CN116910357A

CN116910357A - Data processing method and related device

Info

Publication number: CN116910357A
Application number: CN202310729226.4A
Authority: CN
Inventors: 陈渤; 汪宇豪; 赵翔宇; 郭慧丰; 唐睿明
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2023-06-16
Filing date: 2023-06-16
Publication date: 2023-10-20

Abstract

The data processing method can be applied to the field of artificial intelligence, and comprises the following steps: acquiring a prompt and a first characteristic representation; the prompt is obtained according to information related to a recommended scene; the first feature is represented by extracting the feature of the attribute information of the user and the object; predicting the operation information of the user on the object through a recommendation model according to the fusion result of the prompt and the first characteristic representation; and recommending the article to the user when the operation information meets the preset condition. According to the method, the prompt which can carry information related to the recommended scene is used as input of the recommended model, the recommended model can be guided to predict the characteristics of the scene which is biased to the prompt indication when the operation information is predicted, and the prediction precision of the multi-recommended scene is improved on the premise that the scale of the recommended model is not increased.

Description

Data processing method and related device

Technical Field

The present application 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. Moreover, if the features under a plurality of scenes are extracted by one feature extraction network, the network cannot learn the common behavior characteristics due to the difference of the features between different scenes, so that the prediction accuracy of the operation information is poor.

Disclosure of Invention

The application provides a data processing method which can improve the prediction precision of multiple recommendation scenes on the premise of ensuring that the scale of a recommendation model is not increased.

In a first aspect, the present application provides a data processing method, the method comprising: acquiring a prompt and a first characteristic representation; the prompt is obtained according to information related to a recommended scene; the first feature is represented by extracting the feature of the attribute information of the user and the object; predicting the operation information of the user on the object through a recommendation model according to the fusion result of the prompt and the first characteristic representation; and recommending the article to the user when the operation information meets the preset condition.

In the existing implementation, the characteristic representation corresponding to the attribute information of the user and the object is used as the input of the recommendation model to predict the operation information of the user on the object, however, in order to still obtain a high-precision prediction result in multiple recommendation scenes, one implementation is to construct a more complex recommendation model, wherein the recommendation model comprises a plurality of branches (i.e. a plurality of towers), each branch can be responsible for processing the prediction of one recommendation scene, however, as the recommendation scenes are increased, the scale of the recommendation model is increased, which is not acceptable in some scenes.

In the embodiment of the application, besides the characteristic representation corresponding to the attribute information of the user and the object is used as the input of the recommendation model, the prompt capable of carrying the information related to the recommendation scene (namely, the prompt is obtained according to the information related to the recommendation scene) is used as the input of the recommendation model, so that the recommendation model can be guided to predict the characteristics of the scene which is biased to the prompt indication when the operation information is predicted, and the prediction precision of the multi-recommendation scene is improved on the premise of ensuring that the scale of the recommendation model is not increased.

In one possible implementation, the information related to the recommended scenario includes: indication information of the recommended scene; or attribute information of the user; or, the characteristic of the attribute information of the user is represented.

In one possible implementation, the acquiring a prompt includes: performing single-heat coding on the information related to the recommended scene to obtain the campt; or, processing the information related to the recommended scene through a neural network to obtain the prompt; or, processing the information related to the recommended scene through a neural network to obtain a plurality of weights, wherein each weight corresponds to one feature representation, and fusing the plurality of feature representations according to the weights to obtain the prompt.

In one possible implementation, the recommended scenario may be an application that serves a particular need, such as a browser, video, or a specific channel, such as an entertainment channel, news channel, science channel, etc. in a browser 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.

In one possible implementation, different said recommended scenes may be different physical scenes in which the recommendation is located, e.g. different cities, different provinces, etc.

In one possible implementation, different of the recommendation scenarios may be applications developed for different developers.

In one possible implementation, different said recommended scenarios may be different or different classes of e-commerce products.

In one possible implementation, the attribute information includes user attributes of the user, the user attributes 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.

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 does not limit the specific type of attribute information of the user;

the article may be a physical article or a virtual article, for example, may be an article such as APP, audio/video, web page, news information, etc., 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, etc., and the good score may be a score, a comment, etc. for the article; the application is not limited to a particular type of attribute information for the item.

