User portrait generation method and device based on a buried point and a computer device

Abstract

The application relates to a user portrait generation method and device based on a burying point and a computer device. The method comprises the following steps: first, constructing a burying point list and an event strategy prototype according to a target service, wherein the analysis conditions in the event strategy prototype comprise trigger conditions and non-trigger conditions, and the analysis conditions are in an AND relationship; then, obtaining behavior information of a user in a preset time period, decomposing the behavior information according to the burying point list to obtain multiple sub-behavior information, analyzing each sub-behavior information according to the trigger conditions and the non-trigger conditions of the pre-set event strategy and filling in a detail block, obtaining corresponding event strategy details, generating a user portrait according to the event strategy details, and performing service pushing according to the user portrait. The method can balance the accuracy and real-time performance of user portrait generation, and is beneficial to service providers to provide accurate services for users in real time.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus and computer equipment for generating user profiles based on data tracking. Background Technology

[0002] As the internet gradually enters the era of big data, businesses are focusing on how to leverage big data to precisely deliver services to users, leading to the emergence of user profiling. To accurately push services that users are interested in, cultivate new user interests, and improve the user experience, while also facilitating the discovery of potential users, it is essential to ensure the accuracy and real-time nature of user profile generation. Summary of the Invention

[0003] Therefore, it is necessary to provide a user profile generation method, device, and computer equipment based on data tracking to address the aforementioned technical issues, which can generate user profiles more accurately while also ensuring the real-time nature of user profile generation.

[0004] A user profile generation method based on event tracking, the method comprising:

[0005] A list of event tracking points is constructed based on the target service; the list includes the event tracking point name and the event tracking object.

[0006] An event strategy prototype is constructed based on the target service. The event strategy prototype includes an event strategy details section and analysis conditions for the event strategy. The analysis conditions include triggering conditions and non-triggering conditions. Each event strategy corresponds to at least one triggering condition and at least one non-triggering condition. The triggering conditions under the same event strategy are related by "AND".

[0007] Obtain user behavior information within a preset time period, and decompose the behavior information according to the tracking point list to obtain multiple sub-behavior information;

[0008] The information of each sub-behavior is analyzed according to the pre-set event strategy triggering and non-triggering conditions and filled into the details section to obtain the corresponding event strategy details;

[0009] User profiles are generated based on event strategy details, and services are pushed based on these user profiles.

[0010] A user profile generation device based on data tracking, the device comprising:

[0011] The event tracking list building module is used to build an event tracking list based on the target service; the event tracking list includes the event tracking name and the event tracking object;

[0012] The event strategy prototype building module is used to build event strategy prototypes based on the target service. The event strategy prototype includes an event strategy details section and analysis conditions for the event strategy. The analysis conditions include triggering conditions and non-triggering conditions. Each event strategy corresponds to at least one triggering condition and at least one non-triggering condition. The triggering conditions under the same event strategy are related by "AND".

[0013] The behavior information decomposition module is used to obtain user behavior information within a preset time period, and decompose the behavior information according to the tracking point list to obtain multiple sub-behavior information.

[0014] The sub-behavior information analysis module is used to analyze each sub-behavior information according to the pre-set event strategy triggering and non-triggering conditions and fill it into the details section to obtain the corresponding event strategy details;

[0015] The user profile generation module is used to generate user profiles based on event policy details and to push services based on user profiles.

[0016] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in the method described above.

[0017] The aforementioned user profile generation method, apparatus, and computer equipment based on event tracking include: First, constructing an event tracking list and an event strategy prototype based on the target service, wherein the analysis conditions in the event strategy prototype include triggering conditions and non-triggering conditions, and the analysis conditions are related by "AND"; Next, acquiring user behavior information within a preset time period, decomposing the behavior information according to the event tracking list to obtain multiple sub-behavior information, then analyzing each sub-behavior information according to the pre-set triggering and non-triggering conditions of the event strategy and filling it into the details section to obtain the corresponding event strategy details, generating a user profile based on the event strategy details, and pushing services based on the user profile.

