CN113407843B - User portrait generation method, device, electronic device and computer storage medium - Google Patents
User portrait generation method, device, electronic device and computer storage medium Download PDFInfo
- Publication number
- CN113407843B CN113407843B CN202110779706.2A CN202110779706A CN113407843B CN 113407843 B CN113407843 B CN 113407843B CN 202110779706 A CN202110779706 A CN 202110779706A CN 113407843 B CN113407843 B CN 113407843B
- Authority
- CN
- China
- Prior art keywords
- user
- data
- variable
- result
- neural network
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/45—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to a data analysis technology, and discloses a user portrait generation method, which comprises the following steps: performing content identification on user data according to the data type of the user data to obtain data content; according to the data content, performing first user attribute analysis on at least two preset user variables by utilizing a first neural network trained in advance to obtain a first result of each user variable; performing second user attribute analysis on the user variable by taking the first result as a parameter of the first neural network to obtain a second result of the user variable; and constructing a variable subset of the user variable according to the second result, and carrying out data fusion on the variable subset by utilizing a pre-trained second neural network to obtain the user portrait. In addition, the invention also relates to a blockchain technology, and user data can be stored in nodes of the blockchain. The invention also provides a user portrait generating device, an electronic device and a computer readable storage medium. The invention can solve the problem of lower accuracy in user portrait generation.
Description
Technical Field
The present invention relates to the field of data analysis technologies, and in particular, to a user portrait generating method, apparatus, electronic device, and computer readable storage medium.
Background
Because of the wide application of user portraits technology in the fields of advertising, marketing, wind control, recruitment and the like, the construction of high-precision user portraits has been increasingly valued by Internet enterprises.
The current method for constructing user portraits is mostly a portraits construction method based on data collection, such as uniformly storing user data acquired by various channels as user portraits. In the method, the generated user portraits are only data collection, and user data of various sources or modes (such as texts, images and relational databases) cannot be associated, so that the generated user portraits have lower accuracy.
Disclosure of Invention
The invention provides a user portrait generating method, a user portrait generating device and a computer readable storage medium, which mainly aim to solve the problem of lower precision in user portrait generation.
In order to achieve the above object, the present invention provides a user portrait generating method, including:
acquiring user data, identifying the data type of the user data, and carrying out content identification on the user data by adopting a content identification method corresponding to the data type to obtain data content;
according to the data content, performing first user attribute analysis on at least two preset user variables by using a first neural network trained in advance to obtain a first result of each user variable;
Performing second user attribute analysis on the user variable by taking the first result as a parameter of the first neural network to obtain a second result of the user variable;
And constructing a variable subset of the user variable according to the second result, and carrying out data fusion on the variable subset by utilizing a pre-trained second neural network to obtain a user portrait.
Optionally, the identifying the data type of the user data includes: extracting a data type field of each data in the user data; and according to the data type field, searching in a preset standard type table to obtain the data type corresponding to the data type field.
Optionally, before the first user attribute analysis is performed on at least two preset user variables by using the first neural network trained in advance according to the data content, the method further includes:
Basic training data are obtained, the basic training data are utilized to carry out iterative training on the first neural network for a first preset number of times, and a training result output by the first neural network is obtained;
acquiring feedback data of a user on the training result;
And performing iterative training on the first neural network for a second preset number of times by using the feedback data and the basic training data to obtain a trained first neural network.
Optionally, the performing, according to the data content, first user attribute analysis on at least two preset user variables by using a first neural network trained in advance to obtain a first result of each user variable includes:
Performing vector conversion on the user variable by using the first neural network to obtain a user vector, and performing feature extraction and vector conversion on the data content to obtain a content vector;
calculating an association value between the user vector and the content vector by using a preset relation function;
selecting a target vector with the association value larger than a preset threshold value from the content vectors;
and performing activation operation on the target vector and the user vector by using a preset activation function to obtain a first result of each user variable.
Optionally, the second user attribute analysis is performed on the user variable by using the first result as a parameter of the first neural network to obtain a second result of the user variable, including:
sequentially selecting target variables from the user variables;
performing parameter conversion on first results corresponding to the other user variables except the target variable in the user variables to obtain result parameters;
performing parameter assignment on the first neural network by utilizing the result parameters;
And analyzing the target variable by using the first neural network after parameter assignment to obtain a second result corresponding to the target variable.
