CN112148976A - Data processing method and device, electronic equipment and storage medium - Google Patents
Data processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112148976A CN112148976A CN202010999965.1A CN202010999965A CN112148976A CN 112148976 A CN112148976 A CN 112148976A CN 202010999965 A CN202010999965 A CN 202010999965A CN 112148976 A CN112148976 A CN 112148976A
- Authority
- CN
- China
- Prior art keywords
- behavior data
- information
- feature information
- user
- interest
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 40
- 230000004927 fusion Effects 0.000 claims abstract description 37
- 238000007499 fusion processing Methods 0.000 claims abstract description 16
- 230000006399 behavior Effects 0.000 claims description 493
- 238000012545 processing Methods 0.000 claims description 92
- 239000013598 vector Substances 0.000 claims description 54
- 238000011176 pooling Methods 0.000 claims description 32
- 238000000605 extraction Methods 0.000 claims description 22
- 230000007246 mechanism Effects 0.000 claims description 21
- 230000015654 memory Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 230000003993 interaction Effects 0.000 claims description 10
- 238000009825 accumulation Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 description 15
- 230000006870 function Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 13
- 230000007774 longterm Effects 0.000 description 11
- 239000011159 matrix material Substances 0.000 description 9
- 230000004913 activation Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000007526 fusion splicing Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application provides a data processing method and device, electronic equipment and a storage medium. Wherein, the method comprises the following steps: acquiring historical behavior data of a user, wherein the historical behavior data comprises first behavior data and second behavior data, the first behavior data is behavior data within a first preset time period, the second behavior data is behavior data within a second preset time period, and the first preset time period is longer than the second preset time period; respectively extracting the characteristics of the first behavior data and the second behavior data to obtain the characteristic information of the first behavior data and the characteristic information of the second behavior data; and performing fusion processing on the feature information of the first behavior data and the feature information of the second behavior data to obtain fusion feature information, and determining interest information of the user according to the fusion feature information. By the method and the device, accurate interest information of the user can be acquired according to historical behavior data of the user.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a data processing method and apparatus, an electronic device, and a storage medium.
Background
With the continuous development of internet technology, it is becoming more and more common to recommend corresponding content to users based on their interests, and common application scenarios include various recommendation scenarios such as advertisement recommendation, video recommendation, news recommendation, e-commerce recommendation, and the like. In a content recommendation scenario, user interests need to be modeled so that recommended content is accepted by the user.
At present, the existing modeling mode generally models the long-term interest of the user and the short-term interest of the user separately, and the modeling mode does not consider the relevance between the long-term interest and the short-term interest of the user, so that the interest of the user cannot be accurately and comprehensively acquired.
Disclosure of Invention
The embodiment of the invention provides a data processing method, a data processing device, electronic equipment and a storage medium, which can more accurately determine interest information of a user according to historical behavior data of the user.
An embodiment of the present application provides a data processing method, which specifically includes:
acquiring historical behavior data of a user, wherein the historical behavior data comprises first behavior data and second behavior data, the first behavior data is behavior data in a first preset time period, the second behavior data is behavior data in a second preset time period, and the first preset time period is longer than the second preset time period;
respectively extracting features of the first behavior data and the second behavior data to obtain feature information of the first behavior data and feature information of the second behavior data;
and fusing the characteristic information of the first behavior data and the characteristic information of the second behavior data to obtain fused characteristic information, and determining the interest information of the user according to the fused characteristic information.
The embodiment of the application provides a data processing device, and the device has the function of realizing the data processing method. The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring historical behavior data of a user, the historical behavior data comprises first behavior data and second behavior data, the first behavior data is behavior data in a first preset time period, the second behavior data is behavior data in a second preset time period, and the first preset time period is longer than the second preset time period;
a feature extraction unit, configured to perform feature extraction on the first behavior data and the second behavior data, respectively, to obtain feature information of the first behavior data and feature information of the second behavior data;
and the processing unit is used for carrying out fusion processing on the characteristic information of the first behavior data and the characteristic information of the second behavior data to obtain fusion characteristic information, and determining the interest information of the user according to the fusion characteristic information.
The embodiment of the application provides an electronic device, which comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are connected with each other, the memory is used for storing a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions for executing the operation related to the data processing method.
The embodiment of the application provides a computer readable storage medium for storing computer program instructions for an electronic device, which comprises a program for executing the data processing method.
Embodiments of the present application provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the data processing method.
According to the embodiment of the application, the historical behavior data of the user is divided into the first behavior data and the second behavior data, the first behavior data is subjected to feature extraction to obtain the feature information of the first behavior data, the second behavior data is subjected to feature extraction to obtain the feature information of the second behavior data, the feature information of the first behavior data and the feature information of the second behavior data are subjected to fusion processing, and more accurate interest information of the user can be obtained.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a block diagram of a data processing system according to an embodiment of the present application;
FIG. 2 is a model diagram of an interest recognition network model provided by an embodiment of the present application;
fig. 3 is a flowchart of a data processing method provided in an embodiment of the present application;
FIG. 4 is a schematic diagram of a pooling process provided by an embodiment of the present application;
FIG. 5 is a flow chart of another data processing method provided by an embodiment of the present application;
fig. 6 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the descriptions of "first", "second", etc. referred to in the embodiments of the present application are only for descriptive purposes and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a technical feature defined as "first" or "second" may explicitly or implicitly include at least one such feature.
Cloud technology (Cloud technology) is based on a general term of network technology, information technology, integration technology, management platform technology, application technology and the like applied in a Cloud computing business model, can form a resource pool, is used as required, and is flexible and convenient. Cloud computing technology will become an important support. Background services of the technical network system require a large amount of computing and storage resources, such as video websites, picture-like websites and more web portals. With the high development and application of the internet industry, each article may have its own identification mark and needs to be transmitted to a background system for logic processing, data in different levels are processed separately, and various industrial data need strong system background support and can only be realized through cloud computing.
Big data (Big data) refers to a data set which cannot be captured, managed and processed by a conventional software tool within a certain time range, and is a massive, high-growth-rate and diversified information asset which can have stronger decision-making power, insight discovery power and flow optimization capability only by a new processing mode. With the advent of the cloud era, big data has attracted more and more attention, and the big data needs special technology to effectively process a large amount of data within a tolerance elapsed time. The method is suitable for the technology of big data, and comprises a large-scale parallel processing database, data mining, a distributed file system, a distributed database, a cloud computing platform, the Internet and an extensible storage system.
According to the embodiment of the application, cloud computing is performed on big data through a cloud technology, wherein the big data refers to historical behavior data of a user on a social product within a specified time, and the historical behavior data specifically includes click behaviors and browsing behaviors of the user on XX video playing software within one year, or click behaviors and browsing behaviors of the user on XX news software within one year and the like.
Currently, the existing modeling mode generally models the long-term interest of the user and the short-term interest of the user separately, and the modeling mode does not consider the correlation between the long-term interest and the short-term interest of the user, so that the interest of the user in the product cannot be reflected more accurately and more comprehensively. Based on this, an embodiment of the present application provides a data processing method, which specifically includes: acquiring historical behavior data of a user, wherein the historical behavior data comprises first behavior data and second behavior data, the first behavior data is behavior data in a first preset time period, the second behavior data is behavior data in a second preset time period, and the first preset time period is longer than the second preset time period; respectively extracting features of the first behavior data and the second behavior data to obtain feature information of the first behavior data and feature information of the second behavior data; and fusing the characteristic information of the first behavior data and the characteristic information of the second behavior data to obtain fused characteristic information, and determining the interest information of the user according to the fused characteristic information. According to the data processing method provided by the embodiment of the application, the long-term and short-term fusion behavior data of the user are obtained by fusing the long-term behavior data and the short-term behavior data of the user, so that the interest of the user can be determined more comprehensively and accurately, and the precision of a recommendation algorithm can be improved.
It should be noted that the method and the device are applicable to the related fields of natural language processing, deep neural network and the like based on artificial intelligence, can be applied to products such as Tencent advertisements, Tencent videos and Tencent news, and are used for improving the precision of a recommendation algorithm of the products, and the specific application scene can be as follows: according to the historical behavior data of the user in a period of time, information which is interesting to the user can be recommended to the user more specifically.
The electronic device referred to in the embodiments of the present application is an entity for receiving or transmitting signals. Common electronic devices include, for example: the Mobile terminal may be a Mobile phone, a tablet computer, a laptop computer, a palmtop computer, a Mobile Internet Device (MID), a vehicle, a roadside Device, an aircraft, a wearable Device, and an intelligent Device having a data analysis function and a data processing function, such as a smart watch, a smart bracelet, and a pedometer, but the embodiment of the present application is not limited thereto.
In order to better understand the data processing method provided in the embodiments of the present application, a system architecture diagram applicable to the embodiments of the present application is described below.
Referring to fig. 1, fig. 1 is a schematic diagram of an architecture of a data processing system according to an embodiment of the present application, and as shown in fig. 1, the system architecture diagram includes: electronic device 100, network 200, and server 300. Where the electronic device 100 is connected to the server 300 via the network 200, the network 200 may be a wide area network or a local area network, or a combination thereof.
In a possible implementation manner, the server 300 stores historical behavior data of the user, and the electronic device 100 may obtain the historical behavior data of the user in a specified time period from the server 300 through the network 200, specifically, the electronic device 100 obtains a browsing behavior of the user on XX news software within three months, or a clicking behavior of the user on XX advertisement software or a browsing behavior of the user on XX video software, and the like.
In a possible implementation manner, the electronic device 100 includes XX news software, XX advertisement software, and XX video software, and the electronic device 100 directly obtains browsing behavior of the XX news software by a user within three months, or clicking behavior of the XX advertisement software by the user or browsing behavior of the XX video software by the user, and the like.
In one implementation, the electronic device 100 performs feature extraction on the acquired historical behavior data, and specifically, the electronic device 100 performs feature extraction on the acquired first behavior data and performs feature extraction on the acquired second behavior data to obtain feature information of the first behavior data and feature information of the second behavior data. The first behavior data may be behavior data of a user within three months, and the second behavior data may be behavior data of a user within one month.
In one implementation, the electronic device 100 performs fusion processing on the feature information of the first behavior data and the feature information of the second behavior data to obtain fused feature information, and determines interest information of the user according to the fused feature information. The electronic device 100 may send the obtained interest information of the user to the server 300 through the network 200, and the server 300 may perform a local storage operation on the interest information of the user received, so as to perform interest recommendation on the user through the user behavior of the user in the following. The electronic device 100 may also recommend the user in real time according to the obtained interest information of the user, and a recommendation interface is shown in fig. 1.
It is to be understood that the system architecture diagram described in the embodiment of the present application is for more clearly illustrating the technical solution of the embodiment of the present application, and does not constitute a limitation to the technical solution provided in the embodiment of the present application, and as a person having ordinary skill in the art knows that along with the evolution of the system architecture and the appearance of a new service scenario, the technical solution provided in the embodiment of the present application is also applicable to similar technical problems.
Referring to fig. 2, fig. 2 is a model diagram of an interest recognition network model according to an embodiment of the present application. As shown in FIG. 2, the interest recognition network model may include a word embedding processing module 210, an attention module 220, and a concatenation module 230.
In a possible implementation manner, the word embedding processing module 210 performs word embedding processing on the historical behavior data, the attribute information, and the third behavior data of the user to obtain a word vector of the historical behavior data, a word vector of the attribute information, and a word vector of the third behavior data. The historical behavior data comprises first behavior data and second behavior data, the first behavior data is behavior data in a first preset time period, the second behavior data is behavior data in a second preset time period, the first preset time period is longer than the second preset time period, the third behavior data is behavior data in a third preset time period, and the distance between the third preset time period and the current time period does not exceed the preset time period. The word embedding processing module 210 converts words in the text into word vectors determined by the context environment thereof, and specifically, the word embedding processing module 210 obtains historical behavior data of the user and processes the historical behavior data of the user, where the historical behavior data of the user includes at least one word, so as to obtain at least one word embedding matrix, and then truncates and completes the at least one word embedding matrix, so as to obtain word vectors of the historical behavior data of the user, specifically, word vectors of the first behavior data and word vectors of the second behavior data. Similarly, the word embedding processing module 210 processes the attribute information of the user to obtain at least one word embedding matrix, and then truncates and completes the at least one word embedding matrix to obtain a word vector of the attribute information of the user. The word embedding processing module 210 processes the third row of behavior data to obtain at least one word embedding matrix, and then truncates and completes the at least one word embedding matrix to obtain a word vector of the third row of behavior data.
In a possible implementation manner, first, the attention mechanism module 220 receives the word vector of the first behavior data, the word vector of the second behavior data, and the word vector of the attribute information sent from the word embedding processing module 210, performs average pooling on the word vector of the first behavior data to obtain feature information of the first behavior data, and performs cumulative pooling on the word vector of the second behavior data to obtain feature information of the second behavior data. Then, the attention mechanism module 220 performs fusion processing and splicing processing on the feature information of the second behavior data and the feature information of the first behavior data through an attention mechanism to obtain fused feature information. Finally, the attention mechanism module 220 performs a splicing process on the feature information of the fusion feature information, the feature information of the second behavior data, and the feature information of the attribute information to obtain spliced feature information.
In one possible implementation, the stitching module 230 receives the stitching feature information output from the attention mechanism module 220, and outputs the interest information of the user through processing of a plurality of full connection layers and activation functions by using the stitching feature information as an input of the attention module of the interest recognition network model.
In one possible implementation, the accuracy of the interest information of the user can be obtained by processing the interest information of the user with the feature information of the third behavior feature through an attention mechanism. The accuracy is used for adjusting parameters of the interest recognition network model, specifically, if the accuracy is greater than a preset degree threshold, it is determined that the interest information of the user is accurate, and if the accuracy is less than the preset degree threshold, it is determined that the interest information of the user is inaccurate, and the activation function can be replaced or the number of network channels can be increased.
Referring to fig. 3, fig. 3 is a flowchart of a data processing method according to an embodiment of the present disclosure. The method is applied to the electronic device, and as shown in fig. 3, the data processing method may include steps S310 to S330. Wherein:
step S310: the method comprises the steps of obtaining historical behavior data of a user, wherein the historical behavior data comprises first behavior data and second behavior data, the first behavior data is behavior data within a first preset time period, the second behavior data is behavior data within a second preset time period, and the first preset time period is larger than the second preset time period.
The historical behavior data comprises first behavior data and second behavior data, the first behavior data is behavior data in a first preset time period, the second behavior data is behavior data in a second preset time period, and the first preset time period is larger than the second preset time period. Specifically, the first behavior data is behavior data of the user within 90 days, and the second behavior data is behavior data of the user within 7 days. The behavior data may have different definitions according to different specific application scenarios, for example, in a video application scenario, the behavior data may be a playing behavior of a user, in an advertisement application scenario, the behavior data may be a clicking behavior of the user, in a news application scenario, the behavior data may be a browsing behavior of the user, and the like, which is not limited in the present invention.
Step S320: and respectively extracting the characteristics of the first behavior data and the second behavior data to obtain the characteristic information of the first behavior data and the characteristic information of the second behavior data.
In a possible implementation manner, first, the electronic device performs word embedding processing on the first behavior data to obtain a word vector of the first behavior data. The electronic equipment carries out word embedding processing on the first behavior data through a word embedding model to obtain at least one word embedding matrix, and carries out truncation and completion on the at least one word embedding matrix to obtain a word vector of the first behavior data of the user. It should be noted that, the electronic device may perform word embedding processing on the first behavior data in a embedding data processing manner, which is not limited in the present invention.
For example, the electronic device performs Word embedding processing on the first behavior data through a Word2vec model, wherein the Word2vec can quickly and effectively express a Word into a vector form through an optimized training model according to a given corpus, a new tool is provided for application research in the field of natural language processing, and Word2vec relies on skip-grams or continuous Word bag (CBOW) to establish neural Word embedding. The electronic device then converts the words in the first behavior data into Word vectors determined by its context by using the Word2vec model. Therefore, the probability distribution of each keyword and different word combinations appearing in the first behavior data can be obtained through neural network learning, a word vector matrix corresponding to each word in the first behavior data can be obtained, and finally, the word vector matrixes are truncated and supplemented to obtain the word vector of the first behavior data of the user.
In a possible implementation manner, the electronic device performs average pooling on the word vectors of the first behavior data to obtain feature information of the first behavior data. As shown in fig. 4, fig. 4 is a schematic diagram of a pooling process provided in an embodiment of the present application, where the pooling process may include an average pooling (avg-pooling) process and a cumulative pooling (sum-pooling) process, and the purpose of the pooling process is to reduce dimension. Since the long-term behavior data of the user tends to be stable, the word vector of the first behavior data is subjected to average pooling. For example, by performing average pooling on word vectors of behavior data of users within 90 days, feature information of the behavior data of the users within 90 days can be obtained, and specifically, the users are sports fans, so the feature information of the behavior data of the users within 90 days includes sports tag information. In this way, the key data in the first behavior data can be abstracted, and the miscellaneous data can be removed, so that the hardware cost of data processing can be reduced, and the processing time can be reduced.
In a possible implementation manner, the electronic device performs word embedding processing on the second behavior data through a word embedding model or an embedding data processing manner, so as to obtain a word vector of the second behavior data. And performing accumulation pooling on the word vectors of the second behavior data to obtain characteristic information of the second behavior data. As shown in fig. 4, after pooling the behavior data, the feature information of the obtained behavior data is reduced in both dimension and parameter. Because the short-term behavior data of the user is often greatly influenced by temporary factors such as hot spots and the like, and the data fluctuation in a short term is obvious, the word vectors of the second behavior data are subjected to accumulation pooling processing to obtain the characteristic information of the second behavior data. For example, the word vectors of the behavior data of the user within 7 days are accumulated and pooled, so that the feature information of the behavior data of the user within 7 days can be obtained, specifically, the user has a baby in the near future, and then the user starts to pay attention to the mother-infant information, so that the feature information of the behavior data of the user within 7 days includes mother-infant label information. By the method, the accumulated pooling processing is carried out on the behavior data of the user in a short period, so that the interest change of the user caused by the fluctuation in the short period can not be ignored due to the long-term behavior data of the user, the interest information of the user can be reflected more comprehensively in real time, and the accuracy of the interest information of the user is improved.
