CN115168720A - Content interaction prediction method and related equipment - Google Patents

Content interaction prediction method and related equipment Download PDF

Info

Publication number
CN115168720A
CN115168720A CN202210830680.4A CN202210830680A CN115168720A CN 115168720 A CN115168720 A CN 115168720A CN 202210830680 A CN202210830680 A CN 202210830680A CN 115168720 A CN115168720 A CN 115168720A
Authority
CN
China
Prior art keywords
target
interaction
content
feature
interactive
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210830680.4A
Other languages
Chinese (zh)
Inventor
谢若冰
朱勇椿
张绍亮
夏锋
林乐宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN202210830680.4A priority Critical patent/CN115168720A/en
Publication of CN115168720A publication Critical patent/CN115168720A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Analysis (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Algebra (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Software Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses a content interaction prediction method and related equipment, and related embodiments can be applied to various scenes such as cloud technology, artificial intelligence, intelligent traffic, auxiliary driving and the like; feature extraction on interactive operation can be carried out on the target content to obtain a target first operation feature and a target sharing operation feature of the target content on first interactive operation; determining an initial predicted interaction result of the target content on the first interaction operation based on the target first operation characteristic; performing logistic regression analysis on the target sharing operation characteristics, and predicting negative noise information generated by the second interactive operation on the first interactive operation; and correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result. According to the method and the device, the predicted interaction result of the target content on the first interaction operation can be corrected by capturing the negative noise information generated by the second interaction operation on the first interaction operation, and the prediction accuracy of the interaction result on the first interaction operation is improved.

Description

Content interaction prediction method and related equipment
Technical Field
The present application relates to the field of computer technologies, and in particular, to a content interaction prediction method and related devices.
Background
With the rapid development of artificial intelligence technology, more and more application scenes recommend personalized content to users by using the artificial intelligence technology so as to improve the interactive experience of the users.
In the process of recommending contents for a user, the related art generally predicts the click probability and the reading time length corresponding to each candidate content through a multitask model, and then selects the target content recommended to the user from the candidate contents according to the predicted click probability and the reading time length. However, the current multitask model generally focuses too much on tasks with rich supervision signals (such as estimation of click probability), so that the prediction effect on tasks with less supervision signals (such as estimation of reading duration) is poor.
Disclosure of Invention
The embodiment of the application provides a content interaction prediction method and related equipment, wherein the related equipment comprises a content interaction prediction device, electronic equipment, a computer readable storage medium and a computer program product, and the prediction accuracy of an interaction result in a first interaction operation can be improved.
The embodiment of the application provides a content interaction prediction method, which comprises the following steps:
acquiring target content; extracting features of the target content in interactive operation to obtain target first operation features and target shared operation features of the target content in first interactive operation, wherein the target shared operation features are features shared by the first interactive operation and second interactive operation, and the second interactive operation is a front operation depended on by the first interactive operation;
determining an initial predicted interaction result of the target content on the first interaction operation based on the target first operation characteristic;
performing logistic regression analysis on the target sharing operation characteristics to predict negative noise information generated by the second interactive operation on the first interactive operation;
and correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation.
Correspondingly, an embodiment of the present application provides a content interaction prediction apparatus, including:
an acquisition unit configured to acquire target content; extracting features of the target content in interactive operation to obtain target first operation features and target shared operation features of the target content in first interactive operation, wherein the target shared operation features are features shared by the first interactive operation and second interactive operation, and the second interactive operation is a front operation depended on by the first interactive operation;
a determining unit, configured to determine, based on the target first operation feature, an initial predicted interaction result of the target content on the first interaction operation;
the prediction unit is used for carrying out logistic regression analysis on the target sharing operation characteristics so as to predict negative noise information generated by the second interactive operation on the first interactive operation;
and the correcting unit is used for correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation.
Optionally, in some embodiments of the application, the obtaining unit may be specifically configured to perform feature extraction on an interactive operation on the target content, so as to obtain a target first operation feature of the target content on a first interactive operation, a target second operation feature of the target content on a second interactive operation, and a target shared operation feature;
the content interaction prediction apparatus may further include a result determination unit as follows:
the result determining unit is configured to determine a predicted interaction result of the target content on the second interaction operation based on the target second operation characteristic.
Optionally, in some embodiments of the present application, the obtaining unit may include an extracting subunit and an interacting subunit, as follows:
the extracting subunit is configured to extract a first operation feature of the target content in a first interactive operation, a second operation feature of the target content in a second interactive operation, and a shared operation feature;
and the interaction subunit is configured to perform feature interaction processing on the first operation feature, the second operation feature, and the shared operation feature to obtain a target first operation feature corresponding to the first interaction operation, a target second operation feature corresponding to the second interaction operation, and a target shared operation feature.
Optionally, in some embodiments of the present application, the interaction subunit may be specifically configured to fuse the first operation feature and the shared operation feature, and update the first operation feature based on the fused feature; fusing the second operating characteristic and the shared operating characteristic, and updating the second operating characteristic based on the fused characteristic; fusing the first operating characteristic, the second operating characteristic and the shared operating characteristic, and updating the shared operating characteristic based on the fused characteristic; and returning to execute the step of fusing the first operation characteristic and the shared operation characteristic and updating the first operation characteristic based on the fused characteristic until a target shared operation characteristic meeting a preset characteristic interaction condition, a target first operation characteristic corresponding to the first interactive operation and a target second operation characteristic corresponding to the second interactive operation are obtained.
Optionally, in some embodiments of the present application, the determining unit includes a fusion subunit and a determining subunit, as follows:
the fusion subunit is configured to fuse the target shared operation feature and the target first operation feature to obtain a first fusion operation feature;
and the determining subunit is configured to determine, based on the first fusion operation characteristic, an initial predicted interaction result of the target content on the first interaction operation.
Optionally, in some embodiments of the application, the obtaining unit may be specifically configured to perform feature extraction on interactive operation on the target content through a content interaction prediction model, so as to obtain a target first operation feature and a target sharing operation feature of the target content on the first interactive operation.
Optionally, in some embodiments of the present application, the content interaction prediction apparatus may further include a training unit, where the training unit is configured to train the content interaction prediction model; specifically, the training unit may include a data acquisition subunit, a feature extraction subunit, an interaction result determination subunit, an analysis subunit, and an adjustment subunit, as follows:
the data acquisition subunit is configured to acquire training data, where the training data includes sample content, a first expected interaction result of the sample content in the first interaction operation, and a second expected interaction result in the second interaction operation;
the characteristic extraction subunit is used for carrying out characteristic extraction on the sample content in interactive operation through a content interactive prediction model to obtain a target first operation characteristic of the sample content in first interactive operation, a target second operation characteristic in second interactive operation and a target sharing operation characteristic;
an interaction result determining subunit, configured to determine, based on the target first operation feature and the target second operation feature, an initial first actual interaction result of the sample content on the first interaction operation and a second actual interaction result on the second interaction operation, respectively;
the analysis subunit is configured to perform logistic regression analysis on the target sharing operation feature to predict actual negative noise information generated by the second interactive operation on the first interactive operation; correcting the initial first actual interaction result based on the actual negative noise information to obtain a target first actual interaction result;
and the adjusting subunit is configured to adjust parameters of the content interaction prediction model according to the initial first actual interaction result, the target first actual interaction result, the first expected interaction result, the second actual interaction result, and the second expected interaction result, so as to obtain a trained content interaction prediction model.
Optionally, in some embodiments of the present application, the adjusting subunit may be specifically configured to calculate a first loss value between the initial first actual interaction result and the first expected interaction result; calculating a second loss value between the target first actual interaction result and the first expected interaction result; calculating a third loss value between the second actual interaction result and the second expected interaction result; and adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value and the third loss value to obtain a trained content interaction prediction model.
Optionally, in some embodiments of the present application, the content interaction prediction model includes a base prediction module and a negative noise modeling module; the step of adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value, and the third loss value to obtain the trained content interaction prediction model may include:
adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value and the third loss value to obtain a pre-trained content interaction prediction model;
masking the sample content through a basic prediction module in a pre-trained content interaction prediction model to obtain target content information of which the correlation with the second interaction operation meets a preset correlation condition; performing feature extraction on interactive operation on the target content information to obtain target enhanced sharing operation features of the sample content;
predicting actual strengthened negative noise information generated by the second interactive operation on the first interactive operation based on the target strengthened sharing operation characteristics through a negative noise modeling module in a pre-trained content interactive prediction model;
and adjusting parameters of the negative noise modeling module based on the actual reinforced negative noise information and the first expected interaction result to obtain a trained content interaction prediction model.
Optionally, in some embodiments of the present application, before the step "adjusting parameters of the negative noise modeling module based on the actual enhanced negative noise information and the first expected interaction result to obtain the trained content interaction prediction model", the method may further include:
performing feature extraction on interactive operation on the target content information through a basic prediction module in a pre-trained content interactive prediction model to obtain a target strengthened first operation feature of the sample content on first interactive operation;
determining an initial actual enhanced interaction result of the sample content on the first interaction operation based on the target enhanced first operation feature;
the step of adjusting parameters of the negative noise modeling module based on the actual reinforced negative noise information and the first expected interaction result to obtain a trained content interaction prediction model may include:
based on the actual enhanced negative noise information, correcting the initial actual enhanced interaction result to obtain a target actual enhanced interaction result of the sample content on the first interaction operation;
and adjusting parameters of the negative noise modeling module based on the target actual enhanced interaction result and the first expected interaction result to obtain a trained content interaction prediction model.
The electronic device provided by the embodiment of the application comprises a processor and a memory, wherein the memory stores a plurality of instructions, and the processor loads the instructions to execute the steps in the content interaction prediction method provided by the embodiment of the application.
The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps in the content interaction prediction method provided in the embodiment of the present application.
In addition, a computer program product is provided in the embodiments of the present application, and includes a computer program or instructions, and the computer program or instructions, when executed by a processor, implement the steps in the content interaction prediction method provided in the embodiments of the present application.
The embodiment of the application provides a content interaction prediction method and related equipment, which can acquire target content; extracting features of the target content in interactive operation to obtain a target first operation feature and a target shared operation feature of the target content in first interactive operation, wherein the target shared operation feature is a feature shared by the first interactive operation and a second interactive operation, and the second interactive operation is a preposed operation depended on by the first interactive operation; determining an initial predicted interaction result of the target content on the first interaction operation based on the target first operation characteristic; performing logistic regression analysis on the target sharing operation characteristics to predict negative noise information generated by the second interactive operation on the first interactive operation; and correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation. According to the method and the device, the predicted interaction result of the target content on the first interaction operation can be corrected by capturing the negative noise information generated by the second interaction operation on the first interaction operation, and the prediction accuracy of the interaction result on the first interaction operation is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1a is a schematic view of a scene of a content interaction prediction method provided in an embodiment of the present application;
FIG. 1b is a flowchart of a content interaction prediction method provided in an embodiment of the present application;
FIG. 1c is a diagram of a model architecture of a content interaction prediction method provided in an embodiment of the present application;
FIG. 1d is another model architecture diagram of a content interaction prediction method provided in an embodiment of the present application;
fig. 1e is an explanatory diagram of a content interaction prediction method provided in an embodiment of the present application;
FIG. 2 is another flowchart of a content interaction prediction method provided by an embodiment of the present application;
fig. 3 is a schematic structural diagram of a content interaction prediction apparatus according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the application provides a content interaction prediction method and related equipment, and the related equipment can comprise a content interaction prediction device, electronic equipment, a computer readable storage medium and a computer program product. The content interaction prediction apparatus may be specifically integrated in an electronic device, and the electronic device may be a terminal or a server.
It is understood that the content interaction prediction method of the present embodiment may be executed on the terminal, may also be executed on the server, and may also be executed by both the terminal and the server. The above examples should not be construed as limiting the present application.
As shown in fig. 1a, the content interaction prediction method executed by the terminal and the server together is taken as an example. The content interaction prediction system provided by the embodiment of the application comprises a terminal 10, a server 11 and the like; the terminal 10 and the server 11 are connected via a network, for example, a wired or wireless network connection, wherein the content interaction prediction device may be integrated in the server.
The server 11 may be configured to: acquiring target content; extracting features of the target content in interactive operation to obtain a target first operation feature and a target shared operation feature of the target content in first interactive operation, wherein the target shared operation feature is a feature shared by the first interactive operation and a second interactive operation, and the second interactive operation is a preposed operation depended on by the first interactive operation; determining an initial predicted interaction result of the target content on the first interaction operation based on the target first operation characteristic; performing logistic regression analysis on the target sharing operation characteristics to predict negative noise information generated by the second interactive operation on the first interactive operation; and correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation. The server 11 may be a single server, or a server cluster or a cloud server composed of a plurality of servers. In the content interaction prediction method or apparatus disclosed in the present application, a plurality of servers can be grouped into a blockchain, and the servers are nodes on the blockchain.
Wherein, the terminal 10 may be configured to: and receiving a target prediction interaction result of the target content on the first interaction operation, which is sent by the server 11, and recommending the content based on the target prediction interaction result. The terminal 10 may include a mobile phone, an intelligent voice interaction device, an intelligent appliance, a vehicle-mounted terminal, an aircraft, a tablet Computer, a notebook Computer, or a Personal Computer (PC), etc. A client, which may be an application client or a browser client or the like, may also be provided on the terminal 10.
The steps of performing content interactive prediction and the like in the server 11 may be executed by the terminal 10.
The content interaction prediction method provided by the embodiment of the application relates to natural language processing and machine learning in the field of artificial intelligence.
Among them, artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making. The artificial intelligence technology is a comprehensive subject, and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning, automatic driving, intelligent traffic and the like.
Among them, natural Language Processing (NLP) is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that enable efficient communication between humans and computers using natural language. Natural language processing is a science integrating linguistics, computer science and mathematics. Therefore, the research in this field will involve natural language, i.e. the language people use daily, so it has a close relation with the research of linguistics. Natural language processing techniques typically include text processing, semantic understanding, machine translation, robotic question and answer, knowledge mapping, and the like.
Machine Learning (ML) is a multi-domain cross subject, and relates to multiple subjects such as probability theory, statistics, approximation theory, convex analysis and algorithm complexity theory. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach to make computers have intelligence, and is applied in various fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and teaching learning.
The following are detailed below. It should be noted that the following description of the embodiments is not intended to limit the preferred order of the embodiments.
The embodiment will be described from the perspective of a content interaction prediction apparatus, which may be specifically integrated in an electronic device, and the electronic device may be a server or a terminal, and the like.
It is understood that in the specific implementation of the present application, related data such as reading duration and the like related to user information are involved, when the above embodiments of the present application are applied to specific products or technologies, user permission or consent needs to be obtained, and the collection, use and processing of related data need to comply with related laws and regulations and standards of related countries and regions.
The content interaction prediction method can be applied to scenes such as content recommendation. The embodiment can be applied to various scenes such as cloud technology, artificial intelligence, intelligent traffic, auxiliary driving and the like.
As shown in fig. 1b, a specific flow of the content interaction prediction method may be as follows:
101. acquiring target content; and extracting features of the target content in interactive operation to obtain a target first operation feature of the target content in first interactive operation and a target sharing operation feature, wherein the target sharing operation feature is a feature shared by the first interactive operation and a second interactive operation, and the second interactive operation is a front operation depended on by the first interactive operation.
The target content is a content of an interaction result to be predicted, and the interaction result to be predicted may specifically include an interaction result in the first interaction operation, or may also be an interaction result in the second interaction operation, which is not limited in this embodiment. It should be noted that the content format of the target content may include text, audio, image, video, and the like.
The second interactive operation is a front operation which is depended by the first interactive operation, the second interactive operation and the first interactive operation have dependency relationship in operation time, and the operation time of the second interactive operation is before the operation time of the first interactive operation. For example, in a specific scenario, the target content is content recommended to a target object, the second interaction operation is a click operation on the content, the first interaction operation is reading duration or a sharing operation for the content, and the like, predicting the interaction result in the second interaction operation may specifically be predicting whether the target object clicks the target content, and predicting the interaction result in the first interaction operation may specifically be predicting reading duration of the target object on the target content, or whether the target content is to be shared. It can be understood that the target object may read or share the target content only by clicking the target content, and therefore, the click is a preceding operation corresponding to the reading duration or the sharing.
Because the operation time of the first interactive operation and the second interactive operation has a dependency relationship, if the same content interactive prediction model is used for predicting the interactive results of the first interactive operation and the second interactive operation, the number of samples of the first interactive operation and the second interactive operation in the model training process is different greatly, so that the first interactive operation has fewer supervision signals, and the second interactive operation has more supervision signals.
In particular, when the first interactive operation (such as reading duration) and the second interactive operation (such as clicking operation) are jointly trained, some task-specific problems exist:
one is the data sparseness problem of reading time compared to clicking operations. For example, in some real recommendation systems, only a small portion of the exposed articles are read by click, which means that the data collected for training the prediction task of reading duration is generally far lower than that of click, which causes a problem that the shared parameter part (such as shared feature embedding and underlying shared expert layer) of the multi-task learning model is mainly optimized under the supervision of click signals. Specifically, the shared parameters account for more than 99% of the total parameters of the multitask learning model, which indicates that the multitask model is mainly optimized for the click task and is not optimized for the reading duration task.
Secondly, the complex relation between the clicking operation and the reading duration is coupled with the depth. The interaction operation of the user and the target content follows the behavior sequence mode of 'exposure-click-reading', so that the click operation and the reading time have a high dependence and a severe coupling relationship. Despite the strong correlation between the two, there is still a conflict between the two targets. For example, a headline eye-catching article may have poor content, and the user closes the article soon after clicking, which results in a high click but a short read time for the article.
In the prior art, a multitask model for predicting click operation and reading time usually ignores the negative influence of click on the reading time, and due to the fact that a seesaw effect existing in the multitask model excessively concerns tasks with rich monitoring signals (such as click estimation), the effect on tasks with few monitoring signals (such as reading time estimation) is poor, namely the prediction on the interactive result corresponding to the first interactive operation is inaccurate, and the prior model cannot obtain a good effect on two targets of click estimation and reading time estimation.
The content interaction prediction method can provide a multitask causal framework, and the adverse effect is explicitly captured and removed by introducing causal inference so as to improve the prediction effect of the reading time.
Wherein causal inference is a research area in statistics for analyzing causal relationships between variables; in this embodiment, the first interaction depends on the second interaction, and the two interactions can be regarded as having a causal relationship.
Optionally, in this embodiment, the step of "performing feature extraction on the target content in the interactive operation to obtain a target first operation feature and a target shared operation feature of the target content in the first interactive operation" may include:
and performing feature extraction on the interactive operation on the target content to obtain a target first operation feature of the target content on the first interactive operation, a target second operation feature on the second interactive operation and a target sharing operation feature.
Wherein the target shared operation characteristic is a characteristic shared by the first interactive operation and the second interactive operation; the target first operational characteristic may be considered to be a unique characteristic of the first interaction and the target second operational characteristic may be considered to be a unique characteristic of the second interaction.
Optionally, in this embodiment, the step of "performing feature extraction on the target content in the interactive operation to obtain a target first operation feature and a target shared operation feature of the target content in the first interactive operation" may include:
and performing feature extraction on the interactive operation on the target content through a content interactive prediction model to obtain a target first operation feature and a target sharing operation feature of the target content on the first interactive operation.
In this embodiment, a target first operation feature of the target content on the first interactive operation, a target second operation feature on the second interactive operation, and a target sharing operation feature may be extracted through the content interaction prediction model.
The content interaction prediction model is specifically a neural Network model, the neural Network may be a Residual Network (ResNet, residual Network), a Dense connection convolution Network (densneet, dense connectivity Network), or the like, and it should be understood that the neural Network of this embodiment is not limited to the above listed types.
Specifically, the content interaction prediction model is a multitask model, and may include a feature extraction network with a multilayer structure and a tower network corresponding to each task in the target multitask; each layer of the feature extraction network comprises a plurality of expert networks and gating networks corresponding to the tasks. For example, the content interaction prediction model may include a multi-layer feature extraction network and a tower network corresponding to both a prediction task corresponding to the first interaction operation and a prediction task corresponding to the second interaction operation.
The feature extraction network can be used for extracting unique features and shared features of each task, and the tower network can be used for meeting specific application requirements of each task, such as classification tasks or prediction tasks. In each layer of feature extraction network, a plurality of expert networks and gate control networks corresponding to the tasks are arranged, and the expert networks can comprise task sharing experts and task exclusive experts.
Wherein, in the multitask learning process, the output of the expert network can be subjected to weight control by using a gate control network; and selectively controlling the expert network in the multitask model through the output weight. The gate control network can be used for fusing the characteristic data extracted by the expert network, the expert network weights output by the gate control network corresponding to different tasks are different, the obtained characteristic fusion data of each task at the level have difference, and different expert networks can learn different signals from different angles due to the weight distribution of the gate control network; and then, taking the feature fusion data corresponding to each task as the input of the feature extraction network of the next level, thereby performing feature interaction until the feature fusion data are finally input to the tower network corresponding to each task to obtain the processing result of each task. In the content interaction prediction model, for each task, the corresponding gating network is also multi-layered, and the number of layers is the same as that of the feature extraction network. In the embodiment, the specificity of the tasks is distinguished under the scene of processing a plurality of associated tasks, the correlation among the tasks is fused, and the generalization capability and the accuracy of the processing result of the model can be effectively improved.
The expert network can adopt different network structures and parameters aiming at different tasks based on the same characterization input. The same network framework can be adopted for the tower network of each task, and different network frameworks can also be adopted, so that the multi-task model has flexible variability.
Among them, multi-task learning (MTL) is a field in machine learning, a machine learning method that puts a plurality of related tasks together based on shared characterization data, and is also a kind of transfer learning. The learning mode learns different tasks to the information of the related fields, then shares the information in the model based on the information of the fields, and mutually learns and shares the information through a plurality of tasks so as to improve the generalization capability and effect of the model.
In one embodiment, as shown in fig. 1c, the model structure diagram of the content interaction prediction model is shown, and the content interaction prediction model may be composed of a bottom multi-layer expert network (Experts) and a top task-specific Tower (Tower) network to learn the high-order interaction of each input embedded vector. Each expert module consists of a plurality of sub-networks, each of which is called an expert. In the expert module, a task sharing expert and a task exclusive expert are explicitly separated so as to avoid mutual interference among tasks; while gating networks are used to incorporate the knowledge of a lower level expert.
Specifically, the content interaction prediction model may be used to predict an interaction result on the first interaction operation, and is recorded as a task T; the content interaction prediction model can also be used for predicting an interaction result on the second interaction operation, and is marked as a task C, and the gating network is indicated by G.
The gate control network formula of the task k in the j-th layer expert network is shown as the formula (1):
g k,j (x)＝w k,j (g k,j-1 (x))S k,j (x) (1)
where x is the embedded vector of the input, w k,j Is a weight function of task k, and the structure of the weight function is based on a single-layer network with Softmax as an activation function, as shown in equation (2):
Figure BDA0003745503740000131
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA0003745503740000132
is a parameter matrix. Note that the gating network of the first layer is slightly different, and the corresponding formula of the gating network of the first layer is shown in equation (3):
g k,1 (x)＝w k,1 (x)S k,1 (x) (3)
wherein S is k,j Is a selection matrix of task k in the j-th network from selection directionA quantity composition comprising a shared expert and an expert dedicated to task k, as shown in equation (4):
Figure BDA0003745503740000133
wherein the content of the first and second substances,
Figure BDA0003745503740000134
the experts are respectively exclusive to the task k in the j-th network and have m in total k An expert dedicated to each task,
Figure BDA0003745503740000135
the equal is a single expert shared by tasks in the j-th network and has m S The tasks share experts. It should be noted that the selection matrix of the shared expert module is slightly different and is composed of all shared experts and task-specific experts.
Optionally, in this embodiment, the step of "performing feature extraction on the interactive operation on the target content to obtain a target first operation feature of the target content on the first interactive operation, a target second operation feature on the second interactive operation, and a target shared operation feature" may include:
extracting a first operation characteristic of the target content on a first interactive operation, a second operation characteristic on a second interactive operation and a shared operation characteristic;
and performing feature interaction processing on the first operation feature, the second operation feature and the shared operation feature to obtain a target first operation feature corresponding to the first interactive operation, a target second operation feature corresponding to the second interactive operation and a target shared operation feature.
Specifically, content information of the target content in each dimension may be input into the content interaction prediction model, and the content information of the target content in each dimension may include a content title, content publisher information, a content cover page, content itself information, and the like. According to a first interaction (e.g. reading duration) and a second interaction (e.g. reading duration)Click operation), the content information of the target content in each dimension can be divided into common features F normal (e.g., user identification Information (ID) and article identification information), exposure feature F exposure (e.g., title and cover pictures, which have an effect on click and reading duration) and post-click feature F posst-click (e.g., the contents of an article viewed after clicking, which have a direct influence on the reading duration only), so that the input content information f can be represented by the following equation (5):
f＝(F normal ,F exposure ,F post-click ) (5)
specifically, as shown in fig. 1C, a first operation feature may be obtained by extraction of a task-specific expert T of a first layer, a second operation feature may be obtained by extraction of a task-specific expert C of the first layer, and a shared operation feature may be obtained by extraction of a task-shared expert of the first layer; and then, performing feature interactive processing on the first operation feature, the second operation feature and the shared operation feature through the feature extraction networks of the next layers, so that the task exclusive expert T of the last layer outputs a target first operation feature, the task exclusive expert C of the last layer outputs a target second operation feature, and the task shared expert of the last layer outputs a target shared operation feature.
Optionally, in this embodiment, the step of performing feature interaction processing on the first operation feature, the second operation feature, and the shared operation feature to obtain a target first operation feature corresponding to the first interactive operation, a target second operation feature corresponding to the second interactive operation, and a target shared operation feature may include:
fusing the first operating characteristic and the shared operating characteristic, and updating the first operating characteristic based on the fused characteristic;
fusing the second operating characteristic and the shared operating characteristic, and updating the second operating characteristic based on the fused characteristic;
fusing the first operating characteristic, the second operating characteristic and the shared operating characteristic, and updating the shared operating characteristic based on the fused characteristic;
and returning to execute the step of fusing the first operation characteristic and the shared operation characteristic and updating the first operation characteristic based on the fused characteristic until a target shared operation characteristic meeting a preset characteristic interaction condition, a target first operation characteristic corresponding to the first interactive operation and a target second operation characteristic corresponding to the second interactive operation are obtained.
The preset feature interaction condition may be set according to an actual situation, which is not limited in this embodiment. For example, the preset feature interaction condition may specifically be that the number of updates reaches a preset number. In some embodiments, the preset feature interaction condition may be determined according to the number of layers of the feature extraction network in the content interaction prediction model.
The first operation characteristic and the shared operation characteristic can be fused through a gating network; there are various fusion manners, which are not limited in this embodiment, for example, the fusion manner may be a weighting operation, or a splicing operation. And inputting the fused features into the next layer of task-specific expert T, and updating the first operation features based on the output features of the next layer of task-specific expert T, specifically, determining the output features processed by the next layer of task-specific expert T as new first operation features.
The second operation characteristic and the shared operation characteristic can be fused through a gating network; there are various fusion manners, which are not limited in this embodiment, for example, the fusion manner may be a weighting operation, or a splicing operation. And inputting the fused features into the next layer of task-specific expert C, and updating the second operation features based on the output features of the next layer of task-specific expert C, specifically, determining the output features processed by the next layer of task-specific expert C as new second operation features.
The first operation characteristic, the second operation characteristic and the shared operation characteristic can be fused through the gating network; there are various fusion manners, which are not limited in this embodiment, for example, the fusion manner may be a weighting operation, or a splicing operation. And inputting the fused features into a next-layer task sharing expert, and updating the shared operation features based on the output features of the next-layer task sharing expert, wherein the output features processed by the next-layer task sharing expert can be determined as new shared operation features.
102. Based on the target first operation characteristic, determining an initial predicted interaction result of the target content on the first interaction operation.
Optionally, in this embodiment, the step "determining an initial predicted interaction result of the target content on the first interaction operation based on the target first operation feature" may include:
fusing the target sharing operation characteristic and the target first operation characteristic to obtain a first fused operation characteristic;
and determining an initial predicted interaction result of the target content on the first interaction operation based on the first fusion operation characteristic.
The target sharing operation feature and the target first operation feature may be fused through a gating network, where the fusion mode may be weighting operation or splicing processing, and the present embodiment is not limited to this. And the first fusion operation characteristics obtained by fusion are used as the input of a tower network T in the content interaction prediction model, and the initial prediction interaction result of the target content on the first interaction operation is obtained through the processing of the tower network T.
The tower network T may be a neural network structure, which may include a convolutional layer, a full connection layer, and the like, which is not limited in this embodiment. In particular, the tower network T may comprise a Multilayer Perceptron (MLP). And performing full connection processing on the first fusion operation characteristic through a multilayer perceptron, predicting the probability that the target content belongs to each preset interaction result in the first interaction operation, and determining the initial predicted interaction result of the target content in the first interaction operation according to the probability.
In some embodiments, the preset interaction result with the highest probability may be determined as the initial predicted interaction result of the target content on the first interaction operation; in other embodiments, a preset interaction result with a probability greater than a preset value may also be determined as an initial predicted interaction result of the target content in the first interaction operation.
For example, if the first interactive operation is the reading duration of the target content, the reading duration interval may be divided according to actual conditions, for example, the reading duration interval may be divided into three subintervals, i.e., the reading time is less than 3 minutes, the reading time is between 3 and 10 minutes, and the reading time is greater than 10 minutes, and the preset interactive result corresponding to the first interactive operation may include three conditions corresponding to the three subintervals.
For another example, the first interactive operation is a sharing operation on the target content, and the preset interactive result corresponding to the first interactive operation may include two situations of sharing and not sharing.
Optionally, in this embodiment, the step of "performing feature extraction on an interactive operation on the target content to obtain a target first operation feature and a target shared operation feature of the target content on a first interactive operation" may include:
performing feature extraction on interactive operation on the target content to obtain a target first operation feature of the target content on first interactive operation, a target second operation feature on second interactive operation and a target sharing operation feature;
the content interaction prediction method may further include:
and determining a predicted interaction result of the target content on the second interaction operation based on the target second operation characteristic.
In some embodiments, the step of determining a predicted interaction result of the target content on the second interaction operation based on the target second operation characteristic may include:
fusing the target sharing operation characteristic and the target second operation characteristic to obtain a second fused operation characteristic;
and determining a predicted interaction result of the target content on the second interaction operation based on the second fusion operation characteristic.
The target sharing operation feature and the target second operation feature may be fused through a gating network, where the fusion mode may be weighting operation or splicing processing, and the present embodiment is not limited to this. And the second fusion operation characteristics obtained by fusion are used as the input of a tower network C in the content interaction prediction model, and the predicted interaction result of the target content on the second interaction operation is obtained through the processing of the tower network C.
The tower network C may be a neural network structure, which may include a convolutional layer, a full connection layer, and the like, which is not limited in this embodiment. In particular, the tower network C may comprise a Multilayer Perceptron (MLP). And performing full connection processing on the second fusion operation characteristics through the multilayer perceptron, predicting the probability that the target content belongs to each preset interaction result in the second interaction operation, and determining the predicted interaction result of the target content in the second interaction operation according to the probability.
In some embodiments, the preset interaction result with the highest probability may be determined as the predicted interaction result of the target content on the second interaction operation; in other embodiments, the preset interaction result with the probability greater than the preset value may also be determined as the predicted interaction result of the target content in the second interaction operation.
For example, the second interaction operation is a click operation on the target content, and the preset interaction result corresponding to the second interaction operation may include two cases, namely a click and a non-click.
103. And performing logistic regression analysis on the target sharing operation characteristics to predict negative noise information generated by the second interactive operation on the first interactive operation.
In this embodiment, a negative noise modeling module in the content interaction prediction model may perform logistic regression analysis on the target sharing operation features; specifically, feature selection processing may be performed on the target sharing operation feature through a gate control network, the processed target sharing operation feature may be input to the negative noise modeling module, and the negative noise modeling module may perform logistic regression analysis on the processed target sharing operation feature to predict negative noise information generated by the second interactive operation on the first interactive operation.
The logistic regression analysis may specifically include performing sigmoid function or tanh function operation through a hidden layer in a Multilayer Perceptron (MLP).
In which a sigmoid Function, i.e., an S-shaped growth curve, may be used as an Activation Function (Activation Function) in a neural network or in a logistic regression process to map variables to a zero to one numerical range. the tanh function, i.e., the tanh tangent, may be used in neural networks in the field of deep learning as an activation function.
104. And correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation.
Wherein the negative noise information comprises a negative impact of the second interactive operation on the first interactive operation. The modification of the initial prediction interaction result may specifically be that the negative noise information is subtracted from the initial prediction interaction result, so that a target prediction interaction result of the target content in the first interaction operation is obtained, and the target prediction interaction result is a predicted value obtained by subtracting the negative influence.
Specifically, if the first interactive operation is the reading duration and the second interactive operation is the clicking operation, the negative impact can be subtracted from the original reading duration prediction value (i.e., the initial prediction interactive result) through correction, so as to achieve the purposes of relieving the negative impact of the clicking operation on the reading duration and strengthening the positive impact.
In a specific embodiment, the content interaction prediction method provided by the application can be applied to a content recommendation scene, and after a target prediction interaction result corresponding to each content on a first interaction operation is obtained, a target recommended content can be selected from each content according to the target prediction interaction result for recommendation.
The content interaction prediction model may be specifically provided to the content interaction prediction apparatus after being trained by another device, or may be trained by the content interaction prediction apparatus itself.
If the content interaction prediction device is trained by itself, before the step "feature extraction on the interaction operation is performed on the target content through a content interaction prediction model to obtain a target first operation feature and a target sharing operation feature of the target content on the first interaction operation", the content interaction prediction method may further include:
acquiring training data, wherein the training data comprises sample content, a first expected interaction result of the sample content on the first interaction operation, and a second expected interaction result on the second interaction operation;
extracting features of the sample content in interactive operation through a content interactive prediction model to obtain a target first operation feature of the sample content in first interactive operation, a target second operation feature of the sample content in second interactive operation and a target sharing operation feature;
determining an initial first actual interaction result of the sample content on the first interaction operation and a second actual interaction result on the second interaction operation based on the target first operation characteristic and the target second operation characteristic, respectively;
performing logistic regression analysis on the target sharing operation characteristics to predict actual negative noise information generated by the second interactive operation on the first interactive operation; correcting the initial first actual interaction result based on the actual negative noise information to obtain a target first actual interaction result;
and adjusting parameters of the content interaction prediction model according to the initial first actual interaction result, the target first actual interaction result, the first expected interaction result, the second actual interaction result and the second expected interaction result to obtain the trained content interaction prediction model.
The first expected interaction result may be an expected probability that the sample content belongs to each preset interaction result in the first interaction operation; the second expected interaction result may be an expected probability that the sample content belongs to each preset interaction result in the second interaction operation.
Optionally, in this embodiment, the step "adjusting parameters of the content interaction prediction model according to the initial first actual interaction result, the target first actual interaction result, the first expected interaction result, the second actual interaction result, and the second expected interaction result to obtain a trained content interaction prediction model" may include:
calculating a first loss value between the initial first actual interaction result and the first expected interaction result;
calculating a second loss value between the target first actual interaction result and the first expected interaction result;
calculating a third loss value between the second actual interaction result and the second expected interaction result;
and adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value and the third loss value to obtain a trained content interaction prediction model.
The training process specifically includes the steps of adjusting parameters of the content interaction prediction model by using a back propagation algorithm, and optimizing the parameters of the content interaction prediction model based on the first loss value, the second loss value and the third loss value, so that the first loss value, the second loss value and the third loss value meet preset loss conditions, and the trained content interaction prediction model is obtained. Specifically, the preset loss condition may be that the sum of the first loss value, the second loss value and the third loss value is less than a preset loss value, and the preset loss value may be set according to actual conditions.
There are various ways to calculate the loss value, which is not limited in this embodiment, for example, it may be a cross entropy loss function or a mean square error loss function.
In a specific embodimentIn an embodiment, the initial first actual interaction result is recorded as
Figure BDA0003745503740000201
The first expected interaction result is recorded as
Figure BDA0003745503740000202
The first actual interaction result of the target is recorded as
Figure BDA0003745503740000203
The second actual interaction result is recorded as
Figure BDA0003745503740000204
The second expected interaction result is recorded as
Figure BDA0003745503740000205
The calculation processes of the first loss value, the second loss value and the third loss value are respectively shown as an equation (6), an equation (7) and an equation (8):
Figure BDA0003745503740000206
Figure BDA0003745503740000207
Figure BDA0003745503740000208
wherein L is T Is a first loss value, L MTC Is the second loss value, L C Is the third loss value. S is an exposure sample data set, S + The sample data set clicked on is represented, and i represents the content of each sample.
Specifically, if the second interactive operation is a click operation, the method further includes
Figure BDA0003745503740000209
Indicating a genuine click-tag, usually by1 indicates a click, 0 indicates no click, L C Representing a loss of the click task; if the first interaction is reading time, the reading duration can be modeled as a multi-class problem, the continuous duration value is divided into a plurality of intervals,
Figure BDA00037455037400002010
a vector of true values corresponding to an interval j after discretizing the reading time into M groups is represented, the vector has values of 0 except for a value of 1 in the dimension of the group to which the true values belong T Indicating the loss of reading duration of the original multitask, L MTC Indicating a loss of reading time after correction.
For example, the reading time period can be divided into three groups, namely three subintervals, namely a reading time period of less than 3 minutes, a reading time period of 3 to 10 minutes and a reading time period of more than 10 minutes.
The step of adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value, and the third loss value to obtain the trained content interaction prediction model may include:
fusing the first loss value, the second loss value and the third loss value to obtain a total loss value;
and adjusting parameters of the content interaction prediction model based on the total loss value to obtain the trained content interaction prediction model.
There are various fusion methods, such as weighted fusion. Specifically, the calculation process of the total loss value L may be as shown in equation (9):
L＝L C +L T +L MTC (9)
in one embodiment, after adjusting the parameters of the content interaction prediction model based on the total loss value, the model may be retrained again by weakening the input features associated with the first interaction operation (e.g., the reading duration) during the training process, so that the model better models the real negative impact.
Optionally, in this embodiment, the content interaction prediction model includes a basic prediction module and a negative noise modeling module; the step of adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value, and the third loss value to obtain the trained content interaction prediction model may include:
adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value and the third loss value to obtain a pre-trained content interaction prediction model;
masking the sample content through a basic prediction module in a pre-trained content interaction prediction model to obtain target content information of which the correlation with the second interaction operation meets a preset correlation condition; performing feature extraction on interactive operation on the target content information to obtain target enhanced sharing operation features of the sample content;
predicting actual strengthened negative noise information generated by the second interactive operation on the first interactive operation based on the target strengthened sharing operation characteristics through a negative noise modeling module in a pre-trained content interactive prediction model;
and adjusting parameters of the negative noise modeling module based on the actual intensified negative noise information and the first expected interaction result to obtain a trained content interaction prediction model.
Wherein, the basic prediction module can be a part of the content interaction prediction model except the negative noise modeling module.
In order to make the learned negative influence of the second interactive operation more accurate, the representation of the shared expert can be intervened from the aspect of the input features, so that the representation mainly contains the knowledge of the second interactive operation, and the negative noise modeling module is induced to learn the negative influence with higher information content.
The preset association condition may be that the content information obtained by the mask processing does not include a feature that only has a direct influence on the first interaction operation, which is not limited in this embodiment.
In one embodiment, the first interaction is a reading duration, and the second interaction is a reading durationFor click operation, the content information of the sample content in each dimension can be divided into common features F normal (e.g., user identification Information (ID) and article identification information), exposure feature F exposure (e.g., title and cover pictures, which have an effect on click and reading duration) and post-click feature F post-click (e.g., the contents of an article that is viewed after clicking, which has a direct effect on the duration of reading).
In training the parameters of the negative noise modeling module, the impact of post-click features should be reduced and the impact of exposed features emphasized accordingly. Therefore, the negative noise modeling module can be more accurately close to the negative influence of clicking on the reading time by removing the input of the information characteristic (the characteristic after clicking) which predicts the reading time in a more positive direction. The specific way may be to click on the feature F post-click MASK processing is performed, and thus the processed target content information can be represented by the following equation (10):
f＝(F normal ,F exposure ,[MASK]) (10)
wherein, the masking process can process the feature value in the clicked feature into a null value of-1. The real negative influence is approached by weakening the input characteristics related to the reading time through the masking process.
Optionally, in this embodiment, before the step "based on the actual enhanced negative noise information and the first expected interaction result, adjust a parameter of the negative noise modeling module to obtain a trained content interaction prediction model", the method may further include:
performing feature extraction on interactive operation on the target content information through a basic prediction module in a pre-trained content interactive prediction model to obtain a target strengthened first operation feature of the sample content on first interactive operation;
determining an initial actual enhanced interaction result of the sample content on the first interaction operation based on the target enhanced first operation feature;
the step of adjusting parameters of the negative noise modeling module based on the actual enhanced negative noise information and the first expected interaction result to obtain a trained content interaction prediction model may include:
correcting the initial actual enhancement interaction result based on the actual enhancement negative noise information to obtain a target actual enhancement interaction result of the sample content on the first interaction operation;
and adjusting parameters of the negative noise modeling module based on the target actual enhanced interaction result and the first expected interaction result to obtain a trained content interaction prediction model.
The initial actual enhanced interaction result may be corrected by subtracting the actual enhanced negative noise information from the initial actual enhanced interaction result.
And then adjusting parameters of the negative noise modeling module based on the fourth loss value. Wherein, the fourth loss value can be calculated based on the cross entropy loss function, and the calculation process can refer to the above equation (7),
Figure BDA0003745503740000231
what is shown here is the target actual augmented interaction result.
In a specific embodiment, referring to the model structure diagram of fig. 1d, a process of model training is shown, where a left half of fig. 1d represents a process of adjusting parameters of the content interaction prediction model based on total loss, and a right half of fig. 1d represents a process of adjusting parameters of the content interaction prediction model based on the fourth loss value after masking sample content, which is specifically described as follows:
for the left half part, calculating an initial first actual interaction result and a target first actual interaction result of the sample content in a first interaction operation and a second actual interaction result in a second interaction operation to calculate a first loss value, a second loss value and a third loss value, and fusing the first loss value, the second loss value and the third loss value to obtain a total loss value; and then, based on the total loss value, adjusting parameters of the opaque part (or the part with low transparency) of the model on the left side of fig. 1d, that is, adjusting parameters of the part except the negative noise modeling module in the content interaction prediction model.
Then, referring to the right half, masking the clicked features to obtain target content information of the sample content, performing feature extraction on interactive operation on the target content information to obtain a target actual enhanced interactive result of the sample content on the first interactive operation, calculating to obtain a fourth loss value based on the target actual enhanced interactive result, and adjusting parameters of an opaque part (or a part with low transparency) of the model on the right side of fig. 1d based on the fourth loss value, that is, adjusting parameters of parts of the content interaction prediction model except for the tower network C, the tower network T, the task-specific expert C on the last layer and the task-specific expert T.
The content interaction prediction method can be used for scenes such as content recommendation, can be used for helping to relieve the interference of clicking on reading time or watching time in multi-task recommendation, and can also be used for relieving the interference of other multi-behaviors with dependency relationships, such as the interference of clicking on sharing. The method can capture the negative influence between targets through a negative noise modeling module, subtract the negative influence from an original estimated value to obtain an estimated value for relieving the negative influence, and finally use the estimated value after subtracting the negative influence.
In a specific embodiment, as shown in fig. 1c, the present embodiment may predict the interaction result of the target content on the first interaction (e.g. reading duration) and on the second interaction (e.g. clicking) through the content interaction prediction model. Wherein in particular the negative noise modelling module is used to learn the negative impact of the reading time task due to the click task.
The Negative noise Modeling module may also be referred to as a Negative Impact Modeling (NIM) module, and an input of the Negative noise Modeling module is an output g of a task sharing expert in the last layer S,L (x) As shown in formula (11):
g S,L (x)＝w S,L (g S,L-1 (x))S S,L (x) (11)
wherein S is S,L (x) Selecting only the task sharing expert of that layer, w S,L Is a weight function. Finally, the predicted value of the negative influence of the click on the reading time, namely the negative noise information can be obtained
Figure BDA0003745503740000241
Specifically, as shown in formula (12):
Figure BDA0003745503740000242
wherein, t NIN Representing the tower network to which the negative noise modeling module corresponds.
In particular, the amount of the solvent to be used,
Figure BDA0003745503740000243
indicating that the reading duration prediction is mainly affected by the click signal, if the original reading duration output in the multi-task learning framework is expressed as
Figure BDA0003745503740000244
Then, a predicted reading time value after removing the click influence can be obtained, as shown in equation (13):
Figure BDA0003745503740000245
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA0003745503740000246
for initial prediction of interaction results for reading duration
Figure BDA0003745503740000247
And obtaining a target prediction interaction result after correction.
The misclassified reading duration interval will be higher due to the negative impact of the click signal
Figure BDA0003745503740000248
Values are then estimated from the original estimates
Figure BDA0003745503740000249
Subtracting this value will result in a higher prediction probability for the correct reading time interval.
Wherein the original prediction of click and read durations
Figure BDA00037455037400002410
As shown in equation (14) and equation (15):
Figure BDA00037455037400002411
Figure BDA00037455037400002412
wherein, t C And t T Tower networks for predicting click and reading time periods, i.e., tower network C (tower C) and tower network T (tower T) in the model structure diagram of fig. 1C,
Figure BDA0003745503740000251
i.e. the predicted interaction result on the second interaction operation as described in the above embodiments,
Figure BDA0003745503740000252
i.e. the initial predicted interaction result on the first interaction operation as described in the above embodiment.
Wherein, a tower network can be constructed by using neural networks such as a multilayer perceptron MLP and the like; g C,L And g T,L And L is the layer number of the bottom expert module for the corresponding gating network.
In a specific embodiment, the content interaction prediction method provided by the application is significantly superior to the existing correlation model in the prediction of the reading time, and the prediction effect of the click task is better. The test effect on the log data of a certain recommendation system is shown in fig. 1e, where MTC (Multi-Task practical frame) is a model provided by the present application after including the negative impact modeling module, and MTC-fea is a model provided by the present application which includes the negative impact modeling module and is trained by using the features of MASK, that is, a model considering the negative impact of the feature level on the basis of MTC; NFM, deepFM, autoInt and AFN are single task models, MMOE, AITM and PLE are multi-task models, and compared with other models, the model MTC-fea provided by the application has the best effect on all indexes related to reading time.
The correlation indicators include mean absolute error-class (MAE _ class), root mean square error-class (RMSE _ class), recall (Recall), F1, mean Absolute Error (MAE), and Root Mean Square Error (RMSE). F1 is a comprehensive evaluation index, and the higher the F1 value is, the better the prediction effect is. AUC is a model evaluation index.
The estimation of the reading time is very important for the recommendation system, because the longer reading time generally represents that the target object has greater interest in the recommended content, the defect that the click may not reflect the real preference of the target object is effectively overcome, and the click only reflects the interest of the target object in the content title. Accurate reading duration estimation is beneficial to recommending the content really meeting the interest of the target object, so that the user experience is improved.
As can be seen from the above, the present embodiment can acquire the target content; extracting features of the target content in interactive operation to obtain target first operation features and target shared operation features of the target content in first interactive operation, wherein the target shared operation features are features shared by the first interactive operation and second interactive operation, and the second interactive operation is a front operation depended on by the first interactive operation; determining an initial predicted interaction result of the target content on the first interaction operation based on the target first operation characteristic; performing logistic regression analysis on the target sharing operation characteristics to predict negative noise information generated by the second interactive operation on the first interactive operation; and correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation. According to the method and the device, the predicted interactive result of the target content on the first interactive operation can be corrected by capturing the negative noise information generated by the second interactive operation on the first interactive operation, and the prediction accuracy of the interactive result on the first interactive operation is improved.
The method described in the foregoing embodiment will be described in further detail below by way of example in which the content interaction prediction apparatus is specifically integrated in a server.
An embodiment of the present application provides a content interaction prediction method, and as shown in fig. 2, a specific flow of the content interaction prediction method may be as follows:
201. the server acquires target content; and extracting features of the target content in interactive operation to obtain a target first operation feature of the target content in first interactive operation and a target sharing operation feature, wherein the target sharing operation feature is a feature shared by the first interactive operation and a second interactive operation, and the second interactive operation is a front operation depended on by the first interactive operation.
The second interactive operation is a front operation which is depended by the first interactive operation, the second interactive operation and the first interactive operation have dependency relationship in operation time, and the operation time of the second interactive operation is before the operation time of the first interactive operation. For example, in a specific scenario, the target content is content recommended to a target object, the second interaction operation is a click operation on the content, the first interaction operation is reading duration or a sharing operation for the content, and the like, predicting the interaction result in the second interaction operation may specifically be predicting whether the target object clicks the target content, and predicting the interaction result in the first interaction operation may specifically be predicting reading duration of the target object on the target content, or whether the target content is to be shared. It can be understood that the target object may read or share the target content only by clicking the target content, and therefore, the click is a preceding operation corresponding to the reading duration or the sharing.
Optionally, in this embodiment, the step of "performing feature extraction on the target content in the interactive operation to obtain a target first operation feature and a target shared operation feature of the target content in the first interactive operation" may include:
and performing feature extraction on the interactive operation on the target content to obtain a target first operation feature of the target content on the first interactive operation, a target second operation feature on the second interactive operation and a target sharing operation feature.
Wherein the target shared operation characteristic is a characteristic shared by the first interactive operation and the second interactive operation; the target first operational characteristic may be considered to be a unique characteristic of the first interaction and the target second operational characteristic may be considered to be a unique characteristic of the second interaction.
Optionally, in this embodiment, the step of "performing feature extraction on the target content in the interactive operation to obtain a target first operation feature and a target shared operation feature of the target content in the first interactive operation" may include:
and performing feature extraction on the interactive operation on the target content through a content interactive prediction model to obtain a target first operation feature and a target sharing operation feature of the target content on the first interactive operation.
In this embodiment, a target first operation feature of the target content on the first interactive operation, a target second operation feature on the second interactive operation, and a target sharing operation feature may be extracted through the content interaction prediction model.
Specifically, the content interaction prediction model is a multitask model, and may include a feature extraction network with a multilayer structure and a tower network corresponding to each task in the target multitask; each layer of the feature extraction network comprises a plurality of expert networks and gating networks corresponding to the tasks. For example, the content interaction prediction model may include a multi-layer feature extraction network and a tower network corresponding to both a prediction task corresponding to the first interaction and a prediction task corresponding to the second interaction.
Optionally, in this embodiment, the step of "performing feature extraction on the interactive operation on the target content to obtain a target first operation feature of the target content on the first interactive operation, a target second operation feature on the second interactive operation, and a target shared operation feature" may include:
extracting a first operation characteristic of the target content on a first interactive operation, a second operation characteristic on a second interactive operation and a shared operation characteristic;
and performing feature interaction processing on the first operation feature, the second operation feature and the shared operation feature to obtain a target first operation feature corresponding to the first interactive operation, a target second operation feature corresponding to the second interactive operation and a target shared operation feature.
Optionally, in this embodiment, the step of performing feature interaction processing on the first operation feature, the second operation feature, and the shared operation feature to obtain a target first operation feature corresponding to the first interactive operation, a target second operation feature corresponding to the second interactive operation, and a target shared operation feature may include:
fusing the first operating characteristic and the shared operating characteristic, and updating the first operating characteristic based on the fused characteristic;
fusing the second operating characteristic and the shared operating characteristic, and updating the second operating characteristic based on the fused characteristic;
fusing the first operating characteristic, the second operating characteristic and the shared operating characteristic, and updating the shared operating characteristic based on the fused characteristic;
and returning to execute the step of fusing the first operation characteristic and the shared operation characteristic and updating the first operation characteristic based on the fused characteristic until a target shared operation characteristic meeting a preset characteristic interaction condition, a target first operation characteristic corresponding to the first interactive operation and a target second operation characteristic corresponding to the second interactive operation are obtained.
The preset feature interaction condition may be set according to an actual situation, which is not limited in this embodiment. For example, the preset feature interaction condition may specifically be that the number of updates reaches a preset number. In some embodiments, the preset feature interaction condition may be determined according to the number of layers of the feature extraction network in the content interaction prediction model.
202. The server determines an initial predicted interaction result of the target content on the first interaction operation based on the target first operation characteristic.
Optionally, in this embodiment, the step of determining an initial predicted interaction result of the target content on the first interaction operation based on the target first operation feature may include:
fusing the target sharing operation characteristic and the target first operation characteristic to obtain a first fused operation characteristic;
and determining an initial predicted interaction result of the target content on the first interaction operation based on the first fusion operation characteristic.
The target sharing operation feature and the target first operation feature may be fused through a gating network, and the fusion manner may be a weighted operation, or a splicing process, which is not limited in this embodiment. And the first fusion operation characteristics obtained by fusion are used as the input of a tower network T in the content interaction prediction model, and the initial prediction interaction result of the target content on the first interaction operation is obtained through the processing of the tower network T.
The tower network T may be a neural network structure, which may include a convolutional layer, a full connection layer, and the like, which is not limited in this embodiment. In particular, the tower network T may comprise a Multilayer Perceptron (MLP). And performing full connection processing on the first fusion operation characteristic through a multilayer perceptron, predicting the probability that the target content belongs to each preset interaction result in the first interaction operation, and determining the initial predicted interaction result of the target content in the first interaction operation according to the probability.
In some embodiments, the preset interaction result with the highest probability may be determined as the initial predicted interaction result of the target content on the first interaction operation; in other embodiments, a preset interaction result with a probability greater than a preset value may also be determined as an initial predicted interaction result of the target content in the first interaction operation.
Optionally, in this embodiment, the step of "performing feature extraction on an interactive operation on the target content to obtain a target first operation feature and a target shared operation feature of the target content on a first interactive operation" may include:
performing feature extraction on interactive operation on the target content to obtain a target first operation feature of the target content on first interactive operation, a target second operation feature on second interactive operation and a target sharing operation feature;
the content interaction prediction method may further include:
and determining a predicted interaction result of the target content on the second interaction operation based on the target second operation characteristic.
In some embodiments, the step of determining a predicted interaction result of the target content on the second interaction operation based on the target second operation characteristic may include:
fusing the target sharing operation characteristic and the target second operation characteristic to obtain a second fused operation characteristic;
and determining a predicted interaction result of the target content on the second interaction operation based on the second fusion operation characteristic.
The target sharing operation feature and the target second operation feature may be fused through a gating network, and the fusion manner may be a weighted operation, or a splicing process, which is not limited in this embodiment. And the second fusion operation characteristics obtained by fusion are used as the input of a tower network C in the content interaction prediction model, and the prediction interaction result of the target content on the second interaction operation is obtained through the processing of the tower network C.
203. And the server performs logistic regression analysis on the target sharing operation characteristics to predict negative noise information generated by the second interactive operation on the first interactive operation.
In this embodiment, a negative noise modeling module in the content interaction prediction model may perform logistic regression analysis on the target sharing operation features; specifically, feature selection processing may be performed on the target sharing operation feature through a gate control network, the processed target sharing operation feature may be input to the negative noise modeling module, and the negative noise modeling module may perform logistic regression analysis on the processed target sharing operation feature to predict negative noise information generated by the second interactive operation on the first interactive operation.
The logistic regression analysis may specifically include performing sigmoid function or tanh function operation through a hidden layer in a Multilayer Perceptron (MLP).
The sigmoid Function, i.e., the sigmoid growth curve, may be used as an Activation Function (Activation Function) in a neural network or in a logistic regression process to map variables to a numerical range from zero to one. the tanh function, namely hyperbolic tangent, can be used as an activation function in a neural network in the deep learning field.
204. And the server corrects the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation.
Wherein the negative noise information comprises a negative influence of the second interactive operation on the first interactive operation. The modification of the initial prediction interaction result may specifically be that the negative noise information is subtracted from the initial prediction interaction result, so that a target prediction interaction result of the target content in the first interaction operation is obtained, and the target prediction interaction result is a predicted value obtained by subtracting the negative influence.
The content interaction prediction model may be specifically provided to the content interaction prediction apparatus after being trained by another device, or may be trained by the content interaction prediction apparatus itself.
If the content interaction prediction device is trained by itself, before the step "feature extraction on the interaction operation is performed on the target content through a content interaction prediction model to obtain a target first operation feature and a target sharing operation feature of the target content on the first interaction operation", the content interaction prediction method may further include:
acquiring training data, wherein the training data comprises sample content, a first expected interaction result of the sample content on the first interaction operation, and a second expected interaction result on the second interaction operation;
performing feature extraction on interactive operation on the sample content through a content interactive prediction model to obtain a target first operation feature of the sample content on first interactive operation, a target second operation feature of the sample content on second interactive operation and a target sharing operation feature;
determining an initial first actual interaction result of the sample content on the first interaction operation and a second actual interaction result on the second interaction operation based on the target first operation characteristic and the target second operation characteristic, respectively;
performing logistic regression analysis on the target sharing operation characteristics to predict actual negative noise information generated by the second interactive operation on the first interactive operation; correcting the initial first actual interaction result based on the actual negative noise information to obtain a target first actual interaction result;
and adjusting parameters of the content interaction prediction model according to the initial first actual interaction result, the target first actual interaction result, the first expected interaction result, the second actual interaction result and the second expected interaction result to obtain a trained content interaction prediction model.
The first expected interaction result may be an expected probability that the sample content belongs to each preset interaction result in the first interaction operation; the second expected interaction result may be an expected probability that the sample content belongs to each preset interaction result in the second interaction operation.
Optionally, in this embodiment, the step "adjusting parameters of the content interaction prediction model according to the initial first actual interaction result, the target first actual interaction result, the first expected interaction result, the second actual interaction result, and the second expected interaction result to obtain a trained content interaction prediction model" may include:
calculating a first loss value between the initial first actual interaction result and the first expected interaction result;
calculating a second loss value between the target first actual interaction result and the first expected interaction result;
calculating a third loss value between the second actual interaction result and the second expected interaction result;
and adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value and the third loss value to obtain a trained content interaction prediction model.
The training process specifically includes the steps of adjusting parameters of the content interaction prediction model by using a back propagation algorithm, and optimizing the parameters of the content interaction prediction model based on the first loss value, the second loss value and the third loss value, so that the first loss value, the second loss value and the third loss value meet preset loss conditions, and the trained content interaction prediction model is obtained. Specifically, the preset loss condition may be that the sum of the first loss value, the second loss value and the third loss value is less than a preset loss value, and the preset loss value may be set according to actual conditions.
There are various ways to calculate the loss value, which is not limited in this embodiment, for example, it may be a cross entropy loss function or a mean square error loss function.
In one embodiment, after adjusting the parameters of the content interaction prediction model based on the total loss value, the model may be retrained again by weakening the input features associated with the first interaction operation (e.g., the reading duration) during the training process, so that the model better models the real negative impact.
Optionally, in this embodiment, the content interaction prediction model includes a basic prediction module and a negative noise modeling module; the step of adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value, and the third loss value to obtain the trained content interaction prediction model may include:
adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value and the third loss value to obtain a pre-trained content interaction prediction model;
masking the sample content through a basic prediction module in a pre-trained content interaction prediction model to obtain target content information of which the correlation with the second interaction operation meets a preset correlation condition; performing feature extraction on interactive operation on the target content information to obtain target enhanced sharing operation features of the sample content;
predicting actual strengthened negative noise information generated by the second interactive operation on the first interactive operation based on the target strengthened sharing operation characteristics through a negative noise modeling module in a pre-trained content interactive prediction model;
and adjusting parameters of the negative noise modeling module based on the actual intensified negative noise information and the first expected interaction result to obtain a trained content interaction prediction model.
Wherein the basic prediction module can be a part of the content interaction prediction model except the negative noise modeling module.
Wherein, in order to make the learned negative impact of the second interactive operation more accurate, the representation of the sharing expert may be intervened from the perspective of the input features to mainly contain the knowledge of the second interactive operation, thereby inducing the negative noise modeling module to learn a higher negative impact of the information amount.
The preset association condition may be that the content information obtained by the mask processing does not include a feature that only has a direct influence on the first interaction operation, which is not limited in this embodiment.
Optionally, in this embodiment, before the step "based on the actual enhanced negative noise information and the first expected interaction result, adjust a parameter of the negative noise modeling module to obtain a trained content interaction prediction model", the method may further include:
performing feature extraction on interactive operation on the target content information through a basic prediction module in a pre-trained content interactive prediction model to obtain a target strengthened first operation feature of the sample content on first interactive operation;
determining an initial actual enhanced interaction result of the sample content on the first interaction operation based on the target enhanced first operation feature;
the step of adjusting parameters of the negative noise modeling module based on the actual enhanced negative noise information and the first expected interaction result to obtain a trained content interaction prediction model may include:
based on the actual enhanced negative noise information, correcting the initial actual enhanced interaction result to obtain a target actual enhanced interaction result of the sample content on the first interaction operation;
and adjusting parameters of the negative noise modeling module based on the target actual enhanced interaction result and the first expected interaction result to obtain a trained content interaction prediction model.
The initial actual enhanced interaction result may be corrected by subtracting the actual enhanced negative noise information from the initial actual enhanced interaction result.
As can be seen from the above, the present embodiment may obtain the target content through the server; extracting features of the target content in interactive operation to obtain target first operation features and target shared operation features of the target content in first interactive operation, wherein the target shared operation features are features shared by the first interactive operation and second interactive operation, and the second interactive operation is a front operation depended on by the first interactive operation; determining an initial predicted interaction result of the target content on the first interaction operation based on the target first operation characteristic; performing logistic regression analysis on the target sharing operation characteristics to predict negative noise information generated by the second interactive operation on the first interactive operation; and correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation. According to the method and the device, the predicted interactive result of the target content on the first interactive operation can be corrected by capturing the negative noise information generated by the second interactive operation on the first interactive operation, and the prediction accuracy of the interactive result on the first interactive operation is improved.
In order to better implement the above method, an embodiment of the present application further provides a content interaction prediction apparatus, as shown in fig. 3, the content interaction prediction apparatus may include an obtaining unit 301, a determining unit 302, a predicting unit 303, and a correcting unit 304, as follows:
(1) An acquisition unit 301;
an acquisition unit configured to acquire target content; and extracting features of the target content in interactive operation to obtain a target first operation feature of the target content in first interactive operation and a target sharing operation feature, wherein the target sharing operation feature is a feature shared by the first interactive operation and a second interactive operation, and the second interactive operation is a front operation depended on by the first interactive operation.
Optionally, in some embodiments of the application, the obtaining unit may be specifically configured to perform feature extraction on an interactive operation on the target content, so as to obtain a target first operation feature of the target content on a first interactive operation, a target second operation feature on a second interactive operation, and a target sharing operation feature;
the content interaction prediction apparatus may further include a result determination unit as follows:
the result determining unit is used for determining a predicted interaction result of the target content on the second interaction operation based on the target second operation characteristic.
Optionally, in some embodiments of the present application, the obtaining unit may include an extracting subunit and an interacting subunit, as follows:
the extracting subunit is configured to extract a first operation feature of the target content in a first interactive operation, a second operation feature of the target content in a second interactive operation, and a shared operation feature;
and the interaction subunit is configured to perform feature interaction processing on the first operation feature, the second operation feature, and the shared operation feature to obtain a target first operation feature corresponding to the first interactive operation, a target second operation feature corresponding to the second interactive operation, and a target shared operation feature.
Optionally, in some embodiments of the present application, the interaction subunit may be specifically configured to fuse the first operation feature and the shared operation feature, and update the first operation feature based on the fused feature; fusing the second operating characteristic and the shared operating characteristic, and updating the second operating characteristic based on the fused characteristic; fusing the first operating characteristic, the second operating characteristic and the shared operating characteristic, and updating the shared operating characteristic based on the fused characteristic; and returning to execute the step of fusing the first operation characteristic and the shared operation characteristic and updating the first operation characteristic based on the fused characteristic until a target shared operation characteristic meeting a preset characteristic interaction condition, a target first operation characteristic corresponding to the first interactive operation and a target second operation characteristic corresponding to the second interactive operation are obtained.
(2) A determination unit 302;
a determining unit, configured to determine, based on the target first operation feature, an initial predicted interaction result of the target content on the first interaction operation.
Optionally, in some embodiments of the present application, the determining unit includes a fusion subunit and a determining subunit, as follows:
the fusion subunit is configured to fuse the target shared operation feature and the target first operation feature to obtain a first fusion operation feature;
and the determining subunit is used for determining an initial predicted interaction result of the target content on the first interaction operation based on the first fusion operation characteristic.
(3) A prediction unit 303;
and the prediction unit is used for carrying out logistic regression analysis on the target sharing operation characteristics so as to predict the negative noise information generated by the second interactive operation on the first interactive operation.
(4) A correction unit 304;
and the correcting unit is used for correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation.
Optionally, in some embodiments of the application, the obtaining unit may be specifically configured to perform feature extraction on an interactive operation on the target content through a content interactive prediction model, so as to obtain a target first operation feature and a target sharing operation feature of the target content on a first interactive operation.
Optionally, in some embodiments of the present application, the content interaction prediction apparatus may further include a training unit, where the training unit is configured to train the content interaction prediction model; specifically, the training unit may include a data acquisition subunit, a feature extraction subunit, an interaction result determination subunit, an analysis subunit, and an adjustment subunit, as follows:
the data acquisition subunit is configured to acquire training data, where the training data includes sample content, a first expected interaction result of the sample content on the first interaction operation, and a second expected interaction result on the second interaction operation;
the characteristic extraction subunit is used for carrying out characteristic extraction on the sample content in interactive operation through a content interactive prediction model to obtain a target first operation characteristic of the sample content in first interactive operation, a target second operation characteristic in second interactive operation and a target sharing operation characteristic;
an interaction result determining subunit, configured to determine, based on the target first operation feature and the target second operation feature, an initial first actual interaction result of the sample content on the first interaction operation and a second actual interaction result on the second interaction operation, respectively;
the analysis subunit is configured to perform logistic regression analysis on the target sharing operation feature to predict actual negative noise information generated by the second interactive operation on the first interactive operation; correcting the initial first actual interaction result based on the actual negative noise information to obtain a target first actual interaction result;
and the adjusting subunit is configured to adjust parameters of the content interaction prediction model according to the initial first actual interaction result, the target first actual interaction result, the first expected interaction result, the second actual interaction result, and the second expected interaction result, so as to obtain the trained content interaction prediction model.
Optionally, in some embodiments of the application, the adjusting subunit may be specifically configured to calculate a first loss value between the initial first actual interaction result and the first expected interaction result; calculating a second loss value between the target first actual interaction result and the first expected interaction result; calculating a third loss value between the second actual interaction result and the second expected interaction result; and adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value and the third loss value to obtain a trained content interaction prediction model.
Optionally, in some embodiments of the present application, the content interaction prediction model includes a base prediction module and a negative noise modeling module; the step of adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value, and the third loss value to obtain the trained content interaction prediction model may include:
adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value and the third loss value to obtain a pre-trained content interaction prediction model;
masking the sample content through a basic prediction module in a pre-trained content interaction prediction model to obtain target content information of which the relevance with the second interaction operation meets a preset relevance condition; performing feature extraction on interactive operation on the target content information to obtain target enhanced sharing operation features of the sample content;
predicting actual strengthened negative noise information generated by the second interactive operation on the first interactive operation based on the target strengthened sharing operation characteristics through a negative noise modeling module in a pre-trained content interactive prediction model;
and adjusting parameters of the negative noise modeling module based on the actual intensified negative noise information and the first expected interaction result to obtain a trained content interaction prediction model.
Optionally, in some embodiments of the application, before the step "adjusting parameters of the negative noise modeling module based on the actual enhanced negative noise information and the first expected interaction result to obtain a trained content interaction prediction model", the method may further include:
performing feature extraction on interactive operation on the target content information through a basic prediction module in a pre-trained content interactive prediction model to obtain a target strengthened first operation feature of the sample content on first interactive operation;
determining an initial actual enhanced interaction result of the sample content on the first interaction operation based on the target enhanced first operation feature;
the step of adjusting parameters of the negative noise modeling module based on the actual enhanced negative noise information and the first expected interaction result to obtain a trained content interaction prediction model may include:
based on the actual enhanced negative noise information, correcting the initial actual enhanced interaction result to obtain a target actual enhanced interaction result of the sample content on the first interaction operation;
and adjusting parameters of the negative noise modeling module based on the target actual enhanced interaction result and the first expected interaction result to obtain a trained content interaction prediction model.
As can be seen from the above, the present embodiment may acquire target content through the acquisition unit 301; extracting features of the target content in interactive operation to obtain target first operation features and target shared operation features of the target content in first interactive operation, wherein the target shared operation features are features shared by the first interactive operation and second interactive operation, and the second interactive operation is a front operation depended on by the first interactive operation; determining, by the determining unit 302, an initial predicted interaction result of the target content on the first interaction operation based on the target first operation feature; performing logistic regression analysis on the target sharing operation features through a prediction unit 303 to predict negative noise information generated by the second interactive operation on the first interactive operation; and modifying the initial predicted interaction result by a modifying unit 304 based on the negative noise information to obtain a target predicted interaction result of the target content on the first interaction operation. According to the method and the device, the predicted interactive result of the target content on the first interactive operation can be corrected by capturing the negative noise information generated by the second interactive operation on the first interactive operation, and the prediction accuracy of the interactive result on the first interactive operation is improved.
An electronic device according to an embodiment of the present application is further provided, as shown in fig. 4, which shows a schematic structural diagram of the electronic device according to the embodiment of the present application, where the electronic device may be a terminal or a server, and specifically:
the electronic device may include components such as a processor 401 of one or more processing cores, memory 402 of one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 4 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. Wherein:
the processor 401 is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, and performs various functions of the electronic device and processes data by operating or executing software programs and/or modules stored in the memory 402 and calling data stored in the memory 402. Alternatively, processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 401.
The memory 402 may be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by operating the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 402 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 access to the memory 402.
The electronic device further comprises a power supply 403 for supplying power to the various components, and preferably, the power supply 403 is logically connected to the processor 401 through a power management system, so that functions of managing charging, discharging, and power consumption are realized through the power management system. The power supply 403 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.
The electronic device may further include an input unit 404, and the input unit 404 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
Although not shown, the electronic device may further include a display unit and the like, which are not described in detail herein. Specifically, in this embodiment, the processor 401 in the electronic device loads the executable file corresponding to the process of one or more application programs into the memory 402 according to the following instructions, and the processor 401 runs the application programs stored in the memory 402, thereby implementing various functions as follows:
acquiring target content; extracting features of the target content in interactive operation to obtain a target first operation feature and a target shared operation feature of the target content in first interactive operation, wherein the target shared operation feature is a feature shared by the first interactive operation and a second interactive operation, and the second interactive operation is a preposed operation depended on by the first interactive operation; determining an initial predicted interaction result of the target content on the first interaction operation based on the target first operation characteristic; performing logistic regression analysis on the target sharing operation characteristics to predict negative noise information generated by the second interactive operation on the first interactive operation; and correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
As can be seen from the above, the present embodiment can acquire the target content; extracting features of the target content in interactive operation to obtain target first operation features and target shared operation features of the target content in first interactive operation, wherein the target shared operation features are features shared by the first interactive operation and second interactive operation, and the second interactive operation is a front operation depended on by the first interactive operation; determining an initial predicted interaction result of the target content on the first interaction operation based on the target first operation characteristic; performing logistic regression analysis on the target sharing operation characteristics to predict negative noise information generated by the second interactive operation on the first interactive operation; and correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation. According to the method and the device, the predicted interactive result of the target content on the first interactive operation can be corrected by capturing the negative noise information generated by the second interactive operation on the first interactive operation, and the prediction accuracy of the interactive result on the first interactive operation is improved.
It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.
To this end, embodiments of the present application provide a computer-readable storage medium, in which a plurality of instructions are stored, where the instructions can be loaded by a processor to execute the steps in any one of the content interaction prediction methods provided in the embodiments of the present application. For example, the instructions may perform the steps of:
acquiring target content; extracting features of the target content in interactive operation to obtain a target first operation feature and a target shared operation feature of the target content in first interactive operation, wherein the target shared operation feature is a feature shared by the first interactive operation and a second interactive operation, and the second interactive operation is a preposed operation depended on by the first interactive operation; determining an initial predicted interaction result of the target content on the first interaction operation based on the target first operation characteristic; performing logistic regression analysis on the target sharing operation characteristics to predict negative noise information generated by the second interactive operation on the first interactive operation; and correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
Wherein the computer-readable storage medium may include: read Only Memory (ROM), random Access Memory (RAM), magnetic or optical disks, and the like.
Since the instructions stored in the computer-readable storage medium may execute the steps in any content interaction prediction method provided in the embodiments of the present application, beneficial effects that can be achieved by any content interaction prediction method provided in the embodiments of the present application may be achieved, which are detailed in the foregoing embodiments and will not be described herein again.
According to an aspect of the application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions are read by a processor of a computer device from a computer-readable storage medium, and the computer instructions are executed by the processor to cause the computer device to perform the methods provided in the various alternative implementations of the content interaction prediction aspect described above.
The content interaction prediction method and the related device provided by the embodiment of the present application are described in detail above, and a specific example is applied in the present application to explain the principle and the embodiment of the present application, and the description of the above embodiment is only used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims (14)

1. A method for content interaction prediction, comprising:
acquiring target content; extracting features of the target content in interactive operation to obtain a target first operation feature and a target shared operation feature of the target content in first interactive operation, wherein the target shared operation feature is a feature shared by the first interactive operation and a second interactive operation, and the second interactive operation is a preposed operation depended on by the first interactive operation;
determining an initial predicted interaction result of the target content on the first interaction operation based on the target first operation characteristic;
performing logistic regression analysis on the target sharing operation characteristics to predict negative noise information generated by the second interactive operation on the first interactive operation;
and correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation.
2. The method according to claim 1, wherein the performing feature extraction on the target content in an interactive operation to obtain a target first operation feature and a target sharing operation feature of the target content in a first interactive operation includes:
performing feature extraction on interactive operation on the target content to obtain a target first operation feature of the target content on first interactive operation, a target second operation feature on second interactive operation and a target sharing operation feature;
the method further comprises the following steps:
and determining a predicted interaction result of the target content on the second interaction operation based on the target second operation characteristic.
3. The method of claim 2, wherein the performing feature extraction on the target content to obtain a target first operation feature on a first interactive operation, a target second operation feature on a second interactive operation, and a target sharing operation feature of the target content comprises:
extracting a first operation characteristic of the target content on a first interactive operation, a second operation characteristic on a second interactive operation and a shared operation characteristic;
and performing feature interaction processing on the first operation feature, the second operation feature and the shared operation feature to obtain a target first operation feature corresponding to the first interactive operation, a target second operation feature corresponding to the second interactive operation and a target shared operation feature.
4. The method according to claim 3, wherein the performing feature interaction processing on the first operation feature, the second operation feature, and the shared operation feature to obtain a target first operation feature corresponding to the first interactive operation, a target second operation feature corresponding to the second interactive operation, and a target shared operation feature comprises:
fusing the first operating characteristic and the shared operating characteristic, and updating the first operating characteristic based on the fused characteristic;
fusing the second operating characteristic and the shared operating characteristic, and updating the second operating characteristic based on the fused characteristic;
fusing the first operating characteristic, the second operating characteristic and the shared operating characteristic, and updating the shared operating characteristic based on the fused characteristic;
and returning to execute the step of fusing the first operation characteristic and the shared operation characteristic and updating the first operation characteristic based on the fused characteristic until a target shared operation characteristic meeting a preset characteristic interaction condition, a target first operation characteristic corresponding to the first interactive operation and a target second operation characteristic corresponding to the second interactive operation are obtained.
5. The method of claim 1, wherein determining an initial predicted interaction result of the target content on the first interaction operation based on the target first operational characteristic comprises:
fusing the target sharing operation characteristic and the target first operation characteristic to obtain a first fused operation characteristic;
determining an initial predicted interaction result of the target content on the first interaction operation based on the first fusion operation characteristic.
6. The method according to claim 1, wherein the performing feature extraction on the target content in an interactive operation to obtain a target first operation feature and a target sharing operation feature of the target content in a first interactive operation includes:
and performing feature extraction on the interactive operation on the target content through a content interactive prediction model to obtain a target first operation feature and a target sharing operation feature of the target content on the first interactive operation.
7. The method according to claim 6, wherein before performing feature extraction on the target content in the interactive operation through a content interaction prediction model to obtain a target first operation feature and a target sharing operation feature of the target content in the first interactive operation, the method further comprises:
acquiring training data, wherein the training data comprises sample content, a first expected interaction result of the sample content on the first interaction operation, and a second expected interaction result on the second interaction operation;
extracting features of the sample content in interactive operation through a content interactive prediction model to obtain a target first operation feature of the sample content in first interactive operation, a target second operation feature of the sample content in second interactive operation and a target sharing operation feature;
determining an initial first actual interaction result of the sample content on the first interaction operation and a second actual interaction result on the second interaction operation based on the target first operation characteristic and the target second operation characteristic, respectively;
performing logistic regression analysis on the target sharing operation characteristics to predict actual negative noise information generated by the second interactive operation on the first interactive operation; correcting the initial first actual interaction result based on the actual negative noise information to obtain a target first actual interaction result;
and adjusting parameters of the content interaction prediction model according to the initial first actual interaction result, the target first actual interaction result, the first expected interaction result, the second actual interaction result and the second expected interaction result to obtain a trained content interaction prediction model.
8. The method of claim 7, wherein the adjusting parameters of the content interaction prediction model according to the initial first actual interaction result, the target first actual interaction result, the first expected interaction result, the second actual interaction result, and the second expected interaction result to obtain a trained content interaction prediction model comprises:
calculating a first loss value between the initial first actual interaction result and the first expected interaction result;
calculating a second loss value between the target first actual interaction result and the first expected interaction result;
calculating a third loss value between the second actual interaction result and the second expected interaction result;
and adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value and the third loss value to obtain a trained content interaction prediction model.
9. The method of claim 8, wherein the content interaction prediction model comprises a base prediction module and a negative noise modeling module; adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value and the third loss value to obtain a trained content interaction prediction model, including:
adjusting parameters of the content interaction prediction model according to the first loss value, the second loss value and the third loss value to obtain a pre-trained content interaction prediction model;
masking the sample content through a basic prediction module in a pre-trained content interaction prediction model to obtain target content information of which the correlation with the second interaction operation meets a preset correlation condition; performing feature extraction on interactive operation on the target content information to obtain target enhanced sharing operation features of the sample content;
predicting actual reinforced negative noise information generated by the second interactive operation on the first interactive operation based on the target reinforced sharing operation characteristic through a negative noise modeling module in a pre-trained content interactive prediction model;
and adjusting parameters of the negative noise modeling module based on the actual intensified negative noise information and the first expected interaction result to obtain a trained content interaction prediction model.
10. The method of claim 9, wherein before the adjusting parameters of the negative noise modeling module based on the actual enhanced negative noise information and the first expected interaction result to obtain the trained content interaction prediction model, the method further comprises:
performing feature extraction on the target content information in interactive operation through a basic prediction module in a pre-trained content interactive prediction model to obtain a target reinforced first operation feature of the sample content in first interactive operation;
determining an initial actual enhanced interaction result of the sample content on the first interaction operation based on the target enhanced first operation feature;
adjusting parameters of the negative noise modeling module based on the actual reinforced negative noise information and the first expected interaction result to obtain a trained content interaction prediction model, including:
based on the actual enhanced negative noise information, correcting the initial actual enhanced interaction result to obtain a target actual enhanced interaction result of the sample content on the first interaction operation;
and adjusting parameters of the negative noise modeling module based on the target actual enhanced interaction result and the first expected interaction result to obtain a trained content interaction prediction model.
11. A content interaction prediction apparatus, comprising:
an acquisition unit configured to acquire target content; extracting features of the target content in interactive operation to obtain a target first operation feature and a target shared operation feature of the target content in first interactive operation, wherein the target shared operation feature is a feature shared by the first interactive operation and a second interactive operation, and the second interactive operation is a preposed operation depended on by the first interactive operation;
a determining unit, configured to determine, based on the target first operation feature, an initial predicted interaction result of the target content on the first interaction operation;
the prediction unit is used for carrying out logistic regression analysis on the target sharing operation characteristics so as to predict negative noise information generated by the second interactive operation on the first interactive operation;
and the correcting unit is used for correcting the initial prediction interaction result based on the negative noise information to obtain a target prediction interaction result of the target content on the first interaction operation.
12. An electronic device comprising a memory and a processor; the memory stores an application program, and the processor is configured to execute the application program in the memory to perform the operations of the content interaction prediction method according to any one of claims 1 to 10.
13. A computer-readable storage medium storing instructions adapted to be loaded by a processor to perform the steps of the content interaction prediction method according to any one of claims 1 to 10.
14. A computer program product comprising a computer program or instructions, characterized in that the computer program or instructions, when executed by a processor, implement the steps in the content interaction prediction method of any one of claims 1 to 10.
CN202210830680.4A 2022-07-14 2022-07-14 Content interaction prediction method and related equipment Pending CN115168720A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210830680.4A CN115168720A (en) 2022-07-14 2022-07-14 Content interaction prediction method and related equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210830680.4A CN115168720A (en) 2022-07-14 2022-07-14 Content interaction prediction method and related equipment

Publications (1)

Publication Number Publication Date
CN115168720A true CN115168720A (en) 2022-10-11

Family

ID=83495817

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210830680.4A Pending CN115168720A (en) 2022-07-14 2022-07-14 Content interaction prediction method and related equipment

Country Status (1)

Country Link
CN (1) CN115168720A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116911913A (en) * 2023-09-12 2023-10-20 深圳须弥云图空间科技有限公司 Method and device for predicting interaction result
CN117556150A (en) * 2024-01-11 2024-02-13 腾讯科技（深圳）有限公司 Multi-target prediction method, device, equipment and storage medium

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116911913A (en) * 2023-09-12 2023-10-20 深圳须弥云图空间科技有限公司 Method and device for predicting interaction result
CN116911913B (en) * 2023-09-12 2024-02-20 深圳须弥云图空间科技有限公司 Method and device for predicting interaction result
CN117556150A (en) * 2024-01-11 2024-02-13 腾讯科技（深圳）有限公司 Multi-target prediction method, device, equipment and storage medium
CN117556150B (en) * 2024-01-11 2024-03-15 腾讯科技（深圳）有限公司 Multi-target prediction method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN111897941B (en) Dialogue generation method, network training method, device, storage medium and equipment
US20190354868A1 (en) Multi-task neural networks with task-specific paths
CN111741330B (en) Video content evaluation method and device, storage medium and computer equipment
CN112052948B (en) Network model compression method and device, storage medium and electronic equipment
CN115168720A (en) Content interaction prediction method and related equipment
CN109816438B (en) Information pushing method and device
CN112221159B (en) Virtual item recommendation method and device and computer readable storage medium
CN110795944A (en) Recommended content processing method and device, and emotion attribute determining method and device
CN111708823B (en) Abnormal social account identification method and device, computer equipment and storage medium
CN112395515B (en) Information recommendation method and device, computer equipment and storage medium
CN111382190A (en) Object recommendation method and device based on intelligence and storage medium
CN114330510A (en) Model training method and device, electronic equipment and storage medium
CN111046655B (en) Data processing method and device and computer readable storage medium
CN116992151A (en) Online course recommendation method based on double-tower graph convolution neural network
CN114896519A (en) Early rumor detection method and device based on position characteristics
CN115168722A (en) Content interaction prediction method and related equipment
CN115423016A (en) Training method of multi-task prediction model, multi-task prediction method and device
CN114548382A (en) Migration training method, device, equipment, storage medium and program product
CN114611990A (en) Method and device for evaluating contribution rate of element system of network information system
Etefaghi et al. AdaInNet: an adaptive inference engine for distributed deep neural networks offloading in IoT-FOG applications based on reinforcement learning
CN117556150B (en) Multi-target prediction method, device, equipment and storage medium
CN116883673B (en) Semantic segmentation model training method, device, equipment and storage medium
CN117711001B (en) Image processing method, device, equipment and medium
CN113392221B (en) Method and related device for processing thin entity
CN118094233A (en) Content processing model integration method and related equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination