User source label determination method and device, equipment and storage medium
By acquiring user device identification information and integrating multi-channel behavioral data, we can accurately locate relevant advertising items for user conversion, solving the problem of poor user source matching and optimizing advertising delivery strategies.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-30
- Publication Date
- 2026-03-13
AI Technical Summary
Existing technologies cannot accurately locate user conversion channels, resulting in poor user source matching and impacting the formulation and optimization of subsequent advertising strategies.
By obtaining users' device identification information, querying user behavior records from various advertising channels, configuring attribution windows, identifying associated advertising items, and integrating primary source tags and human source tags, a target source tag is formed.
It improved the matching effect of user sources, ensured the formulation and optimization of advertising strategies, and improved the accuracy of attribution.
Smart Images
Figure CN121660754A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for determining user source tags. Background Technology
[0002] As the market continues to expand and the number of game users continues to rise, competition among game products is intensifying due to homogenization. Therefore, accurately identifying potential players and efficiently acquiring users has become a key focus for the industry. At this juncture, accurately identifying and attributing player sources is crucial. It not only helps manufacturers determine which channels are most effective for promotion and allocate marketing budgets rationally, but also enables them to develop personalized marketing strategies based on the characteristics of players from different sources, improving user retention and activity, thereby enhancing the market competitiveness of game products.
[0003] In related technologies, simple rule matching or manual statistics are used to determine user sources. However, in actual applications, user behavior paths are more complex, and the aforementioned methods cannot accurately locate user conversion channels, resulting in poor user source matching and affecting the formulation and optimization of subsequent advertising strategies. Summary of the Invention
[0004] This application provides a method, apparatus, device, and storage medium for determining user source tags, which solves the problem in related technologies that it is impossible to accurately locate the user's conversion channel, resulting in poor user source matching and affecting the formulation and optimization of subsequent advertising strategies. It can combine user behavior information from multiple channels to accurately locate the related advertising items for user conversion, improve the user source matching effect, and ensure the formulation and optimization of subsequent advertising strategies.
[0005] In a first aspect, embodiments of this application provide a method for determining user source tags, the method comprising: Obtain the device identification information of the user to be processed who triggered the target conversion event, and query the user behavior records corresponding to each preset advertising channel based on the device identification information; Configure the attribution window period corresponding to the preset behavior event according to the trigger time node of the target conversion event, and determine the associated advertising item from each user behavior record according to the preset behavior event and the corresponding attribution window period; A first source tag is constructed based on the associated advertising items corresponding to each user behavior record, and the manual source tag of the user to be processed is queried. The first source tag and the manual source tag are integrated to obtain the target source tag.
[0006] Secondly, embodiments of this application also provide a user source tag determination device, including: The record query module is configured to obtain the device identification information of the pending user who triggered the target conversion event, and query the user behavior records corresponding to each preset advertising channel based on the device identification information. The ad item determination module is configured to configure an attribution window period corresponding to a preset behavior event based on the trigger time node of the target conversion event, and determine the associated ad item from each user behavior record based on the preset behavior event and the corresponding attribution window period; The tag generation module is configured to construct a first source tag based on the associated advertising items corresponding to each user behavior record, query the manual source tag of the user to be processed, and integrate the first source tag and the manual source tag to obtain the target source tag.
[0007] Thirdly, embodiments of this application also provide a user source tag determination device, the device comprising: One or more processors; Storage device, configured to store one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the user source tag determination method described in the embodiments of this application.
[0008] Fourthly, embodiments of this application also provide a non-volatile storage medium for storing computer-executable instructions, which, when executed by a computer processor, are configured to perform the user source tag determination method described in embodiments of this application.
