A method, device, medium and equipment for generating an intelligent activity flow

Abstract

The application relates to the fields of artificial intelligence and digital medicine, and discloses a method, device, medium and equipment for generating an intelligent activity process, which comprises the following steps: acquiring a crowd label, an activity time and an activity type of an activity crowd; generating an intelligent activity process and setting a timing task according to the crowd label, the activity time and the activity type of the activity crowd; and executing corresponding actions according to the execution sequence of the intelligent activity process after the timing task is triggered. The embodiments of the application can generate a branch structure of an activity process by combining a crowd label, and form a final intelligent activity process through the adjustment of a user, so that flexible configuration and intelligent optimization of the activity process are realized, diversified and personalized processes are realized, and the technical problems of single activity form and low matching degree between a target crowd and an activity process are solved.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence and digital healthcare, and in particular to a method, apparatus, medium, and device for generating intelligent activity processes. Background Technology

[0002] We are currently in the retail digitalization 3.0 stage: "people" have become the core of retail transformation, and the main goal of this stage is to achieve digital reach, operation and management of "people" across all channels.

[0003] The service model has shifted from traditional individuals or users to digital users. Institutions need to leverage the latest technologies and online channels to provide continuous service and operations to users. They need the capability to manage and sustain user engagement. For example, in the healthcare field, most hospital internet healthcare service platforms currently focus on lightweight services such as appointments, registration, and examinations. However, a significant portion of healthcare expenditures occur within hospital settings, including testing, treatment, medication, surgery, and hospitalization. Healthcare needs are complex, long-term, and personalized. The healthcare closed loop includes health management, self-diagnosis, self-medication, triage, waiting, diagnosis, treatment, in-hospital rehabilitation, and out-of-hospital rehabilitation. Among these, diagnostic and treatment services are the most essential and have the greatest service value. However, current internet healthcare platforms cannot yet reach these two core aspects. Neither pharmacies nor hospitals can create a closed loop for the patient's medical process. As people's living standards improve, they are no longer satisfied with simply "getting cured" but desire comprehensive health services throughout their entire lifespan. Instead, the focus has shifted from simply treating illness to health management, aiming to achieve the ultimate goal of reducing medication and hospital visits, thereby improving the overall health of the population. However, health management is individualized, and existing standardized service processes are no longer suitable. Similarly, in the commercial sector, existing technologies allow for the creation of different campaign flows based on various marketing activities, enabling proactive marketing, consumer behavior marketing, and targeted marketing. Each marketing campaign requires highly customized development and configuration of the campaign flow and UI, with each campaign individually requiring specific execution time, conditions, and content. Because these processes are relatively fixed, they are difficult to reuse across multiple campaigns and cannot be intelligently optimized based on audience tags and marketing objectives using historical campaign analysis. This fails to leverage the value of historical marketing feedback data, and the promotional methods are limited, resulting in inaccurate matching between target audiences and campaign flows. Furthermore, more manual design, adjustment, and optimization are required, increasing labor costs and the complexity of designing and implementing each marketing campaign. Summary of the Invention

[0004] In view of this, this application provides a method, apparatus, storage medium and computer equipment for generating intelligent event processes, which can realize flexible configuration and intelligent optimization of event processes, realize diversified promotion forms, and solve the technical problems of single promotion forms and low matching degree between target groups and event processes.

[0005] According to one aspect of this application, a method for generating intelligent activity flows is provided, comprising:

[0006] Obtain the audience tags, event time, and event type of the event participants. The audience tags include user profiles, user attributes, and user characteristics.

[0007] Based on the audience tags, activity time, and activity type of the participants, an intelligent activity flow is generated and a scheduled task is set. The activity flow includes at least one branch and at least two flow nodes. The flow nodes are either condition judgment nodes or action execution nodes. The connection order between the nodes is the execution order of the intelligent activity flow, and the activity time is the execution time of the intelligent activity flow.

[0008] Once a scheduled task is triggered, the corresponding actions are executed according to the execution order of the intelligent activity flow.