Optionally, the constructing the variable subset of the user variables according to the second result includes:
Collecting second results corresponding to all target variables into a user variable set;
and grouping the second results in the user variable set for multiple times according to different preset numbers, and taking the results obtained by grouping each time as the variable subset.
Optionally, the data fusion of the variable subset by using a pre-trained second neural network to obtain a user portrait includes:
Sequentially selecting a target subset from the variable subsets;
Inputting the second results corresponding to the rest variable subsets except the target subset in the variable subsets and the data content corresponding to the user variables in the target subset into the second neural network for analysis to obtain a third result;
vector conversion is carried out on the third result to obtain a result vector;
and splicing each vector in the result vectors by using a preset data aggregation algorithm to obtain the user portrait.
In order to solve the above problems, the present invention also provides a user portrait generating device, the device comprising:
The content identification module is used for acquiring user data, identifying the data type of the user data, and carrying out content identification on the user data by adopting a content identification method corresponding to the data type to obtain data content;
the first analysis module is used for carrying out first user attribute analysis on at least two preset user variables by utilizing a first neural network trained in advance according to the data content to obtain a first result of each user variable;
the second analysis module is used for carrying out second user attribute analysis on the user variable by taking the first result as the parameter of the first neural network to obtain a second result of the user variable;
And the user portrait generation module is used for constructing a variable subset of the user variables according to the second result, and carrying out data fusion on the variable subset by utilizing a pre-trained second neural network to obtain the user portrait.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
a memory storing at least one instruction; and
And the processor executes the instructions stored in the memory to realize the user portrait generation method.
In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium having stored therein at least one instruction that is executed by a processor in an electronic device to implement the user portrait creation method described above.
The embodiment of the invention realizes the generation of the user portrait based on the multi-source data by identifying the user data with different data types, and improves the accuracy of the user portrait; performing a first user attribute analysis on different user variables, performing a second user attribute analysis on the user variables by taking the result values as parameters, the accuracy of the analysis results is improved, and the analysis results are fused into the user portrait by constructing the subset of the analysis results, so that the accuracy of the generated user portrait is improved. Therefore, the user portrait generating method, the user portrait generating device, the electronic equipment and the computer readable storage medium can solve the problem of lower accuracy of labels generated on resources.
Drawings
FIG. 1 is a flowchart of a user portrait creation method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a training process of a first neural network according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a second user attribute analysis according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of a user image generating apparatus according to an embodiment of the present invention;
Fig. 5 is a schematic structural diagram of an electronic device for implementing the user portrait generating method according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides a user portrait generation method. The execution subject of the user portrait generation method includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the user portrayal generation method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Referring to fig. 1, a flowchart of a user portrait generating method according to an embodiment of the present invention is shown. In this embodiment, the user portrait generation method includes:
S1, acquiring user data, identifying the data type of the user data, and adopting a content identification method corresponding to the data type to identify the content of the user data to obtain data content.
In the embodiment of the invention, the user data can be data generated by a user or data related to the user. Such as shopping records for the user, recruitment resumes for the user, travel videos for the user, and the like.
The embodiment of the invention can grasp the user data from a pre-constructed database, a network cache or a blockchain node for storing the user data.
In one practical application scenario of the present invention, the user data includes data of multiple data types, for example, photo resume stored in image form, user video stored in video form, or user web browsing record stored in data form.
In one embodiment of the present invention, the identifying the data type of the user data includes: extracting a data type field of each data in the user data; and according to the data type field, searching in a preset standard type table to obtain the data type corresponding to the data type field.
In detail, a preset python sentence having a data type field extracting function may be used to extract a data type field of each data in the user data, where the data type field is a field in the user data for identifying a data type of each data.
Specifically, the standard type table includes a plurality of data type fields and data types corresponding to each data type field, and the standard type table can be uploaded by a user in advance.
According to the embodiment of the invention, different processing modes are selected according to the data types to identify the content of the user data.
