Training method of data processing model and data processing method and device

Abstract

The invention provides a training method of a data processing model and a data processing method and device, and relates to the technical field of data processing, in particular to a large model technology and a content recommendation technology. According to the implementation scheme, a training sample set is determined, wherein each training sample in the training sample set comprises spliced sample content and a comment text for the sample content; determining at least one matching sample matched with the training sample; coding the training sample by using a data processing model with a current parameter to obtain a representation vector of the training sample; encoding the at least one matching sample by using a data processing model with a current parameter to obtain a representation vector of the matching sample; and adjusting the current parameter of the data processing model so as to minimize the loss between the characterization vector of the training sample and the characterization vector of the matching sample.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, in particular to large model technology and content recommendation technology, and specifically to a data processing model training method, data processing method, device, electronic device, computer-readable storage medium and computer program product. Background Art

[0002] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0003] The construction of content representation vector aims to convert the content to be recommended into a vector that can be used in the recommendation algorithm, which is an important link in the recommendation system.

[0004] The methods described in this section are not necessarily methods that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any method described in this section is considered to be prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized in any prior art. Summary of the invention

[0005] The present disclosure provides a training method for a data processing model, a data processing method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

[0006] According to one aspect of the present disclosure, a method for training a data processing model is provided, comprising: determining a training sample set, wherein each training sample in the training sample set comprises concatenated sample content and comment text for the sample content; determining at least one matching sample that matches the training sample; encoding the training sample using a data processing model with current parameters to obtain a representation vector of the training sample; encoding the at least one matching sample using a data processing model with current parameters to obtain a representation vector of the matching sample; and adjusting the current parameters of the data processing model to minimize the loss between the representation vector of the training sample and the representation vector of the matching sample.

[0007] According to another aspect of the present disclosure, a data processing method is provided, including: determining content to be processed and comment text for the content to be processed; concatenating the content to be processed and the comment text to obtain content to be encoded; and encoding the content to be encoded using a data processing model to obtain a representation vector for the content to be processed, wherein the data processing model is trained using the training method as described above.

[0008] According to another aspect of the present disclosure, a training device for a data processing model is provided, comprising: a sample determination unit, configured to determine a training sample set, wherein each training sample in the training sample set comprises a concatenated sample content and a comment text for the sample content; a matching sample determination unit, configured to determine at least one matching sample that matches the training sample; an encoding unit, configured to encode the training sample using a data processing model with current parameters to obtain a representation vector of the training sample, and to encode the at least one matching sample using the data processing model with current parameters to obtain a representation vector of the matching sample; and a parameter adjustment unit, configured to adjust the current parameters of the data processing model to minimize the loss between the representation vector of the training sample and the representation vector of the matching sample.

[0009] According to another aspect of the present disclosure, a data processing device is provided, including: an input unit, configured to determine content to be processed and a comment text for the content to be processed; a splicing unit, configured to splice the content to be processed and the comment text to obtain content to be encoded; and an encoding unit, configured to encode the content to be encoded using a data processing model to obtain a representation vector for the content to be processed, wherein the data processing model is trained using the training method described above.

[0010] According to another aspect of the present disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method according to an embodiment of the present disclosure.

[0011] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is further provided, where the computer instructions are used to cause the computer to execute the method according to the embodiment of the present disclosure.

[0012] According to another aspect of the present disclosure, a computer program product is further provided, including a computer program, wherein the computer program implements the method according to the embodiment of the present disclosure when being executed by a processor.

[0013] According to another aspect of the present disclosure, a content recommendation system is also provided, including: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to an embodiment of the present disclosure.

[0014] According to one or more embodiments of the present disclosure, the model can encode both the content itself and the comment text on the content when generating a representation vector for the content, so that the comment text on the content can be used as supplementary information when generating the representation vector for the content, thereby improving the accuracy and comprehensiveness of the content representation vector.

[0015] 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 disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0017] Figure 1 A schematic diagram showing an exemplary system in which the various methods described herein may be implemented according to an embodiment of the present disclosure;

[0018] Figure 2 An exemplary process of a data processing model training method according to an embodiment of the present disclosure is shown;

[0019] Figure 3 An exemplary flow chart of a data processing method according to an embodiment of the present disclosure is shown;

[0020] Figure 4 The following illustrates a usage scenario of a content recommendation method according to an embodiment of the present disclosure;

[0021] Figure 5 An exemplary block diagram of a training device for a data processing model according to an embodiment of the present disclosure is shown;

[0022] Figure 6 An exemplary block diagram of a data processing device according to an embodiment of the present disclosure is shown;

[0023] Figure 7 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0024] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0025] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, temporal relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0026] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0027] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0028] Figure 1 FIG. 1 is a schematic diagram of an exemplary system 100 in which various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. Figure 1 , the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

[0029] In an embodiment of the present disclosure, the server 120 may run one or more services or software applications that enable execution of the method according to an embodiment of the present disclosure.

[0030] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtualized environments and virtualized environments. In some embodiments, these services may be provided as web-based services or cloud services, such as provided to users of client devices 101, 102, 103, 104, 105, and / or 106 under a software as a service (SaaS) model.

[0031] exist Figure 1 In the configuration shown, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may in turn utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

[0032] The user may use client devices 101, 102, 103, 104, 105, and / or 106 to obtain user input and provide output information to the user. The client device may provide an interface that enables a user of the client device to interact with the client device. The client device may also output information to the user via the interface. Figure 1 Only six client devices are depicted, but one skilled in the art will appreciate that the present disclosure may support any number of client devices.

[0033] Client devices 101, 102, 103, 104, 105 and / or 106 may include various types of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, game systems, thin clients, various messaging devices, sensors or other sensing devices, etc. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as GOOGLE Chrome OS); or include various mobile operating systems, such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular phones, smart phones, tablet computers, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Game systems may include various handheld game devices, Internet-enabled game devices, etc. Client devices are capable of executing various different applications, such as various Internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and may use various communication protocols.

[0034] The network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP / IP, SNA, IPX, etc. By way of example only, the one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0035] Server 120 may include one or more general purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0036] The computing units in the server 120 may run one or more operating systems including any of the above operating systems and any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0037] In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and / or 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and / or 106.

[0038] In some embodiments, the server 120 may be a server of a distributed system, or a server combined with a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in a cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0039] The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The databases 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The databases 130 may be of different types. In some embodiments, the databases used by the server 120 may be, for example, relational databases. One or more of these databases may store, update, and retrieve data to and from the databases in response to commands.

[0040] In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the applications may be different types of databases, such as a key-value store, an object store, or a conventional store backed by a file system.

[0041] Figure 1The system 100 may be configured and operated in various ways to enable the application of various methods and apparatuses described in the present disclosure.

[0042] In the content recommendation system, the construction of content representation vectors aims to convert items (such as articles, videos, etc.) into vectors that can be used in recommendation algorithms. The construction of content representation vectors is a crucial link in the recommendation system. The construction result of content representation vectors mainly depends on the text description of the content itself, image information, or the historical interaction between users and content.

[0043] However, these traditional representation methods largely ignore the importance of interactive comments, a key information. In fact, user comments not only instantly reflect the user's intuitive feedback and initial impression of the pushed content, but also reveal the depth and breadth of the user's interests. User comments are by no means a simple pile of words. They contain users' deep understanding and multi-dimensional views of the pushed content. These views can go beyond the expressive information of the content itself and further reflect multiple levels such as personal preferences, emotional tendencies, values ​​and even social and cultural backgrounds. Therefore, user comments are a valuable and effective supplement to the content representation vector. The information in user comments can provide a richer, three-dimensional description of the content vector that is closer to the user's real needs and emotional experience.

[0044] Therefore, by incorporating user comments into the consideration of content representation, not only can the personalization of the recommendation system be improved, making it more accurately match users' personalized needs and interests, but it can also enhance users' identification and satisfaction with the recommended content, thereby building a more positive and healthy interactive relationship between users and the recommendation system.

[0045] Although user comments can serve as an effective supplement in the representation of content vectors, the unstructured, diverse and complex nature of comment information makes it difficult to effectively extract, understand and represent key information and user sentiment in comments, which in turn affects the accuracy and effectiveness of content representation vectors.

[0046] In view of this, the present disclosure proposes a new model training method and data processing method for generating content representation vectors. The method according to the embodiment of the present disclosure aims to comprehensively consider the content's own text information (such as title, abstract, text, etc.), the user's content interaction behavior (such as clicks, browsing time, likes, sharing, etc.), and user comments in the content comment area, and deeply mine and fuse this information by utilizing the powerful capabilities of pre-trained data processing models such as large language models, so as to generate more accurate and comprehensive content representation vectors. This fusion strategy not only enhances the expressive power of content representation, but also helps the recommendation system to understand user preferences more accurately, thereby improving the personalization and relevance of recommendations, optimizing user experience, and ultimately achieving a significant improvement in recommendation effects.

[0047] Figure 2 An exemplary process of a data processing model training method according to an embodiment of the present disclosure is shown.

[0048] like Figure 2 As shown, in step S202, a training sample set is determined, wherein each training sample in the training sample set includes concatenated sample content and comment text for the sample content.

[0049] In step S204, at least one matching sample that matches the training sample is determined.

[0050] In step S206, the training sample is encoded using the data processing model with the current parameters to obtain a characterization vector of the training sample. The at least one matching sample is encoded using the data processing model with the current parameters to obtain a characterization vector of the matching sample.

[0051] In step S208, the current parameters of the data processing model are adjusted to minimize the loss between the characterization vector of the training sample and the characterization vector of the matching sample.

