CN116204709A

CN116204709A - Data processing method and related device

Info

Publication number: CN116204709A
Application number: CN202211733957.8A
Authority: CN
Inventors: 张琪; 夏雪松; 李璟洁; 唐睿明; 董振华; 张瑞
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2022-12-30
Filing date: 2022-12-30
Publication date: 2023-06-02

Abstract

The data processing method can be applied to the field of information recommendation, and comprises the following steps: acquiring a first sample, wherein the first sample comprises first data; the first data is user attribute, article attribute or context information; obtaining a first embedded vector corresponding to the first data from each embedded token in a plurality of embedded tokens; determining a first weight corresponding to each first embedded vector based on the information of the target recommended scene; the first weight is used for fusing a plurality of first embedded vectors to obtain a first fused vector; and obtaining a recommendation result through a recommendation model at least according to the first fusion vector. The multiple embedded vectors are combined through weight determination, so that shared knowledge among fields can be captured, and embedded vectors specific to the fields can be combined, commonalities among the fields can be learned, differences among the fields can be captured, and recommendation accuracy of a recommendation model is improved.

Description

Data processing method and related device

Technical Field

The present disclosure relates to the field of artificial intelligence, and in particular, to a data processing method and related apparatus.

Background

Artificial intelligence (artificial intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use the knowledge to obtain optimal results. In other words, artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar manner to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, enables the machines to have functions of sensing, reasoning and decision.

The selection rate prediction (or referred to as click rate prediction) refers to predicting the probability of selecting an item by a user under a specific environment. For example, in recommendation systems for applications such as application stores and online advertisements, selectivity prediction plays a key role; the method can achieve maximization of the income of enterprises and improvement of user satisfaction through the selection rate prediction, and the recommendation system needs to consider the selection rate of the user on the articles and the price of the articles at the same time, wherein the selection rate is obtained through the prediction of the recommendation system according to the historical behaviors of the user, and the price of the articles represents the income of the system after the articles are selected/downloaded. For example, a function may be constructed that computes a function value based on the predicted user selectivity and the item bids, and the recommendation system ranks the items in descending order of the function value.

To meet the personalized needs of users, the recommendation system includes a plurality of recommendation scenarios: browser, negative one-screen, video streaming, etc. The user generates different behaviors in different scenes according to the preference, and each scene has a behavior characteristic specific to the user. In the usual case, each scene will be modeled separately. The method has the advantages that the single scene is independently modeled, the behavior characteristics of the same user in different scenes can not be effectively captured because the same user has different behaviors in different scenes, and under the condition that the scenes are relatively large, each scene is independently modeled and maintained, so that large manpower and resource consumption can be caused.

Disclosure of Invention

The data processing method can learn commonalities among fields and capture differences among fields, so that recommendation accuracy of a recommendation model is improved.

In a first aspect, the present application provides a data processing method, applied to information recommendation of a target recommendation scene, the method including: acquiring a first sample, wherein the first sample comprises first data; the first data is user attribute, article attribute or context information; obtaining a first embedded vector corresponding to the first data from each embedded token in a plurality of embedded tokens; determining a first weight corresponding to each first embedded vector based on the information of the target recommended scene; the first weight is used for fusing a plurality of first embedded vectors to obtain a first fused vector; and obtaining a recommendation result through a recommendation model at least according to the first fusion vector. The multiple embedded vectors are combined through weight determination, so that shared knowledge among fields can be captured, and embedded vectors specific to the fields can be combined, commonalities among the fields can be learned, differences among the fields can be captured, and recommendation accuracy of a recommendation model is improved.

In one possible implementation, each of the embedded tokens includes a plurality of embedded vectors, each corresponding to a category of a user attribute, a category of an item attribute, or a category of context information.

In one possible implementation, the first sample further includes second data, the first data and the second data being different; the second data is user attribute, article attribute or context information; the method further comprises the steps of: acquiring a second embedded vector corresponding to the second data; determining a second weight corresponding to the first fusion vector and a third weight corresponding to the second embedding vector according to the first fusion vector and the second embedding vector; the second weight is used for fusing with the first fusion vector to obtain a processed first fusion vector, and the third weight is used for fusing with the second embedding vector to obtain a processed second embedding vector; and obtaining a recommendation result through a recommendation model at least according to the first fusion vector, wherein the recommendation result comprises: and obtaining a recommendation result through a recommendation model at least according to the processed first fusion vector and the processed second embedding vector.

In one possible implementation, the determining, according to the first fusion vector and the second embedding vector, a second weight corresponding to the first fusion vector and a third weight corresponding to the second embedding vector includes: and determining a second weight corresponding to the first fusion vector and a third weight corresponding to the second embedding vector according to the information of the target recommended scene, the first fusion vector and the second embedding vector.

Because a certain field may be biased to a certain feature and influence factors of different features are different, a feature importance matrix A aiming at different fields is learned based on Feature Selection Network (feature selection network), then the original unbadd (E) is subjected to ascending weight or descending weight, the purpose of soft selection is achieved, and the final feature V is obtained. Capturing feature preferences of a specific field by introducing feature learning; the feature importance matrixes aiming at different fields are learned, the original ebedding is subjected to ascending weight or descending weight, and the model capturing characteristics and the ability of learning the commonality of all fields are improved.

In one possible implementation, the method further comprises: selecting at least one neural network branch corresponding to the target recommendation scene from a plurality of neural network branches according to the target recommendation scene; processing the first fusion vector by utilizing the at least one neural network branch to obtain at least one vector processing result; the at least one vector processing result is used for fusing to obtain a second fused vector; and obtaining a recommendation result through a recommendation model at least according to the first fusion vector, wherein the recommendation result comprises: and obtaining a recommendation result through a recommendation model at least according to the second fusion vector.

The commonalities and characteristics of the learning domain are cascaded with modules of different widths, and a learnable scheme is introduced to select the branch network.

In one possible implementation, before the processing the first fusion vector using the at least one neural network branch, the method further includes: processing the first fusion vector by a target MLP; said processing said first fusion vector using said at least one neural network branch, comprising: and processing the first fusion vector processed by the target MLP by utilizing the at least one neural network branch.

In one possible implementation, the method further comprises: and fusing the first fusion vector processed by the target MLP with the second fusion vector.

In one possible implementation, the information of the target recommendation scene is specifically an embedded vector.

In one possible implementation of the present invention,

different recommended scenes are different application programs; or,

different recommended scenes are different types of application programs; or,

different recommended scenarios are different functions of the same application.

In one possible implementation, the attribute information includes a user attribute of the user, the user attribute including at least one of: gender, age, occupation, income, hobbies, education level.

In one possible implementation, the attribute information includes an item attribute of the item, the item attribute including at least one of: item name, developer, installation package size, class, good grade.

In one possible implementation, the different recommended scenarios are different applications; or,

different recommended scenes are different types of application programs; or,

In one possible implementation, the apparatus further includes:

and the recommending module is used for determining to recommend the article to the user when the recommending result meets a preset condition.

In a second aspect, the present application provides a data processing method, the method comprising:

acquiring a first sample, wherein the first sample comprises first data; the first data is user attribute, article attribute or context information;

obtaining a first embedded vector corresponding to the first data from each embedded token in a plurality of embedded tokens;

determining a first weight corresponding to each first embedded vector based on the information of the target recommended scene; the first weight is used for fusing a plurality of first embedded vectors to obtain a first fused vector;

Obtaining a recommendation result through a recommendation model at least according to the first fusion vector;

and updating the embedded characterizations and the recommendation model according to the recommendation result and the corresponding true value.

In one possible implementation, the determining, based on the information of the target recommended scenario, a first weight corresponding to each of the first embedded vectors includes:

determining a first weight corresponding to each first embedded vector through a first weight determining network based on the information of the target recommended scene;

the updating the embedded characterizations and the recommendation model according to the recommendation result and the corresponding truth value comprises:

and updating the embedded characterizations, the recommendation model and the first weight determination network according to the recommendation result and the corresponding true value.

In one possible implementation, the first sample further includes second data, the first data and the second data being different; the second data is user attribute, article attribute or context information; the method further comprises the steps of:

acquiring a second fusion vector corresponding to the second data;

according to the first fusion vector and the second fusion vector, a second weight corresponding to the first fusion vector and a third weight corresponding to the second fusion vector are determined through a second weight determining network; the second weight is used for fusing with the first fusion vector to obtain a processed first fusion vector, and the third weight is used for fusing with the second fusion vector to obtain a processed second fusion vector;

And obtaining a recommendation result through a recommendation model at least according to the first fusion vector, wherein the recommendation result comprises:

obtaining a recommendation result through a recommendation model at least according to the processed first fusion vector and the processed second fusion vector;

and updating the embedded characterizations, the recommendation model and the second weight determination network according to the recommendation result and the corresponding true value.

In one possible implementation, the method further comprises:

according to the information of the target recommendation scene, determining a network through branches, and determining a score corresponding to each of a plurality of neural network branches; the score is used for selecting at least one neural network branch corresponding to the target recommendation scene from the plurality of neural network branches;

processing the first fusion vector by utilizing the at least one neural network branch to obtain at least one vector processing result; the at least one vector processing result is used for fusing to obtain a second fused vector;

Obtaining a recommendation result through a recommendation model at least according to the second fusion vector;

and updating the embedded characterizations, the recommendation model and the branch determination network according to the recommendation result and the corresponding true value.

different recommended scenes are different types of application programs; or,

In one possible implementation, the apparatus further includes:

In a third aspect, the present application provides a data processing apparatus applied to information recommendation of a target recommendation scene, the apparatus including:

the device comprises an acquisition module, a sampling module and a sampling module, wherein the acquisition module is used for acquiring a first sample, and the first sample comprises first data; the first data is user attribute, article attribute or context information;

the processing module is used for acquiring a first embedded vector corresponding to the first data from each embedded token in the plurality of embedded tokens;

and obtaining a recommendation result through a recommendation model at least according to the first fusion vector.

In one possible implementation, the first sample further includes second data, the first data and the second data being different; the second data is user attribute, article attribute or context information; the acquisition module is further configured to:

Acquiring a second embedded vector corresponding to the second data;

the processing module is further configured to:

determining a second weight corresponding to the first fusion vector and a third weight corresponding to the second embedding vector according to the first fusion vector and the second embedding vector; the second weight is used for fusing with the first fusion vector to obtain a processed first fusion vector, and the third weight is used for fusing with the second embedding vector to obtain a processed second embedding vector;

and obtaining a recommendation result through a recommendation model at least according to the processed first fusion vector and the processed second embedding vector.

In one possible implementation, the processing module is specifically configured to:

and determining a second weight corresponding to the first fusion vector and a third weight corresponding to the second embedding vector according to the information of the target recommended scene, the first fusion vector and the second embedding vector.

In one possible implementation, the processing module is further configured to:

selecting at least one neural network branch corresponding to the target recommendation scene from a plurality of neural network branches according to the target recommendation scene;

and obtaining a recommendation result through a recommendation model at least according to the second fusion vector.

In one possible implementation, before the processing the first fusion vector using the at least one neural network branch, the processing module is further configured to:

processing the first fusion vector by a target MLP;

and processing the first fusion vector processed by the target MLP by utilizing the at least one neural network branch.

In one possible implementation, the processing module is further configured to:

and fusing the first fusion vector processed by the target MLP with the second fusion vector.

In one possible implementation of the present invention,

different recommended scenes are different application programs; or,

Different recommended scenes are different types of application programs; or,

different recommended scenes are different types of application programs; or,

In one possible implementation, the apparatus further includes:

In a fourth aspect, the present application provides a data processing apparatus, the apparatus comprising:

Acquiring a second fusion vector corresponding to the second data;

the processing module is further configured to:

In one possible implementation, the processing module is further configured to:

different recommended scenes are different types of application programs; or,

In one possible implementation, the apparatus further includes:

In a fifth aspect, embodiments of the present application provide a data processing apparatus, which may include a memory, a processor, and a bus system, where the memory is configured to store a program, and the processor is configured to execute the program in the memory, so as to perform any of the optional methods according to the first aspect.

In a sixth aspect, an embodiment of the present application provides a model training apparatus, which may include a memory, a processor, and a bus system, where the memory is configured to store a program, and the processor is configured to execute the program in the memory, so as to perform any one of the optional methods in the second aspect.

In a seventh aspect, embodiments of the present application provide a computer-readable storage medium having a computer program stored therein, which when run on a computer, causes the computer to perform the first aspect and any of the optional methods described above, and any of the optional methods of the second aspect described above.

In an eighth aspect, embodiments of the present application provide a computer program product comprising code which, when executed, is adapted to carry out the first aspect and any optional method described above, and any optional method of the second aspect described above.

In a ninth aspect, the present application provides a chip system comprising a processor for supporting an execution device or training device to perform the functions involved in the above aspects, e.g. to send or process data involved in the above method; or, information. In one possible design, the chip system further includes a memory for holding program instructions and data necessary for the execution device or the training device. The chip system can be composed of chips, and can also comprise chips and other discrete devices.

Drawings

FIG. 1 is a schematic diagram of a structure of an artificial intelligence main body frame;

FIG. 2 is a schematic diagram of a system architecture according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of a system architecture according to an embodiment of the present disclosure;

fig. 4 is a schematic diagram of a recommended scenario provided in an embodiment of the present application;

fig. 5 is a schematic flow chart of a data processing method according to an embodiment of the present application;

FIG. 6 is a schematic illustration of a recommendation model;

FIG. 7 is a schematic illustration of a recommendation model;

FIG. 8 is a schematic illustration of a recommendation model;

FIG. 9 is a schematic diagram of a data processing apparatus according to an embodiment of the present application;

Fig. 10 is a schematic diagram of an execution device according to an embodiment of the present application;

FIG. 11 is a schematic diagram of a training device according to an embodiment of the present disclosure;

fig. 12 is a schematic diagram of a chip according to an embodiment of the present application.

Detailed Description

Embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention. The terminology used in the description of the embodiments of the invention herein is for the purpose of describing particular embodiments of the invention only and is not intended to be limiting of the invention.

Embodiments of the present application are described below with reference to the accompanying drawings. As one of ordinary skill in the art can appreciate, with the development of technology and the appearance of new scenes, the technical solutions provided in the embodiments of the present application are applicable to similar technical problems.

The terms first, second and the like in the description and in the claims of the present application and in the above-described figures, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and are merely illustrative of the manner in which the embodiments of the application described herein have been described for objects of the same nature. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.

Referring to fig. 1, a schematic structural diagram of an artificial intelligence main body framework is shown in fig. 1, and the artificial intelligence main body framework is described below from two dimensions of "intelligent information chain" (horizontal axis) and "IT value chain" (vertical axis). Where the "intelligent information chain" reflects a list of processes from the acquisition of data to the processing. For example, there may be general procedures of intelligent information awareness, intelligent information representation and formation, intelligent reasoning, intelligent decision making, intelligent execution and output. In this process, the data undergoes a "data-information-knowledge-wisdom" gel process. The "IT value chain" reflects the value that artificial intelligence brings to the information technology industry from the underlying infrastructure of personal intelligence, information (provisioning and processing technology implementation), to the industrial ecological process of the system.

(1) Infrastructure of

The infrastructure provides computing capability support for the artificial intelligence system, realizes communication with the outside world, and realizes support through the base platform. Communicating with the outside through the sensor; the computing power is provided by a smart chip (CPU, NPU, GPU, ASIC, FPGA and other hardware acceleration chips); the basic platform comprises a distributed computing framework, a network and other relevant platform guarantees and supports, and can comprise cloud storage, computing, interconnection and interworking networks and the like. For example, the sensor and external communication obtains data that is provided to a smart chip in a distributed computing system provided by the base platform for computation.

(2) Data

The data of the upper layer of the infrastructure is used to represent the data source in the field of artificial intelligence. The data relate to graphics, images, voice and text, and also relate to the internet of things data of the traditional equipment, including service data of the existing system and sensing data such as force, displacement, liquid level, temperature, humidity and the like.

(3) Data processing

Data processing typically includes data training, machine learning, deep learning, searching, reasoning, decision making, and the like.

Wherein machine learning and deep learning can perform symbolized and formalized intelligent information modeling, extraction, preprocessing, training and the like on data.

Reasoning refers to the process of simulating human intelligent reasoning modes in a computer or an intelligent system, and carrying out machine thinking and problem solving by using formal information according to a reasoning control strategy, and typical functions are searching and matching.

Decision making refers to the process of making decisions after intelligent information is inferred, and generally provides functions of classification, sequencing, prediction and the like.

(4) General capability

After the data has been processed, some general-purpose capabilities can be formed based on the result of the data processing, such as algorithms or a general-purpose system, for example, translation, text analysis, computer vision processing, speech recognition, image recognition, etc.

(5) Intelligent product and industry application

The intelligent product and industry application refers to products and applications of an artificial intelligent system in various fields, is encapsulation of an artificial intelligent overall solution, and realizes land application by making intelligent information decisions, and the application fields mainly comprise: intelligent terminal, intelligent transportation, intelligent medical treatment, autopilot, smart city etc.

The embodiment of the application can be applied to the field of information recommendation, wherein the scenes comprise but are not limited to scenes related to e-commerce product recommendation, search engine result recommendation, software recommendation of an application market, music recommendation, video recommendation, news recommendation, reading content recommendation, lifelong partner related application and the like, and the recommended articles in various application scenes can be called as 'recommended objects'. In different recommendation scenarios, the recommendation object may be a media content item, such as APP, or a video (e.g. a short video or a live video), or music, or a certain commodity (e.g. a presentation interface of an online shopping platform, different commodities may be selected for presentation according to the user), or an article.

For example, taking an application store as an example, a user opens a mobile phone application market to trigger a recommendation module of the application market, and the recommendation module of the application market predicts the possibility of downloading given candidate applications by the user according to the historical downloading records of the user, the clicking records of the user, the self-characteristics, time, places and other environmental characteristic information of the applications. According to the predicted result, the application market is displayed according to the descending order of the possibility, and the effect of improving the application downloading probability is achieved. Specifically, applications that are more likely to be downloaded are ranked in a front position, and applications that are less likely to be downloaded are ranked in a rear position. The behavior of the user is also logged and the parameters of the prediction model are trained and updated through the offline training module.

For example, in the application related to life mate, the cognitive brain can be built by simulating the brain mechanism through various models and algorithms based on the historical data of the user in the fields of video, music, news and the like, and the life learning system framework of the user is built. The life mate can record events occurring in the past of the user according to system data, application data and the like, understand the current intention of the user, predict future actions or behaviors of the user and finally realize intelligent service.

Referring to fig. 4, in the recommendation process, when a user interacts with the recommendation system, a recommendation request is triggered, the recommendation system inputs the request and related feature information into the deployed recommendation model, and then the click rate of the user on all candidate objects is predicted. And then, the candidate objects are arranged in a descending order according to the predicted click rate, and the candidate objects are displayed at different positions in order to serve as recommendation results for users. The user browses the presented items and user behavior such as browsing, clicking, downloading, etc. occurs. The user behaviors can be stored in a log to be used as training data, and the parameters of the recommendation model are updated irregularly through the offline training module, so that the recommendation effect of the model is improved.

For example, a user opens a mobile phone application market to trigger a recommendation module of the application market, and the recommendation module of the application market predicts the possibility of downloading given candidate applications by the user according to the historical downloading records of the user, the clicking records of the user, the self-characteristics of the applications, the time, the place and other environmental characteristic information. According to the predicted result, the application market is displayed according to the descending order of the possibility, and the effect of improving the application downloading probability is achieved. Specifically, applications that are more likely to be downloaded are ranked in a front position, and applications that are less likely to be downloaded are ranked in a rear position. The behavior of the user is also logged and the parameters of the prediction model are trained and updated through the offline training module.

For example, in the application related to life mate, the cognitive brain can be built by simulating the brain mechanism through various models and algorithms based on the historical data of the user in the fields of video, music, news and the like, and the life learning system framework of the user is built. The life mate can record events occurring in the past of the user according to system data, application data and the like, understand the current intention of the user, predict future actions or behaviors of the user and finally realize intelligent service. In the current first stage, behavior data (including information such as terminal side short messages, photos and mail events) of a user are obtained according to a music APP, a video APP, a browser APP and the like, a user portrait system is built, and learning and memory modules based on user information filtering, association analysis, cross-domain recommendation, causal reasoning and the like are realized to build a user personal knowledge map.

Next, an application architecture of the embodiment of the present application is described.

Referring to fig. 2, an embodiment of the present invention provides a recommendation system architecture 200. The data collection device 260 is configured to collect samples, where one training sample may be composed of a plurality of feature information (or described as attribute information and context information, such as user attribute and object attribute), and the feature information may include a plurality of feature information of a user, object feature information and tag feature, where the user feature information is used to characterize a feature of a user, such as gender, age, occupation, hobbies, and the like, the object feature information is used to characterize a feature of an object pushed to the user, different recommendation systems correspond to different objects, and types of features that need to be extracted by different objects are also different, for example, the name (identifier), type, size, and the like of an APP may be extracted from the training sample in the APP market; the object features mentioned in the training sample of the e-commerce APP can be the names of commodities, the category to which the commodities belong, price intervals and the like; the label feature is used to indicate whether the sample is a positive example or a negative example, and in general, the label feature of the sample may be obtained through operation information of the recommended object by the user, the sample in which the user has operated the recommended object is a positive example, the recommended object is not operated by the user, or only the sample browsed is a negative example, for example, when the user clicks or downloads or purchases the recommended object, the label feature is 1, which indicates that the sample is a positive example, and if the user has not operated any recommended object, the label feature is 0, which indicates that the sample is a negative example. The samples may be stored in the database 230 after collection, and some or all of the characteristic information in the samples in the database 230 may also be obtained directly from the client device 240, such as user characteristic information, user operation information on the object (for determining a type identifier), object characteristic information (such as an object identifier), and so on. The training device 220 trains the acquisition model parameter matrix based on the samples in the database 230 for generating the recommendation model 201 (e.g., feature extraction network, neural network, etc. in the embodiments of the present application). How the training device 220 trains to obtain the model parameter matrix for generating the recommendation model 201 will be described in more detail below, the recommendation model 201 can be used to evaluate a large number of objects to obtain the scores of the respective objects to be recommended, further a specified or preset number of objects can be recommended from the evaluation results of the large number of objects, the calculation module 211 obtains the recommendation result based on the evaluation results of the recommendation model 201, and recommends the recommendation result to the client device through the I/O interface 212.

In this embodiment of the present application, the training device 220 may select positive samples and negative samples from the sample set in the database 230 and add the positive samples and the negative samples to the training set, and then train the samples in the training set by using the recommendation model to obtain a trained recommendation model; details of the implementation of the computing module 211 may be found in the detailed description of the method embodiment shown in fig. 5.

The training device 220 is used for constructing the recommendation model 201 after obtaining the model parameter matrix based on sample training, and then sending the recommendation model 201 to the execution device 210, or directly sending the model parameter matrix to the execution device 210, and constructing a recommendation model in the execution device 210 for recommending a corresponding system, for example, the recommendation model obtained based on sample training related to video can be used for recommending video to a user in a video website or an APP, and the recommendation model obtained based on sample training related to APP can be used for recommending APP to the user in an application market.

The execution device 210 is configured with an I/O interface 212, and performs data interaction with an external device, and the execution device 210 may obtain user characteristic information, such as a user identifier, a user identity, a gender, a occupation, a preference, etc., from the client device 240 through the I/O interface 212, and this part of information may also be obtained from a system database. The recommendation model 201 recommends a target recommended object to the user based on the user characteristic information and the object characteristic information to be recommended. The execution device 210 may be disposed in a cloud server or in a user client.

The execution device 210 may invoke data, code, etc. in the data storage system 250 and may store the output data in the data storage system 250. The data storage system 250 may be disposed in the execution device 210, may be disposed independently, or may be disposed in other network entities, and the number may be one or multiple.

The calculation module 211 processes the user feature information by using the recommendation model 201, and the object feature information to be recommended, for example, the calculation module 211 uses the recommendation model 201 to analyze and process the user feature information and the feature information of the object to be recommended, so as to obtain the score of the object to be recommended, and the object to be recommended is ranked according to the score, wherein the object ranked in front is to be the object recommended to the client device 240.

Finally, the I/O interface 212 returns the recommendation to the client device 240 for presentation to the user.

Further, the training device 220 may generate respective recommendation models 201 for different targets based on different sample characteristic information to provide better results to the user.

It should be noted that fig. 2 is only a schematic diagram of a system architecture provided by an embodiment of the present invention, and the positional relationship among devices, apparatuses, modules, etc. shown in the drawing is not limited in any way, for example, in fig. 2, the data storage system 250 is an external memory with respect to the execution device 210, and in other cases, the data storage system 250 may be disposed in the execution device 210.

In this embodiment of the present application, the training device 220, the executing device 210, and the client device 240 may be three different physical devices, or the training device 220 and the executing device 210 may be on the same physical device or a cluster, or the executing device 210 and the client device 240 may be on the same physical device or a cluster.

Referring to fig. 3, a system architecture 300 is provided in accordance with an embodiment of the present invention. In this architecture the execution device 210 is implemented by one or more servers, optionally in cooperation with other computing devices, such as: data storage, routers, load balancers and other devices; the execution device 210 may be disposed on one physical site or distributed across multiple physical sites. The executing device 210 may use data in the data storage system 250 or call program codes in the data storage system 250 to implement an object recommendation function, specifically, input information of objects to be recommended into a recommendation model, generate a pre-estimated score for each object to be recommended by the recommendation model, sort the objects according to the pre-estimated score from high to low, and recommend the objects to be recommended to the user according to the sorting result. For example, the first 10 objects in the ranking result are recommended to the user.

The data storage system 250 is configured to receive and store parameters of the recommendation model sent by the training device, and data for storing recommendation results obtained by the recommendation model, and may also include program code (or instructions) required for normal operation of the storage system 250. The data storage system 250 may be a distributed storage cluster formed by one device or a plurality of devices disposed outside the execution device 210, and when the execution device 210 needs to use the data on the storage system 250, the storage system 250 may send the data required by the execution device to the execution device 210, and accordingly, the execution device 210 receives and stores (or caches) the data. Of course, the data storage system 250 may also be deployed within the execution device 210, and when deployed within the execution device 210, the distributed storage system may include one or more memories, and optionally, when there are multiple memories, different memories may be used to store different types of data, such as model parameters of a recommendation model generated by the training device and data of recommendation results obtained by the recommendation model, may be stored on two different memories, respectively.

The user may operate respective user devices (e.g., local device 301 and local device 302) to interact with the execution device 210. Each local device may represent any computing device, such as a personal computer, computer workstation, smart phone, tablet, smart camera, smart car or other type of cellular phone, media consumption device, wearable device, set top box, game console, etc.

The local device of each user may interact with the performing device 210 through a communication network of any communication mechanism/communication standard, which may be a wide area network, a local area network, a point-to-point connection, etc., or any combination thereof.

In another implementation, the execution device 210 may be implemented by a local device, for example, the local device 301 may obtain user characteristic information and feed back recommendation results to the user based on a recommendation model implementing a recommendation function of the execution device 210, or provide services to the user of the local device 302.

Since the embodiments of the present application relate to a large number of applications of neural networks, for ease of understanding, related terms and related concepts of the neural networks related to the embodiments of the present application will be described below.

1. Click-through probability (CTR)

The click probability, which may also be referred to as a click rate, refers to the ratio of the number of clicks to the number of exposures of recommended information (e.g., recommended items) on a web site or application, and is typically an important indicator in a recommendation system to measure the recommendation system.

2. Personalized recommendation system

The personalized recommendation system is a system for analyzing according to historical data (such as operation information in the embodiment of the application) of a user by using a machine learning algorithm, predicting a new request according to the analysis, and giving a personalized recommendation result.

3. Offline training (offlinenet)

The offline training refers to a module for iteratively updating recommendation model parameters according to an algorithm learned by a device according to historical data (such as operation information in the embodiment of the application) of a user in a personalized recommendation system until the recommendation model parameters reach a set requirement.

4. Online prediction (onlineiference)

The online prediction refers to predicting the preference degree of the user for the recommended item in the current context according to the characteristics of the user, the item and the context based on an offline trained model, and predicting the probability of selecting the recommended item by the user.

For example, fig. 3 is a schematic diagram of a recommendation system provided in an embodiment of the present application. As shown in fig. 3, when a user enters the system, a request for a recommendation is triggered, the recommendation system inputs the request and its related information (e.g., operation information in the embodiment of the present application) into the recommendation model, and then predicts the user's selectivity to items in the system. Further, the items are arranged in a descending order according to the predicted selectivity or some function based on the selectivity, i.e. the recommendation system may display the items in different positions in order as a recommendation to the user. The user browses the different items in place and user actions occur such as browsing, selecting, downloading, etc. Meanwhile, the actual behaviors of the user can be stored in a log to be used as training data, and parameters of the recommendation model are continuously updated through the offline training module, so that the prediction effect of the model is improved.

For example, a user opening an application marketplace in a smart terminal (e.g., a cell phone) may trigger a recommendation system in the application marketplace. The recommendation system of the application market predicts the probability of downloading recommended candidate APP by the user according to the historical behavior log of the user, for example, the historical downloading record of the user, the user selection record and the self-characteristics of the application market, such as time, place and other environmental characteristic information. According to the calculated result, the recommendation system of the application market can display the candidate APP in descending order according to the predicted probability value, so that the downloading probability of the candidate APP is improved.

For example, APP with higher predicted user selectivity may be shown at a forward recommended position and APP with lower predicted user selectivity may be shown at a rearward recommended position.

The recommendation model may be a neural network model, and related terms and concepts of the neural network that may be related to the embodiments of the present application are described below.

(1) Neural network

The neural network may be composed of neural units, which may refer to an arithmetic unit with xs (i.e., input data) and intercept 1 as inputs, and the output of the arithmetic unit may be:

where s=1, 2, … … n, n is a natural number greater than 1, ws is the weight of xs, and b is the bias of the neural unit. f is an activation function (activation functions) of the neural unit for introducing a nonlinear characteristic into the neural network to convert an input signal in the neural unit to an output signal. The output signal of the activation function may be used as an input to a next convolutional layer, and the activation function may be a sigmoid function. A neural network is a network formed by joining together a plurality of the above-described single neural units, i.e., the output of one neural unit may be the input of another neural unit. The input of each neural unit may be connected to a local receptive field of a previous layer to extract features of the local receptive field, which may be an area composed of several neural units.

(2) Deep neural network

Deep neural networks (Deep Neural Network, DNN), also known as multi-layer neural networks, can be understood as neural networks having many hidden layers, many of which are not particularly metrics. From DNNs, which are divided by the location of the different layers, the neural networks inside the DNNs can be divided into three categories: input layer, hidden layer, output layer. Typically the first layer is the input layer, the last layer is the output layer, and the intermediate layers are all hidden layers. The layers are fully connected, that is, any neuron in the i-th layer must be connected to any neuron in the i+1-th layer. Although DNN appears to be complex, it is not really complex in terms of the work of each layer, simply the following linear relational expression:

wherein (1)>

Is an input vector, +.>

Is the output vector, +.>

Is the offset vector, W is the weight matrix (also called coefficient), and α () is the activation function. Each layer is only for the input vector +.>

The output vector is obtained by such simple operation>

Since DNN has a large number of layers, the coefficient W and the offset vector +.>

And thus a large number. The definition of these parameters in DNN is as follows: taking the coefficient W as an example: it is assumed that in DNN of one three layers, the linear coefficients of the 4 th neuron of the second layer to the 2 nd neuron of the third layer are defined as +. >

The superscript 3 represents the number of layers in which the coefficient W is located, and the subscript corresponds to the output third layer index 2 and the input second layer index 4. The summary is: the coefficients from the kth neuron of the L-1 th layer to the jth neuron of the L-1 th layer are defined as +.>

It should be noted that the input layer is devoid of W parameters. In deep neural networks, more hidden layers make the network more capable of characterizing complex situations in the real world. Theoretically, the more parameters the higher the model complexity, the greater the "capacity", meaning that it can accomplish more complex learning tasks. The process of training the deep neural network, i.e. learning the weight matrix, has the final objective of obtaining a weight matrix (a weight matrix formed by a number of layers of vectors W) for all layers of the trained deep neural network.

(3) Loss function

In training the deep neural network, since the output of the deep neural network is expected to be as close to the value actually expected, the weight vector of each layer of the neural network can be updated by comparing the predicted value of the current network with the actually expected target value according to the difference between the predicted value of the current network and the actually expected target value (of course, there is usually an initialization process before the first update, that is, the pre-configuration parameters of each layer in the deep neural network), for example, if the predicted value of the network is higher, the weight vector is adjusted to be predicted to be lower, and the adjustment is continued until the deep neural network can predict the actually expected target value or the value very close to the actually expected target value. Thus, it is necessary to define in advance "how to compare the difference between the predicted value and the target value", which is a loss function (loss function) or an objective function (objective function), which are important equations for measuring the difference between the predicted value and the target value. Taking the loss function as an example, the higher the output value (loss) of the loss function is, the larger the difference is, and then the training of the deep neural network becomes a process of reducing the loss as much as possible.

(4) Back propagation algorithm

An error Back Propagation (BP) algorithm may be used to correct the magnitude of the parameters in the initial model during the training process, so that the error loss of the model is smaller and smaller. Specifically, the input signal is forward-transferred until output, and error loss occurs, and parameters in the initial model are updated by back-propagating the error loss information, so that the error loss converges. The back propagation algorithm is a back propagation motion that dominates the error loss, aiming at deriving optimal model parameters, such as a weight matrix.

(5) Machine learning system

Based on the input data and the labels, training parameters of a machine learning model through optimization methods such as gradient descent and the like, and finally completing prediction of unknown data by utilizing the model obtained through training.

(6) Personalized recommendation system

And analyzing and modeling by utilizing a machine learning algorithm according to the historical data of the user, predicting a new user request according to the analysis and modeling, and giving a personalized recommendation result.

(7) Recommending scenes

A recommended scenario may be an Application (APP) that serves specific needs, such as a browser, video, or a specific channel, such as an entertainment channel, news channel, science channel, etc. in a browser stream.

(8) Multi-scene modeling

And fusing the data of the multiple scenes, training to generate a model, and serving the multiple scenes.

The machine learning system comprises a personalized recommendation system, wherein parameters of a machine learning model are trained through optimization methods such as gradient descent based on input data and labels, and after model parameters are converged, the model can be used for completing prediction of unknown data. Taking click rate prediction in the personalized recommendation system as an example, input data of the personalized recommendation system comprises user attributes, commodity attributes and the like. How to predict the personalized recommendation list according to the preference of the user has important influence on improving the recommendation precision of the recommendation system.

To meet the personalized needs of users, the recommendation system includes a plurality of recommendation scenarios: browser, negative one-screen, video streaming, etc. The user generates different behaviors in different scenes according to the preference, and each scene has a unique behavior characteristic of the user and also has a common behavior characteristic. In the usual case, each scene will be modeled separately.

However, the single scene is independently modeled, and the same user has different behaviors in different scenes, so that the behavior characteristics of the user in different scenes can not be effectively captured, the user preference can be fully learned, and under the condition of more scenes, each scene is independently modeled and maintained, so that larger manpower and resource consumption can be caused.

In order to solve the above problems, the present application provides a data processing method.

Referring to fig. 5, fig. 5 is an embodiment schematic diagram of a data processing method provided in an embodiment of the present application, and as shown in fig. 5, the data processing method provided in the embodiment of the present application includes:

501. acquiring a first sample, wherein the first sample comprises first data; the first data is user attribute, item attribute or context information.

In an embodiment of the present application, the execution subject of step 501 may be a terminal device, which may be a portable mobile device, such as, but not limited to, a mobile or portable computing device (e.g., a smart phone), a personal computer, a server computer, a handheld device (e.g., a tablet) or laptop, a multiprocessor system, a game console or controller, a microprocessor-based system, a set top box, a programmable consumer electronics, a mobile phone, a mobile computing and/or communication device with a wearable or accessory form factor (e.g., a watch, glasses, a headset, or an earplug), a network PC, a minicomputer, a mainframe computer, a distributed computing environment that includes any of the above systems or devices, and the like.

In this embodiment, the execution body of step 501 may be a cloud-side server, and the server may receive operation data of a user sent from a terminal device, and further the server may obtain the operation data of the user.

Wherein the operation data of the user may be obtained based on an interaction record (e.g., a behavior log of the user) between the user and the items, the operation data may include a real operation record of the user on each item, and the operation data may include attribute information of the user, attribute information of each item, context information, and operation types (e.g., clicking, downloading, etc.) of operations performed by the user on the plurality of items.

Wherein the attribute information of the user may be at least one of attribute related to preference characteristics of the user, gender, age, occupation, income, hobbies, and education level, wherein the gender may be male or female, the age may be a number between 0 and 100, the occupation may be teacher, programmer, chef, etc., the hobbies may be basketball, tennis, running, etc., and the education level may be primary school, junior middle school, high school, university, etc.; the present application is not limited to a specific type of attribute information of the user.

The article may be a physical article or a virtual article, for example, may be an Application (APP), an audio/video, a web page, news information, and other articles, and the attribute information of the article may be at least one of an article name, a developer, an installation package size, a class, and a good score, where, taking the article as an application, the class of the article may be a chat class, a running game, an office class, and the like, and the good score may be a score, a comment, and the like for the article; the present application is not limited to a particular type of attribute information for an item.

Wherein the context information may be a temporal context or a location context.

In one possible implementation, the training device may obtain operation data of the user (e.g., a first sample in an embodiment of the present application), where the first sample may include first data, and the first data may be one attribute information of the user, one attribute information of the object, or one context information.

In this embodiment of the present application, information recommendation in a target recommendation scenario may be performed, and in a possible implementation, the target recommendation scenario may be an application program serving a specific requirement, such as a browser, a video, or a specific channel, such as an entertainment channel, a news channel, a science and technology channel in a browser information stream.

In one possible implementation, the different recommended scenarios are different applications, or the different recommended scenarios are different types of applications (e.g., video-class applications and browser-class applications are different applications), or the different recommended scenarios are different functions of the same application (e.g., different channels of the same application, such as news channels, science channels, etc.), and the different functions may be classified according to recommendation classes.

502. A first embedded vector corresponding to the first data is obtained from each embedded token of a plurality of embedded tokens.

In the embodiment of the application, a group of meta-embedding is designed, the dimension size of which is h x f x d, wherein h is the number of the feature embedding in the meta-embedding, and is a super parameter, and h can be smaller than the recommended scene number due to commonality in each field. f is the feature size and d represents the embedding dimension. Each meta-mapping is a subspace of feature expression.

Referring to fig. 6, specifically, meta mapping may include h matrices of size f×d (i.e., embedded tokens in the embodiment of the present application), each of which may include f embedded vectors, where each of the f embedded vectors corresponds to a feature, such as an attribute of a user, an attribute of an object, or context information. For example, one of the f embedded vectors corresponds to the age of the user and one of the embedded vectors corresponds to the gender of the user.

In one possible implementation, the first data represents a feature, and an embedding vector corresponding to the feature of the first data representation may be determined in each of the plurality of embedding tokens, so as to obtain embedding vectors corresponding to the features of the plurality of first data representations (i.e., the first embedding vectors in the embodiments of the present application).

503. Determining a first weight corresponding to each first embedded vector based on the information of the target recommended scene; the first weight is used for fusing the plurality of first embedded vectors to obtain a first fused vector.

In order to obtain the embedded vector corresponding to the feature of the first data representation, the obtained plurality of first embedded vectors may be fused, and specifically, the weight corresponding to each first embedded vector (that is, the first weight in the embodiment of the present application) may be determined according to the information of the target recommended scene.

In one possible implementation, the weight size corresponding to each first embedded vector may be learned through a first weight determining network (or may be referred to as a gating network), that is, information of the target recommended scene may be input to the gating network, so as to obtain a weight corresponding to each first embedded vector. According to the method and the device, the multiple embedded vectors are combined through the gating network, so that shared knowledge among fields can be captured, and field-specific enabling can be combined through the gating network, so that commonalities among learning fields are represented, and differences among the fields are captured.

In one possible implementation, the first sample further includes second data, the first data and the second data being different; the second data is user attribute, article attribute or context information; the first data and the second data may be different attribute information or context information for the same user or item.

And a processing procedure type of the first data, a second embedded vector corresponding to the second data may be obtained (the second embedded vector may also be referred to as a second fusion vector).

In one possible implementation, the first fusion vector and the second embedding vector may be subjected to numerical adjustment of different weights, and specifically, a second weight corresponding to the first fusion vector and a third weight corresponding to the second embedding vector may be determined according to the first fusion vector and the second embedding vector; the second weight is used for fusing with the first fusion vector to obtain a processed first fusion vector, and the third weight is used for fusing with the second embedding vector to obtain a processed second embedding vector.

In one possible implementation, the second weight corresponding to the first fusion vector and the third weight corresponding to the second embedding vector may be determined according to the information of the target recommended scene, the first fusion vector and the second embedding vector. For example, according to the information of the target recommended scene, the first fusion vector and the second embedding vector, a second weight corresponding to the first fusion vector and a third weight corresponding to the second embedding vector may be determined through a second weight determining network.

Alternatively, the first weight determining network and the second weight determining network may be, but not limited to, SE-NET networks.

In one possible implementation, referring to fig. 8, the commonalities and characteristics of the learning domain may be cascaded with modules of different widths, and a learning scheme introduced to select a branching network.

In one possible implementation, at least one neural network branch corresponding to the target recommendation scene may be selected from a plurality of neural network branches according to the target recommendation scene; alternatively, each neural network branch may be a multi-layer persistence (MLP), and the at least one neural network branch may be used to process the first fusion vector to obtain at least one vector processing result; and the at least one vector processing result is used for fusing to obtain a second fused vector. For example, the score corresponding to each neural network branch in the target recommendation scenario may be obtained through a score determining network (for example, the Gating network shown in fig. 8), and the branch with the highest score is selected as the at least one neural network branch, so as to process the embedded vector.

In one possible implementation, the first fusion vector may be processed by a target MLP; and processing the first fusion vector processed by the target MLP by utilizing the at least one neural network branch.

In one possible implementation, the first fusion vector processed by the target MLP may be fused with the second fusion vector.

Through the mode, all the branch networks learn the corresponding relations between different fields and the branch networks through the gating network by the shared characteristic among shared-bottom learning fields. Different field characteristics are learned by training a plurality of sub-model branches, and some similar fields share sub-model learning commonalities, so that prediction accuracy is improved.

504. And obtaining a recommendation result through a recommendation model at least according to the first fusion vector.

In one possible implementation, in the reasoning process of the model, when the target operation information meets a preset condition, it is determined that the item is recommended to the user.

By the method, the probability of the user operating the object can be obtained, information recommendation is performed based on the probability, and specifically, when recommendation information meets preset conditions, the object can be determined to be recommended to the user.

When information recommendation is performed, recommendation information can be recommended to a user in the form of list pages so as to expect the user to perform behavior actions.

The beneficial effects of the embodiments of the present application are described below in conjunction with experimental results:

the technical solutions of the embodiments of the present application were verified on public business datasets and private corporate datasets, and the data statistics are shown in table 1:

TABLE 1

The Ali-CCP contains 3 different fields. The training set and the test set are in time order. Industrial data sets were sampled and collected from mainstream online advertising platforms with 6 different fields (screen breaks, video tiles, motivational video, screen breaks, banners, application icons). The training set, the validation set and the test set are divided in time sequence: three days of data fields collected from 6 businesses were used for training and validation, and then the data was used for testing the next day.

The offline evaluation index is AUC, and the online evaluation index is CTR.

It can be seen that this solution is superior to the baseline model in both public and corporate data sets except for industry Domain #6 (since the example of Domain #6 represents only a small fraction of 0.77%). Comparing the dominant single scene model deep FM, the multitasking model MMoE, the multi-domain recommended DADNN and STAR in the industry, the performance of the related algorithm on the data set is shown in the following table 2:

TABLE 2

The application provides a data processing method applied to information recommendation of a target recommendation scene, which comprises the following steps: acquiring a first sample, wherein the first sample comprises first data; the first data is user attribute, article attribute or context information; obtaining a first embedded vector corresponding to the first data from each embedded token in a plurality of embedded tokens; determining a first weight corresponding to each first embedded vector based on the information of the target recommended scene; the first weight is used for fusing a plurality of first embedded vectors to obtain a first fused vector; and obtaining a recommendation result through a recommendation model at least according to the first fusion vector. According to the method and the device, the multiple embedded vectors are combined through weight determination, so that shared knowledge among fields can be captured, the embedded vectors specific to the fields can be combined, commonalities among the fields can be learned, differences among the fields can be captured, and recommendation accuracy of a recommendation model is improved.

In addition, the embodiment of the application also provides a data processing method which can be applied to a training stage of a model, and the method comprises the following steps:

Acquiring a first sample, wherein the first sample comprises first data; the first data is user attribute, article attribute or context information; obtaining a first embedded vector corresponding to the first data from each embedded token in a plurality of embedded tokens; determining a first weight corresponding to each first embedded vector based on the information of the target recommended scene; the first weight is used for fusing a plurality of first embedded vectors to obtain a first fused vector; obtaining a recommendation result through a recommendation model at least according to the first fusion vector; and updating the embedded characterizations and the recommendation model according to the recommendation result and the corresponding true value.

The description of the training process may refer to the corresponding description of fig. 5 in the above embodiment, and the description is omitted here for the sake of brevity.

In one possible implementation, a first weight corresponding to each first embedded vector may be determined through a first weight determining network based on information of the target recommended scene;

the updating the embedded characterizations and the recommendation model according to the recommendation result and the corresponding truth value comprises: and updating the embedded characterizations, the recommendation model and the first weight determination network according to the recommendation result and the corresponding true value.

In one possible implementation, the first sample further includes second data, the first data and the second data being different; the second data is user attribute, article attribute or context information; the method further comprises the steps of: acquiring a second fusion vector corresponding to the second data; according to the first fusion vector and the second fusion vector, a second weight corresponding to the first fusion vector and a third weight corresponding to the second fusion vector are determined through a second weight determining network; the second weight is used for fusing with the first fusion vector to obtain a processed first fusion vector, and the third weight is used for fusing with the second fusion vector to obtain a processed second fusion vector; and obtaining a recommendation result through a recommendation model at least according to the first fusion vector, wherein the recommendation result comprises: obtaining a recommendation result through a recommendation model at least according to the processed first fusion vector and the processed second fusion vector; the updating the embedded characterizations and the recommendation model according to the recommendation result and the corresponding truth value comprises: and updating the embedded characterizations, the recommendation model and the second weight determination network according to the recommendation result and the corresponding true value.

In one possible implementation, the method further comprises: according to the information of the target recommendation scene, determining a network through branches, and determining a score corresponding to each of a plurality of neural network branches; the score is used for selecting at least one neural network branch corresponding to the target recommendation scene from the plurality of neural network branches; processing the first fusion vector by utilizing the at least one neural network branch to obtain at least one vector processing result; the at least one vector processing result is used for fusing to obtain a second fused vector; and obtaining a recommendation result through a recommendation model at least according to the first fusion vector, wherein the recommendation result comprises: obtaining a recommendation result through a recommendation model at least according to the second fusion vector; the updating the embedded characterizations and the recommendation model according to the recommendation result and the corresponding truth value comprises: and updating the embedded characterizations, the recommendation model and the branch determination network according to the recommendation result and the corresponding true value.

Next, a data processing apparatus provided in an embodiment of the present application will be described from the perspective of the apparatus, and referring to fig. 9, fig. 9 is a schematic structural diagram of a data processing apparatus provided in an embodiment of the present application, and as shown in fig. 9, a data processing apparatus 900 provided in an embodiment of the present application includes:

An acquisition module 901, configured to acquire a first sample, where the first sample includes first data; the first data is user attribute, article attribute or context information;

the specific description of the acquiring module 901 may refer to the description of step 501 in the foregoing embodiment, which is not repeated herein.

A processing module 902, configured to obtain a first embedding vector corresponding to the first data from each of a plurality of embedding tokens;

The specific description of the processing module 902 may refer to the descriptions of

steps

502, 503 and 504 in the above embodiments, which are not repeated here.

Acquiring a second embedded vector corresponding to the second data;

the processing module is further configured to:

In one possible implementation, the processing module is further configured to:

processing the first fusion vector by a target MLP;

In one possible implementation, the processing module is further configured to:

In one possible implementation of the present invention,

different recommended scenes are different application programs; or,

Different recommended scenes are different types of application programs; or,

different recommended scenes are different types of application programs; or,

In one possible implementation, the apparatus further includes:

The embodiment of the application also provides a data processing device, which comprises:

Acquiring a second fusion vector corresponding to the second data;

the processing module is further configured to:

In one possible implementation, the processing module is further configured to:

different recommended scenes are different types of application programs; or,

In one possible implementation, the apparatus further includes:

Next, referring to fig. 10, fig. 10 is a schematic structural diagram of an execution device provided in the embodiment of the present application, where the execution device 1000 may be specifically represented by a mobile phone, a tablet, a notebook computer, an intelligent wearable device, a server, and the like, which is not limited herein. Wherein the execution device 1000 implements the functions of the data processing method in the corresponding embodiment of fig. 5. Specifically, the execution apparatus 1000 includes: a receiver 1001, a transmitter 1002, a processor 1003, and a memory 1004 (where the number of processors 1003 in the execution device 1000 may be one or more), wherein the processor 1003 may include an application processor 10031 and a communication processor 10032. In some embodiments of the present application, the receiver 1001, transmitter 1002, processor 1003, and memory 1004 may be connected by a bus or other means.

Memory 1004 may include read only memory and random access memory and provide instructions and data to processor 1003. A portion of the memory 1004 may also include non-volatile random access memory (non-volatile random access memory, NVRAM). The memory 1004 stores a processor and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operating instructions may include various operating instructions for performing various operations.

The processor 1003 controls the operation of the execution device. In a specific application, the individual components of the execution device are coupled together by a bus system, which may include, in addition to a data bus, a power bus, a control bus, a status signal bus, etc. For clarity of illustration, however, the various buses are referred to in the figures as bus systems.

The methods disclosed in the embodiments of the present application may be applied to the processor 1003 or implemented by the processor 1003. The processor 1003 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuitry of hardware in the processor 1003 or instructions in the form of software. The processor 1003 may be a general purpose processor, a digital signal processor (digital signal processing, DSP), a microprocessor or microcontroller, a visual processor (vision processing unit, VPU), a tensor processor (tensor processing unit, TPU), or the like, and may further include an application specific integrated circuit (application specific integrated circuit, ASIC), a field-programmable gate array (field-programmable gate array, FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components. The processor 1003 may implement or execute the methods, steps and logical blocks disclosed in the embodiments of the present application. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 1004, and the processor 1003 reads information in the memory 1004, and combines the hardware thereof to perform the steps 501 to 504 in the above embodiment.

The receiver 1001 may be used to receive input numeric or character information and to generate signal inputs related to performing relevant settings and function control of the device. The transmitter 1002 may be configured to output numeric or character information via a first interface; the transmitter 1002 may also be configured to send instructions to the disk stack via the first interface to modify data in the disk stack; the transmitter 1002 may also include a display device such as a display screen.

Referring to fig. 11, fig. 11 is a schematic structural diagram of the training device provided in the embodiment of the present application, specifically, the training device 1100 is implemented by one or more servers, where the training device 1100 may be relatively different due to different configurations or performances, and may include one or more central processing units (central processing units, CPU) 1111 (e.g., one or more processors) and a memory 1132, and one or more storage mediums 1130 (e.g., one or more mass storage devices) storing application programs 1142 or data 1144. Wherein the memory 1132 and the storage medium 1130 may be transitory or persistent. The program stored on the storage medium 1130 may include one or more modules (not shown), each of which may include a series of instruction operations on the training device. Still further, the central processor 1111 may be configured to communicate with a storage medium 1130 and execute a series of instruction operations in the storage medium 1130 on the training device 1100.

The training device 1100 may also include one or more power supplies 1126, one or more wired or wireless network interfaces 1150, one or more input-output interfaces 1158; or one or more operating systems 1141, such as Windows ServerTM, mac OS XTM, unixTM, linuxTM, freeBSDTM, etc.

In particular, the training device may perform the steps described in the above embodiments in relation to model training.

Embodiments of the present application also provide a computer program product that, when run on a computer, causes the computer to perform the steps performed by the aforementioned performing device, or causes the computer to perform the steps performed by the aforementioned training device.

There is also provided in an embodiment of the present application a computer-readable storage medium having stored therein a program for performing signal processing, which when run on a computer, causes the computer to perform the steps performed by the aforementioned performing device or causes the computer to perform the steps performed by the aforementioned training device.

The execution device, training device or terminal device provided in the embodiment of the present application may specifically be a chip, where the chip includes: a processing unit, which may be, for example, a processor, and a communication unit, which may be, for example, an input/output interface, pins or circuitry, etc. The processing unit may execute the computer-executable instructions stored in the storage unit to cause the chip in the execution device to perform the data processing method described in the above embodiment, or to cause the chip in the training device to perform the data processing method described in the above embodiment. Optionally, the storage unit is a storage unit in the chip, such as a register, a cache, etc., and the storage unit may also be a storage unit in the wireless access device side located outside the chip, such as a read-only memory (ROM) or other type of static storage device that may store static information and instructions, a random access memory (random access memory, RAM), etc.

Specifically, referring to fig. 12, fig. 12 is a schematic structural diagram of a chip provided in an embodiment of the present application, where the chip may be represented as a neural network processor NPU1200, and the NPU1200 is mounted as a coprocessor on a main CPU (Host CPU), and the Host CPU distributes tasks. The core part of the NPU is an operation circuit 1203, and the operation circuit 1203 is controlled by the controller 1204 to extract matrix data in the memory and perform multiplication operation.

The NPU1200 may implement the data processing method and steps associated with model training provided in the embodiment depicted in fig. 5 through inter-engagement between the various devices within.

More specifically, in some implementations, the operation circuit 1203 in the NPU1200 includes a plurality of processing units (PEs) inside. In some implementations, the operational circuit 1203 is a two-dimensional systolic array. The operation circuit 1203 may also be a one-dimensional systolic array or other electronic circuit capable of performing mathematical operations such as multiplication and addition. In some implementations, the operation circuit 1203 is a general purpose matrix processor.

For example, assume that there is an input matrix a, a weight matrix B, and an output matrix C. The arithmetic circuit fetches the data corresponding to the matrix B from the weight memory 1202 and buffers the data on each PE in the arithmetic circuit. The arithmetic circuit takes matrix a data from the input memory 1201 and performs matrix operation with matrix B, and the obtained partial result or final result of the matrix is stored in an accumulator (accumulator) 1208.

The unified memory 1206 is used to store input data and output data. The weight data is carried directly through the memory cell access controller (Direct Memory Access Controller, DMAC) 1205, the DMAC into the weight memory 1202. The input data is also carried into the unified memory 1206 through the DMAC.

BIU Bus Interface Unit is the bus interface unit 1210 for the AXI bus to interact with the DMAC and the finger memory (Instruction Fetch Buffer, IFB) 1209.

The bus interface unit 1210 (Bus Interface Unit, abbreviated as BIU) is configured to obtain an instruction from an external memory by the instruction fetch memory 1209, and further configured to obtain raw data of the input matrix a or the weight matrix B from the external memory by the memory unit access controller 1205.

The DMAC is mainly used to transfer input data in the external memory DDR to the unified memory 1206 or to transfer weight data to the weight memory 1202 or to transfer input data to the input memory 1201.

The vector calculation unit 1207 includes a plurality of operation processing units, and further processes such as vector multiplication, vector addition, exponential operation, logarithmic operation, magnitude comparison, and the like are performed on the output of the operation circuit 1203 as needed. The method is mainly used for non-convolution/full-connection layer network calculation in the neural network, such as Batch Normalization (batch normalization), pixel-level summation, up-sampling of a characteristic plane and the like.

In some implementations, the vector computation unit 1207 can store the vector of processed outputs to the unified memory 1206. For example, the vector calculation unit 1207 may perform a linear function; alternatively, a nonlinear function is applied to the output of the operation circuit 1203, for example, linear interpolation of the feature plane extracted by the convolution layer, and then, for example, vector of accumulated values, to generate the activation value. In some implementations, the vector calculation unit 1207 generates normalized values, pixel-level summed values, or both. In some implementations, the vector of processed outputs can be used as an activation input to the operational circuitry 1203, for example for use in subsequent layers in a neural network.

An instruction fetch memory (instruction fetch buffer) 1209 connected to the controller 1204, for storing instructions used by the controller 1204;

the unified memory 1206, the input memory 1201, the weight memory 1202, and the finger memory 1209 are all On-Chip memories. The external memory is proprietary to the NPU hardware architecture.

The processor mentioned in any of the above may be a general-purpose central processing unit, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the above-mentioned programs.

It should be further noted that the above-described apparatus embodiments are merely illustrative, and that the units described as separate units may or may not be physically separate, and that units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the application, the connection relation between the modules represents that the modules have communication connection therebetween, and can be specifically implemented as one or more communication buses or signal lines.

From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general purpose hardware, or of course may be implemented by dedicated hardware including application specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components and the like. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions can be varied, such as analog circuits, digital circuits, or dedicated circuits. However, a software program implementation is a preferred embodiment in many cases for the present application. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk or an optical disk of a computer, etc., including several instructions for causing a computer device (which may be a personal computer, a training device, or a network device, etc.) to perform the method described in the embodiments of the present application.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.

The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via a wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be stored by a computer or a data storage device such as a training device, a data center, or the like that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy Disk, a hard Disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.

Claims

1. A data processing method, characterized by information recommendation applied to a target recommendation scene, the method comprising:

2. The method of claim 1, wherein each of the embedded tokens comprises a plurality of embedded vectors, each embedded vector corresponding to a category of a user attribute, a category of an item attribute, or a category of context information.

3. The method of claim 1 or 2, wherein the first sample further comprises second data, the first data and the second data being different; the second data is user attribute, article attribute or context information; the method further comprises the steps of:

Acquiring a second embedded vector corresponding to the second data;

4. The method of claim 3, wherein the determining the second weight corresponding to the first fusion vector and the third weight corresponding to the second embedding vector according to the first fusion vector and the second embedding vector comprises:

5. The method according to any one of claims 1 to 4, further comprising:

6. The method of claim 5, wherein prior to processing the first fusion vector using the at least one neural network branch, the method further comprises:

processing the first fusion vector by a target MLP;

said processing said first fusion vector using said at least one neural network branch, comprising:

7. The method of claim 6, wherein the method further comprises:

8. The method according to any of claims 1 to 7, wherein the information of the target recommendation scenario is embodied as an embedded vector.

9. The method according to any one of claims 1 to 8, wherein,

different recommended scenes are different application programs; or,

different recommended scenes are different types of application programs; or,

10. A method of data processing, the method comprising:

11. The method of claim 10, wherein determining a first weight for each of the first embedded vectors based on the information of the target recommendation scenario comprises:

12. The method of claim 10 or 11, wherein the first sample further comprises second data, the first data and the second data being different; the second data is user attribute, article attribute or context information; the method further comprises the steps of:

acquiring a second fusion vector corresponding to the second data;

13. The method according to any one of claims 10 to 12, further comprising:

14. A data processing apparatus for recommending information for application to a target recommendation scenario, the apparatus comprising:

15. The apparatus of claim 14, wherein each of the embedded tokens comprises a plurality of embedded vectors, each embedded vector corresponding to a category of a user attribute, a category of an item attribute, or a category of context information.

16. The apparatus of claim 14 or 15, wherein the first sample further comprises second data, the first data and the second data being different; the second data is user attribute, article attribute or context information; the acquisition module is further configured to:

acquiring a second embedded vector corresponding to the second data;

the processing module is further configured to:

17. The apparatus according to claim 16, wherein the processing module is specifically configured to:

18. The apparatus of any one of claims 14 to 17, wherein the processing module is further configured to:

19. The apparatus of claim 18, wherein the processing module, prior to processing the first fusion vector with the at least one neural network branch, is further configured to:

processing the first fusion vector by a target MLP;

20. The apparatus of claim 19, wherein the processing module is further configured to:

21. The apparatus according to any of the claims 14 to 20, wherein the information of the target recommendation scenario is embodied as an embedded vector.

22. The device according to any one of claims 14 to 21, wherein,

different recommended scenes are different application programs; or,

different recommended scenes are different types of application programs; or,

23. A data processing apparatus, the apparatus comprising:

24. The apparatus according to claim 23, wherein the processing module is specifically configured to:

25. The apparatus of claim 23 or 24, wherein the first sample further comprises second data, the first data and the second data being different; the second data is user attribute, article attribute or context information; the acquisition module is further configured to:

Acquiring a second fusion vector corresponding to the second data;

the processing module is further configured to:

26. The apparatus of any one of claims 23 to 25, wherein the processing module is further configured to:

27. A computing device, the computing device comprising a memory and a processor; the memory stores code, the processor being configured to retrieve the code and perform the method of any of claims 1 to 13.

28. A computer storage medium storing one or more instructions which, when executed by one or more computers, cause the one or more computers to implement the method of any one of claims 1 to 13.

29. A computer program product comprising code for implementing the method of any of claims 1 to 13 when said code is executed.