In one possible implementation, the feature information of the first behavior data includes a plurality of first unit feature information, and the feature information of the second behavior data includes a plurality of second unit feature information. For example, the first behavior data is behavior data of the user in the last three months, and further, the first behavior data includes behavior data of the user in 90 days and behavior data of the user in 30 days; the second behavior data is the behavior data of the user within the last week, and further comprises the behavior data of the user within 7 days and the behavior data of the user within 3 days. Specifically, the electronic device performs word embedding processing on behavior data of the user within 90 days, and in this way, the first behavior data and the second behavior data are further divided, so that the behavior data of the user within a specified time period can be further analyzed, and the accuracy of the interest information of the user is improved.
For example, the electronic device performs word embedding processing on behavior data of the user within 90 days to obtain word vectors of the behavior data within 90 days, performs average pooling processing on the word vectors of the behavior data within 90 days to obtain feature information of the behavior data within 90 days, namely first unit feature information of the first behavior data, performs word embedding processing on the behavior data of the user within 30 days to obtain word vectors of the behavior data within 30 days, and performs average pooling processing on the word vectors of the behavior data within 30 days to obtain feature information of the behavior data within 30 days, namely first unit feature information of the first behavior data. For another example, the electronic device performs word embedding processing on the behavior data of the user within 7 days to obtain word vectors of the behavior data within 90 days, performs average pooling processing on the word vectors of the behavior data within 7 days to obtain feature information of the behavior data within 7 days, that is, second unit feature information of the second behavior data, performs word embedding processing on the behavior data of the user within 3 days to obtain word vectors of the behavior data within 3 days, and performs average pooling processing on the word vectors of the behavior data within 3 days to obtain feature information of the behavior data within 3 days, that is, second unit feature information of the second behavior data. It should be noted that, in the embodiment of the present application, the feature information of the first behavior data includes 2 pieces of first unit feature information, and the feature information of the second behavior data includes 2 pieces of second unit feature information, which are only used as examples, and the present invention does not specifically limit the number of the feature information of the first behavior data and the feature information of the second behavior data, which is specifically divided into the feature information of the unit behavior data, and does not specifically limit the number of the feature information of the unit behavior data. The time window lengths between the unit feature information included in the feature information of the first behavior data and the unit feature information included in the feature information of the second behavior data may be the same or different.
Step S330: and performing fusion processing on the feature information of the first behavior data and the feature information of the second behavior data to obtain fusion feature information, and determining interest information of the user according to the fusion feature information.
In one possible implementation, the feature information of the first behavior data includes a plurality of first unit feature information, and the feature information of the second behavior data includes a plurality of second unit feature information. Then, the electronic device performs fusion processing on the feature information of the first behavior data and the feature information of the second behavior data to obtain fused feature information, including: firstly, the electronic equipment fuses each second unit feature information in the second unit feature information to each first unit feature information in the first unit feature information through an attention mechanism to obtain a plurality of unit fusion feature information corresponding to the first unit feature information; and then, the electronic equipment splices the unit fusion characteristic information to obtain fusion characteristic information.
For example, the first behavior data is divided into two groups of behavior data (behavior data within 90 days and behavior data within 30 days), and the second behavior data is divided into two groups of behavior data (behavior data within 7 days and behavior data within 3 days). The electronic device uses the feature information of the first behavior data as a key and uses the feature information of the second behavior data as a query through an attention mechanism (attention mechanism), specifically, the electronic device performs attention calculation on the feature information of the behavior data within 7 days and the feature information of the behavior data within 3 days to the feature information of the behavior data within 90 days to obtain the processed feature information of the behavior data within 90 days (second unit feature information); the electronic device performs attention calculation on the feature information of the behavior data within 7 days and the feature information of the behavior data within 3 days to the feature information of the behavior data within 30 days to obtain the processed feature information (second unit feature information) of the behavior data within 30 days. And then, the electronic equipment splices the characteristic information of the behavior data within 90 days after processing and the characteristic information of the behavior data within 30 days after processing to obtain fusion characteristic information.
In a possible implementation manner, the electronic device obtains attribute information of a user, and performs word embedding processing on the attribute information of the user to obtain feature information of the attribute information of the user. The attribute information of the user refers to basic attributes of the user, such as age, gender, and the like.
In a possible implementation manner, the electronic device determines interest information of the user according to feature information of the fusion feature information, the feature information of the second behavior data, and the attribute information of the user. Specifically, the electronic device performs splicing processing on feature information fused with the feature information of the second behavior data and the feature information of the attribute information of the user to obtain spliced feature information; and the electronic equipment inputs the splicing characteristic information into the interest recognition network model so as to output the interest information of the user.
For example, the electronic device uses the splicing feature information as an input of the interest recognition network model, and finally outputs the interest information of the user through the processing of the interest recognition network model. The interest recognition Network model may be based on a deep learning Neural Network model, and specifically may be a Feed Forward Neural Network (FNN) model or a Recurrent Neural Network (RNN) model or a Long Short Term Memory (LSTM) model or other Neural Network models with natural language processing and deep learning capabilities, which is not limited in this invention.
The interest recognition network model may include a hidden layer and an output layer, among others. The hidden layer is characterized by being fully connected and a black box, the interest recognition network model prevents overfitting in the training process through a nonlinear activation function, and generalization capability is improved. In a possible implementation mode, relu can alleviate the saturation condition when the value of y is too large, meanwhile overfitting can be prevented, training is accelerated, and then a relu function is selected as an activation function of the scheme; in order to prevent the occurrence of an overfitting condition (namely the error of a test set is increased due to the fact that the test set is too close to the real distribution of a training set), a regularization norm punishment term is added, and the sigmoid function can be selected as an output function by an output layer of the scheme in consideration of the characteristics of stability and easiness in saturation of the sigmoid function.
According to the data processing method provided by the embodiment of the application, the historical behavior data of the user is divided into the first behavior data and the second behavior data, the first behavior data and the second behavior data are respectively subjected to feature extraction processing to obtain the feature information of the first behavior data and the feature information of the second behavior data, and then the feature information of the first behavior data and the feature information of the second behavior data are fused through an attention mechanism, so that the relevance between the long-term and short-term behavior data of the user can be enhanced, the interest information of the user can be reflected more comprehensively, and the more accurate interest information of the user can be obtained.
Referring to fig. 5, fig. 5 is a flowchart of another data processing method according to an embodiment of the present disclosure. The method is applied to the electronic device, and as shown in fig. 5, the data processing method may include steps S510 to S560. Wherein:
step S510: the method comprises the steps of obtaining historical behavior data of a user, wherein the historical behavior data comprises first behavior data and second behavior data, the first behavior data is behavior data within a first preset time period, the second behavior data is behavior data within a second preset time period, and the first preset time period is larger than the second preset time period.
Step S520: and respectively extracting the characteristics of the first behavior data and the second behavior data to obtain the characteristic information of the first behavior data and the characteristic information of the second behavior data.
Step S530: and performing fusion processing on the feature information of the first behavior data and the feature information of the second behavior data to obtain fusion feature information, and determining interest information of the user according to the fusion feature information.
It should be noted that, for the steps S510 to S530 in the embodiment of the present application, reference may be specifically made to the execution process of the electronic device in the steps S310 to S330 in the foregoing embodiment, and details of the embodiment of the present application are not described herein again.
Step S540: and acquiring third behavior data of the user, wherein the third behavior data is behavior data in a third preset time period, and the time length of the third preset time period from the current time length does not exceed the preset time length.
Specifically, the third behavior data of the user refers to behavior data of the user in a short period of time, and the third behavior data is not included in the first behavior data and the second behavior data. Wherein, the preset time period may be 3 days, and the third time period may be 1 day or 2 days. For example, the third behavior data of the user is the behavior data within 1 day.
Step S550: and performing feature extraction on the third behavior data to obtain feature information of the third behavior data.
In a possible implementation manner, firstly, the electronic device performs word embedding processing on third behavior data to obtain a word vector of the third behavior data; and then, the electronic equipment performs accumulation pooling on the word vectors of the third behavior data to obtain the feature information of the third behavior data.
For example, assuming that the third behavior data is behavior data within 1 day, first, the electronic device performs word embedding processing on the behavior data of the user within 1 day through a word embedding model or an embedding data processing mode to obtain a word vector of the behavior data within 1 day; then, since the third behavior data is behavior data of a shorter period, the pooling processing manner of the third behavior data by the electronic device is accumulation pooling processing, and specifically, the electronic device performs accumulation pooling processing on word vectors of the behavior data within 1 day to obtain feature information of the behavior data within 1 day.
Step S560: and determining the accuracy of the interest information according to the interest information and the characteristic information of the third behavior data, wherein the accuracy is used for adjusting the parameters of the interest recognition network model.
In a possible implementation manner, firstly, the electronic device performs fusion processing on interest information and feature information of third behavior data through an attention mechanism to obtain target feature information; then, the electronic equipment calculates interaction probability between the feature information of the first behavior data and the feature information of the second behavior data and the target feature information according to the target feature information, the feature information of the first behavior data, the feature information of the second behavior data and the feature information of the third behavior data; and finally, the electronic equipment determines the accuracy of the interest information according to the interaction probability.
For example, first, the electronic device uses interest information of the user as a key and feature information of third behavior data as a query through an attention mechanism, and specifically, the electronic device performs attribute calculation on the feature information of behavior data of the user within 1 day and interest information of the user within 90 days to obtain target feature information. Then, assuming that the attribute calculation result (i.e., the target feature information) is v, the feature information of the first behavior data of the user is x1, the feature information of the second behavior data of the user is x2, and the feature information of the third behavior data is y, the interaction probability between the behavior objects based on the first behavior data of the user and the second behavior data and the third behavior data is P ═ exp (v · y)/(exp (v · x1) + exp (v · x 2)). And finally, the electronic equipment determines the accuracy loss of the interest information as-logP according to the interaction probability P.
The accuracy is used for adjusting parameters of the interest recognition network model, specifically, if the accuracy is greater than a preset degree threshold, it is determined that the interest information of the user is accurate, and if the accuracy is less than the preset degree threshold, it is determined that the interest information of the user is inaccurate, and the activation function can be replaced or the number of network channels can be increased. For example, when the calculated accuracy is greater than 80%, it is determined that the interest information of the user is accurate, the interest information of the user obtained through the processing of the interest recognition network model can accurately depict the interest of the user, and the interest information can be locally stored or used as training data of a recommendation algorithm model at a later stage. If the calculated accuracy is less than 80%, it is determined that the interest information of the user is inaccurate, the interest information of the user obtained through the interest recognition network model processing cannot accurately depict the interest of the user, so that the interest recognition network model needs to be optimized, specifically, historical behavior data of the user in a longer time period, for example, historical behavior data of the user in one year, can be obtained; the historical behavior data of the user can also be divided more finely, such as dividing the first behavior data into 5 groups of first unit behavior data and dividing the second behavior data into 5 groups of second unit behavior data; the number of channels of the hidden layer in the interest recognition network model can be increased, and the like.
In a possible implementation manner, after determining that the interest information of the user is accurate, the electronic device acquires preset feature data in a preset database, and calculates similarity between the preset feature data and the interest information, wherein a category corresponding to the preset feature data is a preset category; and if the similarity between the preset characteristic data and the interest information of the user is greater than a preset degree threshold, determining the category of the user as a preset category.
For example, the preset database stores interest tag information (preset feature data) and a crowd package corresponding to the interest tag information (preset feature data), after the electronic device determines that the interest information is accurate, the electronic device calculates the similarity between the interest information and the preset feature data, and if the similarity between the interest information and the preset feature data is greater than 80%, the user is determined to be divided into the crowd package corresponding to the preset feature data.
By the method provided by the embodiment of the application, the third behavior data of the user and the interest information of the user are processed through the attention mechanism, the accuracy of the interest information of the user can be obtained, the parameters of the interest identification network model are adjusted according to the accuracy, and the accuracy of the interest information of the user is further improved.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present disclosure. The data processing apparatus is configured to perform the steps performed by the electronic device in the method embodiments corresponding to fig. 3 to fig. 5, and the data processing apparatus may include:
the acquiring unit 610 is configured to acquire historical behavior data of a user, where the historical behavior data includes first behavior data and second behavior data, the first behavior data is behavior data within a first preset time period, the second behavior data is behavior data within a second preset time period, and the first preset time period is greater than the second preset time period;
a feature extraction unit 620, configured to perform feature extraction on the first behavior data and the second behavior data respectively to obtain feature information of the first behavior data and feature information of the second behavior data;
the processing unit 630 is configured to perform fusion processing on the feature information of the first behavior data and the feature information of the second behavior data to obtain fusion feature information, and determine interest information of the user according to the fusion feature information.
In a possible implementation manner, the determining, by the processing unit 630, the interest information of the user according to the fused feature information includes:
acquiring attribute information of the user, and performing word embedding processing on the attribute information of the user to obtain characteristic information of the attribute information of the user;
and determining the interest information of the user according to the fusion characteristic information, the characteristic information of the second behavior data and the characteristic information of the attribute information of the user.
In a possible implementation manner, the determining, by the processing unit 630, the interest information of the user according to the fusion feature information, the feature information of the second behavior data, and the feature information of the attribute information of the user includes:
inputting the feature information of the fusion feature information, the feature information of the second behavior data and the feature information of the attribute information of the user into a splicing module of an interest recognition network model for splicing to obtain spliced feature information;
inputting the splicing characteristic information into an attention module of the interest recognition network model so as to output interest information of the user.
In one possible implementation manner, the feature information of the first behavior data includes a plurality of first unit feature information, and the feature information of the second behavior data includes a plurality of second unit feature information; the processing unit 630 performs fusion processing on the feature information of the first behavior data and the feature information of the second behavior data to obtain fused feature information, which includes:
fusing each second unit feature information in the plurality of second unit feature information to each first unit feature information in the plurality of first unit feature information respectively through an attention mechanism to obtain a plurality of unit fusion feature information corresponding to the plurality of first unit feature information;
and splicing the unit fusion feature information to obtain fusion feature information.
In a possible implementation manner, the feature extraction unit 620 performs feature extraction on the first behavior data and the second behavior data respectively, and obtaining feature information of the first behavior data and feature information of the second behavior data includes:
performing word embedding processing on the first behavior data to obtain word vectors of the first behavior data, and performing average pooling processing on the word vectors of the first behavior data to obtain characteristic information of the first behavior data;
and performing word embedding processing on the second behavior data to obtain word vectors of the second behavior data, and performing accumulation pooling processing on the word vectors of the second behavior data to obtain characteristic information of the second behavior data.
In a possible implementation manner, after the processing unit 630 determines the interest information of the user according to the fused feature information, the method further includes:
the obtaining unit 610 obtains third behavior data of the user, where the third behavior data is behavior data in a third preset time period, and a distance from a current time period of the third preset time period to the current time period does not exceed a preset time period;
the feature extraction unit 620 performs feature extraction on the third behavior data to obtain feature information of the third behavior data;
the processing unit 630 determines the accuracy of the interest information according to the interest information and the feature information of the third behavior data, and the accuracy is used for adjusting the parameters of the interest recognition network model.
In a possible implementation manner, the processing unit 630 determines the accuracy of the interest information according to the interest information and the feature information of the third behavior data, including:
performing fusion processing on the interest information and the feature information of the third behavior data through an attention mechanism to obtain target feature information;
calculating interaction probability between the feature information of the first behavior data and the feature information of the second behavior data and the target feature information according to the target feature information, the feature information of the first behavior data, the feature information of the second behavior data and the feature information of the third behavior data;
and determining the accuracy of the interest information according to the interaction probability.
Through the data processing device provided by the embodiment of the application, the historical behavior data of the user is divided into the first behavior data and the second behavior data, the first behavior data and the second behavior data are respectively subjected to feature extraction processing to obtain the feature information of the first behavior data and the feature information of the second behavior data, and then the feature information of the first behavior data and the feature information of the second behavior data are fused through an attention mechanism, so that the relevance between the long-term and short-term behavior data of the user can be enhanced, the interest information of the user can be reflected more comprehensively, and the more accurate interest information of the user can be obtained.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application, where the electronic device is configured to execute steps executed by the electronic device in the method embodiments corresponding to fig. 3 to fig. 5, and the electronic device includes: one or more processors 710; one or more input devices 720, one or more output devices 730, and memory 740. The processor 710, the input device 720, the output device 730, and the memory 740 are connected by a bus 750. The memory 720 is used to store a computer program comprising program instructions, and the processor 710 is used to execute the program instructions stored in the memory 740 to perform the following operations:
acquiring historical behavior data of a user, wherein the historical behavior data comprises first behavior data and second behavior data, the first behavior data is behavior data in a first preset time period, the second behavior data is behavior data in a second preset time period, and the first preset time period is longer than the second preset time period;
respectively extracting features of the first behavior data and the second behavior data to obtain feature information of the first behavior data and feature information of the second behavior data;
and fusing the characteristic information of the first behavior data and the characteristic information of the second behavior data to obtain fused characteristic information, and determining the interest information of the user according to the fused characteristic information.
In one possible implementation, the processor 710 determines interest information of the user according to the fused feature information, including:
acquiring attribute information of the user, and performing word embedding processing on the attribute information of the user to obtain characteristic information of the attribute information of the user;
and determining the interest information of the user according to the fusion characteristic information, the characteristic information of the second behavior data and the characteristic information of the attribute information of the user.
In a possible implementation manner, the processor 710 determines interest information of the user according to the fusion feature information, the feature information of the second behavior data, and the feature information of the attribute information of the user, including:
inputting the feature information of the fusion feature information, the feature information of the second behavior data and the feature information of the attribute information of the user into a splicing module of an interest recognition network model for splicing to obtain spliced feature information;
inputting the splicing characteristic information into an attention module of the interest recognition network model so as to output interest information of the user.
In one possible implementation manner, the feature information of the first behavior data includes a plurality of first unit feature information, and the feature information of the second behavior data includes a plurality of second unit feature information; the processor 710 performs fusion processing on the feature information of the first behavior data and the feature information of the second behavior data to obtain fused feature information, including:
fusing each second unit feature information in the plurality of second unit feature information to each first unit feature information in the plurality of first unit feature information respectively through an attention mechanism to obtain a plurality of unit fusion feature information corresponding to the plurality of first unit feature information;
and splicing the unit fusion feature information to obtain fusion feature information.
In a possible implementation manner, the processor 710 performs feature extraction on the first behavior data and the second behavior data respectively, and obtaining feature information of the first behavior data and feature information of the second behavior data includes:
performing word embedding processing on the first behavior data to obtain word vectors of the first behavior data, and performing average pooling processing on the word vectors of the first behavior data to obtain characteristic information of the first behavior data;
and performing word embedding processing on the second behavior data to obtain word vectors of the second behavior data, and performing accumulation pooling processing on the word vectors of the second behavior data to obtain characteristic information of the second behavior data.
In a possible implementation manner, after the processor 710 determines the interest information of the user according to the fused feature information, the method further includes:
acquiring third behavior data of the user, wherein the third behavior data is behavior data in a third preset time period, and the distance between the third preset time period and the current time period does not exceed the preset time period;
performing feature extraction on the third behavior data to obtain feature information of the third behavior data;
and determining the accuracy of the interest information according to the interest information and the characteristic information of the third behavior data, wherein the accuracy is used for adjusting the parameters of the interest identification network model.
In one possible implementation, the processor 710 determines the accuracy of the interest information according to the interest information and the feature information of the third behavior data, including:
performing fusion processing on the interest information and the feature information of the third behavior data through an attention mechanism to obtain target feature information;
calculating interaction probability between the feature information of the first behavior data and the feature information of the second behavior data and the target feature information according to the target feature information, the feature information of the first behavior data, the feature information of the second behavior data and the feature information of the third behavior data;
and determining the accuracy of the interest information according to the interaction probability.
Through the electronic equipment provided by the embodiment of the application, the historical behavior data of the user is divided into the first behavior data and the second behavior data, the first behavior data and the second behavior data are respectively subjected to feature extraction processing to obtain the feature information of the first behavior data and the feature information of the second behavior data, and then the feature information of the first behavior data and the feature information of the second behavior data are fused through an attention mechanism, so that the relevance between the long-term and short-term behavior data of the user can be enhanced, the interest information of the user can be reflected more comprehensively, and the more accurate interest information of the user can be obtained.
According to an aspect of embodiments herein, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the operations involved in the data processing method.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by a computer program, which may be stored in a computer readable storage medium, and when executed, may include the processes of the above embodiments of the data processing method. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
While the invention has been described with reference to a number of embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A method of data processing, the method comprising:
acquiring historical behavior data of a user, wherein the historical behavior data comprises first behavior data and second behavior data, the first behavior data is behavior data in a first preset time period, the second behavior data is behavior data in a second preset time period, and the first preset time period is longer than the second preset time period;
respectively extracting features of the first behavior data and the second behavior data to obtain feature information of the first behavior data and feature information of the second behavior data;
and fusing the characteristic information of the first behavior data and the characteristic information of the second behavior data to obtain fused characteristic information, and determining the interest information of the user according to the fused characteristic information.
2. The method of claim 1, wherein determining interest information of the user based on the fused feature information comprises:
acquiring attribute information of the user, and performing word embedding processing on the attribute information of the user to obtain characteristic information of the attribute information of the user;
and determining the interest information of the user according to the fusion characteristic information, the characteristic information of the second behavior data and the characteristic information of the attribute information of the user.
3. The method according to claim 2, wherein the determining interest information of the user according to the fusion feature information, the feature information of the second behavior data, and the feature information of the attribute information of the user comprises:
inputting the feature information of the fusion feature information, the feature information of the second behavior data and the feature information of the attribute information of the user into a splicing module of an interest recognition network model for splicing to obtain spliced feature information;
inputting the splicing characteristic information into an attention module of the interest recognition network model so as to output interest information of the user.
4. The method according to any one of claims 1 to 3, wherein the feature information of the first behavior data includes a plurality of first unit feature information, the feature information of the second behavior data includes a plurality of second unit feature information, and the fusing the feature information of the first behavior data and the feature information of the second behavior data to obtain fused feature information includes:
fusing each second unit feature information in the plurality of second unit feature information to each first unit feature information in the plurality of first unit feature information respectively through an attention mechanism to obtain a plurality of unit fusion feature information corresponding to the plurality of first unit feature information;
and splicing the unit fusion feature information to obtain fusion feature information.
5. The method according to claim 1, wherein the performing feature extraction on the first behavior data and the second behavior data respectively to obtain feature information of the first behavior data and feature information of the second behavior data comprises:
performing word embedding processing on the first behavior data to obtain word vectors of the first behavior data, and performing average pooling processing on the word vectors of the first behavior data to obtain characteristic information of the first behavior data;
and performing word embedding processing on the second behavior data to obtain word vectors of the second behavior data, and performing accumulation pooling processing on the word vectors of the second behavior data to obtain characteristic information of the second behavior data.
6. The method according to claim 3, wherein after determining the interest information of the user according to the fused feature information, further comprising:
acquiring third behavior data of the user, wherein the third behavior data is behavior data in a third preset time period, and the distance between the third preset time period and the current time period does not exceed the preset time period;
performing word embedding processing on the third behavior data to obtain a word vector of the third behavior data, and performing accumulation pooling processing on the word vector of the third behavior data to obtain feature information of the third behavior data;
and determining the accuracy of the interest information according to the interest information and the characteristic information of the third behavior data, wherein the accuracy is used for adjusting the parameters of the interest identification network model.
7. The method of claim 6, wherein determining the accuracy of the interest information according to the interest information and the feature information of the third behavior data comprises:
performing fusion processing on the interest information and the feature information of the third behavior data through an attention mechanism to obtain target feature information;
calculating interaction probability between the feature information of the first behavior data and the feature information of the second behavior data and the target feature information according to the target feature information, the feature information of the first behavior data, the feature information of the second behavior data and the feature information of the third behavior data;
and determining the accuracy of the interest information according to the interaction probability.
8. A data processing apparatus, comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring historical behavior data of a user, the historical behavior data comprises first behavior data and second behavior data, the first behavior data is behavior data in a first preset time period, the second behavior data is behavior data in a second preset time period, and the first preset time period is longer than the second preset time period;
a feature extraction unit, configured to perform feature extraction on the first behavior data and the second behavior data, respectively, to obtain feature information of the first behavior data and feature information of the second behavior data;
and the processing unit is used for carrying out fusion processing on the characteristic information of the first behavior data and the characteristic information of the second behavior data to obtain fusion characteristic information, and determining the interest information of the user according to the fusion characteristic information.
9. An electronic device, comprising a memory and a processor, wherein the memory stores a set of program codes, and the processor calls the program codes stored in the memory to execute the method of any one of 1 to 7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program comprising program instructions which, when executed by a processor, cause the processor to carry out the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010999965.1A CN112148976A (en) | 2020-09-21 | 2020-09-21 | Data processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010999965.1A CN112148976A (en) | 2020-09-21 | 2020-09-21 | Data processing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112148976A true CN112148976A (en) | 2020-12-29 |
Family
ID=73892709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010999965.1A Pending CN112148976A (en) | 2020-09-21 | 2020-09-21 | Data processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112148976A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344662A (en) * | 2021-05-31 | 2021-09-03 | 联想(北京)有限公司 | Product recommendation method, device and equipment |
| CN118332189A (en) * | 2024-04-17 | 2024-07-12 | 星汉智能科技股份有限公司 | APP prediction method based on pre-training user characterization vector and self-attention mechanism |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111061945A (en) * | 2019-11-11 | 2020-04-24 | 汉海信息技术(上海)有限公司 | Recommendation method and device, electronic equipment and storage medium |
| CN111310056A (en) * | 2020-03-11 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and storage medium based on artificial intelligence |
| CN111444428A (en) * | 2020-03-27 | 2020-07-24 | 腾讯科技（深圳）有限公司 | Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium |
| CN111538907A (en) * | 2020-06-05 | 2020-08-14 | 支付宝(杭州)信息技术有限公司 | Object recommendation method, system and device |
| CN111611490A (en) * | 2020-05-25 | 2020-09-01 | 北京达佳互联信息技术有限公司 | Resource searching method, device, equipment and storage medium |
-
2020
- 2020-09-21 CN CN202010999965.1A patent/CN112148976A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111061945A (en) * | 2019-11-11 | 2020-04-24 | 汉海信息技术(上海)有限公司 | Recommendation method and device, electronic equipment and storage medium |
| CN111310056A (en) * | 2020-03-11 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and storage medium based on artificial intelligence |
| CN111444428A (en) * | 2020-03-27 | 2020-07-24 | 腾讯科技（深圳）有限公司 | Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium |
| CN111611490A (en) * | 2020-05-25 | 2020-09-01 | 北京达佳互联信息技术有限公司 | Resource searching method, device, equipment and storage medium |
| CN111538907A (en) * | 2020-06-05 | 2020-08-14 | 支付宝(杭州)信息技术有限公司 | Object recommendation method, system and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344662A (en) * | 2021-05-31 | 2021-09-03 | 联想(北京)有限公司 | Product recommendation method, device and equipment |
| CN118332189A (en) * | 2024-04-17 | 2024-07-12 | 星汉智能科技股份有限公司 | APP prediction method based on pre-training user characterization vector and self-attention mechanism |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111444428B (en) | Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium | |
| CN110941764A (en) | Object recommendation method and device, computer equipment and storage medium | |
| CN110795657A (en) | Article pushing and model training method and device, storage medium and computer equipment | |
| CN114036398B (en) | Content recommendation and ranking model training method, device, equipment and storage medium | |
| CN111667024B (en) | Content pushing method, device, computer equipment and storage medium | |
| CN112148976A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN113379449A (en) | Multimedia resource recall method and device, electronic equipment and storage medium | |
| CN108512674B (en) | Method, device and equipment for outputting information | |
| CN117459575A (en) | Service data pushing method, device, computer equipment and storage medium | |
| CN111860870B (en) | Training method, device, equipment and medium of interactive behavior determination model | |
| CN116823410A (en) | Data processing method, object processing method, recommending method and computing device | |
| CN112287225A (en) | Object recommendation method and device | |
| CN116578925A (en) | Behavior prediction method, device and storage medium based on feature images | |
| CN116956204A (en) | Network structure determining method, data predicting method and device of multi-task model | |
| CN116188887A (en) | Attribute recognition pre-training model generation method and attribute recognition model generation method | |
| CN115761410A (en) | Training method and device for attribute recognition model and electronic equipment | |
| CN113516524B (en) | Method and device for pushing information | |
| CN111783808B (en) | Method and device for generating information | |
| CN114372202A (en) | Content recommendation method and device, storage medium and electronic equipment | |
| CN114385915A (en) | Content recommendation method and device, storage medium and electronic equipment | |
| CN112446738A (en) | Advertisement data processing method, device, medium and electronic equipment | |
| CN113297471A (en) | Method and device for generating data object label and searching data object and electronic equipment | |
| US12132795B2 (en) | Data recommendation method and apparatus, computer device, and storage medium | |
| CN114282023A (en) | Fingerprint generation method, device, server and storage medium | |
| CN117056561A (en) | Video recommendation method, device, equipment, storage medium and program product |
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 |