In an alternative embodiment of the present invention, content recognition is performed on a text-form portion in user data by using technical means having a text analysis function, such as NLP (Natural Language Processing ), HMM (Hidden Markov Model, hidden markov model), etc., so as to obtain data content corresponding to the text-form portion in the user data; performing content recognition on the part of the image form in the user data by utilizing technical means such as OCR (Optical Character Recognition ) and the like with an image analysis function so as to acquire data content corresponding to the part of the image form of the user data; and (3) carrying out content recognition on the video-form part in the user data by utilizing the technical means such as ASR (Automatic Speech Recognition ) and OCR and the like with the speech analysis function and the image analysis function to acquire the data content corresponding to the video-form part of the user data.
For example, the user data includes data 1, data 2 and data 3, wherein the data type field of the data 1 is a text type field, and content identification is performed by using technical means with text analysis functions such as NLP and HMM, so as to obtain data content corresponding to a text form part in the user data; the data type field of the data 2 is an image type field, and content identification is carried out by utilizing technical means such as OCR and the like with an image analysis function so as to obtain data content corresponding to a part of the user data image form; and the data type field of the data 3 is a video type field, and the content recognition is carried out by combining technical means such as ASR, OCR and the like with a voice analysis function and an image analysis function so as to acquire the data content corresponding to the part of the user data in the video form.
According to the embodiment of the invention, the content identification is carried out on the user data according to the data types, so that the accuracy of acquiring the data content corresponding to each data type is improved.
S2, according to the data content, performing first user attribute analysis on at least two preset user variables by using a first neural network trained in advance to obtain a first result of each user variable.
In the embodiment of the invention, the user variables are information related to the user, such as the age of the user, the gender of the user, the occupation of the user and the like, which are needed to be used when generating the user portrait. The user variable may be preselected by a user.
In the embodiment of the invention, at least two preset user variables can be respectively analyzed according to the data content by utilizing the first neural network trained in advance so as to respectively obtain first results corresponding to different user variables. For example, the data content corresponding to the shopping record of the user is data content a, where the data content a includes: the articles purchased by the user are young clothes and books entered by the computer basic algorithm; when the preset user variables are the age of the user and the occupation of the user, the age of the user can be 20 to 30 years old through the 'young clothes' in the data content A, and the occupation of the user can be a training programmer through the 'computer basic algorithm entry book' in the data content A.
In detail, the first result includes a result about the user variable obtained after the user variable is analyzed according to the data content, for example, when the user variable is the age of the user, the first result may be the age range of the user (for example, 20-30 years old), or may be a pre-counted value of the age of the user (for example, 27 years old).
In one embodiment of the present invention, the first convolutional neural network includes, but is not limited to, a bayesian convolutional neural network and a logistic regression convolutional neural network.
In this embodiment, referring to fig. 2, the training process of the first neural network includes:
s21, acquiring basic training data, and performing iterative training on the first neural network for a first preset number of times by using the basic training data to obtain a training result output by the first neural network;
s22, acquiring feedback data of the training result from a user;
s23, performing iterative training on the first neural network for a second preset number of times by utilizing the feedback data and the basic training data together to obtain a trained first neural network.
In detail, the first preset number of times and the second preset number of times may be the same.
Specifically, the training data of the first convolutional neural network comprises basic training data and incremental training data, wherein the basic data comprises a plurality of pre-constructed data contents and real values of user variables corresponding to the data contents; the incremental training data comprises inputting basic training data into a first convolutional neural network for training, acquiring a predicted value of the first convolutional neural network to a user variable, acquiring feedback data of the user to the predicted value, and taking the feedback data as the incremental training data (for example, certain data in the incremental training data is taken as basic training data and the feedback data of the user to the predicted value corresponding to the basic training data).
In the implementation, the feedback data of the user is used for correcting or confirming the predicted value of the basic training data, so that the training samples are optimized and enriched to train a more accurate first convolutional neural network, and the accuracy of the first result obtained by carrying out first user attribute analysis on the user variable according to the data content is improved.
In the embodiment of the present invention, according to the data content, performing a first user attribute analysis on at least two preset user variables by using a first neural network trained in advance to obtain a first result of each user variable, where the first result includes:
Performing vector conversion on the user variable by using the first neural network to obtain a user vector, and performing feature extraction and vector conversion on the data content to obtain a content vector;
calculating an association value between the user vector and the content vector by using a preset relation function;
selecting a target vector with the association value larger than a preset threshold value from the content vectors;
and performing activation operation on the target vector and the user vector by using a preset activation function to obtain a first result of each user variable.
In detail, the first neural network can be used for carrying out operations such as pooling, convolution and the like on the data content, so that the feature extraction of the data content is realized; and vector conversion is carried out on the results of feature extraction on the user variables and the data contents by using word2vec or NLP (Natural Language Processing ) and other technologies to obtain user vectors and content vectors, and further analysis is carried out according to the user vectors and the content vectors to obtain a first result of each user variable.
Specifically, the preset relationship function includes a cosine distance function, a euclidean distance function, and the like, and the activation function includes, but is not limited to, sigmod activation functions, softmax activation functions.
For example, there are a content vector corresponding to the data content a of the shopping record of the user, a content vector corresponding to the data content B of the web browsing record of the user, a user vector corresponding to the age of the user, and a user vector corresponding to the occupation of the user; calculating an association value between the user vector and the content vector by using a preset relation function, wherein the association value between the content vector corresponding to the data content A and the user vector corresponding to the user age is 80, the association value between the content vector corresponding to the data content A and the user vector corresponding to the user age is 10, the association value between the content vector corresponding to the data content B and the user vector corresponding to the user age is 20, the association value between the content vector corresponding to the data content B and the user vector corresponding to the user age is 90, and when the preset threshold value is 70, the target vector of the content vector corresponding to the user age as the content vector corresponding to the data content A can be determined, and the target vector of the content vector corresponding to the user profession as the content vector corresponding to the data content B; and further, performing an activation operation on the user vector corresponding to the user age and the content vector corresponding to the data content A by using the activation function to obtain a first result of the user age (user variable), and performing an activation operation on the user vector corresponding to the user occupation and the content vector corresponding to the data content B by using the activation function to obtain a first result of the user occupation (user variable).
And S3, taking the first result as a parameter of the first neural network to perform second user attribute analysis on the user variable, so as to obtain a second result of the user variable.
In one practical application scene of the invention, because the data in the data content are all from the same user, certain association exists between different data in the data content, therefore, the embodiment of the invention analyzes the user variable by taking the first result as a parameter to adjust the first result so as to obtain a more accurate second result.
In the embodiment of the present invention, referring to fig. 3, the second user attribute analysis is performed on the user variable by using the first result as the parameter of the first neural network, to obtain a second result of the user variable, including:
S31, sequentially selecting target variables from the user variables;
S32, carrying out parameter conversion on first results corresponding to the rest user variables except the target variable in the user variables to obtain result parameters;
S33, carrying out parameter assignment on the first neural network by utilizing the result parameters;
S34, analyzing the target variable by using the first neural network after parameter assignment to obtain a second result corresponding to the target variable.
In detail, the first results corresponding to the other user variables except the target variable in the user variables may be converted by using a computer sentence with a parameter conversion function, for example, the first results corresponding to the other user variables except the target variable in the user variables are encoded, so as to obtain the result parameters in the form of encoded data.
Specifically, the step of analyzing the target variable by using the first neural network after the parameter assignment is consistent with the step of performing the first user attribute analysis on at least two preset user variables by using the first neural network trained in advance in the step S2, which is not described herein.
The second result is a corrected value of the first result. For example, the first result includes that the age of the user is 20 to 30 years old, the occupation of the user is a practice programmer, when the age of the user is selected as a target variable, the first result is input into the first neural network as data content together with the data content, and the first result is corrected to be a second result after analysis, wherein the age of the user is 20 to 30 years old: the age of the user is 20 to 25 years.
According to the embodiment of the invention, the first result obtained by the first user attribute analysis can be corrected by taking the first result as the parameter to carry out the second user attribute analysis on the user variable, so that the accuracy of the generated second result is improved.
S4, constructing a variable subset of the user variable according to the second result, and carrying out data fusion on the variable subset by utilizing a pre-trained second neural network to obtain a user portrait.
In the embodiment of the invention, in order to improve the accuracy of the generated user portrait, a plurality of data contents can be obtained, each data content can obtain a second result corresponding to a plurality of user variables, a variable subset containing all the user variables is further constructed according to the second result generated by each data content, and the data fusion is carried out on the variable subset by utilizing a pre-trained second neural network to obtain the user portrait.
For example, the second result generated by the presence data content a includes: user age q, programmer of user professional work experience in the year w; the second result generated by the data content B includes: and e, collecting second results corresponding to the data content A and the data content B, and generating a subset of the second results if the user age e is the programmer of the r-year working experience. For example, subset 1 is (user age q, user occupation w, data content B), subset 2 is (user age e, user occupation w, programmer of r years of work experience), and so on.
In an embodiment of the present invention, the constructing a variable subset of the user variables according to the second result includes:
Collecting second results corresponding to all target variables into a user variable set;
and grouping the second results in the user variable set for multiple times according to different preset numbers, and taking the results obtained by grouping each time as the variable subset.
In detail, the preset number is generally equal to or less than the number of second results in the user variable.
For example, the set of user variables is { a, b, c }, the set of user variables is grouped according to a preset number 1 to obtain variable subsets { a }, { b }, and { c }, the set of user variables is grouped according to a preset number 2 to obtain variable subsets { a, b }, { b, c }, and { a, c }, and the set of user variables is grouped according to a preset number 3 to obtain variable subsets { a, b, c }.
In another embodiment of the present invention, the user variable set may be further operated on by a preset subset generating algorithm to generate a variable subset of the user variable, where the subset generating algorithm includes, but is not limited to, an increment method, a bit vector method, and a binary method.
Further, in the embodiment of the present invention, the variable subset is analyzed by using a pre-trained second neural network to generate a user portrait by combining second results corresponding to different data contents, where the training process of the second neural network is the same as that of the first neural network, and details are not described herein.
In the embodiment of the present invention, the data fusion is performed on the variable subset by using a pre-trained second neural network to obtain a user portrait, including:
Sequentially selecting a target subset from the variable subsets;
Inputting the second results corresponding to the rest variable subsets except the target subset in the variable subsets and the data content corresponding to the user variables in the target subset into the second neural network for analysis to obtain a third result;
vector conversion is carried out on the third result to obtain a result vector;
and splicing each vector in the result vectors by using a preset data aggregation algorithm to obtain the user portrait.
In detail, the step of inputting the second results corresponding to the remaining variable subsets except the target subset in the variable subset and the data content corresponding to the user variables in the target subset into the second neural network for analysis is consistent with the step of performing the first user attribute analysis on at least two preset user variables by using the first neural network trained in advance in the step S2, which is not described herein.
The step of performing vector conversion on the third result is consistent with the step of performing vector conversion on the user variable in the step 2, and will not be described herein.
Specifically, the third result is a correction value of the second result.
For example, there is a variable subset Y and a variable subset Z, wherein the variable subset Y includes a second result generated from the data content a: the age of the user is 20 to 25 years, and the occupation of the user is a programmer of working experience of 3 years; included in the variable subset Z is a second result generated from the data content B: the age of the user is 20 to 23 years, and the occupation of the user is a programmer of working experience of 1 year; when the variable subset Y is selected as the target subset, inputting a second result (the age of the user is 20 to 23 years, the occupation of the user is a programmer with 1-year working experience) in the variable subset Z and data content (the articles purchased by the user are young clothes and books entered by a computer basic algorithm) corresponding to the user variable of the second result in the variable subset Y into the second neural network for analysis, so as to obtain a third result: the age of the user is 22 years and the occupation of the user is a programmer working for 1.5 years.
In this embodiment, the third result may be subjected to data fusion by a preset data aggregation algorithm, so as to obtain the user portrait, where the data aggregation algorithm includes but is not limited to: BIRCH algorithm, DBSCAN algorithm, CLRANS algorithm, etc.
For example, if the third result is 22 years old and the user occupation is 1.5 years old, the data fusion algorithm is used to convert the "user age 22 years old" into the first vector, convert the "user occupation is 1.5 years old" into the second vector, and combine the first vector with the second vector to realize the data fusion of the third result, so as to obtain the user portrait.
The embodiment of the invention realizes the generation of the user portrait based on the multi-source data by identifying the user data with different data types, and improves the accuracy of the user portrait; performing a first user attribute analysis on different user variables, performing a second user attribute analysis on the user variables by taking the result values as parameters, the accuracy of the analysis results is improved, and the analysis results are fused into the user portrait by constructing the subset of the analysis results, so that the accuracy of the generated user portrait is improved. Therefore, the user portrait generating method provided by the invention can solve the problem of lower accuracy of the labels generated by the resources.
Fig. 4 is a functional block diagram of a user image generating apparatus according to an embodiment of the present invention.
The user portrait creation apparatus 100 according to the present invention may be mounted in an electronic device. Depending on the functions implemented, the user portrayal generation device 100 may comprise a content recognition module 101, a first analysis module 102, a second analysis module 103 and a user portrayal generation module 104. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
The content recognition module 101 is configured to obtain user data, recognize a data type of the user data, and perform content recognition on the user data by using a content recognition method corresponding to the data type to obtain data content;
the first analysis module 102 is configured to perform, according to the data content, a first user attribute analysis on at least two preset user variables by using a first neural network trained in advance, so as to obtain a first result of each user variable;
The second analysis module 103 is configured to perform a second user attribute analysis on the user variable with the first result as a parameter of the first neural network, to obtain a second result of the user variable;
The user portrait generation module 104 is configured to construct a variable subset of the user variables according to the second result, and perform data fusion on the variable subset by using a pre-trained second neural network to obtain a user portrait.
In detail, each module of the user portrait generating device 100 in the embodiment of the present invention adopts the same technical means as the user portrait generating method described in fig. 1 to 3, and can generate the same technical effects, which is not described herein.
Fig. 5 is a schematic structural diagram of an electronic device for implementing a user portrait creation method according to an embodiment of the present invention.
The electronic device may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program, such as a front-end monitoring program, stored in the memory 11 and executable on the processor 10.
The processor 10 may be formed by an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, and executes various functions of the electronic device and processes data by running or executing programs or modules (e.g., executing a front-end monitoring program, etc.) stored in the memory 11, and calling data stored in the memory 11.
The memory 11 includes at least one type of readable storage medium including flash memory, a removable hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only for storing application software installed in an electronic device and various types of data, such as codes of a front-end monitoring program, but also for temporarily storing data that has been output or is to be output.
The communication bus 12 may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
The communication interface 13 is used for communication between the electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
Fig. 5 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The user portrayal generation program stored in the memory 11 of the electronic device 1 is a combination of instructions which, when run in the processor 10, can implement:
acquiring user data, identifying the data type of the user data, and carrying out content identification on the user data by adopting a content identification method corresponding to the data type to obtain data content;
according to the data content, performing first user attribute analysis on at least two preset user variables by using a first neural network trained in advance to obtain a first result of each user variable;
Performing second user attribute analysis on the user variable by taking the first result as a parameter of the first neural network to obtain a second result of the user variable;
And constructing a variable subset of the user variable according to the second result, and carrying out data fusion on the variable subset by utilizing a pre-trained second neural network to obtain a user portrait.
Specifically, the specific implementation method of the above instructions by the processor 10 may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:
acquiring user data, identifying the data type of the user data, and carrying out content identification on the user data by adopting a content identification method corresponding to the data type to obtain data content;
according to the data content, performing first user attribute analysis on at least two preset user variables by using a first neural network trained in advance to obtain a first result of each user variable;
Performing second user attribute analysis on the user variable by taking the first result as a parameter of the first neural network to obtain a second result of the user variable;
And constructing a variable subset of the user variable according to the second result, and carrying out data fusion on the variable subset by utilizing a pre-trained second neural network to obtain a user portrait.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (9)
1. A user representation generation method, the method comprising:
acquiring user data, identifying the data type of the user data, and carrying out content identification on the user data by adopting a content identification method corresponding to the data type to obtain data content;
according to the data content, performing first user attribute analysis on at least two preset user variables by using a first neural network trained in advance to obtain a first result of each user variable;
Performing second user attribute analysis on the user variable by taking the first result as a parameter of the first neural network to obtain a second result of the user variable;
constructing a variable subset of the user variable according to the second result, and carrying out data fusion on the variable subset by utilizing a pre-trained second neural network to obtain a user portrait;
The first user attribute analysis is performed on at least two preset user variables by using a first neural network trained in advance according to the data content to obtain a first result of each user variable, and the first result comprises:
Performing vector conversion on the user variable by using the first neural network to obtain a user vector, and performing feature extraction and vector conversion on the data content to obtain a content vector;
calculating an association value between the user vector and the content vector by using a preset relation function;
selecting a target vector with the association value larger than a preset threshold value from the content vectors;
and performing activation operation on the target vector and the user vector by using a preset activation function to obtain a first result of each user variable.
2. The user portrait creation method according to claim 1, wherein said identifying a data type of said user data includes: extracting a data type field of each data in the user data; and according to the data type field, searching in a preset standard type table to obtain the data type corresponding to the data type field.
3. The user representation generation method of claim 1, wherein prior to performing a first user attribute analysis on at least two preset user variables using a pre-trained first neural network based on the data content, the method further comprises:
Basic training data are obtained, the basic training data are utilized to carry out iterative training on the first neural network for a first preset number of times, and a training result output by the first neural network is obtained;
acquiring feedback data of a user on the training result;
And performing iterative training on the first neural network for a second preset number of times by using the feedback data and the basic training data to obtain a trained first neural network.
4. The user portrait creation method according to claim 1, wherein the performing, with the first result as a parameter of the first neural network, second user attribute analysis on the user variable to obtain a second result of the user variable includes:
sequentially selecting target variables from the user variables;
performing parameter conversion on first results corresponding to the other user variables except the target variable in the user variables to obtain result parameters;
performing parameter assignment on the first neural network by utilizing the result parameters;
And analyzing the target variable by using the first neural network after parameter assignment to obtain a second result corresponding to the target variable.
5. The user representation generation method of claim 1, wherein said constructing a variable subset of said user variables from said second result comprises:
Collecting second results corresponding to all target variables into a user variable set;
and grouping the second results in the user variable set for multiple times according to different preset numbers, and taking the results obtained by grouping each time as the variable subset.
6. The user representation generating method as claimed in claim 1, wherein said data fusion of said variable subset using a pre-trained second neural network to obtain a user representation comprises:
Sequentially selecting a target subset from the variable subsets;
Inputting the second results corresponding to the rest variable subsets except the target subset in the variable subsets and the data content corresponding to the user variables in the target subset into the second neural network for analysis to obtain a third result;
vector conversion is carried out on the third result to obtain a result vector;
and splicing each vector in the result vectors by using a preset data aggregation algorithm to obtain the user portrait.
7. A user portrayal generating device for implementing a user portrayal generating method according to any one of claims 1 to 6, said device comprising:
The content identification module is used for acquiring user data, identifying the data type of the user data, and carrying out content identification on the user data by adopting a content identification method corresponding to the data type to obtain data content;
the first analysis module is used for carrying out first user attribute analysis on at least two preset user variables by utilizing a first neural network trained in advance according to the data content to obtain a first result of each user variable;
the second analysis module is used for carrying out second user attribute analysis on the user variable by taking the first result as the parameter of the first neural network to obtain a second result of the user variable;
And the user portrait generation module is used for constructing a variable subset of the user variables according to the second result, and carrying out data fusion on the variable subset by utilizing a pre-trained second neural network to obtain the user portrait.
8. An electronic device, the 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 user representation generation method of any one of claims 1 to 6.
9. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the user portrayal generation method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110779706.2A CN113407843B (en) | 2021-07-09 | 2021-07-09 | User portrait generation method, device, electronic device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110779706.2A CN113407843B (en) | 2021-07-09 | 2021-07-09 | User portrait generation method, device, electronic device and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113407843A CN113407843A (en) | 2021-09-17 |
| CN113407843B true CN113407843B (en) | 2024-11-15 |
Family
ID=77685724
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110779706.2A Active CN113407843B (en) | 2021-07-09 | 2021-07-09 | User portrait generation method, device, electronic device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113407843B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116881586A (en) * | 2023-06-12 | 2023-10-13 | 光控特斯联(重庆)信息技术有限公司 | User data Web interface generation method and device, electronic equipment and storage medium |
| CN117742634B (en) * | 2023-12-12 | 2025-10-28 | 深圳市汇川技术股份有限公司 | Industrial control data request method, device, equipment and readable storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711874A (en) * | 2018-12-17 | 2019-05-03 | 平安科技（深圳）有限公司 | User portrait generation method, device, computer equipment and storage medium |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2537670A (en) * | 2015-04-23 | 2016-10-26 | Fujitsu Ltd | A query mediator, a method of querying a polyglot data tier and a computer program executable to carry out a method of querying a polyglot data tier |
| CN110162690B (en) * | 2018-10-23 | 2023-04-18 | 腾讯科技（深圳）有限公司 | Method and device for determining interest degree of user in item, equipment and storage medium |
| CN110321473B (en) * | 2019-05-21 | 2021-05-25 | 山东省计算中心（国家超级计算济南中心） | Method, system, medium and device for pushing diversity preference information based on multimodal attention |
| US11900246B2 (en) * | 2019-09-02 | 2024-02-13 | Samsung Electronics Co., Ltd. | Method and apparatus for recognizing user based on on-device training |
| CN111831901B (en) * | 2020-03-26 | 2024-09-20 | 北京嘀嘀无限科技发展有限公司 | Data processing method, device, equipment and storage medium |
| CN111597348B (en) * | 2020-04-27 | 2024-02-06 | 平安科技（深圳）有限公司 | User image drawing method, device, computer equipment and storage medium |
| CN111652658A (en) * | 2020-06-11 | 2020-09-11 | 北京妙医佳健康科技集团有限公司 | Portrait fusion method, apparatus, electronic device and computer readable storage medium |
| CN112632385B (en) * | 2020-12-29 | 2023-09-22 | 中国平安人寿保险股份有限公司 | Course recommendation method, course recommendation device, computer equipment and medium |
| CN112784070A (en) * | 2020-12-31 | 2021-05-11 | 重庆空间视创科技有限公司 | User portrait method based on big data |
-
2021
- 2021-07-09 CN CN202110779706.2A patent/CN113407843B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711874A (en) * | 2018-12-17 | 2019-05-03 | 平安科技（深圳）有限公司 | User portrait generation method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113407843A (en) | 2021-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112380343B (en) | Problem analysis method, device, electronic equipment and storage medium | |
| CN113157927B (en) | Text classification method, apparatus, electronic device and readable storage medium | |
| CN113821622B (en) | Answer retrieval method and device based on artificial intelligence, electronic equipment and medium | |
| CN113656690B (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN113360768A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN112581227A (en) | Product recommendation method and device, electronic equipment and storage medium | |
| CN116821373B (en) | Map-based prompt recommendation method, device, equipment and medium | |
| CN113344125B (en) | Long text matching recognition method and device, electronic equipment and storage medium | |
| CN113627187B (en) | Named entity recognition method, named entity recognition device, electronic equipment and readable storage medium | |
| CN113868419B (en) | Text classification method, device, equipment and medium based on artificial intelligence | |
| CN112988963A (en) | User intention prediction method, device, equipment and medium based on multi-process node | |
| CN113707302B (en) | Service recommendation method, device, equipment and storage medium based on associated information | |
| CN108959566A (en) | A kind of medical text based on Stacking integrated study goes privacy methods and system | |
| CN112347739B (en) | Applicable rule analysis method, device, electronic device and storage medium | |
| CN112801222A (en) | Multi-classification method and device based on two-classification model, electronic equipment and medium | |
| CN113407843B (en) | User portrait generation method, device, electronic device and computer storage medium | |
| CN115510188A (en) | Text keyword association method, device, equipment and storage medium | |
| CN113592605B (en) | Product recommendation method, device, equipment and storage medium based on similar products | |
| CN112269875B (en) | Text classification method, device, electronic equipment and storage medium | |
| CN111738005B (en) | Named entity alignment method, device, electronic device and readable storage medium | |
| CN113886708A (en) | Product recommendation method, device, equipment and storage medium based on user information | |
| CN112632264A (en) | Intelligent question and answer method and device, electronic equipment and storage medium | |
| CN114548114A (en) | Text emotion recognition method, device, equipment and storage medium | |
| CN112632260A (en) | Intelligent question and answer method and device, electronic equipment and computer readable storage medium | |
| CN112527995A (en) | Question feedback processing method, device and equipment and readable storage medium |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40053539 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |