User portrait determination method, device, and electronic device

Abstract

The present application provides a method, device and electronic device for determining a user portrait, which relates to the field of big data technology, and in particular to the field of data analysis. The specific implementation scheme is: obtaining a data set on a target platform end, wherein the data set includes data information of multiple dimensions; based on the data information of the multiple dimensions, obtaining M first data warehouse tables, each first data warehouse table includes data information of at least one dimension, and different first data warehouse tables correspond to different dimensions, and M is a positive integer; determining the user portrait of the target platform end according to the M first data warehouse tables.

Description

Technical Field

[0001] The present application relates to the field of big data technology, in particular to the field of data analysis, and specifically to a method, device and electronic device for determining a user portrait. Background Art

[0002] With the development of big data technology, user portraits have occupied an increasingly important position in data. Currently, when obtaining user portraits, it is usually necessary to conduct questionnaire surveys on buyers at regular intervals to obtain the buyer's user portraits. Summary of the Invention

[0003] The present application provides a method, device and electronic device for determining a user portrait.

[0004] According to a first aspect of the present application, a method for determining a user profile is provided, comprising:

[0005] Obtaining a data set on a target platform, wherein the data set includes data information in multiple dimensions;

[0006] Based on the data information of the multiple dimensions, M first data bin tables are obtained, each of which includes data information of at least one dimension, and different first data bin tables correspond to different dimensions, where M is a positive integer;

[0007] Determine the user profile of the target platform end according to the M first data warehouse tables.

[0008] According to a second aspect of the present application, a user portrait determination device is provided, comprising:

[0009] An acquisition module is used to acquire a data set on a target platform, wherein the data set includes data information of multiple dimensions;

[0010] an obtaining module, configured to obtain M first data bin tables based on the data information of the multiple dimensions, where each first data bin table includes data information of at least one dimension, and different first data bin tables correspond to different dimensions, and M is a positive integer;

[0011] A determination module is used to determine the user portrait of the target platform end according to the M first data warehouse tables.

[0012] According to a third aspect of the present application, an electronic device is provided, including:

[0013] at least one processor; and

[0014] a memory communicatively connected to at least one processor; wherein,

[0015] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any one of the methods in the first aspect.

[0016] According to a fourth aspect of the present application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute any one of the methods in the first aspect.

[0017] According to a fifth aspect of the present application, a computer program product is provided, comprising a computer program, which implements any one of the methods in the first aspect when executed by a processor.

[0018] In an embodiment of the present application, the user portrait of the target platform can be determined through M first data warehouse tables, and different data warehouse tables correspond to different dimensions, so that the user portrait can be determined from multiple dimensions, thereby improving the accuracy of the user portrait.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is one of the flow charts of the method for determining a user profile provided in an embodiment of the present application;

[0021] Figure 2 This is the second flow chart of the method for determining a user profile provided in an embodiment of the present application;

[0022] Figure 3 This is one of the flowcharts for allocating a unified identifier provided in an embodiment of the present application;

[0023] Figure 4 This is the second flowchart of allocating a unified identifier provided in an embodiment of the present application;

[0024] Figure 5 Schematic diagram of the training process of the label prediction model provided in the embodiment of the present application;

[0025] Figure 6 This is a schematic diagram of the structure of the user portrait determination device provided in an embodiment of the present application;

[0026] Figure 7 is a schematic block diagram of an example electronic device for implementing embodiments of the present application. DETAILED DESCRIPTION

[0027] The following description of exemplary embodiments of the present application is made in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0028] See also Figure 1 , Figure 1 A flowchart of a method for determining a user profile provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, a method for determining a user portrait includes the following steps:

[0029] Step S101: Acquire a data set on a target platform, where the data set includes data information in multiple dimensions.

[0030] Among them, the number of dimensions included in the data set is not limited here. The more dimensions there are, the richer the types of data information are. In this way, the above data information enriches the dimensions of the user portrait of the target platform end that is finally determined, and the accuracy of the user portrait of the target platform end determined based on the above data information is higher, that is, the confidence of the user portrait is higher.

[0031] As an optional implementation manner, obtaining the data set on the target platform includes:

[0032] The data set of the target platform is obtained through multiple channels, wherein one channel obtains data information of at least one dimension.

[0033] The specific types of the above channels are not limited here, for example: Figure 2 The above-mentioned multiple channels may include: at least one of the e-commerce site of the target platform, search channels, recommendation channels, delivery channels, and user terminals corresponding to the target platform. The above-mentioned recommendation channels may refer to at least one of the short video recommendation channels and stream recommendation channels. The above-mentioned delivery channels may refer to advertising delivery channels.

[0034] In addition, the above-mentioned e-commerce site can also be called the merchant backend. When obtaining information through the user end corresponding to the target platform end, data information can be obtained through the user portrait or buyer's business card of the user end, and the type of data information obtained is not limited here. For example: the data information may include the buyer's identity, the size of the company, and other information.

[0035] It should be noted that the target platform end can be referred to as the B-end, and the user end can be referred to as the C-end.

[0036] In the implementation manner of the present application, a data set on the target platform side is obtained through multiple channels. Since the channels for obtaining data information are different, the dimensions corresponding to the data information are usually different, and one channel can obtain data information of at least one dimension. In this way, data information of multiple dimensions can be quickly obtained according to different channels, which improves the acquisition speed of data information of multiple dimensions and enriches the dimensions of the data information.

[0037] Step S102: Based on the data information of the multiple dimensions, M first data warehouse tables are obtained, each of which includes data information of at least one dimension, and different first data warehouse tables correspond to different dimensions, and M is a positive integer.

[0038] The correspondence between the first data warehouse tables and the dimensions of the data information is not limited herein. For example, as an optional embodiment, the first data warehouse tables can have a one-to-one correspondence with the dimensions of the data information, i.e., each first data warehouse table only includes data information of one dimension. It should be noted that data information of multiple dimensions can be stored in a report, and the report can be split to obtain M first data warehouse tables. In this case, the obtained first data warehouse tables can have a one-to-one correspondence with the dimensions of the data information.

[0039] As another optional implementation, the first data warehouse table can have a one-to-many correspondence with the dimensions of the data information. That is, as an optional implementation, after obtaining the M first data warehouse tables, data can be aggregated on the M first data warehouse tables to obtain multiple aggregated first data warehouse tables. The aggregated first data warehouse tables can include data information of at least two dimensions, meaning the aggregated first data warehouse tables can have a one-to-many correspondence with the dimensions. User profiles on the target platform can then be obtained based on the aggregated first data warehouse tables.

[0040] In this way, since the first data warehouse table after data aggregation includes data information of at least two dimensions, the number of first data warehouse tables is reduced, the amount of calculation and calculation space are reduced, and the consumption of computing resources is reduced.

[0041] It should be noted that when data is aggregated on the M first data warehouse tables, the aggregation can be performed according to the target parameters to obtain different types of first data warehouse tables, see Figure 2 The first data warehouse table can include a basic table, an intermediate table, and a historical behavior sequence table. The target parameter type is not limited here. The target parameter can be a period. Thus, the intermediate table determined based on the period can include at least one of a 1-day intermediate table, a 3-day intermediate table, a 30-day intermediate table, and a 90-day intermediate table. This allows first data warehouse tables of different dimensions to be constructed based on different periods, increasing the diversity of the first data warehouse tables.

[0042] It should be noted that during the process of aggregating the above data warehouse tables, it is possible to monitor in real time whether the aggregation process of the above data warehouse tables is proceeding normally.

[0043] It should be noted that the method for obtaining the first data warehouse table based on data information of multiple dimensions is not limited here.

[0044] As an optional implementation manner, obtaining M first data warehouse tables based on the data information of the multiple dimensions includes:

[0045] Assigning a unified identifier related to the dimension to data information of the same dimension, wherein the data information of the same dimension includes data information obtained through at least one channel;

[0046] Based on the unified identification of the data information of the multiple dimensions, M first data warehouse tables are obtained.

[0047] Since the identifiers of data information obtained from different channels are usually different, it is difficult to obtain the first data warehouse table based on a variety of data information obtained from different channels.

[0048] In the implementation manner of the present application, data information of the same dimension can be assigned a unified identifier related to the dimension. When obtaining the first data warehouse table for data information of multiple dimensions, the first data warehouse table can be obtained based on the unified identifier of the data information of the above multiple dimensions, thereby reducing the difficulty of obtaining the first data warehouse table and improving the efficiency of obtaining the first data warehouse table.

[0049] In addition, by assigning a unified identifier, data information from different channels can be fully utilized, increasing the available scope of data information.