[0009] Optionally, the step of generating an intelligent activity flow and setting scheduled tasks based on the crowd tags, activity time, and activity type of the active participants specifically includes:

[0010] Based on the activity time and activity type, set the activity time trigger node and the activity type judgment node to perform the initial process configuration and initialize the scheduled task;

[0011] Based on the audience tags and activity type determination results, an activity flow branch structure is generated through a precise flow model. The activity flow branch structure consists of an ordered connection of at least one flow node and at least one activity sub-flow. The audience tags correspond to the activity sub-flows.

[0012] In response to user adjustments to the event flow, the system adjusts the event flow nodes and branch structure, generates an intelligent event flow, and sets scheduled tasks.

[0013] Optionally, before the step of generating a smart activity flow and setting a scheduled task based on the crowd tags, activity time, and activity type of the active population, the following steps are included:

[0014] Obtain user feedback data from historical activities, and generate an accurate process model based on the user feedback data and collaborative filtering algorithm.

[0015] Optionally, the condition judgment node includes at least one of the following: activity time trigger condition node, activity type judgment node, activity audience tag judgment node, and user behavior judgment node; the action execution node includes at least one of the following: marketing page redirection, lucky draw activity, coupon distribution, and sharing / forwarding.

[0016] Optionally, before the step of obtaining the audience tags, event time, and event type of the event participants, the method further includes:

[0017] Access local and / or external data through at least one of the following methods: table upload, image upload, video upload, adding a database, adding a data table interface, or API interface binding.

[0018] Optionally, distribution channels include: web links, WeChat links, H5 links, SMS, and embedded pages in the app.

[0019] According to a first aspect of this application, an apparatus for generating intelligent activity processes is provided, comprising:

[0020] The acquisition module is used to acquire the audience tags, event time, and event type of the event participants. The audience tags include user profiles, user attributes, and user characteristics.

[0021] The process generation module is used to generate an intelligent activity process and set a scheduled task based on the crowd tags, activity time and activity type of the activity crowd. The activity process includes at least one branch and at least two process nodes. The process nodes are condition judgment nodes or action execution nodes. The connection order between the nodes is the execution order of the intelligent activity process. The activity time is the execution time of the intelligent activity process.

[0022] The execution module is used to perform corresponding actions according to the execution order of the intelligent activity flow after the timed task set by the generation module is triggered.

[0023] Optionally, the process generation module specifically includes:

[0024] The configuration unit is used to set the activity time trigger node and the activity type judgment node according to the activity time and activity type to perform the initial configuration of the process and initialize the scheduled task;

[0025] The generation unit is used to generate an activity process branch structure based on the crowd tags and activity type judgment results of the activity crowd, through a precise process model. The activity process branch structure is an ordered connection of at least one process node and at least one activity sub-process, and the crowd tags correspond to the activity sub-process.

[0026] The adjustment unit is used to respond to user adjustments to the activity flow, adjust the nodes and branch structure of the activity flow, generate intelligent activity flows, and set scheduled tasks.

[0027] Optionally, the device may further include a model generation module, used to obtain user feedback data from historical activities and generate an accurate process model based on the user feedback data and a collaborative filtering algorithm before the process generation module generates an intelligent activity process and sets a scheduled task according to the crowd tags, activity time and activity type of the active population.

[0028] Optionally, the device may further include a data interface module, used to access local data and / or external data through at least one of the following methods before the acquisition module acquires the crowd tags, activity time and activity type of the active crowd: table upload, image upload, video upload, adding a database, adding a data table interface, and API interface binding.

[0029] According to another aspect of this application, a storage medium is provided that stores a computer program thereon, which, when executed by a processor, implements the above-described method for generating intelligent activity flows.

[0030] According to another aspect of this application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the program to implement the above-described method for generating intelligent activity flows.

[0031] By employing the above technical solutions, this application provides a method, apparatus, storage medium, and computer device for generating intelligent activity flows. First, it acquires the audience tags, activity time, and activity type of the target audience. The audience tags include user profiles, user attributes, and user characteristics. Then, based on the audience tags, activity time, and activity type, it generates an intelligent activity flow and sets a scheduled task. The activity flow includes at least one branch and at least two flow nodes. Flow nodes are condition judgment nodes or action execution nodes. The connection order between nodes is the execution order of the intelligent activity flow, and the activity time is the execution time of the intelligent activity flow. After the scheduled task is triggered, the corresponding actions are executed according to the execution order of the intelligent activity flow. This application embodiment can generate a branch structure for the activity flow by combining audience tags and form the final intelligent activity flow through user adjustments, achieving flexible configuration and intelligent optimization of the activity flow, realizing diversified and personalized flows, and solving the technical problems of single activity forms and low matching degree between target audiences and activity flows.

