Object recommendation method and device

Abstract

The invention relates to the technical field of recommendation, and provides an object recommendation method and device. The method comprises the steps that first training data and second training data are obtained, the first training data comprise attribute information of a user or attribute information of a to-be-recommended object, and the second training data comprise the attribute information of the user, the attribute information of the to-be-recommended object and interaction information of the user and the to-be-recommended object; performing feature alignment training on the pre-training language model and the click prediction model by using the first training data; after the click prediction model is subjected to feature alignment training, performing object recommendation training on the click prediction model by using second training data; and recommending a target object to the target user by using the click prediction model after the object recommendation training. By means of the technical means, the problem that in the prior art, the recommendation accuracy is low due to the fact that the semantic feature mining capacity of clicking a prediction model is poor is solved.

Description

Technical Field

[0001] The present application relates to the field of recommendation technology, and in particular to an object recommendation method and device. Background Art

[0002] Traditional click-through rate (CTR) prediction models mine the collaborative relationship between the features of user information and item information to infer the user's preferred items. This recommendation paradigm discards the basic semantic information of user information and item information, or it is difficult to capture the deep semantic information of user information and item information, resulting in the inability to fully utilize the potential of data in CTR tasks and the problem of low recommendation accuracy. Summary of the invention

[0003] In view of this, embodiments of the present application provide an object recommendation method, device, electronic device and computer-readable storage medium to solve the problem in the prior art that the click prediction model has poor ability to mine semantic features, resulting in low recommendation accuracy.

[0004] According to a first aspect of an embodiment of the present application, a method for object recommendation is provided, comprising: obtaining first training data and second training data, wherein the first training data comprises attribute information of a user or attribute information of an object to be recommended, and the second training data comprises attribute information of the user, attribute information of the object to be recommended, and interaction information between the user and the object to be recommended; performing feature alignment training on a pre-trained language model and a click prediction model using the first training data; performing object recommendation training on the click prediction model using the second training data after the click prediction model has passed the feature alignment training; and recommending a target object to a target user using the click prediction model after the object recommendation training.

[0005] According to a second aspect of an embodiment of the present application, an object recommendation device is provided, comprising: an acquisition module, configured to acquire first training data and second training data, wherein the first training data comprises attribute information of a user or attribute information of an object to be recommended, and the second training data comprises attribute information of the user, attribute information of the object to be recommended, and interaction information between the user and the object to be recommended; an alignment training module, configured to perform feature alignment training on a pre-trained language model and a click prediction model using the first training data; a recommendation training module, configured to perform object recommendation training on the click prediction model using the second training data after the click prediction model has passed the feature alignment training; and a recommendation module, configured to recommend a target object to a target user using the click prediction model after the object recommendation training.

[0006] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0007] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0008] Compared with the prior art, the embodiments of the present application have the following beneficial effects: obtaining first training data and second training data, wherein the first training data includes attribute information of the user or attribute information of the object to be recommended, and the second training data includes attribute information of the user, attribute information of the object to be recommended, and interaction information between the user and the object to be recommended; using the first training data to perform feature alignment training on the pre-trained language model and the click prediction model; after the click prediction model has passed the feature alignment training, using the second training data to perform object recommendation training on the click prediction model; using the click prediction model after the object recommendation training to recommend the target object to the target user. The above-mentioned technical means can be used to solve the problem in the prior art that the poor ability of the click prediction model to mine semantic features leads to low recommendation accuracy, thereby improving the ability of the click prediction model to mine semantic features and improving recommendation accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 It is a flowchart of an object recommendation method provided in an embodiment of the present application; Figure 2 It is a flowchart of an alignment training method provided in an embodiment of the present application; Figure 3 is a structural diagram of an object recommendation device provided in an embodiment of the present application; Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0011] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0012] A method and device for recommending an object according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0013] Figure 1 It is a flowchart of an object recommendation method provided in an embodiment of the present application. Figure 1 The object recommendation method can be executed by a computer or a server, or software on a computer or a server. Figure 1 As shown, the object recommendation method includes: S101, obtaining first training data and second training data, wherein the first training data includes attribute information of a user or attribute information of an object to be recommended, and the second training data includes attribute information of the user, attribute information of the object to be recommended, and interaction information between the user and the object to be recommended; S102, performing feature alignment training on a pre-trained language model and a click prediction model using the first training data; S103, after the click prediction model is trained through feature alignment, performing object recommendation training on the click prediction model using the second training data; S104: recommending a target object to a target user by using the click prediction model trained by object recommendation.

[0014] The objects to be recommended can be commodities, houses to be rented or sold, etc., and the following text will take the objects to be recommended as commodities as examples. The first training data contains attribute information of multiple users or attribute information of multiple objects to be recommended. The attribute information of users includes income, age, gender, hobbies, historical shopping records, etc. The attribute information of objects to be recommended includes the parameters of the object, functional uses, evaluations of users who have purchased it, etc. The second training data contains attribute information of multiple users, attribute information of multiple objects to be recommended, and multiple pieces of interaction information between users and objects to be recommended. Each piece of interaction information is an interaction between a user and an object to be recommended. The interaction information includes clicks, evaluations, whether to add to the shopping cart, favorites, etc.

[0015] Pre-trained language models (PLM) are language models that are pre-trained on a large amount of text data. They can better capture the semantic features of information. Click-Through Rate (CTR) models focus more on capturing the embedded features of information.

[0016] The embodiment of the present application uses a pre-trained language model to capture the semantic features of the first training data, and uses a click prediction model to capture the embedded features of the first training data. Then, in the process of aligning the semantic features and the embedded features of the first training data, the pre-trained language model and the click prediction model are trained so that the click prediction model can better capture the semantic features.

[0017] According to the technical solution provided in the embodiment of the present application, the first training data and the second training data are obtained, wherein the first training data contains the attribute information of the user or the attribute information of the object to be recommended, and the second training data contains the attribute information of the user, the attribute information of the object to be recommended, and the interaction information between the user and the object to be recommended; the first training data is used to perform feature alignment training on the pre-trained language model and the click prediction model; after the click prediction model is trained through feature alignment, the second training data is used to perform object recommendation training on the click prediction model; the click prediction model after object recommendation training is used to recommend the target object to the target user. The above-mentioned technical means can be used to solve the problem in the prior art that the poor ability of the click prediction model to mine semantic features leads to low recommendation accuracy, thereby improving the ability of the click prediction model to mine semantic features and improving recommendation accuracy.

[0018] Furthermore, the first training data is used to perform feature alignment training on the pre-trained language model and the click prediction model, including: the first training data contains attribute information of multiple users; the attribute information of each user is input into the pre-trained language model, and the user semantic features of each user are output; the attribute information of each user is input into the click prediction model, and the user embedding features of each user are output; the target loss between the user semantic features and the user embedding features of each user is calculated using the target loss function; and the model parameters of the pre-trained language model and the click prediction model are optimized according to the target loss corresponding to each user.

[0019] The pre-trained language model and click prediction model used in the embodiments of the present application are both the main parts of the model (the parts for feature processing and extraction). The pre-trained language model and the click prediction model need to be added with a fully connected layer for predicting whether to recommend before they can be used.

[0020] Furthermore, a target loss function is used to calculate a target loss between the user semantic features and the user embedded features of each user, including: using a contrast loss function to calculate a target loss between the user semantic features and the user embedded features of each user; or using a mean square error loss function to calculate a target loss between the user semantic features and the user embedded features of each user.

[0021] The target loss may be a contrast loss function and a mean square error loss function, etc. Both the contrast loss function and the mean square error loss function are existing functions and will not be described in detail here.

[0022] Furthermore, the target loss function is used to calculate the target loss between the user semantic features and the user embedded features of each user, including: using the contrast loss function to calculate the contrast loss between the user semantic features and the user embedded features of each user; using the mean square error loss function to calculate the mean square error loss between the user semantic features and the user embedded features of each user; and taking the weighted sum of the contrast loss and the mean square error loss corresponding to each user to obtain the target loss corresponding to each user.