[0009] In this embodiment, user behavior records corresponding to each preset advertising channel are queried based on device identification information. This accurately extracts historical behavior data related to advertising for successfully converted users, providing a reliable reference for subsequent attribution analysis. Attribution windows are configured according to the trigger time of the target conversion event, and associated advertising items are determined from each user behavior record based on the preset behavior event and its corresponding attribution window. This adaptable approach allows for filtering associated advertising items across different preset behavior events, identifying key advertising channels that drive conversions. Integrating the first source tag and the manual source tag yields the target source tag, merging multi-source tags and improving attribution accuracy. The above solution combines user behavior information from multiple channels to accurately locate associated advertising items for user conversions, improving user source matching and ensuring the formulation and optimization of subsequent advertising strategies. Attached Figure Description
[0010] Figure 1 A flowchart illustrating a method for determining user source tags provided in this application embodiment; Figure 2A schematic diagram illustrating the data processing procedure of a user source tag determination method provided in an embodiment of this application; Figure 3 A flowchart of a user source tag determination method, including a process of constructing a first source tag, is provided for embodiments of this application. Figure 4 A flowchart of a user source label determination method, including a process of assigning attribution weight values, is provided for embodiments of this application. Figure 5 A flowchart of another user source tag determination method, including a process of constructing a first source tag, provided for embodiments of this application; Figure 6 A flowchart of a user source label determination method, including a process for configuring an attribution window period corresponding to a preset behavioral event, is provided as an embodiment of this application. Figure 7 A flowchart of a user source tag determination method, including a process for integrating and determining target source tags, is provided for embodiments of this application. Figure 8 A structural block diagram of a user source tag determination device provided in an embodiment of this application; Figure 9 This is a schematic diagram of a user source tag determination device provided in an embodiment of this application. Detailed Implementation
[0011] The embodiments of this application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the embodiments of this application and are not intended to limit the scope of the embodiments. Furthermore, it should be noted that, for ease of description, only the parts relevant to the embodiments of this application are shown in the accompanying drawings, not the entire structure.
[0012] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.
[0013] The user source tag determination method provided in this application embodiment can be executed by a computer device. The computer device refers to any electronic device with data computing, processing and storage capabilities, such as a server. This application embodiment does not limit this.
[0014] Figure 1 A flowchart of a user source tag determination method provided in this application embodiment is shown below. Figure 1 As shown, the method for determining user source tags specifically includes the following steps: Step S101: Obtain the device identification information of the user to be processed that triggered the target conversion event, and query the user behavior records corresponding to each preset advertising channel based on the device identification information.
[0015] The target conversion events can be user account registration, user payment, or user application installation. Device identification information can be parameters used to uniquely identify the user's device. Pre-configured advertising channels can be pre-configured media platforms that deliver advertising content corresponding to the target business to the target audience, such as web platforms or social media. The target business could be a game promotion or an application promotion. User behavior records can be the interaction data of the user to be processed on the pre-configured advertising channels corresponding to the target business, including clicking on ads and browsing page ads, used to trace the conversion path of the user to be processed. The set database can store user behavior records of multiple users on various pre-configured advertising channels. These user behavior records can be linked to the user's device identification information to distinguish different users. Therefore, based on the device identification information, the user behavior records corresponding to each pre-configured advertising channel associated with the user to be processed can be retrieved.
[0016] Step S102: Configure the attribution window period corresponding to the preset behavior event according to the trigger time node of the target conversion event, and determine the associated advertising items from each user behavior record according to the preset behavior event and the corresponding attribution window period.
[0017] The preset behavioral events can be click events, browsing events, etc., related to advertisements. The attribution window can be a valid time range before the target conversion event is triggered. If a user's preset behavioral event occurs within this attribution window, the user's conversion can be attributed to the corresponding advertising channel. For example, a click event is when a user actively clicks on advertising content provided by an advertising channel, which can be considered as expressing clear interest. The correlation between triggering the target conversion event and this click event is relatively high. Therefore, a relatively long attribution window can be set to cover the user's decision-making cycle; for example, user clicks within 7 days prior to the trigger time point, i.e., within 7 days before the target conversion event is triggered, will be included in the attribution. As another example, a browsing event is when a user has viewed advertising content provided by an advertising channel, which can be considered as advertising exposure reaching the user, but without active interaction. The correlation between triggering the target conversion event and this browsing event is relatively low, but the possibility of driving user conversion in the short term is high. Therefore, a relatively short attribution window can be set; for example, user browsing within 1 day prior to the trigger time point, i.e., within 1 day before the target conversion event is triggered, will be included in the attribution. Each preset advertising channel can have multiple ad items set up for the target business. The ad creative content, placement, and format of each ad item can differ. Taking a web platform channel as an example, ad items can be regional image ads at the top or bottom of the webpage, or dynamic video ads in specific areas, etc., and this application does not impose any limitations on this. Associated ad items can be ad items that triggered the preset behavioral event within the attribution window period. For example, if a user viewed an ad item within the previous day, that ad item can be considered an associated ad item. Similarly, if a user clicked on an ad item within the previous seven days, that ad item can be considered an associated ad item.