In a second aspect, the present application provides a data processing method, the method comprising: acquiring a prompt and a first characteristic representation; the prompt is obtained according to information related to a recommended scene; the first feature is represented by extracting the feature of the attribute information of the user and the object; predicting the operation information of the user on the object through a recommendation model according to the fusion result of the prompt and the first characteristic representation; and updating the recommendation model according to the operation information and the corresponding label.

In the existing implementation, when fine tuning of the recommendation model applicable to multiple recommendation scenes is performed, all of the embedding layer and the recommendation model need to be updated, which can lead to negative migration and seesaw effects, that is, improving the recommendation accuracy of a certain scene needs to be at the cost of damaging the performance of other scenes, further resulting in poor recommendation accuracy of the model in multiple scenes,

in the embodiment of the application, the prompt which can indicate the recommended scene is introduced as the input of the recommended model, when the model is finely tuned (optional, also applicable to pre-training), the common part between different scenes can be fixed, and the part which is strongly related to the scene in the model (such as a neural network for generating the prompt or a linear layer in the recommended model) is updated, so that the recommendation precision of the model for the scene is improved when the model of one recommended scene is trained, and the performance of the model in other recommended scenes is not damaged.

In one possible implementation, the acquiring the prompt and the first feature representation includes: processing the information related to the recommended scene through a neural network to obtain the prompt; or, processing the information related to the recommended scene through a neural network to obtain a plurality of weights, wherein each weight corresponds to one feature representation, and fusing the plurality of feature representations according to the weights to obtain the prompt; and extracting the characteristics of the attribute information of the user and the object through the embedded layer to obtain the first characteristic representation.

In one possible implementation, the method further comprises: and updating the neural network according to the operation information and the corresponding label under the condition of keeping the parameters of the embedded layer fixed.

In one possible implementation, the updating the recommendation model includes: only part of the networks in the recommendation model are updated.

In one possible implementation, the partial network is a linear layer.

In one possible implementation, the information related to the recommended scenario includes:

indication information of the recommended scene; or,

attribute information of the user; or,

And the characteristic representation of the attribute information of the user.

In one possible implementation of the present application,

different recommended scenes are different application programs; or,

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

different recommended scenes are different functions of the same application program; or,

different recommended scenes are different physical scenes where the recommendation is located; or,

different recommended scenes are application programs developed by different developers; or,

different recommended scenes are different or different types of e-commerce products.

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

the processing module is used for acquiring a first characteristic representation and a second characteristic representation; the first feature is obtained by extracting the feature of prompt, and the second feature is obtained by extracting the feature of attribute information of a user and an object; the prompt carries information related to the recommended scene; predicting the operation information of the user on the article through a recommendation model according to the fusion result of the first characteristic representation and the second characteristic representation;

And the recommendation model is used for recommending the article to the user when the operation information meets the preset condition.

indication information of the recommended scene; or,

attribute information of the user; or,

and the characteristic representation of the attribute information of the user.

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

performing single-heat coding on the information related to the recommended scene to obtain the campt; or alternatively, the first and second heat exchangers may be,

processing the information related to the recommended scene through a neural network to obtain the prompt; or alternatively, the first and second heat exchangers may be,

and processing the information related to the recommended scene through a neural network to obtain a plurality of weights, wherein each weight corresponds to one feature representation, and fusing the plurality of feature representations according to the weights to obtain the prompt.

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,

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

the processing module is used for acquiring prompt and a first characteristic representation; the prompt is obtained according to information related to a recommended scene; the first feature is represented by extracting the feature of the attribute information of the user and the object;

predicting the operation information of the user on the object through a recommendation model according to the fusion result of the prompt and the first characteristic representation;

and the updating module is used for updating the recommendation model according to the operation information and the corresponding label.

processing the information related to the recommended scene through a neural network to obtain the prompt; or, processing the information related to the recommended scene through a neural network to obtain a plurality of weights, wherein each weight corresponds to one feature representation, and fusing the plurality of feature representations according to the weights to obtain the prompt;

And extracting the characteristics of the attribute information of the user and the object through the embedded layer to obtain the first characteristic representation.

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

and updating the neural network according to the operation information and the corresponding label under the condition of keeping the parameters of the embedded layer fixed.

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

only part of the networks in the recommendation model are updated.

In one possible implementation, the partial network is a linear layer.

indication information of the recommended scene; or,

attribute information of the user; or,

and the characteristic representation of the attribute information of the user.