[0018] As can be seen, this invention sets non-trigger conditions in addition to triggering conditions. The advantage of setting non-trigger conditions is that it allows service providers to accurately identify specific types of users and perform behavioral analysis, resulting in more precise user profiles and facilitating subsequent behavior categorization. Furthermore, compared to existing technologies that only focus on the results of user behavior, leading to a somewhat one-sided user profile, this invention decomposes user behavior according to a preset list of tracking points and determines whether each sub-behavior is triggered. This creates a multi-dimensional user profile, allowing for real-time updates, which is particularly suitable for time-sensitive service push notifications. Each different sub-behavior can be considered a temporary attribute, and based on each temporary attribute, the user's current situation can be analyzed in real time, enabling service providers to respond faster and more effectively.

[0019] In summary, this invention can balance the accuracy and real-time nature of user profile generation, which is beneficial for service providers to provide users with accurate services in real time. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of the process for generating user profiles based on data tracking in one embodiment.

[0021] Figure 2 This is a schematic diagram of the embedded point list in one embodiment;

[0022] Figure 3 This is a schematic diagram of an event strategy prototype in one embodiment;

[0023] Figure 4 This is a schematic diagram illustrating the correspondence between "tracking points", "product categories", "filtering conditions", and "corresponding values" in one embodiment.

[0024] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0026] In one embodiment, such as Figure 1 As shown, a user profile generation method based on event tracking is provided, including the following steps:

[0027] Step 102: Construct a list of event tracking points based on the target service.

[0028] The event tracking list includes the event tracking name and the event tracking object. For example, the event tracking name is "Playback", and the event tracking object is "Video" or "Audio".

[0029] Step 104: Build an event strategy prototype based on the target service.

[0030] The event strategy prototype includes an event strategy details section and event strategy analysis conditions. The analysis conditions include trigger conditions and non-trigger conditions. Each event strategy corresponds to at least one trigger condition and at least one non-trigger condition. The trigger conditions under the same event strategy are related by "AND".

[0031] For example, if user A goes to the supermarket and buys goods, and user B goes to the supermarket but does not buy goods, then A has triggered an event, while B has not. From this, we can filter out B and perform behavioral analysis and speculation.

[0032] As can be seen, in this method, in addition to setting the triggering conditions, non-triggering conditions are further set. The advantage of setting non-triggering conditions is that it makes it easier for service providers to accurately find a certain type of targeted users and conduct behavior analysis, making user profiles more accurate and facilitating subsequent user behavior classification.

[0033] Step 106: Obtain user behavior information within a preset time period, and decompose the behavior information according to the tracking point list to obtain multiple sub-behavior information.

[0034] Considering that a user's behavior is usually sequential, such as clicking, browsing, providing feedback, and taking further action (e.g., whether to make a purchase), it is broken down and analyzed.

[0035] Furthermore, compared to existing technologies that only focus on the results of user behavior, resulting in a relatively one-sided user profile, this invention decomposes user behavior according to a preset list of tracking points and determines whether each sub-behavior is triggered. This can create a multi-dimensional user profile, enabling real-time updates of the user profile. It is especially suitable for time-sensitive service pushes, because each different sub-behavior can be regarded as a temporary attribute. Based on each temporary attribute, the user's current situation can be analyzed in real time, thereby enabling service providers to respond faster, more timely, and more effectively.

[0036] Step 108: Analyze each sub-behavior information according to the pre-set event strategy triggering and non-triggering conditions and fill it into the details section to obtain the corresponding event strategy details.

[0037] Step 110: Generate a user profile based on the event strategy details, and push services based on the user profile.

[0038] The aforementioned user profile generation method based on event tracking includes: First, constructing an event tracking list and an event strategy prototype based on the target service. The analysis conditions in the event strategy prototype include triggering conditions and non-triggering conditions, and these conditions are related by an AND clause. Next, acquiring user behavior information within a preset time period, decomposing the behavior information according to the event tracking list to obtain multiple sub-behavior information, and then analyzing each sub-behavior information according to the pre-set triggering and non-triggering conditions of the event strategy and filling it into the details section to obtain the corresponding event strategy details. A user profile is then generated based on the event strategy details, and service is pushed based on the user profile. This method balances the accuracy and real-time nature of user profile generation, enabling service providers to provide accurate services to users in real time.

[0039] In one embodiment, each tracking point name corresponds to a tracking point code; each tracking point name corresponds to at least one tracking point object. For example... Figure 2As shown, a schematic diagram of the list of tracking points is provided.

[0040] In one embodiment, the event policy details section includes:

[0041] Event policy code, event policy name, and event policy description;

[0042] Event strategy coding consists of the coding of the event tracking name and the coding of the event tracking object;

[0043] The event strategy name consists of the content corresponding to the triggering condition and the non-triggered condition;

[0044] The event strategy description is obtained by adding the number of times the triggering condition and the non-triggering condition are met within a preset time period to the event strategy name; in the event strategy description, the content corresponding to the triggering condition and the non-triggering condition is connected by "AND".

[0045] In one embodiment, the triggering condition or non-triggered condition includes: a first filtering condition and a second filtering condition;

[0046] The first filtering condition consists of the name of the triggered or untriggered event point and the corresponding event point object category; the event point object category is a subordinate concept of the event point object.

[0047] The second filtering criterion includes the number of times the event was triggered or not triggered; the number of times the event was triggered or not triggered includes: the number of times the event was triggered or not triggered when the category ID of the event object is the same, the number of times the event was triggered or not triggered when the category ID of the event object is different, and the number of times the event was triggered or not triggered when the category ID of the event object is unlimited.

[0048] For example, "Trigger, click on PGC images and text, number of times (different IDs) >= 3 times" means clicking on PGC images and texts with different IDs 3 or more times.

[0049] In one embodiment, the triggering condition or non-triggered condition further includes: additional filtering conditions;

[0050] Additional filtering criteria include attributes of the category of the tracked object;

[0051] The additional filtering conditions in the triggering conditions also include the duration of time the user stays on the category page of the tracked object.

[0052] In one embodiment, the event strategy prototype also includes: an expiration period after the event strategy is triggered. The expiration period value can be entered directly or added / reduced using buttons, and the time unit can be selected as minutes / hours / days / weeks / months.

[0053] like Figure 3 The diagram shown illustrates a prototype of the event strategy. Different "events" have different filtering conditions, which are linked to the "tracking points" and "category" selected for that event.

[0054] The logical relationship between the same "Event" filter conditions is "AND"; multiple values ​​can be selected for the same attribute field, and the logical relationship between tags is "OR"; if the logical relationship is "Contains" or "Does not contain", multiple values ​​are separated by ",", and all input boxes in the corresponding values ​​are required; if the logical relationship is "Has a value" or "Is empty", the corresponding value input box does not need to be displayed on the front end. The correspondence between "Event Tracking", "Category", "Filter Condition", and "Corresponding Value" is as follows: Figure 4 As shown.

[0055] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0056] In one embodiment, a user profile generation device based on data tracking is provided, wherein:

[0057] The event tracking list building module is used to build an event tracking list based on the target service; the event tracking list includes the event tracking name and the event tracking object;

[0058] The event strategy prototype building module is used to build event strategy prototypes based on the target service. The event strategy prototype includes an event strategy details section and analysis conditions for the event strategy. The analysis conditions include triggering conditions and non-triggering conditions. Each event strategy corresponds to at least one triggering condition and at least one non-triggering condition. The triggering conditions under the same event strategy are related by "AND".

[0059] The behavior information decomposition module is used to obtain user behavior information within a preset time period, and decompose the behavior information according to the tracking point list to obtain multiple sub-behavior information.

[0060] The sub-behavior information analysis module is used to analyze each sub-behavior information according to the pre-set event strategy triggering and non-triggering conditions and fill it into the details section to obtain the corresponding event strategy details;

[0061] The user profile generation module is used to generate user profiles based on event policy details and to push services based on user profiles.

[0062] For specific limitations regarding the user profile generation device based on event tracking, please refer to the limitations of the user profile generation method based on event tracking mentioned above, which will not be repeated here. Each module in the aforementioned user profile generation device based on event tracking can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0063] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores user behavior data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a user profile generation method based on data tracking.

[0064] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0065] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method described above.

[0066] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0067] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0068] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0069] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A user profile generation method based on event tracking, characterized in that, The method includes: A list of event tracking points is constructed based on the target service; the list of event tracking points includes event tracking point names and event tracking objects. An event strategy prototype is constructed based on the target service; the event strategy prototype includes an event strategy details section and event strategy analysis conditions; the analysis conditions include triggering conditions and non-triggering conditions; each event strategy corresponds to at least one triggering condition and at least one non-triggering condition; the triggering conditions under the same event strategy are related by "AND"; Obtain user behavior information within a preset time period, and decompose the behavior information according to the tracking point list to obtain multiple sub-behavior information; The information of each sub-behavior is analyzed according to the pre-set event strategy triggering and non-triggering conditions and filled into the details section to obtain the corresponding event strategy details; A user profile is generated based on the event policy details, and services are pushed based on the user profile. The event strategy details section includes: Event policy code, event policy name, and event policy description; The event strategy encoding consists of the encoding of the event tracking name and the encoding of the event tracking object; The event strategy name consists of the content corresponding to the triggering condition and the non-triggering condition; The event strategy description is obtained by adding the number of times the triggering condition and the non-triggering condition are met within a preset time period to the event strategy name; in the event strategy description, the contents corresponding to the triggering condition and the non-triggering condition are connected by "AND"; The triggering or non-triggering conditions include: a first filtering condition and a second filtering condition; The first filtering condition consists of the name of the triggered or untriggered tracking point and the corresponding tracking point object category; the tracking point object category is a subordinate concept of the tracking point object. The second filtering condition includes the number of times the event was triggered or not triggered; the number of times the event was triggered or not triggered includes: the number of times the event was triggered or not triggered when the category ID of the event object is the same, the number of times the event was triggered or not triggered when the category ID of the event object is different, and the number of times the event was triggered or not triggered when the category ID of the event object is unlimited.

2. The method according to claim 1, characterized in that, Each tracking point name corresponds to a tracking point code; each tracking point name corresponds to at least one tracking point object.

3. The method according to claim 1, characterized in that, The triggering or non-triggered conditions also include: additional filtering conditions; The additional filtering criteria include the attributes of the category of the tracked object; The additional filtering conditions, among the triggering conditions, also include the duration of user stay on the category page of the tracked object.

4. The method according to claim 1, characterized in that, The event policy prototype also includes: the validity period after the event policy is triggered.

5. A user profile generation device based on data tracking, characterized in that, The device includes: The event tracking list construction module is used to construct an event tracking list based on the target service; the event tracking list includes event tracking names and event tracking objects. An event strategy prototype construction module is used to construct an event strategy prototype based on the target service. The event strategy prototype includes an event strategy details section and analysis conditions for the event strategy. The analysis conditions include triggering conditions and non-triggering conditions. Each event strategy corresponds to at least one triggering condition and at least one non-triggering condition. The triggering conditions under the same event strategy are related by an "AND" clause. The event strategy details section includes: Event policy code, event policy name, and event policy description; The event strategy encoding consists of the encoding of the event tracking name and the encoding of the event tracking object; The event strategy name consists of the content corresponding to the triggering condition and the non-triggering condition; The event strategy description is obtained by adding the number of times the triggering condition and the non-triggering condition are met within a preset time period to the event strategy name; in the event strategy description, the contents corresponding to the triggering condition and the non-triggering condition are connected by "AND"; The triggering or non-triggering conditions include: a first filtering condition and a second filtering condition; The first filtering condition consists of the name of the triggered or untriggered tracking point and the corresponding tracking point object category; the tracking point object category is a subordinate concept of the tracking point object. The second filtering condition includes the number of times the event was triggered or not triggered; the number of times the event was triggered or not triggered includes: the number of times the event was triggered or not triggered when the category ID of the event object is the same, the number of times the event was triggered or not triggered when the category ID of the event object is different, and the number of times the event was triggered or not triggered when the category ID of the event object is unlimited. The behavior information decomposition module is used to obtain user behavior information within a preset time period, and decompose the behavior information according to the tracking point list to obtain multiple sub-behavior information. The sub-behavior information analysis module is used to analyze each sub-behavior information according to the pre-set event strategy triggering and non-triggering conditions and fill it into the details section to obtain the corresponding event strategy details; The user profile generation module is used to generate user profiles based on the event policy details and to push services based on the user profiles.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. 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 according to any one of claims 1 to 4.

Images