[0052] By utilizing the training method of the data processing model provided by the embodiments of the present disclosure, the model can encode both the content itself and the comment text for the content when generating a representation vector for the content, thereby using the comment text for the content as supplementary information when generating the representation vector for the content, thereby improving the accuracy and comprehensiveness of the content representation vector.

[0053] The principles of the present disclosure will be described in detail below.

[0054] In step S202, a training sample set is determined, wherein each training sample in the training sample set includes concatenated sample content and comment text for the sample content.

[0055] The sample content may include any combination of text, image, audio, video, etc. The specific form of the sample content is not limited in the present disclosure.

[0056] In step S204, at least one matching sample that matches the training sample is determined.

[0057] In some embodiments, step S204 may include: in response to determining that the target user of the first sample and the target user of the training sample are matched, determining the first sample as a matching sample of the training sample, wherein the target user of the first sample is determined based on a user interaction associated with the first sample, and the target user of the training sample is determined based on a user interaction associated with the training sample.

[0058] The target users mentioned here are matched when the same target users between the two samples are higher than a predetermined threshold, such as a predetermined user quantity threshold or a user ratio threshold. In the above process, there is no need to consider whether the actual contents of the two training samples are the same or similar. When two sample contents have the same or similar target users, it can be considered that the two sample contents are substantially similar in the sense of content recommendation. By determining samples with matching target users as matching samples during the training process, the model can be trained so that the content representation vectors generated by the model have similar representations for content with similar user interaction situations.

[0059] In the example, the user interaction may include at least one of the following: browsing, viewing time, collection, comment, sharing, purchase, rating, etc. Those skilled in the art may determine the specific content of the user interaction according to the actual application scenario. It is understandable that other user interaction modes may also be specified according to actual conditions without departing from the principles of the present disclosure.

[0060] In some embodiments, users who have user interactions with the sample content may be determined as target users. In other embodiments, users who have interacted with the sample content may be further screened to determine users who have a high degree of interest in the sample content as target users, thereby improving the accuracy of determining matching samples based on user interactions.

[0061] In an example, the interaction history of at least one candidate user who interacts with the training sample can be counted to obtain the interest level of each candidate user for the training sample. Then, a target user can be determined from the at least one candidate user, wherein the target user has an interest level higher than a predetermined interest threshold.

[0062] For example, if the user interaction is the viewing time, the viewing time of the user can be used as the user's interest level in the sample content, and the users of the sample content are sorted in descending order according to the viewing time. An exemplary interest threshold can be a viewing time threshold, or a sorting order threshold for all users in the sample content. For example, the viewing time threshold can be determined as 10 minutes. The sorting order threshold can be determined as the top 20%.

[0063] When user interactions include multiple different types, different types of user interactions can be scored in a normalized manner based on a predetermined rule, and the user's interest level in the sample content can be determined by weighted combination of the normalized scores of different types of user interactions. For example, user interactions can include browsing times, viewing time, and sharing. For browsing times, browsing times less than 5 times can be determined as low frequency, and the normalized score is 1. The browsing times of not less than 5 times and less than 10 times are determined as medium frequency, and the normalized score is 3. The browsing times of not less than 10 times are determined as high frequency, and the normalized score is 5. For viewing time, the normalized score of viewing time within 10 minutes can be determined as 1, the normalized score of viewing time from 10 to 30 minutes can be determined as 3, and the normalized score of viewing time greater than 30 minutes can be determined as 5. For sharing, the normalized score of sharing behavior can be determined as 5, and the normalized score of non-sharing behavior can be determined as 0. The normalized scores of the above different user interaction behaviors can be weighted summed as the user's interest score in the sample content. Then, users of the sample content may be sorted according to the interest scores, and users whose interest scores are higher than a predetermined score threshold or users whose ranking among all users is higher than a sorting order threshold may be determined as target users of the training sample.

[0064] It is understandable that the above rule for determining the user's interest score is only an exemplary description. Those skilled in the art can set any appropriate rule for determining the interest level according to user interaction according to actual conditions.

[0065] In some embodiments, step S204 may include: determining text similarity between text information of the training sample and text information of the second sample. In response to the text similarity being higher than a predetermined similarity threshold, determining the second sample as a matching sample of the training sample. Matching samples determined by text similarity can enable the content representation vector generated by the model to have similar representations for semantically similar content.

[0066] For sample content in text form, its text information may be the text of the sample content itself. For sample content in the form of images, videos, audios, etc., its text information may be text obtained from images through text recognition, text recognized from audio through speech recognition, text in subtitle information in videos, etc.

[0067] In some examples, the second sample may be the content of other training samples. The text whose similarity to the text information of the training sample is higher than a predetermined similarity threshold may be determined as the second text by any suitable semantic similarity determination method. In other examples, the second sample may be generated by scrambling the text information of the training sample. In the example, part of the text in the text content may be replaced with text in other content. For example, the text information of the training text may be separated by sentences, and a certain proportion of sentences may be randomly selected to be replaced with sentences in other content. The above proportion may be determined according to a predetermined similarity threshold. For example, 70% of the sentences may be randomly selected to be replaced with sentences in other content. The proportion of sentences selected for replacement during text replacement may be between 50% and 90%, more preferably between 60% and 80%. Too high a replacement ratio may cause the text obtained after replacement to completely lose similarity, while too low a replacement ratio may cause the result output by the data processing model to be overfitted.

[0068] In some embodiments, the first sample or the combination of the first sample and the second sample can be used as a matching sample for the training sample. In the process of constructing the content representation vector, in addition to satisfying that the representation vectors of matching samples with the same or highly similar content should be as close as possible to reflect their semantic equivalence or high correlation, it is also necessary to consider the importance of user behavior patterns and interaction habits in recommendation. The representation vectors of content with similar user consumption can also maintain a high similarity, thereby generating a representation vector that can reflect the similarity of user interaction habits.

[0069] In the example, the number of the second samples may be less than the number of the first samples. In the example, the proportion of the first samples may be 70%, and the proportion of the second samples may be 30%. Those skilled in the art may adjust the proportion of the first samples and the second samples according to actual conditions. By adjusting the proportion of the first samples and the second samples, it is possible to control whether the model considers more the similarity of the target users between the contents or the semantic similarity between the contents when generating the content representation vector.

[0070] In step S206, the training sample is encoded using the data processing model with current parameters to obtain a characterization vector of the training sample. Step S206 also includes encoding at least one matching sample using the data processing model with current parameters to obtain a characterization vector of the matching sample.

[0071] As mentioned above, the training goal of the data processing model is to make the representation vector of the training sample and the representation vector of its matching sample as similar as possible.

[0072] The data processing model used in the method of the embodiment of the present disclosure may be a large model, such as a large language model LLM, or a large visual model CV, etc. Without departing from the principles of the present disclosure, any suitable data processing model may be used to implement the method provided by the present disclosure.

[0073] In some embodiments, when the content of the training sample is text, the text information of the training sample can be encoded using a data processing model with current parameters, wherein the text information of the training sample includes the spliced ​​content text and comment text. Using the above method, the content of the comment text can be used to effectively supplement the content representation vector. In some implementations, the content text can include information such as the title, category, point of interest, and summary of the content. Similarly, the data processing model can be used to encode the text information of the matching sample, wherein the text information of the matching sample includes the content text corresponding to the matching sample and the result of the splicing of the comment text for the content text of the matching sample.

[0074] In other embodiments, when the content of the training sample contains information other than text, such as images and audio, the vector representation of the multimodal information of the content and the embedded vector of the comment text can be spliced, and the result obtained by splicing the information of the sample content and the comment text can be encoded using a data processing model with current parameters to obtain a representation vector of the training sample. The multimodal information in the sample content can be vectorized using various suitable methods, and the specific method of vectorization is not limited here.

[0075] In some implementations, the text length of the comment text may be less than or equal to the text length of the content text. As mentioned above, adding the information of the comment text during encoding can supplement the information contained in the content representation vector, but since there are certain differences between the content of the comment text and the sample content, it is necessary to control the length of the comment text to avoid the final content representation vector being unable to correctly express the information of the content itself.

[0076] In the example, the comment text for the sample content can be obtained in the following manner: for each comment information among multiple comment information for the sample content, the comment quality score of the comment information is determined; according to the comment quality scores from high to low, at least one comment information with the highest score is determined as the comment text, wherein the sum of the text lengths of the at least one comment information with the highest score determined is less than or equal to the text length of the content text.

[0077] Introducing content vector representation in user comments requires cleaning of user comments. First of all, even for the same content, the quality of each comment varies, which requires the establishment of an effective screening mechanism to eliminate irrelevant, repetitive or low-quality comments from the massive comments, ensuring that the comments that are retained are effective comments with reference value and can truly reflect user needs and opinions. Secondly, different content will attract different numbers of comments due to differences in popularity, topic nature and other factors. Therefore, when obtaining comment text, it is necessary to reasonably set the number of comments to be added based on the amount of information in the content itself, and avoid comment information overload on the basis of ensuring that the comment information effectively supplements the content representation.

[0078] For example, the comment quality score can be first obtained by linearly adding the number of likes, dislikes, and replies based on the posterior indicators of the comment, and the comments with high scores are high-quality comments. Then, all the comments under the content can be sorted in descending order by score, and the comments with the highest scores can be obtained in order from high to low scores, until the ratio of the total number of words in the comment to the number of words in the content text itself is close to 1. In other implementations, one or more comments with the highest scores can be selected from all the comments in order according to the comment quality scores without sorting, until the ratio of the total number of words in the selected comments to the number of words in the content text itself is close to 1.

[0079] In step S208, the current parameters of the data processing model are adjusted to minimize the loss between the characterization vector of the training sample and the characterization vector of the matching sample. The above method can minimize the difference between the characterization vectors of the two matching samples.

[0080] In some embodiments, the loss between the representation vector of the training sample and the representation vector of the matching sample minimizes the similarity between the negative samples while maximizing the similarity between the matching samples. Using the above method, similar data samples can be brought closer and dissimilar data samples can be pushed away. In the example, the above loss can be the InfoNCE loss, and the mathematical expression is:

[0081]

[0082] Among them, z i and z j is a pair of matching positive samples, N is the number of samples, sim is the similarity function, and γ is a predetermined parameter used to control the convergence speed. i and z k is a pair of mismatched negative samples. In the embodiment of the present disclosure, for the training sample z i For example, any other training samples that are not its matching samples can be randomly selected in the training data set as negative samples.

[0083] The method provided by the embodiment of the present disclosure provides a content representation method that integrates content information, user behavior, and user comments using a data processing model. The content representation vector generated by this method is closer to user preferences and performs well in stimulating user interaction.

[0084] Figure 3 An exemplary flow chart of a data processing method according to an embodiment of the present disclosure is shown.

[0085] like Figure 3 As shown, in step S302, the content to be processed and the comment text for the content to be processed may be determined.

[0086] In step S304, the content to be processed and the comment text may be concatenated to obtain the content to be encoded.

[0087] In step S306, the data processing model may be used to encode the content to be encoded to obtain a representation vector for the content to be processed. Figure 2 The training method described is obtained by training.

[0088] In some embodiments, the data processing method 300 may further include: generating recommended content for the user based on the similarity between the representation vector of the content to be processed and the user's interest representation vector. The content representation vector obtained using the method of the embodiment of the present disclosure can be used for content recommendation. In the example, the user's interest representation vector may include the content representation vector of the content that the user has consumed. In the content recommendation method, the existing content can be input into the trained model one by one, and their respective content representation vectors can be generated. Next, the similarity between these content representation vectors and the content representation vectors of the content that the user has consumed is calculated, and a similarity score with the content that the user has consumed is generated for each content. Finally, based on these similarity scores, content with higher similarity scores can be recommended to the user, that is, content that is most similar to the content that the user has consumed or most in line with the user's interests.

[0089] In some embodiments, similar to the method of screening comment texts in the training method, the text length of the comment text is less than or equal to the text length of the content text of the content to be processed. The comment text for the content text can be obtained in the following manner: for each comment information in the multiple comment information for the content to be processed, determine the comment quality score of the comment information; sort the multiple comment information based on the comment quality score; determine at least one comment information with the highest ranking among the sorted multiple comment information as the comment text, wherein the sum of the text lengths of the at least one comment information with the highest ranking is less than or equal to the text length of the content text.

[0090] Figure 4The following illustrates a usage scenario of the content recommendation method according to an embodiment of the present disclosure.

[0091] like Figure 4 As shown, in a recommendation scenario 401 with comments such as news information and social networking, user interaction content 402 including comment content can be obtained. Figure 2 , Figure 3 The steps in the described method can screen out high-quality comments 406 and target users 407 for each content based on the user interaction content 402, and construct a training sample set 403 for adjusting the model. The training sample set 403 can be used to fine-tune the large language model, so that the fine-tuned large language model 404 can consider the comment content as a supplement when generating the content representation vector 405, and can identify the similarity between contents with similar target users. The content representation vector 405 generated by the fine-tuned large model can be used to recommend content in the recommendation scenario 401.

[0092] Figure 5 An exemplary block diagram of a training device for a data processing model according to an embodiment of the present disclosure is shown. Figure 5 The described training device realizes the combination Figure 2 Describe the training method.

[0093] like Figure 5 As shown, the training device 500 may include a sample determination unit 510 , a matching sample determination unit 520 , an encoding unit 530 , and a parameter adjustment unit 540 .

[0094] The sample determination unit 510 may be configured to determine a training sample set, wherein each training sample in the training sample set includes concatenated sample content and comment text for the sample content.

[0095] The matching sample determination unit 520 may be configured to determine at least one matching sample that matches the training sample.

[0096] The encoding unit 530 may be configured to encode the training sample using the data processing model with current parameters to obtain a characterization vector of the training sample, and to encode at least one matching sample using the data processing model with current parameters to obtain a characterization vector of the matching sample.

[0097] The parameter adjustment unit 540 may be configured to adjust current parameters of the data processing model to minimize the loss between the representation vector of the training sample and the representation vector of the matching sample.

[0098] In some embodiments, encoding the training sample using the data processing model with current parameters includes: encoding the text information of the training sample using the data processing model with current parameters, wherein the text information of the training sample includes concatenated content text and comment text.

[0099] In some embodiments, the text length of the comment text is less than or equal to the text length of the content text.

[0100] In some embodiments, the comment text is obtained in the following manner: for each comment information among multiple comment information on the sample content, determining the comment quality score of the comment information; sorting the multiple comment information based on the comment quality score; determining at least one comment information with the highest ranking among the sorted multiple comment information as the comment text, wherein the sum of the text lengths of the at least one comment information with the highest ranking is less than or equal to the text length of the content text.

[0101] In some embodiments, determining at least one matching sample that matches the training sample includes: in response to determining that a target user of the first sample and a target user of the training sample are matched, determining the first sample as a matching sample of the training sample, wherein the target user of the first sample is determined based on a user interaction associated with the first sample, and the target user of the training sample is determined based on a user interaction associated with the training sample.

[0102] In some embodiments, user interaction includes at least one of the following: browsing, viewing time, collection, commenting, sharing, purchasing, and rating.

[0103] In some embodiments, the target user of the training sample is determined by the following operations: statistics are collected on the interaction history of at least one candidate user who has performed user interaction with the training sample to obtain the interest level of each candidate user in the training sample; and a target user is determined from at least one candidate user, wherein the target user has an interest level higher than a predetermined interest threshold.

[0104] In some embodiments, determining at least one matching sample that matches the training sample further includes: determining text similarity between text information of the training sample and text information of a second sample, and in response to the text similarity being higher than a predetermined similarity threshold, determining the second sample as a matching sample of the training sample.

[0105] In some embodiments, the second sample is generated by scrambling text information of the training sample.

[0106] In some embodiments, the number of the second samples is less than the number of the first samples.

[0107] In some embodiments, the loss between the representation vectors of the training samples and the representation vectors of the matching samples minimizes the similarity between the negative samples while maximizing the similarity between the matching samples.

[0108] In some embodiments, the loss is an InfoNCE loss.

[0109] In some embodiments, the data processing model is a large language model.

[0110] It should be understood that Figure 5 The various modules or units of the apparatus 500 shown in FIG. 5 can be used in conjunction with the reference Figure 2 The steps in the method 200 described above correspond to each other. Therefore, the operations, features and advantages described above for the method 200 are also applicable to the device 500 and the modules and units included therein. For the sake of brevity, some operations, features and advantages are not repeated here.

[0111] Figure 6 An exemplary block diagram of a data processing device according to an embodiment of the present disclosure is shown. Figure 6 The data processing device shown in the embodiment implements the combination Figure 3 Describe the data processing methods.

[0112] like Figure 6 As shown, the data processing device 600 may include an input unit 610 , a splicing unit 620 , and an encoding unit 630 .

[0113] The input unit 610 may be configured to determine content to be processed and comment text for the content to be processed.

[0114] The splicing unit 620 may be configured to splice the content to be processed and the comment text to obtain the content to be encoded.

[0115] The encoding unit 630 may be configured to encode the content to be encoded using a data processing model to obtain a representation vector for the content to be processed, wherein the data processing model is a combination of Figure 2 The training method described is obtained by training.

[0116] In some embodiments, the data processing device 600 further includes a recommendation unit configured to generate recommended content for the user according to the similarity between the representation vector of the content to be processed and the user's interest representation vector.

[0117] In some embodiments, the text length of the comment text is less than or equal to the text length of the content text of the content to be processed.

[0118] In some embodiments, the comment text is obtained in the following manner: for each comment information among multiple comment information for the content to be processed, determining the comment quality score of the comment information; sorting the multiple comment information based on the comment quality score; determining at least one comment information with the highest ranking among the sorted multiple comment information as the comment text, wherein the sum of the text lengths of at least one comment information with the highest ranking is less than or equal to the text length of the content text.

[0119] It should be understood that Figure 6 The modules or units of the apparatus 600 shown in FIG. 6 can be used in conjunction with the reference Figure 3 The steps in the method 300 described above correspond to each other. Therefore, the operations, features and advantages described above for the method 300 are also applicable to the device 600 and the modules and units included therein. For the sake of brevity, some operations, features and advantages are not repeated here.

[0120] Although specific functionality is discussed above with reference to specific modules, it should be noted that the functionality of the various units discussed herein may be separated into multiple units, and / or at least some functionality of multiple units may be combined into a single unit.

[0121] It should also be understood that various techniques may be described herein in the general context of software hardware elements or program modules. Figure 5 , Figure 6 The various units described can be implemented in hardware or in hardware in combination with software and / or firmware. For example, these units can be implemented as computer program codes / instructions, which are configured to be executed in one or more processors and stored in a computer-readable storage medium. Alternatively, these units can be implemented as hardware logic / circuits. For example, in some embodiments, one or more of units 510 to 540, units 610 to 630 can be implemented together in a system on chip (System on Chip, SoC). SoC may include an integrated circuit chip (which includes a processor (e.g., a central processing unit (CPU), a microcontroller, a microprocessor, a digital signal processor (DSP), etc.), a memory, one or more communication interfaces, and / or one or more components in other circuits), and may optionally execute the received program code and / or include embedded firmware to perform functions.

[0122] According to another aspect of the present disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method according to an embodiment of the present disclosure.

[0123] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is further provided, where the computer instructions are used to cause the computer to execute the method according to the embodiment of the present disclosure.

[0124] According to another aspect of the present disclosure, a computer program product is further provided, including a computer program, wherein the computer program implements the method according to the embodiment of the present disclosure when being executed by a processor.

[0125] According to another aspect of the present disclosure, a content recommendation system is also provided, including: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to an embodiment of the present disclosure.

[0126] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0127] According to an embodiment of the present disclosure, an electronic device, a readable storage medium and a computer program product are also provided.

[0128] refer to Figure 7 , a block diagram of an electronic device 700 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, 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 processing, 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 disclosure described and / or required herein.

[0129] like Figure 7As shown, the electronic 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. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. 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.

[0130] Multiple components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, an output unit 707, a storage unit 708, and a communication unit 709. The input unit 706 can be any type of device that can input information to the electronic device 700. The input unit 706 can receive input digital or character information and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 707 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 708 can include but is not limited to a disk, an optical disk. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0131] The computing unit 701 may be a variety of general and / or special 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 running 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 methods 200 and 300. For example, in some embodiments, methods 200 and 300 may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic 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 methods 200 and 300 described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to execute the methods 200 and 300 in any other appropriate manner (eg, by means of firmware).

[0132] Various implementations of the systems and techniques described above 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), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including 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.

[0133] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0134] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may 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 may 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.

[0135] 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).

[0136] The systems and techniques described herein can be implemented in a computing system that includes backend 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 frontend components (e.g., a user computer with 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 backend components, middleware components, or frontend 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), the Internet, and a blockchain network.

[0137] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0138] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0139] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A method for training a data processing model, comprising: Determine a training sample set, wherein each training sample in the training sample set includes concatenated sample content and comment text for the sample content; Determining at least one matching sample that matches the training sample; Encoding the training sample using a data processing model with current parameters to obtain a representation vector of the training sample; Encoding the at least one matching sample using a data processing model with current parameters to obtain a representation vector of the matching sample; as well as The current parameters of the data processing model are adjusted to minimize the loss between the characterization vector of the training sample and the characterization vector of the matching sample.

2. The training method according to claim 1, wherein: The encoding of the training sample by using the data processing model with current parameters comprises: The text information of the training sample is encoded using a data processing model with current parameters, wherein the text information of the training sample includes the concatenated content text and the comment text.

3. The training method according to claim 2, wherein: The text length of the comment text is less than or equal to the text length of the content text.

4. The training method according to claim 3, wherein: The comment text is obtained in the following way: For each piece of review information among the plurality of review information for the sample content, determining a review quality score of the review information; At least one comment information with the highest score is determined from the multiple comment information according to the comment quality scores from high to low as the comment text, wherein the sum of the text lengths of the at least one comment information with the highest score is less than or equal to the text length of the content text.

5. The training method according to claim 2, wherein: The determining of at least one matching sample matching the training sample comprises: In response to determining that the target user of the first sample and the target user of the training sample are matched, determining the first sample as a matching sample of the training sample, The target user of the first sample is determined according to the user interaction associated with the first sample, and the target user of the training sample is determined according to the user interaction associated with the training sample.

6. The training method according to claim 5, wherein: The user interaction includes at least one of the following: browsing, viewing time, collection, comment, sharing, purchase, and rating.

7. The training method according to claim 5 or 6, wherein: The target users of the training samples are determined by the following operations: Collecting statistics on the interaction history of at least one candidate user who has performed user interaction with the training sample to obtain an interest level of each candidate user in the training sample; The target user is determined from the at least one candidate user, wherein the target user has an interest level higher than a predetermined interest threshold.

8. The training method according to claim 5, wherein: The determining of at least one matching sample matching the training sample further comprises: Determining text similarity between the text information of the training sample and the text information of the second sample; In response to the text similarity being higher than a predetermined similarity threshold, the second sample is determined as a matching sample of the training sample.

9. The training method according to claim 8, wherein: The second sample is generated by scrambling the text information of the training sample.

10. The training method according to claim 9, wherein: The number of the second samples is less than the number of the first samples.

11. The training method according to claim 1, wherein: The loss between the representation vector of the training sample and the representation vector of the matching sample minimizes the similarity between negative samples while maximizing the similarity between matching samples.

12. The training method according to claim 11, wherein: The loss is the InfoNCE loss.

13. The training method according to claim 1, wherein: The data processing model is a large language model.

14. A data processing method, comprising: Determining content to be processed and comment text for the content to be processed; splicing the content to be processed and the comment text to obtain the content to be encoded; as well as The content to be encoded is encoded using a data processing model to obtain a representation vector for the content to be processed, wherein the data processing model is trained using the training method according to any one of claims 1-13.

15. The data processing method according to claim 14, further comprising: Generate recommended content for the user according to the similarity between the representation vector of the content to be processed and the user's interest representation vector.

16. The data processing method according to claim 14, wherein: The text length of the comment text is less than or equal to the text length of the content text of the content to be processed.

17. The data processing method according to claim 16, wherein: The comment text is obtained in the following way: For each piece of comment information among the plurality of comment information for the content to be processed, determining a comment quality score of the comment information; At least one comment information with the highest score is determined from the multiple comment information according to the comment quality scores from high to low as the comment text, wherein the sum of the text lengths of the at least one comment information with the highest score is less than or equal to the text length of the content text.

18. A training device for a data processing model, comprising: A sample determination unit is configured to determine a training sample set, wherein each training sample in the training sample set includes a concatenated sample content and a comment text for the sample content; a matching sample determining unit, configured to determine at least one matching sample that matches the training sample; an encoding unit configured to encode the training sample using the data processing model with current parameters to obtain a representation vector of the training sample, and to encode the at least one matching sample using the data processing model with current parameters to obtain a representation vector of the matching sample; as well as A parameter adjustment unit is configured to adjust the current parameter of the data processing model so as to minimize the loss between the characterization vector of the training sample and the characterization vector of the matching sample.

19. The training device according to claim 18, wherein: The encoding of the training sample by using the data processing model with current parameters comprises: The text information of the training sample is encoded using a data processing model with current parameters, wherein the text information of the training sample includes the concatenated content text and the comment text.

20. The training device according to claim 19, wherein: The text length of the comment text is less than or equal to the text length of the content text.

21. The training device according to claim 20, wherein: The comment text is obtained in the following way: For each piece of review information among the plurality of review information for the sample content, determining a review quality score of the review information; At least one comment information with the highest score is determined from the multiple comment information according to the comment quality scores from high to low as the comment text, wherein the sum of the text lengths of the at least one comment information with the highest score is less than or equal to the text length of the content text.

22. The training device according to claim 21, wherein: The determining of at least one matching sample matching the training sample comprises: In response to determining that the target user of the first sample and the target user of the training sample are matched, determining the first sample as a matching sample of the training sample, The target user of the first sample is determined according to the user interaction associated with the first sample, and the target user of the training sample is determined according to the user interaction associated with the training sample.

23. The training device according to claim 22, wherein: The user interaction includes at least one of the following: browsing, viewing time, collection, comment, sharing, purchase, and rating.

24. A training device as claimed in claim 22 or 23, wherein: The target users of the training samples are determined by the following operations: Collecting statistics on the interaction history of at least one candidate user who has performed user interaction with the training sample to obtain an interest level of each candidate user in the training sample; The target user is determined from the at least one candidate user, wherein the target user has an interest level higher than a predetermined interest threshold.

25. The training device of claim 22, wherein: The determining of at least one matching sample matching the training sample further comprises: Determining the text similarity between the text information of the training sample and the text information of the second sample, In response to the text similarity being higher than a predetermined similarity threshold, the second sample is determined as a matching sample of the training sample.

26. The training device according to claim 25, wherein: The second sample is generated by scrambling the text information of the training sample.

27. The training device according to claim 26, wherein: The number of the second samples is less than the number of the first samples.

28. The training device of claim 18, wherein: The loss between the representation vector of the training sample and the representation vector of the matching sample minimizes the similarity between negative samples while maximizing the similarity between matching samples.

29. The training device according to claim 28, wherein: The loss is the InfoNCE loss.

30. The training device of claim 18, wherein: The data processing model is a large language model.

31. A data processing device, comprising: An input unit, configured to determine content to be processed and comment text for the content to be processed; A concatenation unit, configured to concatenate the content to be processed and the comment text to obtain content to be encoded; as well as An encoding unit is configured to encode the content to be encoded using a data processing model to obtain a representation vector for the content to be processed, wherein the data processing model is trained using the training method according to any one of claims 1-13.

32. The data processing apparatus according to claim 31, further comprising a recommendation unit configured to: Generate recommended content for the user according to the similarity between the representation vector of the content to be processed and the user's interest representation vector.

33. The data processing apparatus according to claim 31, wherein: The text length of the comment text is less than or equal to the text length of the content text of the content to be processed.

34. The data processing apparatus according to claim 33, wherein: The comment text is obtained in the following way: For each piece of comment information among the plurality of comment information for the content to be processed, determining a comment quality score of the comment information; At least one comment information with the highest score is determined from the multiple comment information according to the comment quality scores from high to low as the comment text, wherein the sum of the text lengths of the at least one comment information with the highest score is less than or equal to the text length of the content text.

35. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in 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 17.

36. 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 1-17.

37. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 17 is implemented.

38. A content recommendation system, comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions executable 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 14 to 17.

Images