[0018] Optionally, the preset behavioral events include click behavioral events and browsing behavioral events, and the attribution window includes a first attribution window corresponding to the click behavioral event and a second attribution window corresponding to the browsing behavioral event. The associated advertising items are determined from each user behavior record based on the preset behavioral events and their corresponding attribution windows, specifically including the following process: Extract at least one first ad item corresponding to a click event and at least one second ad item corresponding to a browsing event from each user behavior record; select a first target ad item from at least one first ad item based on a first attribution window, and select a second target ad item from at least one second ad item based on a second attribution window; merge the first target ad item and the second target ad item to obtain the associated ad item.
[0019] The first attribution window can be used to filter out primary target ad items that may influence user conversion from at least one ad item corresponding to a click behavior event. The second attribution window can be used to filter out secondary target ad items that may influence user conversion from at least one secondary ad item corresponding to a browsing behavior event. Therefore, merging the primary and secondary target ad items yields associated ad items, which can be multiple, each contributing to user conversion to varying degrees.
[0020] Step S103: Construct a first source tag based on the associated advertising items corresponding to each user behavior record, query the manual source tag of the user to be processed, and integrate the first source tag and the manual source tag to obtain the target source tag.
[0021] Each user behavior record can identify associated ad items for its corresponding preset advertising channels. Therefore, merging the associated ad items corresponding to each user behavior record can construct a first source tag, which can be considered as the conversion attribution result automatically determined by the system. In one embodiment, the most recent associated ad item can be selected from the multiple associated ad items, and the first source tag can be constructed based on this associated ad item. In another embodiment, the multiple associated ad items can be sorted by time and assigned different weight values corresponding to different time positions. This weight value can be considered as the degree of influence on user conversion; the larger the weight value, the greater the influence. For example, a larger weight value can be assigned to the most recent or oldest associated ad item, while a smaller weight value can be assigned to associated ad items in the middle. Then, the first source tag can be constructed based on the sorted multiple associated ad items and the weight values corresponding to each associated ad item, for example, "Ad item A: weight value a1 — Ad item B: weight value b1 — Ad item C: weight value c1". The artificial source tag can be a manually tagged conversion source, specifically including associated ad items corresponding to various preset advertising channels in standard settings, or non-standard advertising channels such as various offline activities, for example: "Ad Item B - Activity D". In one embodiment, the first source tag and the artificial source tag can be directly combined to obtain the target source tag. In another embodiment, the first source tag and the artificial source tag can be de-duplicated and combined to obtain the target source tag.
[0022] The above-mentioned approach, which queries user behavior records corresponding to each preset advertising channel based on device identification information, can accurately extract historical behavior data related to advertising for successfully converted users, providing a reliable reference for subsequent attribution analysis. By configuring the attribution window period corresponding to the preset behavior event based on the trigger time node of the target conversion event, and determining associated advertising items from each user behavior record based on the preset behavior event and its corresponding attribution window period, it can adapt to different preset behavior events for filtering associated advertising items and identifying key advertising channels that drive conversions. Integrating the primary source tag and the manual source tag to obtain the target source tag allows for the fusion of multi-source tags, improving attribution accuracy. This solution can combine user behavior information from multiple channels to accurately locate associated advertising items for user conversions, improve user source matching effectiveness, and ensure the formulation and optimization of subsequent advertising strategies.
[0023] Figure 2 This is a schematic diagram of the data processing procedure for a user source tag determination method provided in an embodiment of this application, as shown below. Figure 2 As shown, based on the device identification information 202 of the user to be processed 201, user behavior records 204 (x1, x2, and x3) corresponding to each preset advertising channel 203 (advertising channels A, B, and C are shown in the figure) can be queried. Associated advertising items 205 are determined from each user behavior record 204 according to preset behavioral events and corresponding attribution windows. A first source tag 206 is constructed based on the associated advertising items 205 (d1, d2, and d3 are shown in the figure) corresponding to each user behavior record 204, and the manual source tag 207 of the user to be processed 201 is queried. The first source tag 206 and the manual source tag 207 are then integrated to obtain the target source tag 208.