[0023] In order to further improve the effect of model training, the contrast loss and mean square error loss corresponding to each user can be weighted and summed according to the preset weights as the target loss corresponding to each user.

[0024] Furthermore, the first training data is used to perform feature alignment training on the pre-trained language model and the click prediction model, including: the first training data contains attribute information of multiple objects to be recommended; the attribute information of each object to be recommended is input into the pre-trained language model, and the object semantic features of each object to be recommended are output; the attribute information of each object to be recommended is input into the click prediction model, and the object embedding features of each object to be recommended are output; the target loss between the object semantic features and the object embedding features of each object to be recommended is calculated using the target loss function; and the model parameters of the pre-trained language model and the click prediction model are optimized according to the target loss corresponding to each object to be recommended.

[0025] Furthermore, the target loss function is used to calculate the target loss between the object semantic features and the object embedding features of each object, including: using the contrast loss function to calculate the target loss between the object semantic features and the object embedding features of each object; or using the mean square error loss function to calculate the target loss between the object semantic features and the object embedding features of each object.

[0026] Furthermore, the target loss function is used to calculate the target loss between the object semantic features and the object embedding features of each object, including: using the contrast loss function to calculate the contrast loss between the object semantic features and the object embedding features of each object; using the mean square error loss function to calculate the mean square error loss between the object semantic features and the object embedding features of each object; and weighted summing the contrast loss and mean square error loss corresponding to each object to obtain the target loss corresponding to each object.

[0027] Furthermore, after the click prediction model is trained through feature alignment, the click prediction model is trained for object recommendation using the second training data, including: connecting a fully connected network after the click prediction model; inputting the user's attribute information, the attribute information of the object to be recommended, and the interaction information between the user and the object to be recommended into the click prediction model respectively, and outputting the user's embedded features, the embedded features of the object to be recommended, and the embedded features of the interaction between the user and the object to be recommended; inputting the user's embedded features, the embedded features of the object to be recommended, and the embedded features of the interaction between the user and the object to be recommended into the fully connected network, and outputting a judgment result of whether to recommend the object to be recommended to the user; calculating the prediction loss between the judgment result and the label of the second training data using the cross entropy loss function; and optimizing the model parameters of the click prediction model and the fully connected network based on the prediction loss.

[0028] A user and an object that interacts with the user are taken as a group. The user's attribute information, the object's attribute information, and the interaction information between the user and the object are processed by the click prediction model and the fully connected network to obtain the judgment result of whether to recommend the object to the user. The cross entropy loss function is used to calculate the prediction loss between the judgment result and the label of whether to recommend the object to the user.

[0029] Furthermore, the target object is recommended to the target user using the click prediction model trained by object recommendation, including: inputting the attribute information of the target user, the attribute information of the target object, and the interaction information between the target user and the target object into the click prediction model respectively, and outputting the embedded features of the target user, the embedded features of the target object, and the embedded features of the interaction between the target user and the target object; inputting the embedded features of the target user, the embedded features of the target object, and the embedded features of the interaction between the target user and the target object into the fully connected network, and outputting the judgment result of whether to recommend the target object to the target user.

[0030] The embodiment of the present application is the reasoning stage of the model. The previous embodiment is the training stage of the model. The reasoning stage and the training stage correspond to each other, and the reasoning stage will not be explained in detail here.

[0031] Figure 2 is a flow chart of an alignment training method provided in an embodiment of the present application. Figure 2As shown, the method includes: S201, inputting attribute information of each user into a pre-trained language model, and outputting user semantic features of each user; S202, inputting attribute information of each user into a click prediction model, and outputting user embedding features of each user; S203, using a target loss function to calculate a target loss between the user semantic features and the user embedding features of each user; S204, inputting attribute information of each object to be recommended into a pre-trained language model, and outputting object semantic features of each object to be recommended; S205, inputting attribute information of each object to be recommended into a click prediction model, and outputting object embedding features of each object to be recommended; S206, using a target loss function to calculate the target loss between the object semantic features and the object embedding features of each object to be recommended; S207, optimizing the model parameters of the pre-trained language model and the click prediction model according to the target loss corresponding to each user and the target loss corresponding to each object to be recommended.

[0032] The embodiment of the present application is the reasoning stage of the student model. Prior to the embodiment of the present application, the reasoning stage and the training stage of the network correspond to each other, and the reasoning stage will not be explained in detail here.

[0033] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0034] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0035] Figure 3 is a schematic diagram of an object recommendation device provided in an embodiment of the present application. Figure 3 As shown, the object recommendation device includes: The acquisition module 301 is configured to acquire first training data and second training data, wherein the first training data includes attribute information of the user or attribute information of the object to be recommended, and the second training data includes attribute information of the user, attribute information of the object to be recommended, and interaction information between the user and the object to be recommended; An alignment training module 302 is configured to perform feature alignment training on the pre-trained language model and the click prediction model using the first training data; The recommendation training module 303 is configured to perform object recommendation training on the click prediction model using the second training data after the click prediction model is trained through feature alignment; The recommendation module 304 is configured to recommend a target object to a target user by using the click prediction model trained by object recommendation.

[0036] According to the technical solution provided in the embodiment of the present application, the first training data and the second training data are obtained, wherein the first training data contains the attribute information of the user or the attribute information of the object to be recommended, and the second training data contains the attribute information of the user, the attribute information of the object to be recommended, and the interaction information between the user and the object to be recommended; the first training data is used to perform feature alignment training on the pre-trained language model and the click prediction model; after the click prediction model is trained through feature alignment, the second training data is used to perform object recommendation training on the click prediction model; the click prediction model after object recommendation training is used to recommend the target object to the target user. The above-mentioned technical means can be used to solve the problem in the prior art that the poor ability of the click prediction model to mine semantic features leads to low recommendation accuracy, thereby improving the ability of the click prediction model to mine semantic features and improving recommendation accuracy.

[0037] In some embodiments, the alignment training module 302 is further configured such that the first training data includes attribute information of multiple users; the attribute information of each user is input into a pre-trained language model, and the user semantic features of each user are output; the attribute information of each user is input into a click prediction model, and the user embedding features of each user are output; the target loss function is used to calculate the target loss between the user semantic features and the user embedding features of each user; and the model parameters of the pre-trained language model and the click prediction model are optimized according to the target loss corresponding to each user.

[0038] The pre-trained language model and click prediction model used in the embodiments of the present application are both the main parts of the model (the parts for feature processing and extraction). The pre-trained language model and the click prediction model need to be added with a fully connected layer for predicting whether to recommend before they can be used.

[0039] In some embodiments, the alignment training module 302 is further configured to calculate the target loss between the user semantic features and the user embedded features of each user using a contrast loss function; or to calculate the target loss between the user semantic features and the user embedded features of each user using a mean square error loss function.

[0040] The target loss may be a contrast loss function and a mean square error loss function, etc. Both the contrast loss function and the mean square error loss function are existing functions and will not be described in detail here.

[0041] In some embodiments, the alignment training module 302 is further configured to calculate the contrast loss between the user semantic features and the user embedded features of each user using a contrast loss function; calculate the mean square error loss between the user semantic features and the user embedded features of each user using a mean square error loss function; and weightedly sum the contrast loss and mean square error loss corresponding to each user to obtain the target loss corresponding to each user.

[0042] In order to further improve the effect of model training, the contrast loss and mean square error loss corresponding to each user can be weighted and summed according to the preset weights as the target loss corresponding to each user.

[0043] In some embodiments, the alignment training module 302 is further configured such that the first training data includes attribute information of multiple objects to be recommended; the attribute information of each object to be recommended is input into a pre-trained language model, and the object semantic features of each object to be recommended are output; the attribute information of each object to be recommended is input into a click prediction model, and the object embedding features of each object to be recommended are output; the target loss function is used to calculate the target loss between the object semantic features and the object embedding features of each object to be recommended; and the model parameters of the pre-trained language model and the click prediction model are optimized according to the target loss corresponding to each object to be recommended.

[0044] In some embodiments, the alignment training module 302 is further configured to calculate the target loss between the object semantic features and the object embedding features of each object using a contrast loss function; or to calculate the target loss between the object semantic features and the object embedding features of each object using a mean square error loss function.

[0045] In some embodiments, the alignment training module 302 is further configured to calculate the contrast loss between the object semantic features and the object embedding features of each object using a contrast loss function; calculate the mean square error loss between the object semantic features and the object embedding features of each object using a mean square error loss function; and perform weighted summation of the contrast loss and mean square error loss corresponding to each object to obtain the target loss corresponding to each object.

[0046] In some embodiments, the recommendation training module 303 is further configured to connect a fully connected network after the click prediction model; input the user's attribute information, the attribute information of the object to be recommended, and the interaction information between the user and the object to be recommended into the click prediction model respectively, and output the user's embedded features, the embedded features of the object to be recommended, and the embedded features of the interaction between the user and the object to be recommended; input the user's embedded features, the embedded features of the object to be recommended, and the embedded features of the interaction between the user and the object to be recommended into the fully connected network, and output the judgment result of whether to recommend the object to be recommended to the user; use the cross entropy loss function to calculate the prediction loss between the judgment result and the label of the second training data; optimize the model parameters of the click prediction model and the fully connected network based on the prediction loss.

[0047] A user and an object that interacts with the user are taken as a group. The user's attribute information, the object's attribute information, and the interaction information between the user and the object are processed by the click prediction model and the fully connected network to obtain the judgment result of whether to recommend the object to the user. The cross entropy loss function is used to calculate the prediction loss between the judgment result and the label of whether to recommend the object to the user.

[0048] In some embodiments, the recommendation training module 303 is also configured to input the attribute information of the target user, the attribute information of the target object, and the interaction information between the target user and the target object into the click prediction model respectively, and output the embedded features of the target user, the embedded features of the target object, and the embedded features of the interaction between the target user and the target object; input the embedded features of the target user, the embedded features of the target object, and the embedded features of the interaction between the target user and the target object into the fully connected network, and output the judgment result of whether to recommend the target object to the target user.

[0049] In some embodiments, the alignment training module 302 is further configured to input the attribute information of each user into the pre-trained language model, and output the user semantic features of each user; input the attribute information of each user into the click prediction model, and output the user embedding features of each user; use the target loss function to calculate the target loss between the user semantic features and the user embedding features of each user; input the attribute information of each object to be recommended into the pre-trained language model, and output the object semantic features of each object to be recommended; input the attribute information of each object to be recommended into the click prediction model, and output the object embedding features of each object to be recommended; use the target loss function to calculate the target loss between the object semantic features and the object embedding features of each object to be recommended; optimize the model parameters of the pre-trained language model and the click prediction model according to the target loss corresponding to each user and the target loss corresponding to each object to be recommended.

[0050] The embodiment of the present application is the reasoning stage of the student model. Prior to the embodiment of the present application, the reasoning stage and the training stage of the network correspond to each other, and the reasoning stage will not be explained in detail here.

[0051] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0052] Figure 4 Schematic diagram of an electronic device 4 provided in an embodiment of the present application. Figure 4As shown, the electronic device 4 of this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 401 executes the computer program 403, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0053] The electronic device 4 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 4 may include, but is not limited to, a processor 401 and a memory 402. Those skilled in the art will appreciate that Figure 4 The electronic device 4 is merely an example and does not limit the electronic device 4 , and may include more or less components than those shown in the figure, or different components.

[0054] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0055] The memory 402 may be an internal storage unit of the electronic device 4, for example, a hard disk or memory of the electronic device 4. The memory 402 may also be an external storage device of the electronic device 4, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. The memory 402 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device.

[0056] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0057] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0058] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. An object recommendation method, characterized in that: include: Acquire first training data and second training data, wherein the first training data includes attribute information of the user or attribute information of the object to be recommended, and the second training data includes attribute information of the user, attribute information of the object to be recommended, and interaction information between the user and the object to be recommended; Using the first training data to perform feature alignment training on a pre-trained language model and a click prediction model; After the click prediction model passes the feature alignment training, performing object recommendation training on the click prediction model using the second training data; The click prediction model trained by the object recommendation is used to recommend a target object to a target user.

2. The method according to claim 1, characterized in that Using the first training data to perform feature alignment training on the pre-trained language model and the click prediction model includes: The first training data includes attribute information of multiple users; Inputting attribute information of each user into the pre-trained language model, and outputting user semantic features of each user; Inputting attribute information of each user into the click prediction model, and outputting user embedding features of each user; The target loss function is used to calculate the target loss between the user semantic features and the user embedding features of each user; The model parameters of the pre-trained language model and the click prediction model are optimized according to the target loss corresponding to each user.

3. The method according to claim 2, characterized in that The target loss function is used to calculate the target loss between the user semantic features and the user embedding features of each user, including: Calculate the target loss between the user semantic features and the user embedding features of each user using the contrastive loss function; or The mean square error loss function is used to calculate the target loss between the user semantic features and the user embedding features of each user.

4. The method according to claim 2, characterized in that: The target loss function is used to calculate the target loss between the user semantic features and the user embedding features of each user, including: The contrast loss function is used to calculate the contrast loss between the user semantic features and the user embedding features of each user; The mean square error loss function is used to calculate the mean square error loss between the user semantic features and the user embedding features of each user; The contrast loss and mean square error loss corresponding to each user are weighted summed to obtain the target loss corresponding to each user.

5. The method according to claim 1, characterized in that Using the first training data to perform feature alignment training on the pre-trained language model and the click prediction model includes: The first training data includes attribute information of multiple objects to be recommended; Inputting attribute information of each object to be recommended into the pre-trained language model, and outputting object semantic features of each object to be recommended; Inputting attribute information of each object to be recommended into the click prediction model, and outputting object embedding features of each object to be recommended; The target loss function is used to calculate the target loss between the object semantic features and the object embedding features of each object to be recommended; The model parameters of the pre-trained language model and the click prediction model are optimized according to the target loss corresponding to each object to be recommended.

6. The method according to claim 1, characterized in that After the click prediction model passes the feature alignment training, performing object recommendation training on the click prediction model using the second training data includes: A fully connected network is connected after the click prediction model; Inputting the user's attribute information, the attribute information of the object to be recommended, and the interaction information between the user and the object to be recommended into the click prediction model respectively, and outputting the user's embedded features, the embedded features of the object to be recommended, and the embedded features of the interaction between the user and the object to be recommended; Input the user's embedded features, the embedded features of the object to be recommended, and the embedded features of the interaction between the user and the object to be recommended into the fully connected network, and output a judgment result on whether to recommend the object to be recommended to the user; Calculating the prediction loss between the judgment result and the label of the second training data using a cross entropy loss function; The model parameters of the click prediction model and the fully connected network are optimized according to the prediction loss.

7. The method according to claim 6, characterized in that Recommending a target object to a target user by using the click prediction model trained by the object recommendation includes: Inputting the attribute information of the target user, the attribute information of the target object, and the interaction information between the target user and the target object into the click prediction model respectively, and outputting the embedded features of the target user, the embedded features of the target object, and the embedded features of the interaction between the target user and the target object; The embedded features of the target user, the embedded features of the target object, and the embedded features of the interaction between the target user and the target object are input into a fully connected network, and a judgment result of whether to recommend the target object to the target user is output.

8. An object recommendation device, characterized in that: include: an acquisition module, configured to acquire first training data and second training data, wherein the first training data includes attribute information of the user or attribute information of the object to be recommended, and the second training data includes attribute information of the user, attribute information of the object to be recommended, and interaction information between the user and the object to be recommended; an alignment training module, configured to perform feature alignment training on a pre-trained language model and a click prediction model using the first training data; a recommendation training module, configured to perform object recommendation training on the click prediction model using the second training data after the click prediction model passes the feature alignment training; The recommendation module is configured to recommend a target object to a target user by using the click prediction model trained by the object recommendation.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images