CN118113934A

CN118113934A - Data processing method, apparatus, electronic device, medium, and program product

Info

Publication number: CN118113934A
Application number: CN202410096596.3A
Authority: CN
Inventors: 相宝玉; 黄若丹; 谢竹潇
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2024-01-23
Filing date: 2024-01-23
Publication date: 2024-05-31

Abstract

The disclosure provides a data processing method, a device, electronic equipment, a medium and a program product, and relates to the technical field of data processing, in particular to the field of artificial intelligence and personalized recommendation. The implementation scheme is as follows: determining a first query feature corresponding to the first query information and a user feature corresponding to the user; processing the first query feature and the user feature by using a gain model to obtain a predicted interest score of a user for related content related to the first query information; and determining a first recommended content for the relevant pages of the first query information, wherein the number of relevant content in the first recommended content, which is relevant to the first query information, is determined based on the predicted interest score.

Description

Data processing method, apparatus, electronic device, medium, and program product

Technical Field

The present disclosure relates to the field of data processing technology, and in particular, to the field of artificial intelligence and personalized recommendation, and more particularly, to a data processing method, apparatus, electronic device, computer readable storage medium, and computer program product.

Background

Artificial intelligence is the discipline of studying the process of making a computer mimic certain mental processes and intelligent behaviors (e.g., learning, reasoning, thinking, planning, etc.) of a person, both hardware-level and software-level techniques. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, a machine learning/deep learning technology, a big data processing technology, a knowledge graph technology and the like.

The approaches described in this section are not necessarily approaches that have been previously conceived or pursued. Unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section. Similarly, the problems mentioned in this section should not be considered as having been recognized in any prior art unless otherwise indicated.

Disclosure of Invention

The present disclosure provides a data processing method, apparatus, electronic device, computer readable storage medium, and computer program product.

According to an aspect of the present disclosure, there is provided a data processing method including: determining a first query feature corresponding to the first query information and a user feature corresponding to the user; processing the first query feature and the user feature by using a gain model to obtain a predicted interest score of a user for related content related to the first query information; and determining a first recommended content for the relevant pages of the first query information, wherein the number of relevant content in the first recommended content, which is relevant to the first query information, is determined based on the predicted interest score.

According to another aspect of the present disclosure, there is provided a data processing apparatus including: a feature extraction unit configured to determine a first query feature corresponding to the first query information and a user feature corresponding to the user; a prediction unit configured to process the first query feature and the user feature using a gain model to obtain a predicted interest score of a user for related content related to the first query information; and a recommendation unit configured to determine a first recommended content for a relevant page of the first query information, wherein the number of relevant contents related to the first query information in the first recommended content is determined based on the predicted interest score.

According to another aspect of the present disclosure, there is also provided an electronic apparatus including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method according to embodiments of the present disclosure.

According to another aspect of the present disclosure, there is also provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method according to an embodiment of the present disclosure.

According to another aspect of the present disclosure, there is also provided a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements a method according to embodiments of the present disclosure.

According to one or more embodiments of the present disclosure, by predicting relevance requirements of users based on query information and user information using a gain model, a targeted prediction result may be provided for each query behavior of each user, thereby providing users with more accurate personalized recommendation content.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The accompanying drawings illustrate exemplary embodiments and, together with the description, serve to explain exemplary implementations of the embodiments. The illustrated embodiments are for exemplary purposes only and do not limit the scope of the claims. Throughout the drawings, identical reference numerals designate similar, but not necessarily identical, elements.

FIG. 1 illustrates a schematic diagram of an exemplary system in which various methods described herein may be implemented, in accordance with an embodiment of the present disclosure;

FIG. 2 illustrates an exemplary process of a data processing method according to an embodiment of the present disclosure;

FIG. 3 illustrates an exemplary process of training a gain model according to an embodiment of the present disclosure;

FIG. 4 illustrates an exemplary structure of a gain model of an embodiment of the present disclosure;

FIG. 5 illustrates an exemplary block diagram of a data processing apparatus according to an embodiment of the present disclosure;

fig. 6 illustrates a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the present disclosure, the use of the terms "first," "second," and the like to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of the elements, unless otherwise indicated, and such terms are merely used to distinguish one element from another element. In some examples, a first element and a second element may refer to the same instance of the element, and in some cases, they may also refer to different instances based on the description of the context.

The terminology used in the description of the various illustrated examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context clearly indicates otherwise, the elements may be one or more if the number of the elements is not specifically limited. Furthermore, the term "and/or" as used in this disclosure encompasses any and all possible combinations of the listed items.

Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

Fig. 1 illustrates a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein may be implemented, in accordance with an embodiment of the present disclosure. Referring to fig. 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. Client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

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

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

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

The user may use client devices 101, 102, 103, 104, 105, and/or 106 to conduct information searches and queries. 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. Although fig. 1 depicts only six client devices, those skilled in the art will appreciate that the present disclosure may support any number of client devices.

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, gaming systems, thin clients, various messaging devices, sensors or other sensing devices, and the like. 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 (e.g., 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 telephones, smart phones, tablet computers, personal Digital Assistants (PDAs), and the like. Wearable devices may include head mounted displays (such as smart glasses) and other devices. The gaming system may include various handheld gaming devices, internet-enabled gaming devices, and the like. The client device is capable of executing a variety of different applications, such as various Internet-related applications, communication applications (e.g., email applications), short Message Service (SMS) applications, and may use a variety of communication protocols.

Network 110 may be any type of network known to those skilled in the art that may support data communications using any of a number of available protocols, including but not limited to TCP/IP, SNA, IPX, etc. For 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.

The server 120 may include one or more general purpose computers, special purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-end servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and/or combination. The server 120 may include one or more virtual machines running a virtual operating system, or other computing architecture that involves virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain virtual storage devices of the server). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

The computing units in server 120 may run one or more operating systems including any of the operating systems described above as well as any commercially available server operating systems. 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.

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.

In some implementations, the server 120 may be a server of a distributed system or a server that incorporates 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. The cloud server is a host product in a cloud computing service system, so as to solve the defects of large management difficulty and weak service expansibility in the traditional physical host and Virtual special server (VPS PRIVATE SERVER) service.

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 databases 130 may be used to store information such as audio files and video files. Database 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. Database 130 may be of different types. In some embodiments, the database used by server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve the databases and data from the databases in response to the commands.

In some embodiments, one or more of databases 130 may also be used by applications to store application data. The databases used by the application may be different types of databases, such as key value stores, object stores, or conventional stores supported by the file system.

The system 100 of fig. 1 may be configured and operated in various ways to enable application of the various methods and apparatus described in accordance with the present disclosure.

A user may search for content of interest using a search engine. For example, a user may enter query information in a search engine and browse results returned by the search engine that are related to the query information. After the search requirement of the user is met, recommended content can be provided for the user on the related page of the query information, so that the search product is optimized into a search-push fusion product with personalized recommendation capability.

The recommended content provided to the user on the relevant page can be generally classified into two types, one is the relevant content related to the query information and the other is the personalized content related to the individual characteristics of the user. For example, the related content is pictures, articles, videos, and the like that can be queried based on the query information, and the personalized content is content that is presumed to be of interest to the user based on the user's historical behavior. Personalized content may be irrelevant to the query information. The degree of need for the relevant content of different query information is different for different users.

The following ways are generally adopted in the related art to predict the demand level of the user for the related content:

1. providing fixed N pieces of correlation content for all query requests in the recommended content;

2. Clustering according to semantic vectors of the query request, counting the quantity of related contents of which each clustering center is located at 80 bits, and further determining the recommended quantity of related contents corresponding to the clustering center to which the query request belongs for the current query request;

3. Calculating the number of the related contents positioned at 80 bits in the category according to the preset category to which the query request belongs, and further determining the recommended number of the related contents corresponding to the category to which the query request belongs for the current query request;

4. and calculating the integral 80-bit correlation score according to the preset category to which the query request belongs and the activity degree of the user aiming at the category content, and further determining the recommendation score of the correlation content corresponding to the category to which the query request belongs and the activity degree of the user for the current query request.

However, the related art prediction of the degree of relevance content demand for a user has drawbacks. The first approach is the simplest implementation, but ignores the large difference in relevance requirements under different query requests. In the second approach, the relevance requirements of different query requests cannot be better distinguished, or are limited by the influence of clustering performance and accuracy. The third method distinguishes the correlation requirements of different query requests through the category to which the query requests belong, improves the classification accuracy of the query requests, but does not consider that the correlation requirements of different users on different query requests still have great difference. The fourth method considers the user liveness and the category of the query request at the same time, and cannot accurately predict the personalized relevance requirement of each user under different query requests.

In order to further meet the correlation requirements of user individuation, the present disclosure provides a new data processing method.

Fig. 2 illustrates an exemplary process of a data processing method according to an embodiment of the present disclosure.

In step S202, a first query feature corresponding to the first query information and a user feature corresponding to the user are determined.

In step S204, the first query feature and the user feature are processed using the gain model to obtain a predicted interest score for the user for related content related to the first query information.

In step S206, a first recommended content for the relevant page of the first query information is determined, wherein the number of relevant content in the first recommended content that is relevant to the first query information is determined based on the predicted interest score.

By using the embodiment of the disclosure, the correlation requirements of the users are predicted based on the query information and the user information by using the gain model, and a targeted prediction result can be provided for each query behavior of each user, so that more accurate personalized recommended content is provided for the users.

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

In step S202, a first query feature corresponding to the first query information and a user feature corresponding to the user may be determined.

The first query feature may include at least one of a semantic feature of the first query information and a statistical feature of the first query information. The semantic features may be used to represent specific content of the first query information, and the statistical features may include statistical results of user behaviors in historical query behaviors related to the first query information, and may reflect a degree of interest of the user in the first query information.

In some examples, the semantic features of the first query information may include semantic vectors of the first query information, which may be processed by any natural language vectorization approach to obtain the semantic vectors. In an example, the semantic features of the first query information may also include classification features for the semantics of the first query information, e.g., classification features indicating whether the first query information belongs to offending information (e.g., whether it belongs to pornography information), whether it is time-efficient, may be determined based on the semantics of the first query information.

In some examples, the statistical characteristics of the first query information may include statistical data of user behavior in pages related to the first query information. When determining the statistical characteristics of the first query information, data collection can be performed for all users or randomly selected users, so as to minimize the influence of the personalized behavior of the users on the statistical results of the query information. In an example, the statistical features of the first query information may include statistics of the number of clicks and browsing duration of the user in the results page and the landing page of the first query information, which may reflect the user's interest level in the first query information. The result page refers to a query result list returned by the search engine in response to the first query information, and the landing page refers to a specific page entered by clicking a link in the query result list. For example, the statistical features of the first query information may include a number of searches of the result page of the first query information, a result page click rate of the first query information, a number of times the user enters the landing page, and a number of times the user repeatedly enters the landing page under the same query information.

In an example, the statistical features of the first query information may further include statistics of user clicks and browses of relevant content in relevant pages of the first query information, which may reflect the user's relevance needs under the first query information. For example, the statistical features of the first query information may include a duty cycle of distribution of the lower related content in the landing page, a time period of play of the related content in the landing page, a fast slip rate of the related content in the landing page (i.e., a proportion of the user's fast-sliding through the content), a long-play rate of the related content in the landing page (i.e., a proportion of the user's viewing of the related content exceeding a predetermined threshold (e.g., 10 s)), and a browsing step size of the related content in the landing page (i.e., a number of users viewing of the related content).

The above-described statistical features may be added, subtracted or modified by those skilled in the art according to the actual situation to meet the requirements of the actual application without departing from the principles of the present disclosure.

The user characteristics may include at least one of a historical access characteristic for query content, a historical access characteristic for related content, and a historical access characteristic for personalized content for the user. The user characteristics can reflect the browsing habit of the user after the query request is sent, the browsing habit of the related content and the browsing habit of the personalized content, so that different requirements of the user on the related content and the personalized content are further reflected.

In an example, the historical access characteristics for query content may include a user historical browsing length that indicates how many content the user will browse at a time during historical usage. In the case where the application automatically refreshes the content for the user, the background refresh amount per request may be used to represent the user's historical browsing length. Further, the historical access characteristics of the user may also include how often the user accesses the landing page over a different time range (e.g., 30 days, 14 days, etc.), the number of searches over a period of time (e.g., 30 days), and the average number of repetitions of entry into the landing page over a period of time (e.g., 30 days) with the same query information.

In an example, the historical access characteristics for the relevant content may include a relevant content slip rate, a relevant content play duration ratio, a relevant content long play rate, etc. of the user.

In an example, the historical access characteristics for the personalized content may include a user's personalized content quick slip, a personalized content play duration ratio, a personalized content long play rate, and the like.

The gain model may be used to estimate the impact of an intervention action (event) on the corresponding behavior of the user. Using the gain model, differences in behavior of the same individual in different cases of intervention from non-intervention can be determined. In some embodiments, the gain model may be a uplift model. The principles of the present disclosure will be described in this disclosure using the uplift model as an example. Other gain models with the same function may also be used without departing from the principles of the present disclosure.

Fig. 3 illustrates an exemplary process of training a gain model according to an embodiment of the present disclosure.

In step S302, a sample set of users may be determined. The sample users can be selected from all users in a random mode so as to cover different types of users as much as possible and improve the application range of the trained gain model.

In step S304, a sample user characteristic of the sample user and a second query characteristic of the second query information input by the sample user may be determined.

In step S306, the second recommended content may be provided in a page related to the second query information. In the sample data collected during the training process, a portion of the sample users may be intervened and another portion of the sample users may be a control group that is not intervened. All of the second recommended content is related to the second query information if tampered with, and the second recommended content includes related content related to the second query information and personalized content for the sample user if not tampered with. The recommended content may be provided to the user without intervention in any manner provided in the related art. For the uplift model, in the case of intervention, the intervention information (treatment) of the model may be set to 1, and in the case of no intervention, the intervention information may be set to 0.

For users in the sample user set, only relevant content is provided as a recommendation result for at least a part of sample users in a certain time range. By the method, feedback of different users on the correlation content can be effectively collected, and therefore requirements of the different users on the correlation content are determined.

In step S308, a true interest score of the sample user for the relevant content related to the second query information may be determined based on the browsing time of the sample user for the second recommended content. Wherein the browsing time of the user may be normalized as the score of interest. In the gain model provided by the present disclosure, the user's browsing time for the relevant content is used to determine the user's interest level in the relevant content. It will be appreciated that the higher the user's demand for related content, the longer it will take to browse the related content.

In step S310, the sample user features and the second query features may be processed using a uplift model to obtain a predicted interest score for the sample user for the relevance content. The Uplift model can sense the characteristics of the query information and the user, and predict the interest degree of the user for the relevant content according to the characteristics of the query information and the characteristics of the user. The predicted interest score has the same representation as the real interest score, for example expressed as a normalized result of the browsing time. Other types of parametric representations may also be used by those skilled in the art to predict the score of interest depending on the situation.

In step S312, parameters of the uplift model may be adjusted to minimize the error between the predicted and actual scores of interest. As described above, the true interest score is a true result obtained by providing the recommendation of the related content to the user in its entirety, and can reflect the true demand of the user for the related content. The predicted interest score is a predicted result obtained by processing the query feature and the user feature by using the model. By minimizing the error between the predicted and actual interest scores, the ability of the gain model to perceive query features and user features, and further predict the user's level of interest in the relevant content based on the perceived features, may be improved.

Fig. 4 illustrates an exemplary structure of a gain model of an embodiment of the present disclosure.

As shown in fig. 4, the gain model 400 may include a first fully connected layer 410 and a second fully connected layer 420 in series.

For a user initiated query request, it may be determined that the query features 401 of the query information contained in the query request and the vector representations of the user features 402 of the user are connected together as inputs to the first fully connected layer 410. Further, the input of the first fully connected layer 410 may also include intervention information 403. When recommended content of only relevant content is provided for the user, the intervention information 403 may be set to 1, and in other cases, the intervention information 403 may be set to 0. The person skilled in the art can also set the intervention information to any other suitable value depending on the actual situation.

Referring back to fig. 2, in step S206, a first recommended content for the relevant page of the first query information is determined, wherein the number of relevant content related to the first query information in the first recommended content is determined based on the predicted interest score. The relevant page of the first query information may be a result page or a landing page of the first query information, or may be any other form of page presented to the user in response to a query request containing the first query information. Recommending content refers to recommending content for the user to browse further in the relevant page in addition to the content of the page itself. The recommended content may include relevant content related to the query information, and may also include personalized content related to the user.

In some examples, the number of relevance content may be expressed as an absolute number or a relative number. Absolute number refers to the actual number of pieces of correlation content, e.g., 5 pieces, 10 pieces, etc. of numerical value. The relative amount refers to the ratio of the related content in the first recommended content, for example, 50%, 60%, etc.

The recommended number of relevant content corresponding to the predicted score of interest may be determined by various predetermined mapping means.

In some embodiments, the score of interest may be divided into different gear steps and the recommended number of different relevance content determined for the score of interest for the different gear steps. In an example, taking the normalized result that the predicted interest score is between 0 and 1 as an example, the interest score may be divided into three gear positions of 0 to 0.4,0.4 to 0.7, and 0.7 to 1. The recommended number of the related content may be determined to be 30% for the score of interest of 0 to 0.4, 50% for the score of interest of 0.4 to 0.7, and 80% for the score of interest of 0.7 to 1. The appropriate mapping relationship can be preset by a person skilled in the art according to the actual situation, and the scheme of the present disclosure is not limited thereto.

In other embodiments, the adjustment value may be determined for a reference recommended number of query content based on the predicted interest score. Step S206 may include: determining a reference recommendation number of the correlation content based on the first query information; determining an adjustment value for the correlation content based on the predicted interest score; the recommended number of related content in the first recommended content is determined based on the reference recommended number and the adjustment value. In this case, the reference recommendation number for the query information may be determined according to the content of the query information. Wherein the reference recommendation number may be determined based on the category of the first query information. For example, the reference recommendation number of the relevance contents of the query information under the category to which the query information belongs may be determined according to the category to which the query information belongs using the method provided in the related art. The number of reference recommendations may then be adjusted based on the user's score of interest in the relevance content predicted by the gain model. Also take as an example the normalization result that predicts the score of interest to be between 0 and 1, the score of interest is divided into three gears of 0 to 0.4,0.4 to 0.7, and 0.7 to 1. The adjustment value of the correlation content may be determined to be-30% for a score of interest of 0 to 0.4,0 to 0.7, and +30% for a score of interest of 0.7 to 1. The appropriate mapping relationship can be preset by a person skilled in the art according to the actual situation, and the scheme of the present disclosure is not limited thereto.

In the case of using the uplift model as the gain model, the uplift model may be used to output a first predicted score of interest with intervention and a second predicted score of interest without intervention. Wherein the first predicted score of interest in the case of intervention is a result of processing output of the query feature, the user feature, and the intervention information set to 1 by using the uplift model, and the second score of interest in the case of no intervention is a result of processing output of the query feature, the user feature, and the intervention information set to 0 by using the uplift model. An adjustment value may be determined based on a difference between the first predicted interest score and the second predicted interest score. The difference may be used to represent different performances of the user with intervention (e.g., providing only recommendations of relevant content to the user) and without intervention (e.g., providing recommendations of both relevant content and personalized content to the user at the same time), and the adjustment value of the relevant content may be determined from the different performances of the user. For example, if the predicted interest score that the user outputs with intervention is higher, the larger the number of relevance contents is explained, the longer the user stays on the page, so that the number of relevance contents in the recommended contents can be increased in this case. Otherwise, the number of related contents in the recommended contents can be reduced. The person skilled in the art can determine the specific mapping relationship between the difference value between the first predicted interest score and the second predicted interest score and the adjustment value according to the actual situation.

Step S206 may also include determining how relevant content is presented on the page based on the predicted interest score without departing from the principles of the present disclosure. As previously described, the predicted interest score may reflect the user's interest level in the related content. Therefore, the display characteristics such as the position, the size and the like of the correlation content on the page can be adjusted according to the predicted interest score so as to improve or reduce the attention degree of a user on the correlation content on the page.

Fig. 5 shows an exemplary block diagram of a data processing apparatus according to an embodiment of the present disclosure.

As shown in fig. 5, the apparatus 500 may include a feature extraction unit 510, a prediction unit 520, and a recommendation unit 530.

The feature extraction unit 510 may be configured to determine a first query feature corresponding to the first query information and a user feature corresponding to the user.

The prediction unit 520 may be configured to process the first query feature and the user feature using the gain model to obtain a predicted interest score for the user for related content related to the first query information.

The recommendation unit 530 may be configured to determine first recommended content for the relevant page of the first query information, wherein the number of relevant content in the first recommended content that is relevant to the first query information is determined based on the predicted interest score.

In some embodiments, the gain model is a uplift model.

In some embodiments, uplift models are trained using the following methods: determining a sample user set; determining sample user characteristics of the sample user and second query characteristics of second query information input by the sample user, and providing second recommended content in a page related to the second query information; determining a true interest score of the sample user for the relevant content related to the second query information based on a browsing time of the sample user for the second recommended content; processing the sample user features and the second query features by using uplift model to obtain the predicted interest score of the sample user for the correlation content; and adjusting uplift parameters of the model to minimize the error between the predicted and actual scores of interest.

In some embodiments, all of the second recommended content is related to the second query information if tampered with, and the second recommended content includes related content related to the second query information and personalized content for the sample user if not tampered with.

In some embodiments, the first recommended content further includes personalized content for the user.

In some embodiments, the recommendation unit is configured to: determining a reference recommendation number of the correlation content based on the first query information; determining an adjustment value for the correlation content based on the predicted interest score; the recommended number of related content in the first recommended content is determined based on the reference recommended number and the adjustment value.

In some embodiments, determining the adjustment value for the relevance content based on the predicted interestingness score includes: determining a first predicted score of interest that the gain model outputs if tampered with; determining a second predicted score of interest that the gain model outputs without intervention; an adjustment value is determined based on a difference between the first predicted interest score and the second predicted interest score.

In some embodiments, the reference recommendation number is determined based on a category of the first query information.

In some embodiments, the first query feature comprises at least one of a semantic feature of the first query information and a statistical feature of the first query information.

In some embodiments, the user characteristics include at least one of a historical access characteristic for query content, a historical access characteristic for related content, and a historical access characteristic for personalized content for the user.

Steps S202 to S206 shown in fig. 2 may be performed by using units 510 to 530 shown in fig. 5, and will not be described again.

It should be appreciated that the various modules or units of the apparatus 500 shown in fig. 5 may correspond to the various steps in the method 200 described with reference to fig. 2. Thus, the operations, features and advantages described above with respect to method 200 apply equally to apparatus 500 and the modules and units comprised thereof. For brevity, certain operations, features and advantages are not described in detail herein.

In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.

There is also provided, in accordance with an embodiment of the present disclosure, an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method according to embodiments of the present disclosure.

There is also provided, in accordance with an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform a method according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, there is also provided a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements a method according to an embodiment of the present disclosure.

Referring to fig. 6, a block diagram of an electronic device 600 that may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the electronic device 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 can also be stored. The computing unit 601, ROM 602, and RAM 603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

A number of components in the electronic device 600 are connected to the I/O interface 605, including: an input unit 606, an output unit 607, a storage unit 608, and a communication unit 609. The input unit 606 may be any type of device capable of inputting information to the electronic device 600, the input unit 606 may receive input numeric or character information and generate key signal inputs related to user settings and/or function control of the electronic device, and may include, but is not limited to, a mouse, a keyboard, a touch screen, a trackpad, a trackball, a joystick, a microphone, and/or a remote control. The output unit 607 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, video/audio output terminals, vibrators, and/or printers. Storage unit 608 may include, but is not limited to, magnetic disks, optical disks. The communication unit 609 allows the electronic device 600 to exchange information/data with other devices through a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth (TM) devices, 802.11 devices, wiFi devices, wiMax devices, cellular communication devices, and/or the like.

The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as methods 200, 300. For example, in some embodiments, the methods 200, 300 may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 600 via the ROM 602 and/or the communication unit 609. One or more of the steps of the methods 200, 300 described above may be performed when a computer program is loaded into the RAM 603 and executed by the computing unit 601. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the methods 200, 300 by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here 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 a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), the internet, and blockchain networks.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it is to be understood that the foregoing methods, systems, and apparatus are merely exemplary embodiments or examples, and that the scope of the present invention is not limited by these embodiments or examples but only by the claims following the grant and their equivalents. Various elements of the embodiments or examples may be omitted or replaced with equivalent elements thereof. Furthermore, the steps may be performed in a different order than described in the present disclosure. Further, various elements of the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced by equivalent elements that appear after the disclosure.

Claims

1.A data processing method, comprising:

Determining a first query feature corresponding to the first query information and a user feature corresponding to the user;

Processing the first query feature and the user feature by using a gain model to obtain a predicted interest score of a user for related content related to the first query information; and

Determining first recommended content for relevant pages of the first query information, wherein the number of relevant content in the first recommended content, which is relevant to the first query information, is determined based on the predicted interest score.

2. The method of claim 1, wherein the gain model is a uplift model.

3. The method of claim 2, wherein the uplift model is trained using the following method:

determining a sample user set;

Determining sample user characteristics of the sample user and second query characteristics of second query information input by the sample user;

providing second recommended content in a page related to the second query information;

Determining a true interest score of the sample user for relevant content related to the second query information based on a browsing time of the sample user for the second recommended content;

processing the sample user features and the second query features using the uplift model to obtain a predicted interest score for the sample user for relevance content; and

Parameters of the uplift model are adjusted to minimize the error between the predicted score of interest and the real score of interest.

4. The method of claim 3, wherein,

In case of intervention, all recommended content of the second recommended content is related to the second query information, and

The second recommended content includes, without intervention, relevance content related to the second query information and personalized content for the sample user.

5. The method of any one of claims 1 to 4, wherein the first recommended content further comprises personalized content for a user.

6. The method of any of claims 1-4, wherein determining a first recommended content for the relevant page of the first query information comprises:

Determining a reference recommendation number of the correlation content based on the first query information;

determining an adjustment value for the relevance content based on the predicted interest score;

and determining the recommended quantity of the correlation content in the first recommended content based on the reference recommended quantity and the adjustment value.

7. The method of claim 6, wherein determining an adjustment value for the relevance content based on the predicted interest score comprises:

determining a first predicted score of interest that the gain model outputs if tampered with;

Determining a second predicted score of interest that the gain model outputs without intervention;

The adjustment value is determined based on a difference between the first predicted interest score and the second predicted interest score.

8. The method of claim 6, wherein the reference recommendation number is determined based on a category of the first query information.

9. The method of any of claims 1-4, wherein the first query feature comprises at least one of a semantic feature of the first query information and a statistical feature of the first query information.

10. The method of any of claims 1-4, wherein the user characteristics include at least one of a historical access characteristic for query content, a historical access characteristic for related content, and a historical access characteristic for personalized content for a user.

11. A data processing apparatus comprising:

A feature extraction unit configured to determine a first query feature corresponding to the first query information and a user feature corresponding to the user;

a prediction unit configured to process the first query feature and the user feature using a gain model to obtain a predicted interest score of a user for related content related to the first query information; and

And a recommendation unit configured to determine a first recommended content for a relevant page of the first query information, wherein the number of relevant contents related to the first query information in the first recommended content is determined based on the predicted interest score.

12. The apparatus of claim 11, wherein the gain model is a uplift model.

13. The apparatus of claim 12, wherein the uplift model is trained using the following method:

determining a sample user set;

14. The apparatus of claim 13, wherein,

15. The apparatus of any of claims 11 to 14, wherein the first recommended content further comprises personalized content for a user.

16. The apparatus of any of claims 11 to 14, wherein the recommendation unit is configured to:

17. The apparatus of claim 16, wherein determining an adjustment value for the relevance content based on the predicted interest score comprises:

18. The apparatus of claim 17, wherein the reference recommendation number is determined based on a category of the first query information.

19. The apparatus of any of claims 11 to 14, wherein the first query feature comprises at least one of a semantic feature of the first query information and a statistical feature of the first query information.

20. The apparatus of any of claims 11 to 14, wherein the user characteristics comprise at least one of a historical access characteristic for query content, a historical access characteristic for relevant content, and a historical access characteristic for personalized content for a user.

21. An electronic device, comprising:

At least one processor; and

A memory communicatively coupled to the at least one processor; wherein the method comprises the steps of

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-10.

22. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-10.

23. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method of any of claims 1-10.