[0024] Figure 3 A flowchart of a user source tag determination method, including a process for constructing a first source tag, is provided for embodiments of this application. Figure 3 As shown, the method for determining user source tags specifically includes the following steps: Step S301: Obtain the device identification information of the user to be processed that triggered the target conversion event, and query the user behavior records corresponding to each preset advertising channel based on the device identification information.
[0025] Step S302: Configure the attribution window period corresponding to the preset behavior event according to the trigger time node of the target conversion event, and determine the associated advertising items from each user behavior record according to the preset behavior event and the corresponding attribution window period.
[0026] Step S303: Arrange the associated ad items corresponding to each user behavior record in chronological order to obtain an associated ad sequence; assign corresponding attribution weight values according to the element positions of each associated ad item in the associated ad sequence; combine the associated ad sequence and the attribution weight values assigned to each associated ad item to obtain the first source tag.
[0027] In this context, the element position of each associated ad item in the associated ad sequence can represent its temporal order within the sequence, reflecting its proximity to the target conversion event. For example, if associated ad items are arranged from furthest to closest in time, then the associated ad item with the later element position is closer to the target conversion event. The attribution weight value can represent the degree of contribution of each associated ad item to triggering the target conversion event. Specifically, for each associated ad item at different element positions, attribution weight values can be allocated according to preset rules. In one embodiment, for new business promotions or business scenarios with short promotion cycles, the user's first and last exposure to related ads are more important. Therefore, the associated ad items with the furthest and closest times in the associated ad sequence arranged from furthest to closest in time can be assigned higher attribution weight values, while other associated ad items can be adaptively and evenly assigned smaller attribution weight values. For example, if there are 6 associated ad items in the associated ad sequence, their attribution weight values could be distributed as follows: 40%, 5%, 5%, 5%, 5%, 40%. In one embodiment, for business scenarios with long promotion cycles, the attribution weight values of each associated ad item can be increased sequentially from oldest to newest. For example, if there are four associated ad items in the associated ad sequence, the distribution of the attribution weight values could be: 10%, 20%, 30%, and 40%. Finally, associating and combining each associated ad item with its corresponding attribution weight value yields the first source tag, for example, "Ad item A: weight value a1 — Ad item B: weight value b1 — Ad item C: weight value c1".
[0028] Step S304: Query the manual source tag of the user to be processed, and integrate the first source tag and the manual source tag to obtain the target source tag.
[0029] The above-mentioned method arranges the associated ad items corresponding to each user behavior record in chronological order to obtain an associated ad sequence. Based on the element position of each associated ad item in the associated ad sequence, corresponding attribution weight values are assigned. This allows for the construction of a chronological path of users reaching different ad channels and the reasonable allocation of attribution weight values that influence the degree of conversion, providing more accurate reference information for subsequent user conversion attribution analysis.
[0030] Figure 4 A flowchart of a user source label determination method, including a process of assigning attribution weight values, is provided for embodiments of this application, as shown below. Figure 4 As shown, the method for determining user source tags specifically includes the following steps: Step S401: Obtain the device identification information of the user to be processed that triggered the target conversion event, and query the user behavior records corresponding to each preset advertising channel based on the device identification information.
[0031] Step S402: Configure the attribution window period corresponding to the preset behavior event according to the trigger time node of the target conversion event, and determine the associated advertising items from each user behavior record according to the preset behavior event and the corresponding attribution window period.
[0032] Step S403: Arrange the associated advertising items corresponding to each user behavior record in chronological order to obtain the associated advertising sequence.
[0033] Step S404: Assign a first attribution weight value to the related ad items in the related ad sequence that are at the first and last positions respectively; count the number of elements in the related ad items between the first and last positions, and split the second attribution weight value based on the number of elements and assign it to each related ad item between the first and last positions.
[0034] In this context, the first attribution weight is greater than the second attribution weight. Specifically, the sum of the first and second attribution weights can be 1. For example, if the first attribution weight is 40%, then the first and last associated ad items will each receive a 40% first attribution weight. Correspondingly, the second attribution weight is... If the number of elements in the associated ad items between the first and last positions is N, then the second attribution weight value can be evenly divided into... Alternatively, the second attribution weight can be split into N parts according to the allocation rule that the more recent the time, the greater the weight, and then allocated to each associated ad item located between the first and last positions.
[0035] Step S405: Combine the associated ad sequence and the attribution weight value assigned to each associated ad item to obtain the first source label.
[0036] Step S406: Query the manual source tag of the user to be processed, and integrate the first source tag and the manual source tag to obtain the target source tag.
[0037] The above-mentioned method assigns a first attribution weight value to the related ad items in the related ad sequence, which are at the first and last positions respectively. Based on the statistical number of elements, the second attribution weight value is split and distributed to each related ad item located between the first and last positions. This method can match the user's actual ad contact path to allocate attribution weight values, reasonably quantify the conversion contribution of different related ad items, and is suitable for new business promotion or business scenarios with short promotion cycles.
[0038] Figure 5 A flowchart of another user source tag determination method, including a process for constructing a first source tag, provided for embodiments of this application, is shown below. Figure 5 As shown, the method for determining user source tags specifically includes the following steps: Step S501: Obtain the device identification information of the user to be processed that triggered the target conversion event, and query the user behavior records corresponding to each preset advertising channel based on the device identification information.
[0039] Step S502: Configure the attribution window period corresponding to the preset behavior event according to the trigger time node of the target conversion event, and determine the associated advertising items from each user behavior record according to the preset behavior event and the corresponding attribution window period.
[0040] Step S503: Select the first associated ad item with the smallest timestamp and the second associated ad item with the largest timestamp from the associated ad items corresponding to each user behavior record; combine the first associated ad item and the second associated ad item to obtain the first source tag.
[0041] To improve the data processing efficiency of subsequent user attribution analysis, it's possible to focus on key related ad items in user behavior records, without needing to determine the complete path of the user's ad exposure. Specifically, the first related ad item with the smallest timestamp and the second related ad item with the largest timestamp can be selected, focusing on the user's first and last exposure to the relevant ad. The first and second related ad items can then be combined to obtain the first source tag, making the content of the first source tag relatively concise and suitable for application scenarios requiring rapid user attribution analysis.
[0042] Step S504: Query the manual source tag of the user to be processed, and integrate the first source tag and the manual source tag to obtain the target source tag.
[0043] The above-mentioned method combines the first associated ad item with the smallest timestamp and the second associated ad item with the largest timestamp to obtain the first source tag. This method can construct a first source tag with a smaller data volume, focusing on key associated ad items, which is beneficial for providing lightweight data for subsequent rapid user attribution analysis.
[0044] Figure 6 A flowchart of a user source label determination method, including a process for configuring an attribution window period corresponding to a preset behavioral event, is provided as an embodiment of this application. Figure 6 As shown, the method for determining user source tags specifically includes the following steps: Step S601: Obtain the device identification information of the user to be processed that triggered the target conversion event, and query the user behavior records corresponding to each preset advertising channel based on the device identification information.
[0045] Step S602: Query the first time interval and the second time interval corresponding to the click behavior event and the browsing behavior event, respectively; configure the first attribution window period of the click behavior event according to the trigger time node of the target conversion event and the first time interval; configure the second attribution window period of the browsing behavior event according to the trigger time node of the target conversion event and the second time interval.
[0046] Click events, where users actively click on advertising content from advertising channels, can be seen as expressing clear interest. The correlation between the click event and the target conversion event is strong, and the first time interval configured for this event can cover the user's decision-making cycle. Browsing events, where users have viewed advertising content from advertising channels, can be seen as advertising exposure reaching the user, but without active interaction. The second time interval configured for this event has a higher probability of driving user conversion in a short period. Therefore, the first time interval is longer than the second time interval; for example, the first time interval could be 7 days, and the second time interval could be 1 day. The first attribution window for click events can be based on the trigger time of the target conversion event, shifting backward by the historical time range covered by the first time interval. For example, if the first time interval is 7 days, the first attribution window is within 7 days before the trigger time. The second attribution window for browsing events can be based on the trigger time of the target conversion event, shifting backward by the historical time range covered by the second time interval. For example, if the second time interval is 1 day, the second attribution window is within 1 day before the trigger time.
[0047] Step S603: Determine the associated advertising items from each user behavior record based on the preset behavioral events and the corresponding attribution window periods.
[0048] Step S604: Construct a first source tag based on the associated advertising items corresponding to each user behavior record, query the manual source tag of the user to be processed, and integrate the first source tag and the manual source tag to obtain the target source tag.
[0049] The above-mentioned setting of attribution windows for event types that are adapted to different preset behavioral events can help to accurately extract related advertising items that promote user conversion and ensure the accuracy of the first source tag.
[0050] Figure 7 A flowchart of a user source tag determination method, including a process for integrating and determining target source tags, is provided for embodiments of this application. Figure 7As shown, the method for determining user source tags specifically includes the following steps: Step S701: Obtain the device identification information of the user to be processed that triggered the target conversion event, and query the user behavior records corresponding to each preset advertising channel based on the device identification information.
[0051] Step S702: Configure the attribution window period corresponding to the preset behavior event according to the trigger time node of the target conversion event, and determine the associated advertising items from each user behavior record according to the preset behavior event and the corresponding attribution window period.
[0052] Step S703: Construct the first source tag based on the associated advertising items corresponding to each user behavior record, and query the manual source tag of the user to be processed.
[0053] Step S704: Compare the content of the first source tag and the manual source tag to identify duplicate advertising items; remove duplicate advertising items from the manual source tags to obtain the second source tag; combine the first source tag and the second source tag to obtain the target source tag.
[0054] The first source tag and the manual source tag may record the same associated ad items. By comparing the content of the first source tag and the manual source tag, duplicate ad items can be located. Duplicate ad items are obtained by removing duplicate ad items from the manual source tag. Combining the first source tag and the second source tag yields the target source tag, which integrates source tags determined from different sources, ensuring the integrity of the user conversion path. For example, if the first source tag is "Associated Ad Item A—Associated Ad Item B—Associated Ad Item C", and the manual source tag is "Associated Ad Item B—Offline Activity D", then the duplicate ad item between the first source tag and the manual source tag is "Associated Ad Item B". Removing "Associated Ad Item B" from the manual source tag yields the second source tag: "Offline Activity D". Finally, the first source tag and the second source tag are combined to obtain the target source tag: "Associated Ad Item A—Associated Ad Item B—Offline Activity D—Associated Ad Item C". Specifically, the ad items in the target source tag can be rearranged according to chronological order.
[0055] The above-mentioned method of removing duplicate advertising items from the manual source tags to obtain the second source tag, and combining the first source tag and the second source tag to obtain the target source tag, can integrate multiple source tags and improve the comprehensiveness and accuracy of source tags.
[0056] Figure 8 This is a structural block diagram of a user source tag determination device provided in an embodiment of this application. The device is configured to execute the user source tag determination method provided in the above embodiment, and has corresponding functional modules and beneficial effects for executing the method. Figure 8 As shown, the device specifically includes: The record query module 801 is configured to obtain the device identification information of the pending user who triggered the target conversion event, and query the user behavior records corresponding to each preset advertising channel based on the device identification information. The ad item determination module 802 is configured to configure the attribution window period corresponding to the preset behavior event based on the trigger time node of the target conversion event, and determine the associated ad items from each user behavior record based on the preset behavior event and the corresponding attribution window period. The tag generation module 803 is configured to construct a first source tag based on the associated advertising items corresponding to each user behavior record, query the manual source tag of the user to be processed, and integrate the first source tag and the manual source tag to obtain the target source tag.
[0057] The above-mentioned approach, which queries user behavior records corresponding to each preset advertising channel based on device identification information, can accurately extract historical behavior data related to advertising for successfully converted users, providing a reliable reference for subsequent attribution analysis. By configuring the attribution window period corresponding to the preset behavior event based on the trigger time node of the target conversion event, and determining associated advertising items from each user behavior record based on the preset behavior event and its corresponding attribution window period, it can adapt to different preset behavior events for filtering associated advertising items and identifying key advertising channels that drive conversions. Integrating the primary source tag and the manual source tag to obtain the target source tag allows for the fusion of multi-source tags, improving attribution accuracy. This solution can combine user behavior information from multiple channels to accurately locate associated advertising items for user conversions, improve user source matching effectiveness, and ensure the formulation and optimization of subsequent advertising strategies.
[0058] In one possible embodiment, the label generation module 803 is configured as follows: The associated ad items corresponding to each user behavior record are arranged in chronological order to obtain the associated ad sequence; Assign corresponding attribution weight values based on the element position of each associated ad item in the associated ad sequence; The first source label is obtained by associating and combining the associated ad sequence and the attribution weight value assigned to each associated ad item.
[0059] In one possible embodiment, the attribution weight value includes a first attribution weight value and a second attribution weight value, wherein the first attribution weight value is greater than the second attribution weight value; The tag generation module 803 is also configured as follows: Assign the first attribution weight value to the related ad items in the related ad sequence, which are the first and last elements respectively; The number of elements in the associated ad items between the first and last positions is counted, and the second attribution weight value is split and assigned to each associated ad item between the first and last positions based on the number of elements.
