterized in that: include: Obtaining user behavior data and historical activity data, wherein the user behavior data includes online behavior data of each user on the platform and activity participation data for historical activities; Based on the historical activity data, the online behavior data and activity participation data of the target user, a preference profile of the target user is generated, where the target user is any user on the platform; Pushing platform content to the target user based on the preference profile of the target user; Determining the user activity preference of the platform based on the preference profile of each user on the platform; A current platform activity is formulated based on the historical activity data and the user activity preference, and the current platform activity is published to the platform.

2. The operation management method based on user behavior according to claim 1, characterized in that: The generating a preference profile of the target user based on the historical activity data, the online behavior data and the activity participation data of the target user includes: Determine the behavior type and behavior object of each operation of the target user based on the online behavior data of the target user, wherein the behavior type includes browsing, clicking, purchasing and consulting, and the behavior object represents a page keyword, service or product name; Based on the preset score of each behavior type, the behavior type and behavior object of each operation, the behavior preference score of the target user for each behavior object is calculated, and the behavior preference score of the target user for each behavior object is stored as an online behavior profile; Based on the historical activity data and the activity participation data of the target user, an activity participation portrait of the target user is generated, and the online behavior portrait and the activity participation portrait constitute a preference portrait of the target user.

3. The operation management method based on user behavior according to claim 2, characterized in that: The generating the activity participation portrait of the target user based on the historical activity data and the activity participation data of the target user includes: Based on the activity participation data of the target user, taking the historical activities in which the target user has participated as target historical activities; Extracting the target user's activity feedback on the target historical activity from the activity participation data; extracting activity features of the target historical activity from the historical activity data; Based on the activity feedback and the activity features, a feature preference score of the target user for each activity feature in the target historical activities is determined, and the feature preference score of each activity feature constitutes an activity participation profile of the target user.

4. The operation management method based on user behavior according to claim 1, characterized in that: Determining the user activity preference of the platform based on the preference portrait of each user on the platform includes: Extracting an activity participation profile from the preference profile of each user on the platform; Based on the activity participation portrait of each user, the sum of the feature preference scores of each user corresponding to each activity feature is calculated to obtain a comprehensive feature preference score of each activity feature on the platform; the comprehensive feature preference score of each activity feature on the platform constitutes the user activity preference.

5. The operation management method based on user behavior according to claim 1, characterized in that: The formulating the current platform activity based on the historical activity data and the user activity preference includes: Based on the historical activity data and the user activity preference, the sum of the comprehensive feature preference scores of the various activity features included in each historical activity is calculated to obtain a total activity preference score for each historical activity; Selecting a historical activity with the largest total score of the activity preference from various historical activities as a recommended activity; Determining new activity features based on the user activity preference and the activity features included in the recommended activity; The recommended activities and the newly added activity features are recommended to the platform administrator, and the current platform activities input by the platform administrator are received.

6. The operation management method based on user behavior according to claim 1, characterized in that: The pushing of platform content to the target user based on the preference profile of the target user includes: Determine the behavior objects included in each content to be pushed on the platform, and calculate the sum of the behavior preference scores of each behavior object included in each content to be pushed to obtain the push recommendation value of each content to be pushed; Each content to be pushed on the platform is pushed to the display interface of the target user according to the corresponding push recommendation value from large to small.

7. The operation management method based on user behavior according to claim 1, characterized in that: The method further comprises: When there is a new user on the platform, obtain the new user information and the user information of each historical user on the platform; Matching the newly added user information with the user information of each historical user to determine a target historical user that best matches the newly added user information; The preference portrait of the target historical user is retrieved, and platform content is pushed to the newly added user based on the preference portrait of the target historical user.

8. An operation management system based on user behavior, characterized in that: include: An acquisition module, used to acquire user behavior data and historical activity data, wherein the user behavior data includes online behavior data of each user on the platform and activity participation data for historical activities; A generation module, used to generate a preference profile of the target user based on the historical activity data, the online behavior data and activity participation data of the target user, where the target user is any user on the platform; A push module, used to push platform content to the target user based on the preference profile of the target user; A determination module, configured to determine a user activity preference of the platform based on a preference profile of each user on the platform; A formulation module is used to formulate current platform activities based on the historical activity data and the user activity preference, and publish the current platform activities to the platform.

9. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the user behavior-based operation management method described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the user behavior-based operation management method described in any one of claims 1 to 7.

Images