[0050] The types of unified identifiers for data information of different dimensions can all be the same. That is, the types of unified identifiers corresponding to data information of multiple dimensions can all be the same, but the corresponding values ​​of the unified identifiers are different. In this way, sorting can be performed according to the values ​​of the unified identifiers, so that the data information of multiple dimensions can be sequentially entered into the first data warehouse table in the sorted order, thereby obtaining multiple first data warehouse tables. The values ​​of the unified identifiers can be determined based on the content richness of each data information. The richer the content of the data information, the larger the value of the corresponding unified identifier.

[0051] It should be noted that when the type of the unified identifier is the same but the value is different, the unified identifier can be understood as a parameter of the data information, that is, each data information is assigned a parameter, but the value of the above parameter is not the same.

[0052] It should be noted that when allocating a unified identifier to the data information of the above multiple dimensions, online allocation or offline allocation can be adopted.

[0053] When using offline allocation, see Figure 3 The data information may request a first field. If the first field is successfully requested, the requested first field may be directly used as the unified identifier of the data information. If the first field is not successfully requested, the first field may be assigned to the data information as the unified identifier of the data information. The specific type of the first field is not limited here. For example, the first field may be referred to as an idmapping-proxy field.

[0054] When using online distribution, see Figure 4 In the process shown in S401 to S407, multiple IDs can represent identification information corresponding to different channels. The above multiple identity documents (IDs) can query the cache at the same time, and construct different query results based on whether a valid udwid field can be queried and whether the ID has a record in the cache, so as to assign a unified identifier based on the query results.

[0055] As an optional implementation manner, each piece of data information includes identification information related to a channel, and assigning data information of the same dimension with a unified identification related to the dimension includes at least one of the following:

[0056] If a first dimension exists among the multiple dimensions, modifying identification information related to the channel included in the data information of the first dimension to a unified identification related to the dimension, wherein the first dimension includes data information obtained through multiple channels;

[0057] In the case that there is a second dimension among the multiple dimensions, the data information of the second dimension and the identification information related to the channel are determined as a unified identification related to the dimension, and the second dimension only includes data information obtained through one channel.

[0058] In the implementation manner of the present application, when the data information of the first dimension comes from multiple channels, the channel-related identification information of the data information of the first dimension can be modified to a unified identification; and when the data information of the second dimension comes from only one channel, the channel-related identification information of the data information of the second dimension can be determined as a unified identification. In this way, different methods of determining the unified identification are determined according to whether the data information comes from different channels, thereby making the method of determining the unified identification more flexible and diversified.

[0059] Step S103: Determine the user profile of the target platform end according to the M first data warehouse tables.

[0060] Among them, the specific method of determining the user portrait based on the M first data warehouse tables is not limited here. As an optional implementation method, each first data warehouse table can correspond to a dimension. In this way, the user portrait is obtained by arranging and combining the different dimensions represented by the first data warehouse tables.

[0061] Among them, the above-mentioned different dimensions are not specifically limited here. For example, the above-mentioned different dimensions can also be referred to as different attributes. The different attributes may include at least one of demographic attributes, location attributes, device attributes, value attributes, life cycle attributes, procurement attributes, behavioral attributes and preference attributes.

[0062] Among them, the channel sources of the above-mentioned demographic attributes, location attributes and device attributes can come from user portraits, seller business cards and merchant backgrounds on the user side, value attributes, life cycle attributes and procurement attributes: based on the buyer's procurement behavior characterization on the e-commerce site, behavior includes the number of days between the buyer's most recent purchase and the current time, the total number of purchases, the number of buyer logins in different periods, etc.; behavioral attributes mainly refer to the buyer's activity in different behaviors, terminals and pages on the e-commerce site, which can be divided into different levels of activity based on the buyer's visit time interval and the number of days since the most recent visit; preference attributes can be based on data information obtained from multiple channels to obtain the buyer's preferences for query records (queries), merchants, products, brands, page types, website types and video types on the target platform side.

[0063] As another optional implementation, the user portrait includes portrait tag information, and determining the user portrait of the target platform end according to the M first data warehouse tables includes:

[0064] Input the data information in the M first data warehouse tables into the label prediction model to perform label prediction, and output the portrait label information on the target platform end;

[0065] The label prediction model is a pre-trained network model used to predict the portrait label information of the target platform.

[0066] In the implementation mode of the present application, the data information in the first data warehouse table can be directly input into the label prediction model for label prediction, and the portrait label information of the target platform end can be output. At the same time, since different data warehouse tables correspond to different dimensions, the accuracy of the prediction of the portrait label information can be improved.

[0067] It should be noted that the type of label prediction model is not limited here. For example, the label prediction model can adopt a combination of a deep recommendation (DeepFM) model and a normalized index (Softmax) classifier, and the training process of the above label prediction model is not limited here.

[0068] As an optional implementation method, a group of trusted users can be identified from the buyer's business cards based on identity verification and industry knowledge. The accuracy and credibility of the data information of the trusted users are relatively high, and the above-mentioned trusted users can also be called "seed users". Figure 5 , obtain the behavioral data and user portrait of the above-mentioned "seed user", and extract the data of the behavioral data and user portrait to obtain a feature vector, first input the feature vector into the model to be trained for training, and then input the data output by the model to be trained into the classifier to be trained for training. When the error between the classification result output by the classifier to be trained and the actual result is less than a preset value, the model to be trained and the classifier to be trained can be respectively determined as the DeepFM model and Softmax classifier included in the above-mentioned label prediction model.

[0069] It should be noted that the form of the classification result output by the above-mentioned Softmax classifier is not limited here. For example, the above-mentioned classification result can be expressed in the form of cross entropy.

[0070] The data information of the "non-seed user" can then be input into the DeepFM model and Softmax classifier included in the label prediction model, so as to complete the prediction of the portrait label information of the "non-seed user", that is, predict the user's identity category, and then information can be pushed based on the user's identity category. The above-mentioned information push can include at least one of the information such as video, advertisement and text information.

[0071] Among them, the above-mentioned behavioral data may include: behavioral statistical characteristics, behavioral time series characteristics, behavioral cross-characteristics, access characteristics, inquiry and transaction attribute characteristics; user portraits may include: demographic attributes, location attributes, device attributes, purchasing attributes, behavioral attributes and preference attributes.

[0072] In an embodiment of the present application, through steps S101 to S103, the user portrait of the target platform can be determined through M first data warehouse tables, and different data warehouse tables correspond to different dimensions, so that the user portrait can be determined from multiple dimensions, thereby improving the accuracy of the user portrait.

[0073] See also Figure 6 , Figure 6 This is a schematic diagram of the structure of a user portrait determination device provided by this application, such as Figure 6 As shown, the user portrait determination device 600 includes:

[0074] An acquisition module 601 is used to acquire a data set on a target platform, where the data set includes data information in multiple dimensions.

[0075] An obtaining module 602 is configured to obtain M first data bin tables based on the data information of the multiple dimensions, where each first data bin table includes data information of at least one dimension, and different first data bin tables correspond to different dimensions, and M is a positive integer;

[0076] The determination module 603 is used to determine the user portrait of the target platform end according to the M first data warehouse tables.

[0077] Optionally, the acquisition module 601 is further configured to: acquire the data set of the target platform end through multiple channels, wherein one channel acquires data information of at least one dimension.

[0078] Optionally, the obtaining module 602 includes:

[0079] an allocation submodule, configured to allocate a unified identifier associated with the dimension to data information of the same dimension, wherein the data information of the same dimension includes data information obtained through at least one channel;

[0080] The obtaining submodule is configured to obtain M first data warehouse tables based on the unified identification of the data information of the multiple dimensions.

[0081] Optionally, each piece of data information includes identification information related to a channel, and the allocation submodule includes at least one of the following:

[0082] a modifying unit, configured to modify, when a first dimension exists among the multiple dimensions, identification information related to the channel included in the data information of the first dimension into a unified identification related to the dimension, wherein the first dimension includes data information obtained through multiple channels;

[0083] The determining unit is configured to determine, when a second dimension exists among the multiple dimensions, data information of the second dimension and identification information related to the channel as a unified identification related to the dimension, wherein the second dimension only includes data information obtained through one channel.

[0084] Optionally, the user portrait includes portrait label information, and the determining module 603 is further configured to input the data information in the M first data warehouse tables into a label prediction model for label prediction, and output the portrait label information on the target platform end;

[0085] The label prediction model is a pre-trained network model used to predict the portrait label information of the target platform.

[0086] The user portrait determination device 600 provided in this application can implement each process implemented in the embodiment of the user portrait determination method and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0087] According to an embodiment of the present application, the present application also provides an electronic device, a readable storage medium and a computer program product.

[0088] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0089] like Figure 7 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. Various programs and data required for the operation of the device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0090] Various components in device 700 are connected to I / O interface 705, including an input unit 706, such as a keyboard, mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, optical disk, etc.; and a communication unit 709, such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows device 700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0091] The computing unit 701 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as the user profile determination method. For example, in some embodiments, the user profile determination method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the user profile determination method described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the user profile determination method in any other appropriate manner (e.g., by means of firmware).

[0092] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0093] The program code for implementing the methods of the present application can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow charts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0094] In the context of the present application, a machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0095] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0096] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0097] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0098] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of this application can be achieved. This is not limited herein.

[0099] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. A method for determining a user profile, comprising: Obtaining a data set on a target platform, wherein the data set includes data information in multiple dimensions; Based on the data information of the multiple dimensions, M first data bin tables are obtained, each of which includes data information of at least one dimension, and different first data bin tables correspond to different dimensions, where M is a positive integer; Determine the user profile of the target platform end according to the M first data warehouse tables; The M first data warehouse tables include a basic table, an intermediate table, and a historical behavior sequence table. Data is aggregated on the M first data warehouse tables according to a period, and the user profile of the target platform end is determined based on the first data warehouse table after data aggregation. The first data warehouse table after data aggregation includes data information of at least two dimensions.

2. The method according to claim 1, wherein The step of obtaining the target platform data set includes: The data set of the target platform is obtained through multiple channels, wherein one channel obtains data information of at least one dimension.

3. The method according to claim 1 or 2, wherein: The obtaining of M first data warehouse tables based on the data information of the multiple dimensions includes: Assigning a unified identifier related to the dimension to data information of the same dimension, wherein the data information of the same dimension includes data information obtained through at least one channel; Based on the unified identification of the data information of the multiple dimensions, M first data warehouse tables are obtained.

4. The method according to claim 3, wherein: Each piece of data information includes identification information related to a channel. Assigning a unified identification related to the dimension to the data information of the same dimension includes at least one of the following: If a first dimension exists among the multiple dimensions, modifying identification information related to the channel included in the data information of the first dimension to a unified identification related to the dimension, wherein the first dimension includes data information obtained through multiple channels; In the case that there is a second dimension among the multiple dimensions, the data information of the second dimension and the identification information related to the channel are determined as a unified identification related to the dimension, and the second dimension only includes data information obtained through one channel.

5. The method according to claim 1, wherein the user profile includes profile tag information, and determining the user profile of the target platform end according to the M first data warehouse tables comprises: Input the data information in the M first data warehouse tables into the label prediction model to perform label prediction, and output the portrait label information on the target platform end; The label prediction model is a pre-trained network model used to predict the portrait label information of the target platform.

6. A user profile determination device, comprising: An acquisition module is used to acquire a data set on a target platform, wherein the data set includes data information of multiple dimensions; an obtaining module, configured to obtain M first data bin tables based on the data information of the multiple dimensions, where each first data bin table includes data information of at least one dimension, and different first data bin tables correspond to different dimensions, and M is a positive integer; a determination module, configured to determine a user profile of the target platform end according to the M first data warehouse tables; The M first data warehouse tables include a basic table, an intermediate table, and a historical behavior sequence table. Data is aggregated on the M first data warehouse tables according to a period, and the user profile of the target platform end is determined based on the first data warehouse table after data aggregation. The first data warehouse table after data aggregation includes data information of at least two dimensions.

7. The device according to claim 6, wherein The acquisition module is further configured to acquire the data set of the target platform through multiple channels, wherein one channel acquires data information of at least one dimension.

8. The device according to claim 6 or 7, wherein: The acquisition module includes: an allocation submodule, configured to allocate a unified identifier associated with the dimension to data information of the same dimension, wherein the data information of the same dimension includes data information obtained through at least one channel; The obtaining submodule is configured to obtain M first data warehouse tables based on the unified identification of the data information of the multiple dimensions.

9. The device according to claim 8, wherein Each piece of data information includes identification information related to a channel, and the allocation submodule includes at least one of the following: a modifying unit, configured to modify, when a first dimension exists among the multiple dimensions, identification information related to the channel included in the data information of the first dimension into a unified identification related to the dimension, wherein the first dimension includes data information obtained through multiple channels; The determining unit is configured to determine, when a second dimension exists among the multiple dimensions, data information of the second dimension and identification information related to the channel as a unified identification related to the dimension, wherein the second dimension only includes data information obtained through one channel.

10. The device according to claim 6, wherein The user portrait includes portrait label information. The determination module is further configured to input the data information in the M first data warehouse tables into a label prediction model for label prediction, and output the portrait label information on the target platform end; The label prediction model is a pre-trained network model used to predict the portrait label information of the target platform.

11. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 5.

13. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images