CN113642635A - Model training method and device, electronic device and medium - Google Patents
Model training method and device, electronic device and medium Download PDFInfo
- Publication number
- CN113642635A CN113642635A CN202110925544.9A CN202110925544A CN113642635A CN 113642635 A CN113642635 A CN 113642635A CN 202110925544 A CN202110925544 A CN 202110925544A CN 113642635 A CN113642635 A CN 113642635A
- Authority
- CN
- China
- Prior art keywords
- sample label
- sample
- transformed
- label value
- values
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Abstract
The present disclosure provides a model training method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product, and relates to the field of computers, in particular to the field of deep learning technology. The implementation scheme is as follows: obtaining a plurality of discretized sample label values to be transformed; determining a constraint condition for performing data transformation on a sample label value to be transformed; determining a converted sample label value set meeting constraint conditions through a parameter optimization method, wherein sample label values in the converted sample label value set correspond to the plurality of sample label values to be converted one by one; and training the model based on the transformed sample label value set.
Description
Technical Field
The present disclosure relates to the field of computers, and in particular, to the field of deep learning techniques, and more particularly, to a model training method, apparatus, electronic device, computer-readable storage medium, and computer program product.
Background
Artificial intelligence is the subject of research that makes computers simulate some human mental processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), both at the hardware level and at the software level. The artificial intelligence hardware technology generally comprises technologies such as a sensor, a special artificial intelligence chip, cloud computing, distributed storage, big data processing and the like, and the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, machine learning/deep learning, a big data processing technology, a knowledge graph technology and the like.
With the development of artificial intelligence, the application range of the machine learning model is wider and wider. Different scenes have different sample labels, and the sample labels are generally required to be processed and transformed before model training based on machine learning. The common transformation method is to design a transformation strategy according to manual experience, such as normalization or logarithm operation. The manually set sample label transformation strategy is not necessarily suitable for a specific learning task, and the machine learning effect is influenced.
Disclosure of Invention
The present disclosure provides a model training method, apparatus, electronic device, computer-readable storage medium, and computer program product.
According to an aspect of the present disclosure, there is provided a model training method, including: obtaining a plurality of discretized sample label values to be transformed; determining a constraint condition for performing data transformation on the sample label value to be transformed; determining a converted sample label value set meeting the constraint condition through a parameter optimization method, wherein sample label values in the converted sample label value set correspond to the plurality of sample label values to be converted one by one; and training the model based on the transformed sample label value set.
According to another aspect of the present disclosure, there is provided an information recommendation method including: obtaining predicted interactive behavior data of the user on the information to be recommended based on a model obtained by training the method in one aspect of the disclosure; and recommending the information to be recommended based on the interactive behavior data, wherein the interactive behavior data comprises at least one of the group consisting of: click rate, dwell time.
According to another aspect of the present disclosure, there is provided a model training apparatus including: the acquisition unit is configured to acquire a plurality of discretized sample label values to be transformed; a first determining unit configured to determine a constraint condition for data transformation on the sample tag value to be transformed; a second determining unit, configured to determine, by a parameter optimization method, a transformed sample label value set that satisfies the constraint condition, where sample label values in the transformed sample label value set correspond to the plurality of sample label values to be transformed one to one; and a training unit configured to train the model based on the transformed set of sample label values.
According to another aspect of the present disclosure, there is provided an information recommendation apparatus including: the obtaining unit is configured to obtain predicted interaction behavior data of the user on the information to be recommended based on a model obtained by training through the method according to one aspect of the disclosure; and a recommending unit configured to recommend the information to be recommended based on the interactive behavior data, wherein the interactive behavior data includes at least one of the group consisting of: click rate, dwell time.
According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method according to the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method according to the present disclosure.
According to another aspect of the disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method according to the disclosure.
According to one or more embodiments of the disclosure, a transformation strategy of a sample label does not need to be determined by depending on expert experience, a transformed sample label value more suitable for a given learning task can be obtained in a self-adaptive manner through a parameter optimization method, and the iteration effect of a model can be remarkably improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the embodiments and, together with the description, serve to explain the exemplary implementations of the embodiments. The illustrated embodiments are for purposes of illustration only and do not limit the scope of the claims. Throughout the drawings, identical reference numbers designate similar, but not necessarily identical, elements.
FIG. 1 illustrates a schematic diagram of an exemplary system in which various methods described herein may be implemented, according to an embodiment of the present disclosure;
FIG. 2 shows a flow diagram of a model training method according to an embodiment of the present disclosure;
FIG. 3 shows a sample label value mapping relationship diagram before and after transformation, in accordance with an embodiment of the present disclosure;
FIG. 4 illustrates a flow diagram for determining sample tag values that satisfy constraints through parameter optimization according to one embodiment of the present disclosure;
FIG. 5 illustrates a flow diagram for determining values satisfying a constraint through parameter optimization according to another embodiment of the present disclosure;
FIG. 6 shows a flow diagram of an information recommendation method according to an embodiment of the present disclosure;
FIG. 7 shows a block diagram of a model training apparatus according to an embodiment of the present disclosure;
fig. 8 is a block diagram illustrating a structure of an information recommendation apparatus according to an embodiment of the present disclosure; and
FIG. 9 illustrates a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, the timing relationship, or the importance relationship of the elements, and such terms are used only to distinguish one element from another. In some examples, a first element and a second element may refer to the same instance of the element, and in some cases, based on the context, they may also refer to different instances.
The terminology used in the description of the various described examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the elements may be one or more. Furthermore, the term "and/or" as used in this disclosure is intended to encompass any and all possible combinations of the listed items.
Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.
Fig. 1 illustrates a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein may be implemented in accordance with embodiments of the present disclosure. Referring to fig. 1, the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. Client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.
In embodiments of the present disclosure, server 120 may run one or more services or software applications that enable the model training method to be performed.
In some embodiments, the server 120 may also provide other services or software applications that may include non-virtual environments and virtual environments. In certain embodiments, these services may be provided as web-based services or cloud services, for example, provided to users of client devices 101, 102, 103, 104, 105, and/or 106 under a software as a service (SaaS) model.
In the configuration shown in fig. 1, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or a combination thereof, which may be executed by one or more processors. A user operating a client device 101, 102, 103, 104, 105, and/or 106 may, in turn, utilize one or more client applications to interact with the server 120 to take advantage of the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from system 100. Accordingly, fig. 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.
The user may use client devices 101, 102, 103, 104, 105, and/or 106 to enter corresponding parameters, constraints, and the like. The client device may provide an interface that enables a user of the client device to interact with the client device. The client device may also output information to the user via the interface. Although fig. 1 depicts only six client devices, those skilled in the art will appreciate that any number of client devices may be supported by the present disclosure.
The server 120 may include one or more general purpose computers, special purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-end servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and/or combination. The server 120 may include one or more virtual machines running a virtual operating system, or other computing architecture involving virtualization (e.g., one or more flexible pools of logical storage that may be virtualized to maintain virtual storage for the server). In various embodiments, the server 120 may run one or more services or software applications that provide the functionality described below.
The computing units in server 120 may run one or more operating systems including any of the operating systems described above, as well as any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and/or middle tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, and the like.
In some implementations, the server 120 may include one or more applications, such as applications for services such as object detection and recognition, signal conversion, etc., based on data such as image, video, voice, text, digital signals, etc., to process task requests such as voice interactions, text classification, image recognition, or information recommendations, etc., received from the client devices 101, 102, 103, 104, 105, and 106. The server can train the neural network model by using the training samples according to a specific deep learning task, can test each sub-network in the super-network module of the neural network model, and determines the structure and parameters of the neural network model for executing the deep learning task according to the test result of each sub-network. Various data can be used as training sample data of the deep learning task, such as image data, audio data, video data or text data. After the training of the neural network model is completed, the server 120 may also automatically search out the optimal model parameters through a model search technique to perform a corresponding task.
In some embodiments, the server 120 may be a server of a distributed system, or a server incorporating a blockchain. The server 120 may also be a cloud server, or a smart cloud computing server or a smart cloud host with artificial intelligence technology. The cloud Server is a host product in a cloud computing service system, and is used for solving the defects of high management difficulty and weak service expansibility in the traditional physical host and Virtual Private Server (VPS) service.
The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store data such as sample labels before and after transformation. The data store 130 may reside in various locations. For example, the data store used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The data store 130 may be of different types. In certain embodiments, the data store used by the server 120 may be a database, such as a relational database. One or more of these databases may store, update, and retrieve data to and from the database in response to the command.
In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the application may be different types of databases, such as key-value stores, object stores, or regular stores supported by a file system.
The system 100 of fig. 1 may be configured and operated in various ways to enable application of the various methods and apparatus described in accordance with the present disclosure.
In a recommendation system, information, products, and the like that a user is interested in are generally recommended to the user according to the information requirements of the user. Generally, the historical interest of the user can be learned based on the user characteristics through a machine learning method, so that the interest degree of the user in information to be recommended is obtained. For example, in a machine learning-based information recommendation scenario, common learning tasks may include a CTR (Click-Through-Rate) estimation task, a dwell time estimation task, and the like. For example, an interest index such as CTR of the information to be recommended may be determined based on the trained neural network model, so as to recommend information to the user based on the interest index.
The above neural network model usually needs to transform an original sample label (a sample label to be transformed) before training, and the sample label is a label value of a training sample of the model. In the recommendation system, the sample labels are generally click rate, dwell time, etc. Taking the sample label as the stay time as an example, the common learning task in the recommendation system is the stay time after the user clicks the corresponding image, text, video or commodity. The viewing time of a user in a teletext or video asset or commercial product is typically between a few seconds and a few hours. If the model training is performed directly with the original sample labels, the model is difficult to converge or learn sufficiently. Therefore, a common way of processing is to perform a time-length truncation (for example, processing for more than 1 hour as 1 hour), and then perform a transformation of the sample label, and a common way of transforming is to divide by the maximum value of the label (generally, the above mentioned truncation threshold value) to normalize to between 0 and 1. However, the manually set sample label transformation strategy may not be optimal for a specific learning task, and therefore, the training effect of the model is affected.