[0060] In one possible embodiment, the label generation module 803 is further configured to: Filter the first associated ad item with the smallest timestamp and the second associated ad item with the largest timestamp from the associated ad items corresponding to each user behavior record; The first associated ad item and the second associated ad item are combined to obtain the first source tag.
[0061] In one possible embodiment, the preset behavioral events include click behavioral events and browsing behavioral events, and the attribution window period includes a first attribution window period corresponding to the click behavioral event and a second attribution window period corresponding to the browsing behavioral event; The ad item determination module 802 is also configured as follows: Query the first and second time intervals corresponding to click events and browsing events, respectively; Configure the first attribution window period for click behavior events based on the trigger time node and the first time interval of the target conversion event; Configure the second attribution window period for browsing behavior events based on the trigger time node of the target conversion event and the second time interval.
[0062] In one possible embodiment, the advertisement item determination module 802 is further configured to: Extract at least one first ad item corresponding to a click event and at least one second ad item corresponding to a browsing event from each user behavior record; First target ad items are selected from at least one first ad item based on a first attribution window, and second target ad items are selected from at least one second ad item based on a second attribution window; The first target ad item and the second target ad item are merged to obtain the associated ad item.
[0063] In one possible embodiment, the label generation module 803 is configured as follows: Duplicate ad items are identified by comparing the content of first-source tags and manual-source tags; The second source label is obtained by removing duplicate ad items from the manually sourced label; The target source label is obtained by combining the first source label and the second source label.
[0064] Figure 9 This application provides a schematic diagram of the structure of a user source tag determination device, as shown in the embodiments. Figure 9As shown, the device includes a processor 901, a memory 902, an input device 903, and an output device 904; the number of processors 901 in the device can be one or more. Figure 9 Taking a processor 901 as an example; the processor 901, memory 902, input device 903, and output device 904 in the device can be connected via a bus or other means. Figure 9 Taking a bus connection as an example, the memory 902, as a computer-readable storage medium, can be configured to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the user source tag determination method in this embodiment. The processor 901 executes various functional applications and data processing of the device by running the software programs, instructions, and modules stored in the memory 902, thereby implementing the aforementioned user source tag determination method. The input device 903 can be configured to receive input digital or character information and generate key signal inputs related to user settings and function control of the device. The output device 904 may include a display screen or other display device.
[0065] The user source tag determination device provided above can be used to execute the user source tag determination method provided in any of the above embodiments, and has corresponding functions and beneficial effects.
[0066] This application also provides a non-volatile storage medium containing computer-executable instructions, which, when executed by a computer processor, are configured to perform a user source tag determination method described in the above embodiments. The method includes: acquiring device identification information of a user to be processed that triggers a target conversion event; querying user behavior records corresponding to each preset advertising channel based on the device identification information; configuring an attribution window period corresponding to a preset behavior event based on the triggering time node of the target conversion event; determining associated advertising items from each user behavior record based on the preset behavior event and the corresponding attribution window period; constructing a first source tag based on the associated advertising items corresponding to each user behavior record; querying the manual source tag of the user to be processed; and integrating the first source tag and the manual source tag to obtain a target source tag.
[0067] Storage medium – any type of memory device or storage device. The term “storage medium” is intended to include: mounting media, such as CD-ROMs, floppy disks, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media, optical storage; registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. Furthermore, storage media may reside in a first computer system in which the program is executed, or may reside in a different second computer system connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term “storage medium” can include two or more storage media residing in different locations (e.g., in different computer systems connected via a network). Storage media may store program instructions (e.g., specifically implemented as a computer program) executable by one or more processors.
[0068] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the user source tag determination method described above, but can also execute related operations in the user source tag determination method provided in any embodiment of this application.
[0069] It should be noted that the numbering of each step in this solution is only used to describe the overall design framework of this solution and does not indicate a necessary sequential relationship between the steps. As long as the overall implementation process conforms to the overall design framework of this solution, it falls within the protection scope of this solution. The literal order in the description is not an exclusive limitation on the specific implementation process of this solution. Those skilled in the art should understand that the embodiments of this application can be provided as methods, systems, or computer program products. In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-persistent memory in computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0070] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0071] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.
Claims
1. A method for determining user source tags, characterized in that, include: Obtain the device identification information of the user to be processed who triggered the target conversion event, and query the user behavior records corresponding to each preset advertising channel based on the device identification information; Configure the attribution window period corresponding to the preset behavior event according to the trigger time node of the target conversion event, and determine the associated advertising item from each user behavior record according to the preset behavior event and the corresponding attribution window period; A first source tag is constructed based on the associated advertising items corresponding to each user behavior record, and the manual source tag of the user to be processed is queried. The first source tag and the manual source tag are integrated to obtain the target source tag.
2. The user source tag determination method according to claim 1, characterized in that, The construction of the first source tag based on the associated advertising items corresponding to each of the user behavior records includes: The associated ad items corresponding to each user behavior record are arranged in chronological order to obtain the associated ad sequence; Assign corresponding attribution weight values based on the element positions of each associated ad item in the associated ad sequence; The first source tag is obtained by associating and combining the associated ad sequence and the attribution weight value assigned to each associated ad item.
3. The user source tag determination method according to claim 2, characterized in that, The attribution weight value includes a first attribution weight value and a second attribution weight value, wherein the first attribution weight value is greater than the second attribution weight value; The step of assigning corresponding attribution weight values based on the element positions of each associated ad item in the associated ad sequence includes: Assign a first attribution weight value to the associated ad items in the associated ad sequence, which are the first and last elements respectively; The number of elements in the associated ad items between the first and last positions is counted, and the second attribution weight value is split and assigned to each of the associated ad items between the first and last positions based on the number of elements.
4. The user source tag determination method according to claim 1, characterized in that, The construction of the first source tag based on the associated advertising items corresponding to each of the user behavior records includes: From the associated ad items corresponding to each user behavior record, select the first associated ad item with the smallest timestamp and the second associated ad item with the largest timestamp; The first associated ad item and the second associated ad item are combined to obtain the first source tag.
5. The user source tag determination method according to claim 1, characterized in that, The preset behavioral events include click behavioral events and browsing behavioral events, and the attribution window period includes a first attribution window period corresponding to the click behavioral event and a second attribution window period corresponding to the browsing behavioral event; The step of configuring the attribution window period corresponding to the preset behavior event based on the trigger time node of the target conversion event includes: Query the first time interval and the second time interval corresponding to the click behavior event and the browsing behavior event, respectively; Configure the first attribution window period of the click behavior event according to the trigger time node of the target conversion event and the first time interval; Configure the second attribution window period of the browsing behavior event based on the trigger time node of the target conversion event and the second time interval.
6. The user source tag determination method according to claim 5, characterized in that, The step of determining associated advertising items from each user behavior record based on the preset behavioral event and the corresponding attribution window includes: Extract at least one first advertisement item corresponding to the click behavior event and at least one second advertisement item corresponding to the browsing behavior event from each user behavior record; A first target ad item is selected from the at least one first ad item based on the first attribution window, and a second target ad item is selected from the at least one second ad item based on the second attribution window; The first target ad item and the second target ad item are merged to obtain the associated ad item.
7. The user source tag determination method according to claim 1, characterized in that, The step of integrating the first source tag and the artificial source tag to obtain the target source tag includes: The content of the first source tag and the artificial source tag is compared to identify duplicate advertising items; The second source label is obtained by removing the duplicate ad items from the artificial source label; The first source tag and the second source tag are combined to obtain the target source tag.
8. A user source tag determination device, characterized in that, include: The record query module is configured to obtain the device identification information of the pending user who triggered the target conversion event, and query the user behavior records corresponding to each preset advertising channel based on the device identification information. The ad item determination module is configured to configure an attribution window period corresponding to a preset behavior event based on the trigger time node of the target conversion event, and determine the associated ad item from each user behavior record based on the preset behavior event and the corresponding attribution window period; The tag generation module is configured to construct a first source tag based on the associated advertising items corresponding to each user behavior record, query the manual source tag of the user to be processed, and integrate the first source tag and the manual source tag to obtain the target source tag.
9. A user source tag determination device, characterized in that, The device includes: one or more processors; and a storage device configured to store one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the user source tag determination method according to any one of claims 1-7.
10. A non-volatile storage medium for storing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are configured to perform the user source tag determination method as described in any one of claims 1-7.