[0032] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0033] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0034] Figure 1 A flowchart illustrating a method for generating an intelligent activity flow according to an embodiment of this application is shown.

[0035] Figure 2 A flowchart illustrating a method for generating an intelligent activity flow according to an embodiment of this application is shown.

[0036] Figure 3 This illustration shows a schematic diagram of historical feedback data generated by an intelligent activity provided in an embodiment of this application;

[0037] Figure 4 This illustration shows a schematic diagram of historical feedback data generated by another intelligent activity provided in an embodiment of this application;

[0038] Figure 5 A schematic diagram of the structure of an intelligent activity flow generation device provided in an embodiment of this application is shown. Detailed Implementation

[0039] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0040] This embodiment provides a method for generating intelligent activity flows, such as... Figure 1 As shown, the method includes:

[0041] Step 101: Obtain the audience tags, event time, and event type of the event participants. The audience tags include user profiles, user attributes, and user characteristics.

[0042] Optionally, the configuration of the activity process in this embodiment requires pre-binding data sources (basic information data of the target audience, marketing activity data), multimedia material library (images, animations, short videos, etc.), API interfaces (e.g., coupon platform interfaces, lottery interfaces, etc.) and uploading local data (e.g., table uploads, image uploads, video uploads). The target audience in this embodiment can be marketing users categorized for commercial marketing purposes or patient groups categorized by disease characteristics (people with chronic diseases, people with hypertension, hyperlipidemia, and hyperglycemia, etc.).

[0043] Optionally, the activities in this implementation may include a variety of contents and forms, but are not limited to service activities (hospital patient services, pharmacy membership services, commercial medical insurance user services), marketing activities, business activities, etc.

[0044] Step 102: Generate an intelligent activity flow and set a scheduled task based on the crowd tags, activity time and activity type of the active crowd. The activity flow includes at least one branch and at least two flow nodes. The flow nodes are condition judgment nodes or action execution nodes. The connection order between the nodes is the execution order of the intelligent activity flow. The activity time is the execution time of the intelligent activity flow.

[0045] To achieve accurate matching between the event flow and audience tags, a smart event flow can be generated and timed tasks can be set based on the audience tags, event time, and event type. Specifically, this may include:

[0046] Step 102-1: Based on the activity time and activity type, set the activity time trigger node and activity type judgment node to perform initial process configuration and initialize the scheduled task;

[0047] Step 102-2: Based on the audience tags and activity type judgment results of the event audience, generate an event flow branch structure through a precise flow model. The event flow branch structure is an ordered connection of at least one flow node and at least one event sub-flow. The audience tags correspond to the event sub-flows.

[0048] The audience tags in this step can include various types of tags and their combinations. The activity type may also include product tags, and at the same time, a correspondence is formed between audience tags and individual product tags, and between audience tags and user attributes. Furthermore, audience tags can be divided vertically into basic tags and behavioral tags. The activity sub-process is specifically an ordered connection of a series of execution nodes and condition nodes.

[0049] Basic tags are used to segment users based on their registration information and historical consumption records. For commercial activities, these can include gender, age, geographic location, occupation, and spending power; for the medical service sector, they can include disease type and medical insurance type. Behavioral tags, for commercial activities, refer to tags based on users' browsing, favorites, adding to cart, placing orders, and whether they will repurchase. For medical services, these can include push notifications for prevention, medication purchase, and diagnostic reports. Product tags are tags summarized from conversion data of a product over a period of time. The more data and the more detailed the data, the more accurate the tag positioning. Product tags are also used to mark individual products based on a single user's consumption cycle, related product purchasing power, and repurchase rate.

[0050] To more specifically describe the process of generating the activity flow branch structure using the precise process model in this step, a specific implementation method is given in a business scenario. For example: A smart early warning indicator (active user order conversion rate) has been pre-set. If this indicator value is abnormally low between 9:00 and 10:00 AM on January 5, 2022, with the abnormal dimension being a low active user order conversion rate in Chongqing, the activity flow generation will be triggered. Generation can be fully automated after triggering or manually assisted after a reminder. Regardless of the method used, this step will automatically match the pre-created marketing operation plan, reaching active users in Chongqing who have not yet placed orders with subscription notifications / WeChat / Alipay / SMS / push messages (equivalent to a conditional judgment node for active users placing orders and an activity sub-flow subscription notification / WeChat / Alipay / SMS / push message), and issuing coupons (action execution node) to improve the active user order conversion rate in Chongqing. Once the active user order conversion rate in the city returns to normal after reaching the target, the smart marketing operation plan automatically ends and collects actual feedback data as the basis for subsequent intelligent generation of branch structures. In the context of healthcare services, for example, when a patient purchases a certain medication (such as a medication for chronic diseases), a service process tailored to people with chronic diseases can be generated based on the medication's relevant information, such as its duration, efficacy, treatment stage, combination medications, and pathological prevention. During the user's medication use, reminders or push notifications for prevention and medication purchase can be triggered. Alternatively, user tags can be extracted from the user's uploaded diagnostic reports and consultation content to segment the population and build a refined process model.

[0051] Optionally, before step 102, the process may include obtaining user feedback data from historical activities and generating an accurate process model based on the user feedback data and a collaborative filtering algorithm. Specifically, the accurate process model generation process can be implemented using a collaborative filtering algorithm, for example:

[0052] In commercial event scenarios, collaborative filtering algorithms based on event sub-processes intelligently assign users to event sub-processes with the best click-through rate, user engagement, and user conversion rate by combining audience tags. For example... Figure 3 The sample set formed by feedback data based on historical activities listed in this implementation is used to generate an accurate process model based on this sample set using a collaborative filtering algorithm. The specific process is as follows:

[0053] Firstly, according to Figure 3 The listed scenarios (existing user vectors) are used to calculate the similarity between users, identifying n similar users and labeling them with a user group tag. This tag indicates that this user group prefers distribution methods like WeChat official accounts and H5 pages, resulting in the highest reach (click-through rate). Furthermore, this user group favors coupons and lucky draws, leading to the highest conversion rate. Therefore, any user matching this tag category can be used to generate activity sub-processes in this way. User selection is achieved through a series of conditional nodes, which can be integrated into the front end of the activity sub-process as a data preprocessing step. The generated activity process is intelligently generated based on historical data and can then be manually fine-tuned to tailor specific settings for each activity.

[0054] In healthcare scenarios, collaborative filtering algorithms based on activity sub-processes intelligently assign users activity sub-processes with optimal user satisfaction and follow-up visit rates by combining patient demographic tags. For example... Figure 3 The sample set formed by feedback data based on historical activities listed in this implementation is used to generate an accurate process model based on this sample set using a collaborative filtering algorithm. The specific process is as follows:

[0055] Firstly, according to Figure 4 The listed scenarios (existing patient vectors) are used to calculate the similarity between patients, identifying n similar patients and labeling them with a demographic tag. This tag indicates that this user type prefers service notifications via phone, SMS, official accounts, and mini-programs, resulting in the highest satisfaction. Furthermore, this user type prefers specialist outpatient services and home visits, leading to the highest user satisfaction or repeat visit rate. Therefore, any user matching this tag category can have their service sub-processes generated in this way. User selection is achieved through a series of conditional nodes, which can be integrated into the front end of the activity sub-process as a data preprocessing step. The resulting service process is intelligently generated based on historical data, meeting the personalized needs of different patient types. It can then be manually fine-tuned to specify the individual requirements of each patient.

[0056] Step 102-3: Respond to the user's adjustment operation on the activity process, adjust the nodes and branch structure of the activity process, generate the intelligent activity process and set the scheduled task.

[0057] Optionally, the condition judgment node includes at least one of the following: activity time trigger condition node, activity type judgment node, activity audience tag judgment node, and user behavior judgment node; the action execution node includes at least one of the following: marketing page redirection, lucky draw activity, coupon distribution, and sharing / forwarding.

[0058] Optionally, to expand the diversity of promotion methods, multiple distribution channels can be configured, including: web links, WeChat links, H5 links, SMS, and APP embedded pages.

[0059] The activity flow and configuration in this step can be based on existing front-end frameworks (React, Vue, Angular, etc.) that can implement various visual modeling frameworks. Each node can be defined as a different type of icon. The activity flow generated in step 102 consists of multiple icon nodes and connecting lines between nodes. Clicking different nodes can set the node type as a condition judgment node or an action execution node. The arrows connecting the nodes indicate the execution order of the flow. Different judgment conditions or execution actions can be set for a single node. In step 102-1, the user first sets the initial conditions, sets the activity time trigger node and the activity type judgment node. In step 102-2, it is necessary to determine the activity based on the user's preferences. The group's audience tags and activity type judgment results are used to generate an activity flow branch structure through a precise process model. This marketing model is an optimized model based on feedback data from the activity flow. The marketing model can include various methods, such as: Method 1: setting audience priorities and pushing content based on the audience's preferred methods (WeChat H5 push, WeChat friend sharing), and preferred marketing methods (e.g., preferred vouchers, lucky draws, etc.); Method 2: using the historical feedback indicator distribution of multiple different marketing activity flows as a training dataset to train an automatic learning model to predict the distribution of marketing feedback for each different activity flow branch. After obtaining the predicted distribution, the optimal activity flow branch is derived. After generating the optimal activity flow branch, the next step of adjustment is performed. This next adjustment can be understood as a kind of manual fine-tuning by the user, adjusting the specific flow, such as... Figure 2 As shown in the diagram, the audience labels correspond to the activity sub-processes, and the activity sub-processes are the branching structures of the activity process (corresponding to...). Figure 2 The branch structures (branch structure 1 and branch structure 2) are the optimized results obtained by the system based on the marketing model. Each branch structure includes distribution channels, process nodes, etc. In optimal conditions, no manual adjustments are needed from the user; the default settings are sufficient. However, users can customize the configuration of individual sub-processes within the activity. Figure 2The right side of the page displays various condition nodes and execution nodes. Based on user basic information and audience tags, the user group is selected and the event flow is configured. For example: User is a registered user -> User authorizes registration, triggering a new user gift -> Purchase the new user gift product -> Participate in subsequent promotional activities (blind boxes, lucky draws, lucky bags, etc., not limited to the above activities). The generated activity flow can be divided into a business abstract flow and a page execution flow. The business is abstracted to form a business abstract flow. The business abstract flow uses the process editor function to logically arrange the non-page execution layer to form a marketing behavior loop. For example, multiple abstract logics such as login / registration, browsing the activity homepage, displaying activity products, triggering user tags, tag association, user behavior path, order submission, order confirmation, payment, and post-payment marketing are arranged and recombined to form a complete marketing behavior logic loop. Then, relying on the template editor, the business abstract flow is presented on the page to form the page execution flow. What the activity audience perceives is the page execution flow.

[0060] Step 103: After the scheduled task is triggered, the corresponding actions are executed according to the execution order of the intelligent activity process.

[0061] The intelligent activity flow generation method provided in this invention obtains the audience tags, activity time, and activity type of the activity participants. The audience tags include user profiles, user attributes, and user characteristics. Then, based on the audience tags, activity time, and activity type, an intelligent activity flow is generated and a scheduled task is set. The activity flow includes at least one branch and at least two flow nodes. Flow nodes are condition judgment nodes or action execution nodes. The connection order between nodes is the execution order of the intelligent activity flow, and the activity time is the execution time of the intelligent activity flow. After the scheduled task is triggered, the corresponding actions are executed according to the execution order of the intelligent activity flow. This embodiment of the application can generate the branch structure of the activity flow by combining audience tags and form the final intelligent activity flow through user adjustments, achieving flexible configuration and intelligent optimization of the activity flow, realizing diversified and personalized flows, and solving the technical problems of single activity forms and low matching degree between target audience and activity flow.

[0062] To apply the methods described in these embodiments of the invention to various marketing scenarios and establish a marketing middleware system for enterprises, external systems can be configured to access and use the methods described in these embodiments of the invention through authorized access.

[0063] When users access the marketing campaign page directly through other means, there are two login authorization modes to obtain the system's campaign flow generation capabilities. The authorization modes can include at least the following methods:

[0064] Mode 1: When a user accesses the marketing campaign page directly through other means, the marketing campaign will notify the external system via a notification callback that a user has entered the marketing campaign page and authorized login. The marketing campaign will generate a unique code for the user under the corresponding campaign. After the external system checks the user information to determine whether it is new or old, it will call the marketing campaign's OAuth2 authorization login mechanism and send back the user's pre-generated unique code. The marketing campaign will then destroy the user information and determine whether the user is eligible to participate in the subsequent campaign process. If the user is not eligible to participate in the marketing campaign, the system will notify the user through a Toast layer.

[0065] Mode 2: When a user accesses the marketing campaign page directly through other means, the campaign will invoke a pre-set authorization page on the external system, prompting the user to log in and authorize. After the user completes authorization and login on the external system, they are redirected to the marketing campaign page. The external system uses the OAuth2 authorization login mechanism of the marketing campaign to generate a unique user ID for the current campaign within the marketing campaign system. This binding relationship is released in the marketing campaign system after the user completes the campaign. If the campaign determines that the user is eligible to participate, they will proceed to the next stage of the campaign participation process. If the user is not eligible to participate, a Toast notification will be sent to the user through the system's Toast layer.

[0066] To improve the accuracy of later activity models, historical data is accumulated for learning. Feedback data from each node is collected in the backend. When the program reaches a node during execution, it is determined whether there is an event binding, whether it is triggered by the system or by a person, and whether the node needs to be changed to provide data feedback after triggering. For example, if a marketing user has logged in and authorized and meets the conditions for participating in the activity, a lottery will be held (list of activities). The marketing activity will calculate the lottery results according to the set activity rules and return the data to the external system according to the subsequent process set when the activity was created, such as questionnaires or no process. The marketing activity will provide real-time feedback on the current activity results and generate icons according to the activity cycle.

[0067] The generation of intelligent activity processes can be triggered for fully automated process construction or prompted for manual process construction. For example, when a user's single-item consumption cycle is about to end, the system will automatically push coupons / product recommendation articles, bundles, etc. to activate the user (activation content or form can be flexibly configured). By continuously recording and efficiently statistically analyzing the activation methods, the system will automatically adjust the activation order to ensure activation success rate, reduce business operating costs, and increase customer repurchase rate and number of active users. If the order volume of a certain period has decreased, and the company wants to increase the order volume through marketing activities, then a campaign can be created targeting users who registered this year and whose user tags are still in the mature stage, excluding users who engage in fraudulent orders. If they do not place an order within 10 minutes of launching the app, the system will send them a text message and a coupon to encourage them to place an order. Once they complete the order, the expected goal will be achieved. Once the number of users and marketing rules reach a certain level, the system will have a scientific basis for each marketing strategy and operation plan, which will trigger intelligent early warning. The system's objective analysis is more scientific and does not require human data analysis. When the system determines that a user has not accessed the site for a certain period of time, it will perform a user wake-up operation and try to wake up the user through various wake-up attempts. After the user is re-wake up, the user profile and the success rate of the outreach method will be recalculated.

[0068] The implementation of this embodiment relies on the following: First, a comprehensive data product system and data indicator system are established, clearly defining indicator attributes and dimensions. Second, key operational indicators are intelligently monitored, and intelligent early warnings are issued based on historical indicator data and changes in related indicator data. Abnormal attributes, dimensions, abnormal users, and concurrent early warning indicators of the indicators are analyzed. Then, the intelligent activity process generation method in this embodiment is used to generate abnormal dimensions of operational indicators that trigger early warnings. The marketing automatically ends when the early warning ends, and the time granularity of the indicators can be subdivided to hours, days, and months. Finally, the implementation effect of the strategy is further analyzed and data is collected to guide strategy iteration, forming a self-optimizing closed loop of data-driven operation.

[0069] Furthermore, as Figure 1 In this application embodiment, a device for generating intelligent activity flows is provided, such as... Figure 5 As shown, the device includes:

[0070] The acquisition module 520 is used to acquire the audience tags, event time and event type of the event audience. The audience tags include user profile, user attributes and user characteristics.

[0071] The process generation module 530 is used to generate intelligent activity processes and set timed tasks based on the crowd tags, activity time and activity type of the activity participants. The activity process includes at least one branch and at least two process nodes. The process nodes are condition judgment nodes or action execution nodes. The connection order between nodes is the execution order of the intelligent activity process, and the activity time is the execution time of the intelligent activity process.

[0072] The execution module 540 is used to execute corresponding actions according to the execution order of the intelligent activity flow after the timed task set by the generation module is triggered.

[0073] Optionally, the process generation module 530 specifically includes:

[0074] Configuration unit 531 is used to set the activity time trigger node and activity type judgment node according to the activity time and activity type to perform initial process configuration and initialize the scheduled task;

[0075] The generation unit 532 is used to generate an activity process branch structure based on the audience tags and activity type judgment results of the activity audience through a precise process model. The activity process branch structure consists of an ordered connection of at least one process node and at least one activity sub-process, with the audience tags corresponding to the distribution channels and activity sub-processes.

[0076] The adjustment unit 533 is used to respond to the user's adjustment operation on the activity process, adjust the nodes and branch structure of the activity process, generate intelligent activity processes, and set timed tasks.

[0077] Optionally, the device may further include a model generation module 550, which is used to obtain user feedback data from historical activities and generate an accurate process model based on the user feedback data and a collaborative filtering algorithm before the process generation module generates an intelligent activity process and sets a scheduled task according to the crowd tags, activity time and activity type of the active population.

[0078] Optionally, the device may also include a data interface module 510, which is used to access local data and / or external data through at least one of the following methods before the acquisition module acquires the crowd tags, event time and event type of the active crowd: table upload, image upload, video upload, adding a database, adding a data table interface, and API interface binding.

[0079] It should be noted that other corresponding descriptions of the functional units involved in the intelligent activity flow generation device provided in this application embodiment can be found in the following references. Figures 1 to 2 The corresponding descriptions in the method will not be repeated here.

[0080] Based on the above, Figures 1 to 2Accordingly, this application also provides a storage medium storing a computer program, which, when executed by a processor, implements the above-described method. Figures 1 to 2 The method for generating intelligent activity flows is shown.

[0081] Based on this understanding, the technical solution of this application can be embodied in the form of a software product. This software product can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or portable hard drive), and includes several instructions to cause a computer device (such as a personal computer, server, or network device) to execute the methods described in the various implementation scenarios of this application.

[0082] Based on the above, Figures 1 to 2 The method shown, and Figure 3 To achieve the above objectives, the present application also provides a computer device, specifically a personal computer, server, network device, etc., as shown in the virtual device embodiment. This computer device includes a storage medium and a processor; the storage medium stores a computer program; the processor executes the computer program to achieve the above-described objectives. Figures 1 to 2 The method for generating intelligent activity flows is shown.

[0083] Optionally, the computer device may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Bluetooth interfaces, Wi-Fi interfaces), etc.

[0084] Those skilled in the art will understand that the computer device structure provided in this embodiment does not constitute a limitation on the computer device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0085] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages and stores the hardware and software resources of a computer device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software within the physical device.

[0086] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented using software plus necessary general-purpose hardware platforms, or it can be implemented using hardware. First, the audience tags, activity time, and activity type of the active group are obtained. The audience tags include user profiles, user attributes, and user characteristics. Then, based on the audience tags, activity time, and activity type, an intelligent activity flow is generated and a scheduled task is set. This activity flow includes at least one branch and at least two flow nodes. Flow nodes are condition judgment nodes or action execution nodes. The connection order between nodes is the execution order of the intelligent activity flow, and the activity time is the execution time of the intelligent activity flow. After the scheduled task is triggered, the corresponding actions are executed according to the execution order of the intelligent activity flow. This application embodiment can generate a branch structure for the activity flow by combining audience tags, and form the final intelligent activity flow through user adjustments, achieving flexible configuration and intelligent optimization of the activity flow, realizing diversified and personalized processes, and solving the technical problems of single activity forms and low matching degree between target audiences and activity flows.

[0087] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing this application. Those skilled in the art will understand that the modules in the apparatus of the embodiment can be distributed within the apparatus of the embodiment as described, or can be modified to be located in one or more apparatuses different from this embodiment. The modules of the above-described embodiment can be combined into one module, or further divided into multiple sub-modules.

[0088] The serial numbers in this application are for descriptive purposes only and do not represent the superiority or inferiority of any particular implementation scenario. The above disclosures are merely a few specific implementation scenarios of this application; however, this application is not limited thereto, and any variations conceived by those skilled in the art should fall within the protection scope of this application.

Claims

1. A method for generating an intelligent marketing process, characterized in that, include: Obtain the audience tags, event time, and event type of the event participants. The audience tags include user profiles, user attributes, and user characteristics. Obtain user feedback data from historical activities, and generate an accurate process model based on the user feedback data and collaborative filtering algorithm; Based on the activity time and activity type, set the activity time trigger node and activity type judgment node for initial process configuration to initialize the scheduled task; based on the audience tags and activity type judgment results, generate the activity process branch structure through a precise process model, wherein the activity process branch structure is an ordered connection of at least one process node and at least one activity sub-process, and the audience tags correspond to the activity sub-processes; generating the activity process branch structure specifically includes: dividing the generated activity process into a business abstract flow and a page execution flow; abstracting the business to form the business abstract flow, and using the process editor function to logically arrange the non-page execution layer of the business abstract flow to form a marketing behavior closed loop; relying on the template editor to present the business abstract flow on the page to form the page execution flow; In response to user adjustments to the activity flow, the activity flow nodes and branch structure are adjusted to generate an intelligent activity flow and set a scheduled task. The activity flow includes at least one branch and at least two flow nodes. The flow nodes are condition judgment nodes or action execution nodes. The connection order between the nodes is the execution order of the intelligent activity flow. The activity time is the execution time of the intelligent activity flow. Once a scheduled task is triggered, the corresponding actions are executed according to the execution order of the intelligent activity flow.

2. The method according to claim 1, characterized in that, The condition judgment nodes include at least one of the following: activity time trigger condition node, activity type judgment node, activity audience tag judgment node, and user behavior judgment node. The action execution nodes include at least one of the following: marketing page redirection, lucky draw activity, coupon distribution, and sharing / forwarding.

3. A device for generating intelligent activity processes, characterized in that, include: The acquisition module is used to acquire the audience tags, event time, and event type of the event participants. The audience tags include user profiles, user attributes, and user characteristics. The model generation module is used to obtain user feedback data from historical activities and generate an accurate process model based on the user feedback data and collaborative filtering algorithm before the process generation module generates an intelligent activity process and sets a scheduled task according to the activity group's tags, activity time and activity type. The process generation module is used to generate an intelligent activity process and set a scheduled task based on the audience tags, activity time, and activity type of the active participants. The activity process includes at least one branch and at least two process nodes, where each node is a condition judgment node or an action execution node. The connection order between the nodes is the execution order of the intelligent activity process, and the activity time is the execution time of the intelligent activity process. Specifically, the process generation module includes: a configuration unit, used to set an activity time trigger node and an activity type judgment node based on the activity time and activity type to perform initial process configuration and initialize the scheduled task; and a generation unit, used to generate a precise process based on the audience tags and activity type judgment results of the active participants. The model generates an activity flow branch structure, wherein the activity flow branch structure is an ordered connection of at least one flow node and at least one activity sub-flow, and the audience tag corresponds to the activity sub-flow. The generation of the activity flow branch structure specifically includes: dividing the generated activity flow into a business abstract flow and a page execution flow; abstracting the business to form the business abstract flow, and using the flow editor function to logically arrange the non-page execution layer of the business abstract flow to form a marketing behavior closed loop; relying on the template editor to present the business abstract flow on the page to form the page execution flow; and an adjustment unit, used to respond to the user's adjustment operation on the activity flow, adjust the activity flow nodes and branch structure, generate an intelligent activity flow, and set a scheduled task. The execution module is used to execute corresponding actions according to the execution order of the intelligent activity process after the timed task set by the process generation module is triggered.

4. The apparatus according to claim 3, characterized in that, The device may further include: The data interface module is used to access local data and / or external data through at least one of the following methods before the acquisition module obtains the crowd tags, event time and event type of the event participants: table upload, image upload, video upload, adding database, adding data table interface, and API interface binding.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method for generating the intelligent activity flow according to any one of claims 1 to 2.

6. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for generating intelligent activity flow according to any one of claims 1 to 2.

Images