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,

In a fifth aspect, an embodiment of the present application provides 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 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 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 and any of the optional methods described above, and any of the optional methods of the third 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 of the optional methods described above, and any of the optional methods 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 application;

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

fig. 4 is a schematic diagram of a recommendation 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 flow chart of a data processing method according to an embodiment of the present application;

FIG. 7 is a schematic flow chart of a data processing method according to an embodiment of the present application;

FIG. 8 is a schematic flow chart of a data processing method according to an embodiment of the present application;

FIG. 9 is a schematic flow chart of a data processing method according to an embodiment of the present application;

FIG. 10 is a flowchart of a data processing method according to an embodiment of the present application;

FIG. 11 is a schematic diagram of a data processing apparatus according to an embodiment of the present application;

FIG. 12 is a schematic diagram of an implementation device according to an embodiment of the present application;

FIG. 13 is a schematic diagram of a training device according to an embodiment of the present application;

fig. 14 is a schematic diagram of a chip according to an embodiment of the present application.

Detailed Description

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

Embodiments of the present application are described below with reference to the accompanying drawings. As one of ordinary skill in the art can know, with the development of technology and the appearance of new scenes, the technical scheme provided by the embodiment of the application is also applicable to similar technical problems.

The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements 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 embodiments of the application have been described in connection with the description of the objects having the same attributes. 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, application market recommendation, music recommendation, video recommendation and the like, and the recommended objects in various application scenes can be also called as 'objects' so as to facilitate subsequent description, namely in different recommendation scenes, the recommended objects can be APP, video, or music, or a certain commodity (such as a presentation interface of an online shopping platform, different commodities can be displayed for presentation according to different users), and the essence can also be presented through the recommendation result of a recommendation model. These recommendation scenarios typically involve user behavior log collection, log data preprocessing (e.g. quantization, sampling, etc.), sample set training to obtain recommendation models, analysis of the objects (e.g. APP, music, etc.) involved in the scenario to which the training sample items correspond according to the recommendation models, e.g. the samples selected in the recommendation model training session come from the mobile phone APP application market user's operation behavior on the recommended APP, the recommendation models thus trained are then applicable to the mobile phone APP application market described above, or the APP application market for other types of terminals may be used to make recommendations of the terminal APP. The recommendation model finally calculates the recommendation probability or score of each object to be recommended, the recommendation system sorts the recommendation results selected according to a certain selection rule, for example, the recommendation results are sorted according to the recommendation probability or score, and the recommendation results are presented to the user through corresponding application or terminal equipment, and the user operates the objects in the recommendation results to generate links such as user behavior logs.

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 an embodiment of the present application is described.

Referring to fig. 2, an embodiment of the present application provides a recommendation system architecture 200. The data collection device 260 is configured to collect samples, where a training sample may be composed of a plurality of feature information (or be described as attribute information, such as user attribute and article attribute), and the feature information may include user feature information and 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, etc., 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 not wanted, for example, the object feature extracted in the training sample of the APP market may be a name (identifier), a type, a size, etc. of APP; 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 an embodiment 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 the embodiment of the present application, the training device 220 may select positive and negative samples from the sample set in the database 230 and add the positive and 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 the 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 application. 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.

Because the embodiments of the present application relate to a large number of applications of neural networks, for convenience 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 utilizing a machine learning algorithm, predicting a new request 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 in a personalized recommendation system according to historical data (such as operation information in the embodiment of the application) of a user until the recommendation model parameters reach set requirements.

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 associated information (e.g., operational information in the embodiment of the present application) into the recommendation model, and then predicts the user's selectivity for items within 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 may be 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 having a plurality of hidden layersThe term "many" is not particularly limited to a particular metric. 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.

(9) Prompt

Is a natural language term and has a division of hard templates and soft templates. A hard template is generally a number of natural language words or sentences with certain meanings; soft templates generally refer to parameterized token vectors that do not have meaning.

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 the prior art, the STAR (Star Topology Adaptive Recommender) model captures common behavior characteristics of different scenes of a user through a multi-scene model, for example, in the STAR model, a common characteristic extraction network is trained to adapt to each scene, however, the common characteristic extraction network in the prior art cannot extract embedded representation capable of accurately representing the common behavior characteristics of different scenes of the user, so that the generalization of a recommendation model in each scene is poor.

In order to solve the above problems, the present application provides a data processing method, which can be an inference process of a model.