Accordingly, a model training method is provided according to an embodiment of the present disclosure. FIG. 2 shows a flow diagram of a model training method according to an embodiment of the present disclosure. As shown in fig. 2, method 200 may include: obtaining a plurality of discretized sample label values to be transformed (step 210); determining a constraint condition for data transformation of a sample label value to be transformed (step 220); determining a transformed sample label value set which meets constraint conditions through a parameter optimization method, wherein sample label values in the transformed sample label value set correspond to a plurality of sample label values to be transformed one by one (step 230); and training the model based on the transformed set of sample label values (step 240).
According to the model training method disclosed by the embodiment of the disclosure, a transformation strategy of the sample label does not need to be determined by depending on expert experience, the transformed sample label value more suitable for a given learning task can be obtained in a self-adaptive manner through the parameter optimization method, and the iteration effect of the model can be remarkably improved.
According to some embodiments, obtaining a discretized plurality of sample label values to be transformed may comprise: determining the value range of the sample label value to be transformed; and in the value range, carrying out discretization value taking based on a preset sampling interval to obtain the plurality of sample label values to be transformed.
Taking a click duration estimation model in a recommendation system as an example, a sample label of the model is the watching duration of a user in a picture or video resource or a commodity, which is generally between several seconds and several hours. Thus, for example, a duration cut-off, e.g., a 1-hour process over 1 hour, may be performed first to determine the value range for the sample label. Sampling is performed over the range of values after truncation (0-1 hour in the above example) to obtain a plurality of discrete points. For example, sampling may be performed within the value range based on a preset sampling interval, and the more sampling points, the smoother the subsequently obtained transformation curve for representing the mapping relationship between the original sample label and the transformed sample label, and of course, the more parameter values that need to be optimized.
In some examples, the original sample label may also be a discrete value, such as a label value in a binary model, without limitation.
As shown in fig. 3, the horizontal axis Y represents the original sample label (i.e., the sample label to be transformed), and the vertical axis Y' represents the transformed sample label value. Thus, the transformation function can be represented by a discretized pair of parameter maps: (Y)1,Y′1)…(Yn,Y′n). The point corresponding to the original sample label obtained by sampling is Y1、…、Yn(ii) a Suppose that the point corresponding to the transformed sample label is Y'1、…、Y′nI.e. the parameter value to be optimized. Exemplarily, Y in FIG. 31、YnMay be discrete points divided according to the value range of the original sample label, wherein the sampling mode may be equally spaced division or equally frequency division according to the sample size (so that the sample size of each interval is basically consistent), and the threshold value Y is exceededTCan be set to Y by uniform truncationT。
After obtaining the discretization value of the original sample label, a transformed sample label set corresponding to the original sample label and meeting the constraint condition can be determined by a parameter optimization method.
According to some embodiments, the constraint may be expressed according to the following formula:
(Y′k+1-Y′k)(Yk+1-Yk)>0
wherein, Yk、Yk+1Are respectively sample tag values before conversion, Y'k、Y′k+1Are each Yk、Yk+1The transformed sample label value, where k is 1,2, …, n, n is a positive integer.
In some embodiments, after model training based on the transformed sample labels, the result of model prediction needs to be inversely transformed to the original data form. Since it is necessary to ensure that the transformation function is invertible, it is necessary to ensure that the transformation curve as shown in fig. 3 is monotonically increasing,namely: (Y'k+1-Y′k)(Yk+1-Yk)>0. In addition, by limiting the constraint conditions, the searching efficiency of the parameter optimizing process can be more efficient.
According to some embodiments, as shown in fig. 4, determining a set of transformed sample tag values that satisfy the constraint by a parameter optimization method (step 230) may include: initializing to obtain a first number of sets of sample label values, wherein each set of sample label values in the first number of sets of sample label values includes a plurality of sample label values that satisfy a constraint and that are in one-to-one correspondence with the plurality of sample label values to be transformed (step 410); pre-training the model based on the first number of sample label value sets respectively to obtain corresponding model indexes (step 420); and using the sample label value set corresponding to the optimal model index as the transformed sample label value set (step 430).
For example, after obtaining a plurality of original sample tag values to be transformed, a set of transformed sample tag values corresponding to the original sample tag values to be transformed one by one may be obtained using a general parameter optimization Method, including but not limited to automatic machine learning (AutoML), evolutionary learning (ES), Grid Search (Grid Search), Random Search (Random Search), bayesian optimization (e.g., gaussian process), Amoeba algorithm (Amoeba or Nelder-Mead), Cross Entropy Method (Cross-Entropy Method), and so on. Examples of obtaining the set of transformed sample tag values by a parameter optimization method may include: initialization to obtain a first number of sample label value sets, i.e. a first number of transformed sample label value sets. For example, a plurality of sets of sample label values satisfying the above constraint formula may be randomly generated; alternatively, the sample label value set satisfying the above constraint formula can be obtained by any known transformation method. Then, model pre-training can be performed by using the sample label values of each group to obtain model indexes, and the sample label value set corresponding to the optimal model index is used as the transformed sample label value set for model training.
It is to be understood that the "pre-training" process herein is a training process for determining the first set of gradient values, as distinguished from the model training process in step 240.
According to some embodiments, the model indicator may include: positive negative sequence ratio (PNR), area under the curve (AUC, e.g., ROC curve area), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the like, without limitation. Taking the above duration estimation as an example, a positive-negative sequence ratio index (PNR) of the model can be obtained, so as to select a group of gradient values corresponding to the optimal index according to the model index.
According to some embodiments, as shown in fig. 5, determining the transformed set of sample tag values satisfying the constraint by the parameter optimization method may further include: the following operations are performed one or more times (step 510): generating a new second number of sample label value sets based on a plurality of sample label values in the sample label value sets corresponding to the optimal model indicator (step 5101); modifying sample label values of the new second number of sample label value sets that do not satisfy the constraint condition so as to satisfy the constraint condition (step 5102); pre-training the model based on the corrected second number of sample label value sets respectively to obtain corresponding model indexes (step 5103); determining a sample label value set corresponding to the optimal model index (step 5104); the sample label value set corresponding to the optimal model index is used as the transformed sample label value set (step 520).
In some examples, the execution times of steps 5101-5104 may be set according to actual requirements, for example, a fixed number of times may be set; or may be set to achieve a corresponding index requirement, etc.
In the parameter optimization process, a new second number of sample label value sets may be generated based on a plurality of sample label values in the sample label value set corresponding to the optimal model index. Specifically, a plurality of sample label values in the sample label value set corresponding to the optimal model index may be respectively subjected to corresponding mathematical operations (for example, by an ameba method), so as to obtain a new sample label value set. The different parameter optimization methods may operate differently to generate the new second number of sets of sample tag values. For example, a perturbation may be added to a plurality of sample label values in the set of sample label values corresponding to the optimal model index to generate a new second number of sets of sample label values.
In generating a new set of sample label values, for example by adding a perturbation, there will typically be sample label value generation that does not satisfy the above constraints. For sample label values that do not satisfy the constraint formula mentioned above, they may be discarded or revised. But dropping may reduce the efficiency of parameter optimization because it is likely that many candidate sample tag values will be dropped. Different parameter optimization methods add perturbations to the parameters (sample tag values) in different ways, and even if the parameters generated randomly by initialization satisfy the constraints, the new parameters do not necessarily satisfy the constraints during the perturbation process, and thus are discarded. Thus, according to some embodiments, modifying the sample tag values of the new second number of sample tag value sets that do not satisfy the constraint comprises: determining a maximum sample label value after transformation, a minimum sample label value after transformation and a sample label value variation interval corresponding to the parameter optimization method; and correcting the sample label value which does not meet the constraint condition based on the maximum sample label value, the minimum sample label value and the minimum sample label value change interval.
In some embodiments, the parameter minimum sample tag value change interval is set to step > 0. Assuming that the sample labels are discretized into n points, the minimum value of the transformed sample labels is set to min _ val >0, and the maximum value is set to max _ val > min _ val. The above-mentioned transition interval, minimum value and maximum value may be set according to a specific service scenario, for example, min _ val may be set to 0, and max _ val may be set to 1. It will be appreciated that it is necessary to ensure that max _ val > -min _ val + (n-1) step so that the interval between transformed sample tag values is at least the set interval step. Exemplarily, set v (i) to represent the transformed sample label value of the ith original sample label, 0< ═ i < n (the sample label is discretized into n points); the above configuration can be set before the parameter optimization method is started and kept unchanged during the optimization process. After the configuration data is set, parameter optimization can be performed to obtain corresponding transformed sample tag values. In the optimization process, the transformed sample label value which does not satisfy the constraint condition can be corrected based on the following correction method:
(1) the following auxiliary variables are initialized: prev min val step, low min val step, and high max val-n step;
(2) for each i of [0, n), repeating the following operations in sequence:
low＝prev+step
high＝high+step
v(i)＝max(low,min(high,v(i)))
prev＝v(i)
that is, when i is equal to 0, the above operation is performed once based on the initial auxiliary variable; when i is equal to 1, the operation is executed again on the basis of the auxiliary variable calculated when i is equal to 0; when i is 2, the above operation … is performed again on the basis of the auxiliary variable calculated when i is 1 until the above operation is iteratively performed for each value of i. In this way, v (i) does not change after the iteration is performed for the transformed sample label values that satisfy the constraint; and the transformed sample label values that do not satisfy the constraint are modified.
By correcting the transformed sample tag value which does not meet the constraint condition so as to enable the transformed sample tag value to meet the constraint condition, the efficiency of parameter optimization can be improved, and the optimization process is more efficient.
According to some embodiments, training the model based on the transformed set of sample label values comprises: obtaining a first sample label value corresponding to a training sample; and determining the sample label value after the first sample label value is transformed by a linear interpolation method based on the transformed sample label value set, and performing model training based on the transformed sample label value.
By parameter optimization, transformed sample label values corresponding to each discretized original sample label value can be obtained. For any given original sample label value Y, the transformed sample label value corresponding to point Y may be obtained by interpolation methods including, but not limited to, linear interpolation, lagrange interpolation, newton interpolation, cubic hermitian interpolation, and the like.
With continued reference to FIG. 3, for a value of Y betweenk、Yk+1The transformed sample label value Y' may be determined, for example, by a linear interpolation method based on the following formula:
after the transformed sample label value is obtained, the model can be trained based on the transformed sample label value.
For the model trained based on the transformed sample label, the prediction result p' can be inversely transformed as follows: firstly, finding out an interval [ Y ' in which p ' is positioned 'k,Y′k+1]Then, inverse mapping is carried out by using the following linear interpolation transformation to obtain a predicted value p in the threshold range of the original sample label:
according to an embodiment of the present disclosure, as shown in fig. 6, there is also provided an information recommendation method 600, including: acquiring predicted interaction behavior data of the user on the information to be recommended based on a model trained by the method (step 610); and recommending the information to be recommended based on the interactive behavior data (step 620).
The interaction behavior data comprises at least one of the group consisting of: click rate, dwell time, play-out rate, interaction rate, etc. The interaction modes corresponding to the interaction rates include, but are not limited to: like likes, replies, comments, collections, shares, concerns, awards, etc.
In some examples, information to be recommended, such as live videos, commodities, and the like, may be obtained. For example, data of information to be recommended on a predetermined platform may be acquired, or data of information to be recommended on a corresponding platform or browser china may be captured, so as to recommend the corresponding information to be recommended to a corresponding user based on the data.
In some examples, feature extraction may be performed on the information to be recommended. For example, each piece of information to be recommended may be subjected to content understanding to obtain features corresponding thereto. In the commodity push scenario, the feature may be the name, category, brand, model, color, etc. of the commodity. Taking the example that the information to be recommended includes lipstick, the obtained characteristics may be: lipstick (name), XX (brand), 770 (model, i.e. color number), true red (color), makeup (category), etc. For example, the identified commodity category may also be a fine-grained classification such as lip makeup. In some examples, the extracted target feature may be used as tag data of corresponding information to be recommended. For example, content understanding can be performed on corresponding information to be recommended through a recognition model based on deep learning to recognize text features and the like in the information to be recommended. Illustratively, the recognition model may be a model based on natural language processing, such as DSSM (deep Structured Semantic model), BERT (bidirectional Encoder retrieval from transformations), and the like. For example, text data in the information to be recommended may be obtained to obtain corresponding keywords. For example, if the information to be recommended to be identified is a picture, text data in the picture may be identified to extract corresponding target features based on keywords. If the information to be recommended to be identified is the short video, the short video can be subjected to frame fetching to obtain an extracted picture of each frame; and identifying characters in the picture to obtain character data. Additionally or alternatively, speech data in the short video may also be converted to text data by providing speech recognition techniques (ASR). And finally, obtaining corresponding target characteristics based on a keyword extraction technology. For example, corresponding visual features in the information to be recommended may also be identified, for example, based on the ResNet101 model, so as to convert the identified visual features into text data, thereby obtaining corresponding target features.
After the corresponding features are obtained, corresponding identification can be carried out according to the obtained model so as to predict the interest degree of the user for the information to be recommended, and the interest degree can be represented through the predicted interactive behavior data. The interaction behavior data may be, for example, click rate, dwell time, etc. Therefore, information recommendation can be performed based on the predicted interactive behavior data to match information to be recommended, which is interested by the user, so that different information recommendation effects can be generated for different users, and the information click rate of the user is improved.
According to an embodiment of the present disclosure, as shown in fig. 7, there is also provided a model training apparatus 700, including: an obtaining unit 710 configured to obtain a plurality of discretized sample label values to be transformed; a first determining unit 720 configured to determine a constraint condition for data transformation on the sample tag value to be transformed; a second determining unit 730, configured to determine, by a parameter optimization method, a transformed sample label value set that satisfies the constraint condition, where sample label values in the transformed sample label value set correspond to the plurality of sample label values to be transformed one to one; and a training unit 740 configured to train the model based on the transformed set of sample label values.
Here, the operations of the above units 710 to 740 of the model training apparatus 700 are similar to the operations of the steps 210 to 240 described above, and are not described herein again.
According to an embodiment of the present disclosure, as shown in fig. 8, there is also provided an information recommendation apparatus 800 including: an obtaining unit 810, configured to obtain predicted interaction behavior data of the user for the information to be recommended based on the model trained by the foregoing method; and a recommending unit 820 configured to recommend the information to be recommended based on the interactive behavior data. The interaction behavior data may include, but is not limited to: click rate, dwell time, play-out rate, interaction rate, etc. The interaction modes corresponding to the interaction rates include, but are not limited to: like a praise, a reply, a comment, a collection, a share, an attention and a reward.
In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.
According to an embodiment of the present disclosure, there is also provided an electronic device, a readable storage medium, and a computer program product.
Referring to fig. 9, a block diagram of a structure of an electronic device 900, which may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic device is intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 9, the apparatus 900 includes a computing unit 901, which can perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM)902 or a computer program loaded from a storage unit 908 into a Random Access Memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The calculation unit 901, ROM 902, and RAM 903 are connected to each other via a bus 904. An input/output (I/O) interface 905 is also connected to bus 904.
A number of components in the device 900 are connected to the I/O interface 905, including: an input unit 906, an output unit 907, a storage unit 908, and a communication unit 909. The input unit 906 may be any type of device capable of inputting information to the device 900, and the input unit 906 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device, and may include, but is not limited to, a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and/or a remote control. Output unit X07 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, a video/audio output terminal, a vibrator, and/or a printer. Storage unit 908 may include, but is not limited to, a magnetic disk, an optical disk. The communication unit 909 allows the device 900 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and/or chipsets, such as bluetooth (TM) devices, 1302.11 devices, WiFi devices, WiMax devices, cellular communication devices, and/or the like.
The computing unit 901 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The computing unit 901 performs the various methods and processes described above, such as the methods 200 or 600. For example, in some embodiments, the method 200 or 600 may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 900 via ROM 902 and/or communications unit 909. When the computer program is loaded into RAM 903 and executed by computing unit 901, one or more steps of method 200 or 600 described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the method 200 or 600 by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be performed in parallel, sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it is to be understood that the above-described methods, systems and apparatus are merely exemplary embodiments or examples and that the scope of the present invention is not limited by these embodiments or examples, but only by the claims as issued and their equivalents. Various elements in the embodiments or examples may be omitted or may be replaced with equivalents thereof. Further, the steps may be performed in an order different from that described in the present disclosure. Further, various elements in the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced with equivalent elements that appear after the present disclosure.
Claims (19)
1. A model training method, comprising:
obtaining a plurality of discretized sample label values to be transformed;
determining a constraint condition for performing data transformation on the sample label value to be transformed;
determining a converted sample label value set meeting the constraint condition through a parameter optimization method, wherein sample label values in the converted sample label value set correspond to the plurality of sample label values to be converted one by one; and
training the model based on the transformed sample label value set.
2. The method of claim 1, wherein obtaining a discretized plurality of exemplar label values to be transformed comprises:
determining the value range of the sample label value to be transformed; and
and in the value range, carrying out discretization value taking based on a preset sampling interval to obtain the plurality of sample label values to be transformed.
3. The method of claim 1, wherein determining the set of transformed sample tag values that satisfy the constraint by a parameter optimization method comprises:
initializing to obtain a first number of sets of sample label values, wherein each set of sample label values of the first number of sets of sample label values comprises a plurality of sample label values in one-to-one correspondence with the plurality of sample label values to be transformed that satisfy the constraint;
pre-training the model based on the first number of sample label value sets respectively to obtain corresponding model indexes; and
and taking the sample label value set corresponding to the optimal model index as the transformed sample label value set.
4. The method of claim 3, wherein determining the set of transformed sample tag values that satisfy the constraint by a parameter optimization method further comprises:
performing the following one or more times:
generating a new second number of sample tag value sets based on a plurality of sample tag values in the sample tag value set corresponding to the optimal model indicator;
modifying sample tag values in the new second number of sample tag value sets that do not satisfy the constraint to satisfy the constraint;
pre-training the model based on the corrected sample label value sets of the second quantity respectively to obtain corresponding model indexes; and
determining a sample label value set corresponding to the optimal model index;
and taking the sample label value set corresponding to the optimal model index as the transformed sample label value set.
5. The method of claim 4, wherein modifying the sample tag values in the new second number of sample tag value sets that do not satisfy the constraint comprises:
determining a maximum sample label value after transformation, a minimum sample label value after transformation and a sample label value variation interval corresponding to the parameter optimization method; and
and correcting the sample label value which does not meet the constraint condition based on the maximum sample label value, the minimum sample label value and the minimum sample label value change interval.
6. The method of claim 1, wherein training the model based on the transformed set of sample tag values comprises:
obtaining a first sample label value corresponding to a training sample;
and determining the sample label value after the first sample label value is transformed by a linear interpolation method based on the transformed sample label value set, and performing model training based on the transformed sample label value.
7. The method of claim 1, wherein the constraint is expressed according to the following formula:
(Y′k+1-Y′k)(Yk+1-Yk)>0
wherein, Yk、Yk+1Are respectively sample tag values before conversion, Y'k、Y′k+1Are each Yk、Yk+1The transformed sample label value data, where k is 1,2, …, n, n is a positive integer.
8. The method of claim 3 or 4, wherein the model metrics comprise one or more of the group consisting of: positive and negative sequence ratio, area under the curve, root mean square error, average absolute error.
9. An information recommendation method, comprising:
acquiring predicted interaction behavior data of the user on the information to be recommended based on a model trained by the method according to any one of claims 1-8; and
recommending the information to be recommended based on the interactive behavior data.
10. A model training apparatus comprising:
the acquisition unit is configured to acquire a plurality of discretized sample label values to be transformed;
a first determining unit configured to determine a constraint condition for data transformation on the sample tag value to be transformed;
a second determining unit, configured to determine, by a parameter optimization method, a transformed sample label value set that satisfies the constraint condition, where sample label values in the transformed sample label value set correspond to the plurality of sample label values to be transformed one to one; and
a training unit configured to train the model based on the transformed set of sample label values.
11. The apparatus of claim 10, wherein the obtaining unit comprises:
a unit for determining a value range of the sample label value to be transformed; and
and the unit is used for carrying out discretization value taking on the basis of a preset sampling interval in the value taking range so as to obtain the plurality of sample label values to be transformed.
12. The apparatus of claim 10, wherein the second determining unit comprises:
means for initializing to obtain a first number of sets of sample label values, wherein each set of sample label values in the first number of sets of sample label values comprises a plurality of sample label values in one-to-one correspondence with the plurality of sample label values to be transformed that satisfy the constraint;
means for pre-training the model based on the first number of sample label value sets, respectively, to obtain corresponding model indices; and
and the unit is used for taking the sample label value set corresponding to the optimal model index as the transformed sample label value set.
13. The apparatus of claim 12, wherein the second determining unit further comprises:
means for performing the following one or more times:
generating a new second number of sample tag value sets based on a plurality of sample tag values in the sample tag value set corresponding to the optimal model indicator;
modifying sample tag values in the new second number of sample tag value sets that do not satisfy the constraint to satisfy the constraint;
pre-training the model based on the corrected sample label value sets of the second quantity respectively to obtain corresponding model indexes; and
determining a sample label value set corresponding to the optimal model index;
and a unit for using the sample label value set corresponding to the optimal model index as the transformed sample label value set.
14. The apparatus of claim 13, wherein means for modifying the sample tag values in the new second number of sample tag value sets that do not satisfy the constraint comprises:
a unit for determining a transformed maximum sample label value, a transformed minimum sample label value, and a sample label value variation interval corresponding to the parameter optimization method; and
means for modifying the exemplar label values that do not satisfy the constraint condition based on the maximum exemplar label value, the minimum exemplar label value, and the minimum exemplar label value change interval.
15. The method of claim 10, wherein the training unit comprises:
a unit for obtaining a first sample label value corresponding to a training sample;
and the unit is used for determining the sample label value after the first sample label value is transformed by a linear interpolation method based on the transformed sample label value set and carrying out model training based on the transformed sample label value.
16. An information recommendation apparatus comprising:
an obtaining unit, configured to obtain predicted interaction behavior data of the user on the information to be recommended based on a model trained by the method according to any one of claims 1-8; and
and the recommending unit is configured to recommend the information to be recommended based on the interactive behavior data.
17. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8 or claim 9.
18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-8 or claim 9.
19. A computer program product comprising a computer program, wherein the computer program realizes the method of any one of claims 1-8 or claim 9 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110925544.9A CN113642635B (en) | 2021-08-12 | 2021-08-12 | Model training method and device, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110925544.9A CN113642635B (en) | 2021-08-12 | 2021-08-12 | Model training method and device, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113642635A true CN113642635A (en) | 2021-11-12 |
| CN113642635B CN113642635B (en) | 2023-09-15 |
Family
ID=78421192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110925544.9A Active CN113642635B (en) | 2021-08-12 | 2021-08-12 | Model training method and device, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642635B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114612725A (en) * | 2022-03-18 | 2022-06-10 | 北京百度网讯科技有限公司 | Image processing method, device, equipment and storage medium |
| CN115293291A (en) * | 2022-08-31 | 2022-11-04 | 北京百度网讯科技有限公司 | Training method of ranking model, ranking method, device, electronic equipment and medium |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040193419A1 (en) * | 2003-03-31 | 2004-09-30 | Kimball Steven F. | Cascaded hidden Markov model for meta-state estimation |
| US9704054B1 (en) * | 2015-09-30 | 2017-07-11 | Amazon Technologies, Inc. | Cluster-trained machine learning for image processing |
| CN111210024A (en) * | 2020-01-14 | 2020-05-29 | 深圳供电局有限公司 | Model training method and device, computer equipment and storage medium |
| CN111275089A (en) * | 2020-01-16 | 2020-06-12 | 北京松果电子有限公司 | Classification model training method and device and storage medium |
| CN111967611A (en) * | 2020-08-20 | 2020-11-20 | 贝壳技术有限公司 | Feature generation method and apparatus, electronic device, and storage medium |
| US20200401852A1 (en) * | 2019-06-20 | 2020-12-24 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for generating information assessment model |
| CN112241452A (en) * | 2020-10-16 | 2021-01-19 | 百度(中国)有限公司 | Model training method and device, electronic equipment and storage medium |
| CN112464100A (en) * | 2020-12-14 | 2021-03-09 | 未来电视有限公司 | Information recommendation model training method, information recommendation method, device and equipment |
| WO2021042556A1 (en) * | 2019-09-03 | 2021-03-11 | 平安科技（深圳）有限公司 | Classification model training method, apparatus and device, and computer-readable storage medium |
| CN112684497A (en) * | 2019-10-17 | 2021-04-20 | 中国石油天然气集团有限公司 | Seismic waveform clustering method and device |
| CN112733911A (en) * | 2020-12-31 | 2021-04-30 | 平安科技（深圳）有限公司 | Entity recognition model training method, device, equipment and storage medium |
| US20210158195A1 (en) * | 2019-11-26 | 2021-05-27 | International Business Machines Corporation | Data label verification |
| CN112906799A (en) * | 2021-02-25 | 2021-06-04 | 深圳前海微众银行股份有限公司 | Regression learning adjusting method, device and system and computer readable storage medium |
| CN113033219A (en) * | 2021-03-25 | 2021-06-25 | 北京百度网讯科技有限公司 | Model training method and device, electronic equipment and computer readable storage medium |
| US20210201147A1 (en) * | 2018-11-28 | 2021-07-01 | Tencent Technology (Shenzhen) Company Limited | Model training method, machine translation method, computer device, and storage medium |
-
2021
- 2021-08-12 CN CN202110925544.9A patent/CN113642635B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040193419A1 (en) * | 2003-03-31 | 2004-09-30 | Kimball Steven F. | Cascaded hidden Markov model for meta-state estimation |
| US9704054B1 (en) * | 2015-09-30 | 2017-07-11 | Amazon Technologies, Inc. | Cluster-trained machine learning for image processing |
| US20210201147A1 (en) * | 2018-11-28 | 2021-07-01 | Tencent Technology (Shenzhen) Company Limited | Model training method, machine translation method, computer device, and storage medium |
| US20200401852A1 (en) * | 2019-06-20 | 2020-12-24 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for generating information assessment model |
| WO2021042556A1 (en) * | 2019-09-03 | 2021-03-11 | 平安科技（深圳）有限公司 | Classification model training method, apparatus and device, and computer-readable storage medium |
| CN112684497A (en) * | 2019-10-17 | 2021-04-20 | 中国石油天然气集团有限公司 | Seismic waveform clustering method and device |
| WO2021105157A1 (en) * | 2019-11-26 | 2021-06-03 | International Business Machines Corporation | Data label verification |
| US20210158195A1 (en) * | 2019-11-26 | 2021-05-27 | International Business Machines Corporation | Data label verification |
| CN111210024A (en) * | 2020-01-14 | 2020-05-29 | 深圳供电局有限公司 | Model training method and device, computer equipment and storage medium |
| CN111275089A (en) * | 2020-01-16 | 2020-06-12 | 北京松果电子有限公司 | Classification model training method and device and storage medium |
| CN111967611A (en) * | 2020-08-20 | 2020-11-20 | 贝壳技术有限公司 | Feature generation method and apparatus, electronic device, and storage medium |
| CN112241452A (en) * | 2020-10-16 | 2021-01-19 | 百度(中国)有限公司 | Model training method and device, electronic equipment and storage medium |
| CN112464100A (en) * | 2020-12-14 | 2021-03-09 | 未来电视有限公司 | Information recommendation model training method, information recommendation method, device and equipment |
| CN112733911A (en) * | 2020-12-31 | 2021-04-30 | 平安科技（深圳）有限公司 | Entity recognition model training method, device, equipment and storage medium |
| CN112906799A (en) * | 2021-02-25 | 2021-06-04 | 深圳前海微众银行股份有限公司 | Regression learning adjusting method, device and system and computer readable storage medium |
| CN113033219A (en) * | 2021-03-25 | 2021-06-25 | 北京百度网讯科技有限公司 | Model training method and device, electronic equipment and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 张随雨;杨成;: "一种多标签统一域嵌入的推荐模型", 哈尔滨工业大学学报, no. 05, pages 185 - 191 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114612725A (en) * | 2022-03-18 | 2022-06-10 | 北京百度网讯科技有限公司 | Image processing method, device, equipment and storage medium |
| CN114612725B (en) * | 2022-03-18 | 2023-04-25 | 北京百度网讯科技有限公司 | Image processing method, device, equipment and storage medium |
| CN115293291A (en) * | 2022-08-31 | 2022-11-04 | 北京百度网讯科技有限公司 | Training method of ranking model, ranking method, device, electronic equipment and medium |
| CN115293291B (en) * | 2022-08-31 | 2023-09-12 | 北京百度网讯科技有限公司 | Training method and device for sequencing model, sequencing method and device, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113642635B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113807440B (en) | Method, apparatus, and medium for processing multimodal data using neural networks | |
| CN113836333A (en) | Training method of image-text matching model, method and device for realizing image-text retrieval | |
| CN114612749B (en) | Neural network model training method and device, electronic device and medium | |
| CN112579909A (en) | Object recommendation method and device, computer equipment and medium | |
| CN114648638A (en) | Training method of semantic segmentation model, semantic segmentation method and device | |
| CN113642635B (en) | Model training method and device, electronic equipment and medium | |
| CN113642740B (en) | Model training method and device, electronic equipment and medium | |
| CN115082740B (en) | Target detection model training method, target detection device and electronic equipment | |
| JP2024509014A (en) | Sorting method, sorting model training method, device, electronic device and storage medium | |
| CN114723949A (en) | Three-dimensional scene segmentation method and method for training segmentation model | |
| CN112949433B (en) | Method, device and equipment for generating video classification model and storage medium | |
| CN113868453B (en) | Object recommendation method and device | |
| JP2024507602A (en) | Data processing methods and methods for training predictive models | |
| CN113722594B (en) | Training method and device of recommendation model, electronic equipment and medium | |
| CN114120416A (en) | Model training method and device, electronic equipment and medium | |
| CN114707638A (en) | Model training method, model training device, object recognition method, object recognition device, object recognition medium and product | |
| CN115131562B (en) | Three-dimensional scene segmentation method, model training method, device and electronic equipment | |
| CN116070711B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN114821233B (en) | Training method, device, equipment and medium of target detection model | |
| CN115511779B (en) | Image detection method, device, electronic equipment and storage medium | |
| CN113722534B (en) | Video recommendation method and device | |
| CN113836939B (en) | Text-based data analysis method and device | |
| CN117273107A (en) | Training method and training device for text generation model | |
| CN117351330A (en) | Image processing method, training method, device and equipment of image processing model | |
| CN117710504A (en) | Image generation method, training method, device and equipment of image generation model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |