Target user determination method and apparatus, computer device, storage medium, and computer program product

Abstract

The application relates to a target user determination method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining historical working information of each user in a plurality of service platforms in a historical time period and historical activity parameters of historical activities provided by each service platform, and obtaining target activity parameters and target activity requirements of a target activity provided by each service platform; for a target service platform in each service platform, determining target working information of each user for the target activity provided by the target service platform according to the historical working information and the historical activity parameters, the target service platform being any service platform in each service platform; and determining a target user from each user according to the target working information, the target activity parameters and the target activity requirements, so that the target service platform promotes the target activity provided by the target service platform to the target user. The method can avoid the occurrence of resource waste.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, computer equipment, storage medium, and computer program product for identifying a target user. Background Technology

[0002] An aggregation platform refers to a platform that aggregates the transportation resources provided by multiple third-party ride-hailing service providers to offer ride-hailing services to users. Due to the complex organizational structure of aggregation platforms, the competition among ride-hailing service providers within the platform, both on the same platform and across platforms, is significant.

[0003] In existing technologies, ride-hailing service providers select some drivers from multiple drivers based on causal inference methods and provide them with marketing activities to incentivize them to provide more transportation resources to the ride-hailing service provider.

[0004] However, because this method selects drivers with poor accuracy, the marketing campaign is less effective, resulting in a waste of resources. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product with high accuracy for identifying target users, which can improve the effectiveness of marketing activities and avoid the problem of resource waste.

[0006] Firstly, this application provides a method for determining a target user, including:

[0007] Obtain historical work information of each user in multiple service platforms within a historical time period and historical activity parameters of historical activities provided by each service platform, and obtain target activity parameters and target activity requirements of target activities provided by each service platform;

[0008] For each target service platform in the service platform, the target work information of each user for the target activity provided to the target service platform is determined based on the historical work information and the historical activity parameters. The target service platform is any one of the service platforms.

[0009] Based on the target work information, target activity parameters, and target activity requirements, target users are identified from among the users, so that the target service platform can promote the target activities provided by the target service platform to the target users.

[0010] In one embodiment, determining the target work information for each user's target activity provided to the target service platform based on the historical work information and the historical activity parameters includes: performing clustering processing on each user based on the historical work information to obtain clustering results for each user; determining the login probability information of each user logging into the target service platform based on the clustering results, the historical work information, and the historical activity parameters; and determining the target work information based on the clustering results, the login probability information, and the historical work information.

[0011] In one embodiment, the clustering process for each user based on the historical work information to obtain clustering results for each user includes: determining the work status information of each user on each service platform based on the historical work information; and clustering each user based on the work status information to obtain clustering results for each user. The clustering results include single-use and multi-use, where single-use indicates that the user only provides services on the target service platform, and multi-use indicates that the user provides services on the target service platform and also on service platforms other than the target service platform.

[0012] In one embodiment, determining the login probability information of each user logging into the target service platform based on the clustering results, the historical work information, and the historical activity parameters includes: for each user, determining a target login probability information determination model from multiple pre-trained candidate login probability information determination models based on the user's clustering results; and inputting the historical work information and the historical activity parameters into the target login probability information determination model to obtain the user's login probability information.

[0013] In one embodiment, determining the target job information based on the clustering result, the login probability information, and the historical job information includes: if the clustering result is unidirectional, determining the target job information based on the login probability information and the historical job information; if the clustering result is multidirectional, determining whether the user has chosen to provide services on the target service platform based on the login probability information and the historical job information, and if so, determining the target job information based on the historical job information.

[0014] In one embodiment, the target activity requirement includes a first requirement and a second requirement. Determining the target user from among the users based on the target work information, the target activity parameters, and the target activity requirement includes: if the target activity requirement is the first requirement, inputting the target work information and the target activity parameters into a first model to obtain the target user output by the first model; if the target activity requirement is the second requirement, inputting the target work information and the target activity parameters into a second model to obtain the target user output by the second model; wherein the first model includes a first parameter, the second model includes a second parameter, the first parameter is determined based on the first requirement, and the second parameter is determined based on the second requirement.

[0015] Secondly, this application also provides a target user determination device, comprising:

[0016] The acquisition module is used to acquire the historical work information of each user in multiple service platforms within a historical time period and the historical activity parameters of the historical activities provided by each service platform, and to acquire the target activity parameters and target activity requirements of the target activities provided by each service platform.

[0017] The determination module is used to determine, for each target service platform in the service platform, the target work information of each user for the target activity provided by the target service platform based on the historical work information and the historical activity parameters, wherein the target service platform is any one of the service platforms.

[0018] The execution module is used to determine the target user from among the users based on the target work information, the target activity parameters, and the target activity requirements, so that the target service platform can promote the target activity provided by the target service platform to the target user.

[0019] Thirdly, this application also provides a computer device, 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 in any of the embodiments of the first aspect above.

[0020] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of the embodiments of the first aspect above.

[0021] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the embodiments of the first aspect above.

[0022] The aforementioned target user determination method, apparatus, computer equipment, storage medium, and computer program product acquire historical work information of each user across multiple service platforms within a historical time period, as well as historical activity parameters of historical activities provided by each service platform. They also acquire target activity parameters and target activity requirements for target activities provided by each service platform. For a target service platform among these platforms, they determine the target work information of each user for the target activities provided by that target service platform based on the historical work information and historical activity parameters. The target service platform can be any one of the service platforms. Based on the target work information, target activity parameters, and target activity requirements, they determine the target user from among the users, enabling the target service platform to promote the target activities provided by the target service platform to the target user. The target user determination method provided in this application identifies target users for each platform from multiple users based on the historical work information of each user on each platform and the historical activity parameters of each service platform. This method promotes the target activities provided to the target users of each service platform. By taking into account the historical work information of users on each platform and the historical activity parameters of each service platform, the accuracy of the identified target users for each service platform is higher, the effect of the promoted target activities is better, and the problem of resource waste can be effectively avoided. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a method for determining a target user in one embodiment;

[0025] Figure 2 This is a flowchart illustrating a method for determining target work information for each user in relation to a target activity provided by a target service platform, as described in one embodiment.

[0026] Figure 3 This is a flowchart illustrating a method for obtaining clustering results for each user in one embodiment;

[0027] Figure 4 This is a flowchart illustrating a method for determining the login probability information of each user's target service platform in one embodiment.

[0028] Figure 5 This is a flowchart illustrating a method for determining target job information based on clustering results, login probability information, and historical job information in one embodiment.

[0029] Figure 6 This is a flowchart illustrating a method for determining a target user in one embodiment;

[0030] Figure 7 A flowchart illustrating the target user determination method in another embodiment;

[0031] Figure 8 This is a structural block diagram of a target user determination device in one embodiment;

[0032] Figure 9 This is an internal structural diagram of a computer device in one embodiment;

[0033] Figure 10 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation

[0034] 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.

[0035] An aggregation platform refers to a platform that aggregates the transportation resources provided by multiple third-party ride-hailing service providers to offer ride-hailing services to users. Due to the complex organizational structure of aggregation platforms, the competition among ride-hailing service providers within the platform, both on the same platform and across platforms, is significant.

[0036] In existing technologies, ride-hailing service providers select some drivers from multiple drivers based on causal inference methods and provide them with marketing activities to incentivize them to provide more transportation resources to the ride-hailing service provider.

[0037] However, because this method selects drivers with poor accuracy, the marketing campaign is less effective, resulting in a waste of resources.

[0038] In view of this, this application provides a method for determining target users, which can effectively improve the accuracy of identifying target users for various service platforms, resulting in better promotional activities and effectively avoiding resource waste.

[0039] The target user determination method provided in this application can be executed by a computer device, which can be a terminal or a server. The terminal can be, but is not limited to, various personal computers, laptops, tablets, and IoT devices, while the server can be a standalone server or a server cluster composed of multiple servers.

[0040] In one exemplary embodiment, such as Figure 1As shown, a method for determining target users is provided, which includes the following steps:

[0041] Step 101: Obtain the historical work information of each user in multiple service platforms within the historical time period and the historical activity parameters of the historical activities provided by each service platform, and obtain the target activity parameters and target activity requirements of the target activities provided by each service platform.

[0042] Optionally, the historical period can be a time period pre-set by the technician according to actual needs. The historical period can be one month or one year. This application does not limit this.

[0043] This user can be a ride-hailing driver, and this historical work information can be used to characterize the user's daily order completion status. Specifically, it can include the user's daily driving hours, number of completed orders, earnings from completed orders, and activity rewards received.

[0044] This historical activity can include reward-based activities and guarantee-based activities. Reward-based activities refer to activities that award a fixed reward to the user when the user meets the preset conditions. Guarantee-based activities refer to activities that, when the user meets the preset conditions, if their order earnings are less than a preset earnings value, will award a supplementary reward to make up the difference between the user's order earnings and the preset earnings value.

[0045] The parameters for this historical campaign include the target user list for the campaign, the campaign duration, the required number of orders to be completed, and the campaign reward metrics.

[0046] This target activity includes both reward-based and guarantee-based activities. The parameters for this target activity can include relevant content from the historical activity parameters mentioned above, as well as parameters for reward-based and guarantee-based activities. The reward-based activity parameter is the ratio of the activity reward to the preset number of orders completed during the activity. The guarantee-based activity parameter is the difference between the preset benefit value of the activity and the product of the preset number of orders completed during the activity and the average benefit of the user's historical order completion volume. This target activity requirement is essentially the preset condition that the user must meet.

[0047] In some exemplary embodiments, the historical work information of each user in multiple service platforms during the historical time period, the historical activity parameters of the historical activities provided by each service platform, the target activity parameters and target activity requirements of the target activities provided by each service platform can be obtained through the service information database.

[0048] Step 102: For each target service platform in the service platform, determine the target work information of each user for the target activity provided to the target service platform based on the historical work information and the historical activity parameters.

[0049] The target service platform can be any one of the various service platforms.

[0050] Optionally, this target work information can be used to characterize the completion status of each user's target activities provided by the target service platform.

[0051] In some exemplary embodiments, for the target service platform in each service platform, the historical work information of each user, the historical activity parameters and the target activity parameters of the target activity can be input into a pre-trained target work information determination model to obtain the target work information of each user output by the target work information determination model.

[0052] Step 103: Based on the target work information, target activity parameters, and target activity requirements, identify target users from among the users, so that the target service platform can promote the target activities provided by the target service platform to the target users.

[0053] In some exemplary embodiments, the target work information, target activity parameters, and target activity requirements of each user can be input into a pre-trained target user determination model to obtain the target user output by the target user determination model.

[0054] It can also determine the matching degree between each user and the target activity based on each user's work information, target activity parameters, and target activity requirements, and identify users whose matching degree is greater than the preset matching degree threshold as the target user.

[0055] Furthermore, after identifying target users, the target service platform can promote the target activities it provides to these users. Since the target users are precisely selected, the effectiveness of the target activities can be effectively improved, thereby avoiding the problem of wasting resources.

[0056] The aforementioned method for determining target users involves acquiring historical work information of each user across multiple service platforms within a historical time period, as well as historical activity parameters of historical activities provided by each service platform. It also acquires target activity parameters and target activity requirements for target activities provided by each service platform. For a target service platform within each service platform, the method determines the target work information for each user regarding the target activities offered by that target service platform based on the historical work information and historical activity parameters. The target service platform can be any one of the various service platforms. Based on the target work information, target activity parameters, and target activity requirements, the method identifies target users from among the users, enabling the target service platform to promote its target activities to those target users. The target user determination method provided in this application identifies target users for each platform from among multiple users based on the historical work information of each user across various platforms and the historical activity parameters of each service platform. By considering the historical work information of users on each platform and the historical activity parameters of each service platform, the accuracy of the identified target users for each service platform is higher, resulting in better promotion of target activities and effectively avoiding resource waste.

[0057] In one exemplary embodiment, such as Figure 2 As shown, determining the target work information for each user's target activities on the target service platform based on the historical work information and historical activity parameters includes the following steps:

[0058] Step 201: Based on the historical work information, perform clustering processing on each user to obtain the clustering results for each user.

[0059] Optionally, the clustering results can be used to characterize whether each user is a single user. As mentioned above, the aggregation platform contains multiple ride-hailing service providers; therefore, a user may provide transportation resources to only one ride-hailing service provider, or they may provide transportation resources to multiple ride-hailing service providers.

[0060] Optionally, the historical work information of each user can be input into a pre-trained clustering result determination model to obtain the clustering results for each user.

[0061] Step 202: Determine the login probability information of each user on the target service platform based on the clustering results, historical work information, and historical activity parameters.

[0062] In some exemplary embodiments, the clustering results, the historical work information, and the historical activity parameters can be input into a pre-trained login probability information determination model to obtain the login probability information output by the login probability information determination model.

[0063] For example, different service platforms can correspond to different login probability information determination models, or only one login probability information determination model can be trained, but the identifier corresponding to the target service platform must also be input when inputting.

[0064] Step 203: Determine the target job information based on the clustering results, the login probability information, and the historical job information.

[0065] In some exemplary embodiments, the clustering result, the login probability information, and the historical job information can be input into a pre-trained target job information determination model to obtain the target job information output by the target job information determination model.

[0066] In one exemplary embodiment, such as Figure 3 As shown, the clustering process for each user based on the historical work information to obtain the clustering results for each user includes the following steps:

[0067] Step 301: Determine the work status information of each user on each service platform based on the historical work information;

[0068] Step 302: Based on the work status information, perform clustering processing on each user to obtain the clustering results for each user.

[0069] The clustering results include monophasic and polyphasic types. Monophasic indicates that the user provides services only on the target service platform, while polyphasic indicates that the user provides services on the target service platform and also on service platforms other than the target service platform.

[0070] In some exemplary embodiments, a user's work status information on each service platform can be determined based on the user's historical work information. For example, an aggregation platform includes service platforms corresponding to three ride-hailing service providers, namely A1, A2, and A3. If it is determined from the user's historical work information that the user only provides transportation resources on platform A1, then the user's work status information can be determined as A1. If it is determined from the user's historical work information that the user provides transportation resources on both platforms A1 and A3, then the user's work status information can be determined as A1 and A3.

[0071] Furthermore, if the target service platform is A1 and the user's historical work information is A1, then the user's clustering result can be determined to be single-person; if the target service platform is A1 and the user's historical work information is A1 and A3, then the user's clustering result can be determined to be multi-person.

[0072] In an optional embodiment of this application, the silhouette coefficient method can also be used to determine the second clustering result of each user based on the historical work information. The second clustering result is used to characterize the order completion volume of each user. The difference in order completion volume between different types of users can be determined through the second clustering result.

[0073] In one exemplary embodiment, such as Figure 4 As shown, the method for determining the login probability information of each user on the target service platform based on the clustering results, historical work information, and historical activity parameters includes the following steps:

[0074] Step 401: For each user in the user group, determine the target login probability information determination model from multiple pre-trained candidate login probability information determination models based on the clustering results of the user.

[0075] Step 402: Input the historical work information and the historical activity parameters into the target login probability information determination model to obtain the user's login probability information.

[0076] Optionally, this login probability information is used to characterize the probability that a user logs into the target service platform.

[0077] For example, different clustering results correspond to different models for determining login probability information.

[0078] In some exemplary embodiments, for each user, the candidate login probability information determination model corresponding to the clustering result can be determined from multiple pre-trained candidate login probability information determination models based on the clustering result, and used as the target login probability information determination model.

[0079] Furthermore, the user's historical work information, historical activity parameters, and historical characteristic data can be input into the target login probability information determination model to obtain the user's login probability information.

[0080] The model for determining the login probability information can be a logistic regression model. The historical feature data can characterize the user's enthusiasm and fatigue level in providing transportation resources. This historical feature data may include the user's average number of completed orders within a preset time period, the duration of login to the target service platform, the number of days the user has continuously provided transportation resources, and the number of days without providing transportation resources.

[0081] The above method, for each user, determines the target login probability information determination model from multiple pre-trained candidate login probability information determination models based on the user's clustering results, and inputs the historical work information and historical activity parameters into the target login probability information determination model to obtain the user's login probability information. Since the clustering results include single-user and dual-user, the probability of single-user and dual-user logging into the target service platform is different. Therefore, using different models for prediction based on different clustering results can effectively improve the accuracy of the prediction results.

[0082] In one exemplary embodiment, such as Figure 5 As shown, determining the target job information based on the clustering results, login probability information, and historical job information includes the following steps:

[0083] Step 501: If the clustering result is solitary, determine the target job information based on the login probability information and the historical job information.

[0084] Specifically, this target information could be the user's predicted order volume.

[0085] In some exemplary embodiments, if the clustering result is singular and the login probability indicated by the login probability information is greater than a preset login probability threshold, the user's historical job information and historical feature data can be input into a pre-trained target job information determination model to obtain the target job information output by the target job information determination model. The target job information determination model can be a fitted fixed-effects regression model.

[0086] Step 502: If the clustering result is multi-functional, determine whether the user has chosen to provide services on the target service platform based on the login probability information and the historical work information. If so, determine the target work information based on the historical work information.

[0087] In some exemplary embodiments, if the clustering result is multi-faceted, the system first determines whether the user has chosen to provide services on the target service platform based on the login probability information and the historical work information.

[0088] Furthermore, after determining that the user provides services on the target service platform, the target work information is then determined based on the historical work information.

[0089] In one exemplary embodiment, such as Figure 6 As shown, the target activity requirements include a first requirement and a second requirement. The process of determining the target user from among the users based on the target work information, the target activity parameters, and the target activity requirements includes the following steps:

[0090] Step 601: If the target activity requirement is the first requirement, input the target work information and the target activity parameters into the first model to obtain the target user output by the first model;

[0091] Step 602: If the target activity requirement is the second requirement, input the target work information and the target activity parameters into the second model to obtain the target user output by the second model;

[0092] The first model contains a first parameter, and the second model contains a second parameter. The first parameter is determined based on the first requirement, and the second parameter is determined based on the second requirement.

[0093] Optionally, the first requirement could be maximizing efficiency, that is, maximizing the revenue of the target service platform. The second requirement could be maximizing order completion, that is, maximizing the number of orders completed by each target user.

[0094] The first parameter and the second parameter can be understood as the weight ratio of each piece of information and each parameter in the target work information and target activity parameters, which can be preset by technical personnel according to actual needs.

[0095] In some exemplary embodiments, when the target activity requirement is the first requirement, the initial parameters in the initial model can be adjusted to the first parameters to obtain the first model. The target work information and the target activity parameters are then input into the first model to obtain the target user output by the first model. Promoting the target activity to the target user can maximize the revenue of the target service platform.

[0096] Furthermore, if the target activity requirement is the second requirement, the initial parameters in the initial model can be adjusted to the second parameters to obtain the second model. The target work information and the target activity parameters can then be input into the second model to obtain the target users output by the second model. Promoting the target activity to these target users can maximize the number of orders completed by the target service platform.

[0097] In one exemplary embodiment, such as Figure 7 As shown, another method for determining target users is provided, which includes the following steps:

[0098] Step 701: Obtain the historical work information of each user in multiple service platforms within the historical time period and the historical activity parameters of the historical activities provided by each service platform, and obtain the target activity parameters and target activity requirements of the target activities provided by each service platform.

[0099] Step 702: For each target service platform in the service platform, determine the work status information of each user on each service platform based on the historical work information; perform clustering processing on each user based on the work status information to obtain the clustering results for each user; wherein, the clustering results include monophasic and multiphasic, the monophasic is used to indicate that the user only provides services on the target service platform, and the multiphasic is used to indicate that the user provides services on the target service platform and also provides services on service platforms other than the target service platform; the target service platform is any one of the service platforms.

[0100] Step 703: For each user among all users, determine the target login probability information determination model from multiple pre-trained candidate login probability information determination models based on the user's clustering results; input the historical work information and the historical activity parameters into the target login probability information determination model to obtain the user's login probability information;

[0101] Step 704: If the clustering result is unidirectional, determine the target job information based on the login probability information and the historical job information; if the clustering result is multidirectional, determine whether the user has chosen to provide services on the target service platform based on the login probability information and the historical job information. If so, determine the target job information based on the historical job information.

[0102] Step 705: If the target activity requirement is the first requirement, input the target work information and the target activity parameters into the first model to obtain the target user output by the first model; if the target activity requirement is the second requirement, input the target work information and the target activity parameters into the second model to obtain the target user output by the second model; so that the target service platform promotes the target activity provided by the target service platform to the target user; wherein the first model contains a first parameter, the second model contains a second parameter, the first parameter is determined according to the first requirement, and the second parameter is determined according to the second requirement.

[0103] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0104] Based on the same inventive concept, this application also provides a target user determination apparatus for implementing the target user determination method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more target user determination apparatus embodiments provided below can be found in the limitations of the target user determination method described above, and will not be repeated here.

[0105] In one exemplary embodiment, such as Figure 8 As shown, a target user determination device 800 is provided, including: an acquisition module 801, a determination module 802, and an execution module 803, wherein:

[0106] The acquisition module 801 is used to acquire the historical work information of each user in multiple service platforms within a historical time period and the historical activity parameters of the historical activities provided by each service platform, and to acquire the target activity parameters and target activity requirements of the target activities provided by each service platform.

[0107] The determination module 802 is used to determine, for each target service platform in the service platform, the target work information of each user for the target activity provided by the target service platform based on the historical work information and the historical activity parameters, wherein the target service platform is any one of the service platforms.

[0108] The execution module 803 is used to determine the target user from among the users based on the target work information, the target activity parameters and the target activity requirements, so that the target service platform can promote the target activity provided by the target service platform to the target user.

[0109] In one embodiment, the determining module 802 is specifically configured to perform clustering processing on each user based on the historical work information to obtain the clustering results of each user; determine the login probability information of each user logging into the target service platform based on the clustering results, the historical work information, and the historical activity parameters; and determine the target work information based on the clustering results, the login probability information, and the historical work information.

[0110] In one embodiment, the determining module 802 is specifically configured to determine the working status information of each user on each service platform based on the historical working information; perform clustering processing on each user based on the working status information to obtain the clustering result of each user; wherein, the clustering result includes monophasic and polyphasic, the monophasic is used to indicate that the user only provides services on the target service platform, and the polyphasic is used to indicate that the user provides services on the target service platform and also provides services on service platforms other than the target service platform.

[0111] In one embodiment, the determining module 802 is specifically used to determine a target login probability information determining model for each user based on the user's clustering results from multiple pre-trained candidate login probability information determining models; and input the historical work information and the historical activity parameters into the target login probability information determining model to obtain the user's login probability information.

[0112] In one embodiment, the determining module 802 is specifically used to determine the target job information based on the login probability information and the historical job information when the clustering result is unidirectional; and to determine whether the user has chosen to provide services on the target service platform based on the login probability information and the historical job information when the clustering result is multidirectional, and if so, to determine the target job information based on the historical job information.

[0113] In one embodiment, the target activity requirement includes a first requirement and a second requirement. The execution module 803 is specifically configured to, when the target activity requirement is the first requirement, input the target work information and the target activity parameters into a first model to obtain the target user output by the first model; and when the target activity requirement is the second requirement, input the target work information and the target activity parameters into a second model to obtain the target user output by the second model; wherein the first model contains a first parameter and the second model contains a second parameter, the first parameter being determined based on the first requirement and the second parameter being determined based on the second requirement.

[0114] The modules in the aforementioned target user determination device 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, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0115] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational 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 a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements a target user determination method.

[0116] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. 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 and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for determining a target user. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0117] Those skilled in the art will understand that Figure 9 and Figure 10 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.

[0118] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0119] Obtain historical work information of each user in multiple service platforms within a historical time period and historical activity parameters of historical activities provided by each service platform, and obtain target activity parameters and target activity requirements of target activities provided by each service platform;

[0120] For each target service platform in the service platform, the target work information of each user for the target activity provided to the target service platform is determined based on the historical work information and the historical activity parameters. The target service platform is any one of the service platforms.

[0121] Based on the target work information, target activity parameters, and target activity requirements, target users are identified from among the users, so that the target service platform can promote the target activities provided by the target service platform to the target users.

[0122] In one embodiment, when the processor executes the computer program, it further performs the following steps: clustering each user based on the historical work information to obtain clustering results for each user; determining the login probability information of each user logging into the target service platform based on the clustering results, the historical work information, and the historical activity parameters; and determining the target work information based on the clustering results, the login probability information, and the historical work information.

[0123] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the working status information of each user on each service platform based on the historical working information; performing clustering processing on each user based on the working status information to obtain the clustering result of each user; wherein the clustering result includes monophasic and polyphasic, the monophasic being used to indicate that the user only provides services on the target service platform, and the polyphasic being used to indicate that the user provides services on the target service platform and also provides services on service platforms other than the target service platform.

[0124] In one embodiment, when the processor executes the computer program, it further performs the following steps: for each of the users, determining a target login probability information determination model from multiple pre-trained candidate login probability information determination models based on the clustering results of the user; inputting the historical work information and the historical activity parameters into the target login probability information determination model to obtain the login probability information of the user.

[0125] In one embodiment, when the processor executes the computer program, it further performs the following steps: if the clustering result is unidirectional, determine the target job information based on the login probability information and the historical job information; if the clustering result is multidirectional, determine whether the user has chosen to provide services on the target service platform based on the login probability information and the historical job information, and if so, determine the target job information based on the historical job information.

[0126] In one embodiment, when the processor executes the computer program, it further performs the following steps: if the target activity requirement is the first requirement, inputting the target work information and the target activity parameters into a first model to obtain the target user output by the first model; if the target activity requirement is the second requirement, inputting the target work information and the target activity parameters into a second model to obtain the target user output by the second model; wherein the first model contains a first parameter, the second model contains a second parameter, the first parameter is determined according to the first requirement, and the second parameter is determined according to the second requirement.

[0127] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0128] Obtain historical work information of each user in multiple service platforms within a historical time period and historical activity parameters of historical activities provided by each service platform, and obtain target activity parameters and target activity requirements of target activities provided by each service platform;

[0129] For each target service platform in the service platform, the target work information of each user for the target activity provided to the target service platform is determined based on the historical work information and the historical activity parameters. The target service platform is any one of the service platforms.

[0130] Based on the target work information, target activity parameters, and target activity requirements, target users are identified from among the users, so that the target service platform can promote the target activities provided by the target service platform to the target users.

[0131] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: clustering each user based on the historical work information to obtain clustering results for each user; determining the login probability information of each user logging into the target service platform based on the clustering results, the historical work information, and the historical activity parameters; and determining the target work information based on the clustering results, the login probability information, and the historical work information.

[0132] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the working status information of each user on each service platform based on the historical working information; performing clustering processing on each user based on the working status information to obtain the clustering result of each user; wherein the clustering result includes monophasic and polyphasic, the monophasic being used to indicate that the user only provides services on the target service platform, and the polyphasic being used to indicate that the user provides services on the target service platform and also provides services on service platforms other than the target service platform.

[0133] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: for each of the users, determining a target login probability information determination model from multiple pre-trained candidate login probability information determination models based on the clustering results of the user; inputting the historical work information and the historical activity parameters into the target login probability information determination model to obtain the login probability information of the user.

[0134] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: if the clustering result is unidirectional, determine the target job information based on the login probability information and the historical job information; if the clustering result is multidirectional, determine whether the user has chosen to provide services on the target service platform based on the login probability information and the historical job information, and if so, determine the target job information based on the historical job information.

[0135] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: if the target activity requirement is the first requirement, inputting the target work information and the target activity parameters into a first model to obtain the target user output by the first model; if the target activity requirement is the second requirement, inputting the target work information and the target activity parameters into a second model to obtain the target user output by the second model; wherein the first model contains a first parameter, the second model contains a second parameter, the first parameter is determined according to the first requirement, and the second parameter is determined according to the second requirement.

[0136] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0137] Obtain historical work information of each user in multiple service platforms within a historical time period and historical activity parameters of historical activities provided by each service platform, and obtain target activity parameters and target activity requirements of target activities provided by each service platform;

[0138] For each target service platform in the service platform, the target work information of each user for the target activity provided to the target service platform is determined based on the historical work information and the historical activity parameters. The target service platform is any one of the service platforms.

[0139] Based on the target work information, target activity parameters, and target activity requirements, target users are identified from among the users, so that the target service platform can promote the target activities provided by the target service platform to the target users.

[0140] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: clustering each user based on the historical work information to obtain clustering results for each user; determining the login probability information of each user logging into the target service platform based on the clustering results, the historical work information, and the historical activity parameters; and determining the target work information based on the clustering results, the login probability information, and the historical work information.

[0141] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the working status information of each user on each service platform based on the historical working information; performing clustering processing on each user based on the working status information to obtain the clustering result of each user; wherein the clustering result includes monophasic and polyphasic, the monophasic being used to indicate that the user only provides services on the target service platform, and the polyphasic being used to indicate that the user provides services on the target service platform and also provides services on service platforms other than the target service platform.

[0142] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: for each of the users, determining a target login probability information determination model from multiple pre-trained candidate login probability information determination models based on the clustering results of the user; inputting the historical work information and the historical activity parameters into the target login probability information determination model to obtain the login probability information of the user.

[0143] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: if the clustering result is unidirectional, determine the target job information based on the login probability information and the historical job information; if the clustering result is multidirectional, determine whether the user has chosen to provide services on the target service platform based on the login probability information and the historical job information, and if so, determine the target job information based on the historical job information.

[0144] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: if the target activity requirement is the first requirement, inputting the target work information and the target activity parameters into a first model to obtain the target user output by the first model; if the target activity requirement is the second requirement, inputting the target work information and the target activity parameters into a second model to obtain the target user output by the second model; wherein the first model contains a first parameter, the second model contains a second parameter, the first parameter is determined according to the first requirement, and the second parameter is determined according to the second requirement.

[0145] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0146] Those skilled in the art will understand that all or part of the processes in 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. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0147] 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.

[0148] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. 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 application should be determined by the appended claims.

Claims

1. A target user determining method, characterized by, The method comprises: obtaining historical working information of each user in a plurality of service platforms in a historical time period and historical activity parameters of historical activities provided by each service platform, and obtaining target activity parameters and target activity requirements of a target activity provided by each service platform; for a target service platform in each service platform, determining working condition information of each user in each service platform according to the historical working information; performing clustering processing on each user according to the working condition information to obtain a clustering result of each user; wherein the clustering result includes single habitat and multiple habitats, the single habitat is used to indicate that the user only provides services in the target service platform, the multiple habitats are used to indicate that the user provides services in the target service platform and in a service platform other than the target service platform, and the target service platform is any service platform in each service platform; for each of each user, determining a target login probability information determination model from a plurality of pre-trained candidate login probability information determination models according to the clustering result of the user; inputting the historical working information and the historical activity parameters into the target login probability information determination model to obtain login probability information of the user; in the case that the clustering result is single habitat, determining target working information according to the login probability information and the historical working information; in the case that the clustering result is multiple habitats, determining whether the user selects to provide services in the target service platform according to the login probability information and the historical working information, if yes, determining the target working information according to the historical working information; determining a target user from each user according to the target working information, the target activity parameters and the target activity requirements, so that the target service platform promotes the target activity provided by the target service platform to the target user.

2. The method of claim 1, wherein, The target activity requirements include first requirements and second requirements, and determining a target user from each user according to the target working information, the target activity parameters and the target activity requirements comprises: in the case that the target activity requirements are the first requirements, inputting the target working information and the target activity parameters into a first model to obtain a target user output by the first model; in the case that the target activity requirements are the second requirements, inputting the target working information and the target activity parameters into a second model to obtain a target user output by the second model; wherein the first model contains a first parameter, the second model contains a second parameter, the first parameter is determined according to the first requirements, and the second parameter is determined according to the second requirements, the first requirements are maximization of the target service platform revenue, and the second requirements are maximization of the target user order completion quantity.

3. The method of claim 1, wherein, The target working information is used to represent the completion of each user for the target activity provided by the target service platform.

4. The method of claim 1, wherein, The method further comprises: The profile coefficient method is used to determine a second clustering result of each user according to the historical work information, and the second clustering result is used to represent the order completion amount of each user.

5. The method of claim 1, wherein, The login probability information is used to represent the probability of a user logging into the target service platform.

6. The method of claim 1, wherein, The target work information is the predicted order completion amount of the user.

7. A target user determining apparatus characterized by comprising: The device comprises: An acquisition module is configured to acquire historical work information of users in multiple service platforms and historical activity parameters of historical activities provided by the service platforms in a historical period, and acquire target activity parameters and target activity demand of a target activity provided by a target service platform. A determination module is configured to determine work condition information of each user in each service platform according to the historical work information, and perform clustering processing on each user according to the work condition information to obtain a clustering result of each user, wherein the clustering result includes single habitat and multiple habitat, the single habitat is used to indicate that the user provides services only in the target service platform, the multiple habitat is used to indicate that the user provides services in the target service platform and in a service platform other than the target service platform, and the target service platform is any one of the service platforms; for each user, a target login probability information determination model is determined from multiple pre-trained candidate login probability information determination models according to the clustering result of the user; the historical work information and the historical activity parameters are input into the target login probability information determination model to obtain login probability information of the user; in the case of single habitat, target work information is determined according to the login probability information and the historical work information; in the case of multiple habitat, it is determined whether the user chooses to provide services in the target service platform according to the login probability information and the historical work information, and if so, the target work information is determined according to the historical work information. An execution module is configured to determine a target user from each user according to the target work information, the target activity parameters and the target activity demand, so that the target service platform promotes the target activity provided by the target service platform to the target user.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6. The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images