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

501. Acquiring a prompt and a first characteristic representation; the prompt is obtained according to information related to a recommended scene; the first feature is represented by extracting the feature of the attribute information of the user and the object;

Next, the sample in the embodiment of the present application is described:

in one possible implementation, the prompt is obtained according to information related to the recommended scene, where the information related to the recommended scene may include indication information of the recommended scene, and further, the prompt is obtained by extracting features from the indication information of the recommended scene.

For example, the indication information of the recommended scene may be an identification for indicating the recommended scene.

In the embodiment of the application, the recommendation system can acquire the current information recommendation scene, and further determine the indication information of the recommendation scene according to the current information recommendation scene.

The prompt obtained according to the indication information of the recommended scene may also be referred to as a scene prompt (domain prompt), and the unique prompt parameter of each scene is generated by using the scene feature.

In one possible implementation, the information related to the recommended scene may be attribute information of the user (or may be referred to as user portrayal features). Further, the prompt is obtained by extracting the characteristics of the attribute information of the user.

The prompt obtained according to the attribute information of the user can also be called as user prompt (user prompt), and user individuation promotion parameters are generated by using the user portrait features to perform individuation modeling.

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.

For example, the prompt may include the first feature representation in the embodiment of the present application (or may also be obtained by feature extracting attribute information of the user through a different feature extraction network (e.g., an embedded layer) that obtains the first feature representation), which is not limited by the present application.

In one possible implementation, the prompt may be a low-dimensional representation corresponding to information related to the recommended scenario.

In one possible implementation, the information related to the recommended scenario may be thermally encoded alone, to obtain the prompt. The method can directly generate the prompt vector through the low-dimensional characterization according to the information (such as ID characteristics) related to the recommended scene, and can be suitable for the condition of fewer categories, such as the prompt generation of the indication information of the scene.

In one possible implementation, the prompt may be obtained by processing information related to the recommended scene through a neural network.

Referring to the left diagram in fig. 6, a fully connected neural network may be used to input information related to a recommended scene and directly generate a prompt. The user image characteristics can be used as the input of the fully-connected neural network to directly generate corresponding user prompts, so that huge parameter overhead caused by a mapping method is avoided.

In one possible implementation, the information related to the recommended scene may be processed through a neural network to obtain multiple weights, each weight corresponds to a feature representation, and the multiple feature representations are fused according to the weights to obtain the prompt.

Referring to the right diagram in fig. 6, the method uses the method of the attention mechanism, takes the feature as Query, maintains a pool of meta-cues (i.e. the feature representation in the embodiment of the present application) as Value, and performs weighting operation on the meta-cues (i.e. the feature representation in the embodiment of the present application) through the attention network (for example, normalization with a softmax function and temperature coefficient as super-parameter). The method is also suitable for the situation of more categories, such as user prompt generation. The user portrayal feature may be regarded as a Query.

For example, the user portrayal feature calculation can be performed by the following formula:

wherein R is the number of meta cues, MP _r Is the r-th element prompt, w _r Is the output predictive weight of the attention network.

In one possible implementation, the attribute information of the user and the item may be feature extracted to obtain a first feature representation. Alternatively, the first feature representation may be a feature that is trained during model training, and stored in the storage space, so that the first feature representation may be directly obtained from the corresponding storage space.

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 application is not limited to a particular type of attribute information for the item.

It should be appreciated that if the template includes both information derived from information indicating a recommended scene and information derived from attribute information of a user, the template may be a fusion result (e.g., a splice result) of a plurality of types of information.

502. And predicting the operation information of the user on the object through a recommendation model according to the fusion result of the prompt and the first characteristic representation.

In one possible implementation, the prompt and the first feature representation may be fused (e.g., spliced), and a fusion result obtained by the fusion may be input into a recommendation model, where the recommendation model may obtain a recommendation prediction (i.e., operation information of the user on the item) through a feature interaction and output layer.

Alternatively, the recommendation model may be an existing depth recommendation model of various types, such as DeepFM, DCN, autoInt.

Illustratively, the feature interaction layer needs to understand the relationships between different feature domains, typically using a linear layer to model linear (low order) feature interactions, while using a deep neural network to model high order feature interactions. The output layer takes the hidden vector h generated by the upper layer as input and outputs the final prediction result, for example, the output layer can perform the calculation of the following formula.

In one possible implementation, the predicted operation information may indicate whether the user performs a target operation, where the target operation may be a behavior operation type of the user, and on the network platform and application, the user often has various interaction forms with the article (i.e. has multiple operation types), such as the operation types of browsing, clicking, joining in a shopping cart, purchasing, etc. of the user in the behavior of the e-commerce platform.

In one possible implementation, the operation information may be a probability that the user will perform a target operation on the item.

For example, the operation information may be whether the user clicks or a probability of clicking.

503. And recommending the article to the user when the operation information meets the preset condition.

In one possible implementation, in the reasoning process of the model, when the 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 embodiment of the application provides a data processing method, which takes a characteristic representation corresponding to attribute information of a user and an object as input of a recommendation model, and takes prompt promtt capable of carrying information related to a recommendation scene (namely, the prompt is obtained according to the information related to the recommendation scene) as input of the recommendation model, so that the characteristics of the scene which is biased to the prompt indication when the recommendation model predicts operation information can be guided to predict, and the prediction precision of multiple recommendation scenes is improved on the premise of ensuring that the scale of the recommendation model is not increased.

The application provides a data processing method which can be a training process of a model, for example, a pre-training process or a fine tuning process of the model.

Referring to fig. 7, fig. 7 is an embodiment schematic diagram of a data processing method provided by an embodiment of the present application, and as shown in fig. 7, the data processing method provided by the embodiment of the present application includes:

701. acquiring a prompt and a first characteristic representation; the prompt is obtained according to information related to a recommended scene; the first feature is represented by extracting the feature of the attribute information of the user and the object;

In one possible implementation, the information related to the recommended scene may be processed through a neural network to obtain the prompt; or, processing the information related to the recommended scene through a neural network to obtain a plurality of weights, wherein each weight corresponds to one feature representation, and fusing the plurality of feature representations according to the weights to obtain the prompt; and extracting the characteristics of the attribute information of the user and the object through the embedded layer to obtain the first characteristic representation.

In one possible implementation, different said recommended scenarios are different applications; or, different recommended scenes are different types of application programs; or, different recommended scenes are different functions of the same application program; or, different recommended scenes are different physical scenes where the recommendation is located; or, different recommended scenes are application programs developed by different developers; or, different recommended scenes are different or different types of e-commerce products.

The specific description of step 701 may refer to the description of step 501 in the above embodiment, and the description is omitted here for the similarity.

702. Predicting the operation information of the user on the object through a recommendation model according to the fusion result of the prompt and the first characteristic representation;

the specific description of step 702 may refer to the description of step 502 in the above embodiment, and the description is omitted here for the similarity.

703. And updating the recommendation model according to the operation information and the corresponding label.

The label corresponding to the operation information may be operation data of the user on the article (the operation data may be real operation data or obtained by a certain data enhancement method, which is not limited in the present application). The operational data of the user may be obtained based on records of interactions between the user and the items (e.g., user's behavioral logs), which may include records of actual operations of the user on the respective items.

The operation information is the feedforward output in the model training process, the label corresponding to the operation information can be used as a true value and the operation information to construct loss, and the recommendation model is updated based on the loss.

Illustratively, the overall optimization penalty is as follows (taking a classification task as an example).

In particular, in one possible implementation, only a part of the networks in the recommendation model may be updated, where the part of the networks may be linear layers.

In particular, in one possible implementation, the neural network (which is the neural network used when generating the prompt) may be updated with the parameters of the embedded layer kept fixed according to the operation information and the corresponding tag.

For example, reference may be made to fig. 8, which is a flow chart illustrating the application of the embodiment corresponding to fig. 7 to a model pre-training process. FIG. 9 is a flow chart of the embodiment of FIG. 7 applied to a model fine tuning process. As shown in fig. 8 and 9, in the model training process, after scene prompt and user prompt are calculated, they are spliced with original feature characterization [ P ] _domain ||P _user ||e]Feature interaction part fed into original single scene recommendation moduleDividing into two parts. The model training process adopts two-stage optimization, comprising two processes (1) pre-training (2) Prompt fine Tuning (Prompt Tuning). The update parameters of the two stages are as follows, wherein the pre-training stage updates all parameters, and the prompt fine tuning stage updates part of the parameters, such as the parameters of scene prompt and user prompt, and the parameters of linear feature interaction.

Referring to fig. 10, fig. 10 is a flowchart of an algorithm according to an embodiment of the present application.

In the prior art, the multi-scene modeling utilizes the method of different parameter sharing modes to migrate useful knowledge among scenes, but has negative migration and teeterboard effect, and simultaneously has high training difficulty and increases the pressure of parameter storage. The embodiment of the application improves the problems at two points, namely, global information about commonalities learned in a pre-training stage is fixed in a fine adjustment stage, and characteristics and individuation of a cross-scene are definitely modeled, so that the functions of a prompt component and two-stage optimization are displayed. The method is more suitable for the deployment mode in the industry, and better prediction effect is obtained at the same time.

Taking the click prediction task as an example, offline experiments were performed on three public datasets, respectively, douban, amazon-5core, and Ali-CCP. Each dataset has three scenarios, and the evaluation index selects Area index (AUC) and logical loss (log) with higher and lower values representing better recommended performance, respectively. The data set statistics are shown in table one and comprise the sparsity of users, articles, interaction quantity and clicks.

Table 1 statistical indicators of experimental data set

Table 2 shows experimental results of the embodiment of the present application on three public data sets, the original single scene recommendation module was selected as DeepFM (Deep Factorization Machine). In addition, the compatibility and effectiveness of the embodiment of the application as a multi-scenario modeling paradigm is verified in another four original single-scenario recommendation modules, as shown in table 3.

TABLE 2

TABLE 3 Table 3

It can be seen that the embodiment of the application achieves a performance significantly exceeding that of other comparative baseline methods on all three public data sets, and exceeds pre-training + fine tuning on different raw single scene recommendation modules. Meanwhile, the embodiment of the application has high storage and calculation efficiency. Specifically, taking deep fm as an example for an original single-scene recommendation module, the pretraining+fine tuning needs to update all parameters from the parameter amount consideration (storage efficiency), while in the experiments of the above three public data sets, the PLATE only needs to update 6.36% (0.54%), 5.95% (0.10%), 4.45% (0.17%) parameters, and can obtain better recommendation performance, the brackets represent the proportion of the newly introduced prompt parameters, and the linear feature interaction part is the mainly updated parameter. On the other hand, from a training time perspective (computational efficiency), especially when the commercial recommendation system is faced with more scenarios, the way to maintain one tower for each scenario becomes impractical (e.g., thousands of scenarios). In the original Amazon dataset with 24 scenes, the GPU training time of the comparative model is as follows: single (24 hours), pre-train & Fine-tune (9 hours), shared Bottom (6 hours), MMoE (8 hours), PLE (12 hours), STAR (6 hours), and training time for the model of the present application is also 6 hours, it can be seen that the training time of the present application is minimal and more efficient.

Next, a data processing apparatus according to an embodiment of the present application will be described from the perspective of the apparatus, and referring to fig. 11, fig. 11 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application, and as shown in fig. 11, a data processing apparatus 1100 according to an embodiment of the present application includes:

an acquisition module 1101 for acquiring a first feature representation and a second feature representation; the first feature is obtained by extracting the feature of prompt, and the second feature is obtained by extracting the feature of attribute information of a user and an object; the prompt carries information related to the recommended scene; predicting the operation information of the user on the article through a recommendation model according to the fusion result of the first characteristic representation and the second characteristic representation;

the specific description of the obtaining module 1101 may refer to the descriptions of steps 501 and 502 in the above embodiments, and will not be repeated here.

And a recommending module 1102, configured to recommend the item to the user when the operation information meets a preset condition.

The specific description of the recommendation module 1102 may refer to the description of step 503 in the above embodiment, which is not repeated here.

indication information of the recommended scene; or,

attribute information of the user; or,

and the characteristic representation of the attribute information of the user.

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,

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

the processing module is used for acquiring prompt and a first characteristic representation; the prompt is obtained according to information related to a recommended scene; the first feature is represented by extracting the feature of the attribute information of the user and the object; predicting the operation information of the user on the object through a recommendation model according to the fusion result of the prompt and the first characteristic representation;

In one possible implementation, the processing module is specifically configured to: processing the information related to the recommended scene through a neural network to obtain the prompt; or, processing the information related to the recommended scene through a neural network to obtain a plurality of weights, wherein each weight corresponds to one feature representation, and fusing the plurality of feature representations according to the weights to obtain the prompt; and extracting the characteristics of the attribute information of the user and the object through the embedded layer to obtain the first characteristic representation.

In one possible implementation, the updating module is further configured to: and updating the neural network according to the operation information and the corresponding label under the condition of keeping the parameters of the embedded layer fixed.

In one possible implementation, the updating module is specifically configured to: only part of the networks in the recommendation model are updated.

In one possible implementation, the partial network is a linear layer.

Referring to fig. 12, fig. 12 is a schematic structural diagram of a terminal device provided by an embodiment of the present application, and a terminal device 1200 may be specifically shown as a mobile phone, a tablet, a notebook computer, an intelligent wearable device, etc., which is not limited herein. Wherein the terminal device 1200 implements the functions of the data processing method in the corresponding embodiment of fig. 5. Specifically, the terminal apparatus 1200 includes: a receiver 1201, a transmitter 1202, a processor 1203 and a memory 1204 (wherein the number of processors 1203 in the terminal device 1200 may be one or more), wherein the processor 1203 may comprise an application processor 12031 and a communication processor 12032. In some embodiments of the application, the receiver 1201, the transmitter 1202, the processor 1203, and the memory 1204 may be connected by a bus or other means.

The memory 1204 may include read only memory and random access memory, and provides instructions and data to the processor 1203. A portion of the memory 1204 may also include non-volatile random access memory (non-volatile random access memory, NVRAM). The memory 1204 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 implementing various operations.

The processor 1203 controls the operation of the terminal device. In a specific application, the individual components of the terminal device are coupled together by a bus system, which may comprise, 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 method disclosed in the above embodiment of the present application may be applied to the processor 1203 or implemented by the processor 1203. The processor 1203 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the method described above may be performed by integrated logic circuitry in hardware or instructions in software in the processor 1203. The processor 1203 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, which is suitable for AI operation, 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 1203 may implement or perform the methods, steps, and logic blocks disclosed in 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 the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding 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 1204, and the processor 1203 reads the information in the memory 1204 and performs the steps of steps 501 to 503 or the steps of 701 to 703 in combination with the hardware.

The receiver 1201 may be used to receive input digital or character information and to generate signal inputs related to the relevant settings and function control of the terminal device. The transmitter 1202 may be configured to output numeric or character information via a first interface; the transmitter 1202 may also be configured to send instructions to the disk stack via the first interface to modify data in the disk stack; transmitter 1202 may also include a display device such as a display screen.

Referring to fig. 13, fig. 13 is a schematic structural diagram of a server according to an embodiment of the present application, specifically, the server 1300 is implemented by one or more servers, where the server 1300 may have a relatively large difference due to different configurations or performances, and may include one or more central processing units (central processing units, CPU) 1313 (e.g., one or more processors) and a memory 1332, and one or more storage media 1330 (e.g., one or more mass storage devices) storing application programs 1342 or data 1344. Wherein the memory 1332 and storage medium 1330 may be transitory or persistent. The program stored on the storage medium 1330 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, the central processor 1313 may be configured to communicate with a storage medium 1330, executing a series of instruction operations in the storage medium 1330 on the server 1300.

The server 1300 may also include one or more power supplies 1326, one or more wired or wireless network interfaces 1350, one or more input/output interfaces 1358; or one or more operating systems 1341, such as Windows ServerTM, mac OS XTM, unixTM, linuxTM, freeBSDTM, etc.

Specifically, the server may perform the steps of step 501 to step 503 or the steps of step 701 to step 703 in the above embodiments.

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

The embodiment of the present application also provides 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 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. 14, fig. 14 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 NPU1400, and the NPU1400 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 1403, and the operation circuit 1403 is controlled by a controller 1404 to extract matrix data in a memory and perform multiplication operation.

The NPU1400 may implement the data processing methods provided in the embodiments described in fig. 5 or fig. 7 through inter-cooperation between the various devices within.

More specifically, in some implementations, the arithmetic circuit 1403 in the NPU1400 includes a plurality of processing units (PEs) inside. In some implementations, the operation circuit 1403 is a two-dimensional systolic array. The operation circuit 1403 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 1403 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 1402 and buffers the data on each PE in the arithmetic circuit. The arithmetic circuit takes matrix a data from the input memory 1401 and performs matrix operation with matrix B, and the partial result or the final result of the matrix obtained is stored in an accumulator (accumulator) 1408.

The unified memory 1406 is used for storing input data and output data. The weight data is directly transferred to the weight memory 1402 through the memory cell access controller (Direct Memory Access Controller, DMAC) 1405. The input data is also carried into the unified memory 1406 via the DMAC.

BIU is Bus Interface Unit, bus interface unit 1410, for the AXI bus to interact with DMAC and finger memory (Instruction Fetch Buffer, IFB) 1409.

The bus interface unit 1410 (Bus Interface Unit, abbreviated as BIU) is configured to fetch the instruction from the external memory by the instruction fetch memory 1409, and further configured to fetch the raw data of the input matrix a or the weight matrix B from the external memory by the memory unit access controller 1405.

The DMAC is mainly used to transfer input data in the external memory DDR to the unified memory 1406 or to transfer weight data to the weight memory 1402 or to transfer input data to the input memory 1401.

The vector calculation unit 1407 includes a plurality of operation processing units, and further processes such as vector multiplication, vector addition, exponential operation, logarithmic operation, size comparison, and the like are performed on the output of the operation circuit 1403 if necessary. 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 1407 can store the vector of processed outputs to the unified memory 1406. For example, the vector calculation unit 1407 may perform a linear function; or, a nonlinear function is applied to the output of the operation circuit 1403, for example, linear interpolation of the feature plane extracted by the convolution layer, and further, for example, vector of accumulated values, to generate an activation value. In some implementations, the vector computation unit 1407 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 arithmetic circuit 1403, e.g., for use in subsequent layers in a neural network.

An instruction fetch memory (instruction fetch buffer) 1409 connected to the controller 1404 and used for storing instructions used by the controller 1404;

the unified memory 1406, the input memory 1401, the weight memory 1402, and the finger memory 1409 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, 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 by means of special purpose hardware including application specific integrated circuits, special purpose CPUs, special purpose memories, special purpose components, etc. 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 for many more of the cases of 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., comprising several instructions for causing a computer device (which may be a personal computer, a training device, a network device, etc.) to perform the method according to 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 method of data processing, the method comprising:

acquiring a prompt and a first characteristic representation; the prompt is obtained according to information related to a recommended scene; the first feature is represented by extracting the feature of the attribute information of the user and the object;

and recommending the article to the user when the operation information meets the preset condition.

2. The method of claim 1, wherein the information related to the recommended scene comprises:

indication information of the recommended scene; or,

attribute information of the user; or,

and the characteristic representation of the attribute information of the user.

3. The method according to claim 1 or 2, wherein the obtaining a prompt comprises:

4. A method according to any one of claims 1 to 3, wherein,

different recommended scenes are different application programs; or,

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

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

and updating the recommendation model according to the operation information and the corresponding label.

6. The method of claim 5, wherein the acquiring a prompt comprises:

7. The method of claim 6, wherein the obtaining the first feature representation comprises:

extracting the characteristics of the attribute information of the user and the object through an embedded layer to obtain the first characteristic representation;

the method further comprises the steps of: and updating the neural network according to the operation information and the corresponding label under the condition of keeping the parameters of the embedded layer fixed.

8. The method of any of claims 5 to 7, wherein the updating the recommendation model comprises:

only part of the networks in the recommendation model are updated.

9. The method of claim 8, wherein the partial network is a linear layer.

10. The method according to any one of claims 5 to 9, wherein the information related to the recommended scene includes:

indication information of the recommended scene; or,

attribute information of the user; or,

and the characteristic representation of the attribute information of the user.

11. A data processing apparatus, the apparatus comprising:

12. The apparatus of claim 11, wherein the information related to the recommended scene comprises:

indication information of the recommended scene; or,

attribute information of the user; or,

and the characteristic representation of the attribute information of the user.

13. The apparatus according to claim 11 or 12, characterized in that the processing module is specifically configured to:

14. The device according to any one of claims 11 to 13, wherein,

different recommended scenes are different application programs; or,

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

15. A data processing apparatus, the apparatus comprising:

16. The apparatus according to claim 15, wherein the processing module is specifically configured to:

17. The apparatus of claim 16, wherein the update module is further configured to:

18. The apparatus according to any one of claims 15 to 17, wherein the updating module is specifically configured to:

only part of the networks in the recommendation model are updated.

19. The apparatus of claim 18, wherein the partial network is a linear layer.

20. The apparatus according to any one of claims 15 to 19, wherein the information related to the recommended scene includes:

indication information of the recommended scene; or,

attribute information of the user; or,

and the characteristic representation of the attribute information of the user.

21. 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 10.

22. 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 10.

23. A computer program product comprising code for implementing the method of any of claims 1 to 10 when said code is executed.