CN113139129A - Virtual reading track map generation method and device, electronic equipment and storage medium - Google Patents
Virtual reading track map generation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113139129A CN113139129A CN202110518009.1A CN202110518009A CN113139129A CN 113139129 A CN113139129 A CN 113139129A CN 202110518009 A CN202110518009 A CN 202110518009A CN 113139129 A CN113139129 A CN 113139129A
- Authority
- CN
- China
- Prior art keywords
- track
- information
- image
- reading
- vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 36
- 230000006870 function Effects 0.000 claims description 33
- 238000006243 chemical reaction Methods 0.000 claims description 21
- 239000011159 matrix material Substances 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000010586 diagram Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000005457 optimization Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000012512 characterization method Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- 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; CALCULATING OR 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
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
-
- 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)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a data analysis technology, and discloses a virtual reading track map generation method, which comprises the following steps: converting the existing information data into an information image; converting the historical reading track into a track vector to mark the information image to obtain a first track image; performing reading track analysis on the first track image by using a countermeasure generation network to obtain a second track image; and when the coincidence degree of the first track image and the second track image is not greater than a preset threshold value, adjusting parameters of the confrontation generation network until the coincidence degree is greater than the preset threshold value, and performing reading track analysis on the information data to be analyzed by using the confrontation generation network to obtain a virtual reading track graph of the user. In addition, the invention also relates to a block chain technology, and the existing resource data can be stored in the nodes of the block chain. The invention also provides a virtual reading track map generation device, equipment and a medium. The invention can solve the problem of low accuracy when analyzing the user preference information.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a virtual reading trajectory graph generation method and device, electronic equipment and a computer readable storage medium.
Background
With the advent of the big data age, companies or enterprises can push massive information to people, such as various news, books, advertisements, and the like. As the demands of people are different, the information required by each person is different, and the information push person is difficult to quickly find the information preferred by the user.
The existing user preference analysis is usually based on the preference analysis of the user portrait, for example, the user portrait is matched with various information to analyze and obtain the information of the user preference, but in the method, because the generation period of the user portrait is long, but the change of the user preference is fast, the accuracy of the analysis result obtained after the user preference information is analyzed based on the user portrait is low.
Disclosure of Invention
The invention provides a method and a device for generating a virtual reading track map and a computer readable storage medium, and mainly aims to solve the problem of low accuracy of analyzing user preference information.
In order to achieve the above object, the method for generating a virtual reading trajectory diagram provided by the present invention comprises:
acquiring the existing information data of a user and the historical reading track of the existing information, and constructing an information image according to the existing information data;
constructing a track vector according to the historical reading track, and marking the information image by using the track vector to obtain a first track image;
performing reading track analysis on the first track image by using a pre-constructed confrontation generation network to obtain a second track image;
calculating the coincidence degree of the first track image and the second track image;
if the contact ratio is smaller than or equal to a preset threshold value, adjusting parameters of the confrontation generation network, and returning to the step of performing reading track analysis on the first track image;
if the contact ratio is larger than the preset threshold value, outputting the confrontation generation network to obtain a reading track generation network;
and acquiring information data to be analyzed, and analyzing the reading track of the information data to be analyzed by using the reading track generation network to obtain a virtual reading track graph of the user.
Optionally, the constructing an information image according to the existing information data includes:
dividing the existing information data according to a first unit time to obtain information subsets;
determining the information reading quantity and the information total quantity of each information subset;
and constructing an information image according to the information reading quantity and the information total quantity of each information subset.
Optionally, the constructing an information image according to the information reading quantity and the information total quantity of each information subset includes:
performing factorization on the total information quantity of the existing information data to obtain an information matrix;
performing a first operation on the information reading quantity of each information subset and a preset unit gray value to obtain a matrix gray;
and performing a second operation by using the matrix gray scale and the information matrix to obtain an information image.
Optionally, the constructing a trajectory vector according to the historical reading trajectory includes:
extracting the browsing duration of each information data in the historical reading track within a second unit time of the user;
and performing vector conversion on each information data in the historical reading track according to the browsing duration to obtain a track vector.
Optionally, the vector conversion of each information data in the historical reading track according to the browsing duration to obtain a track vector includes:
performing vector conversion on each existing information data in the historical reading track by using the following vector conversion algorithm:
wherein Bn is the browsing duration of the nth current information data in the historical reading track, Bn is the track vector of the nth current information data, min (Bn) is the minimum browsing duration in the historical reading track, and max (Bn) is the maximum browsing duration in the historical reading track.
Optionally, the performing reading track analysis on the first track image by using a pre-constructed confrontation generating network to obtain a second track image includes:
mapping the track vector in the first track map to a pre-constructed vector space by using a generator in the countermeasure generation network to obtain a vector representation;
constructing a target function by using a preset adjusting function and the vector representation;
and calculating the first track image by using the target function to obtain a second track image.
Optionally, the calculating the coincidence degree of the first track image and the second track image includes:
calculating a loss value between each track vector in the first track image and the second track image by using a loss function of a discriminator in the countermeasure generating network;
and taking the average value of the loss values as the coincidence degree of the first track image and the second track image.
In order to solve the above problem, the present invention further provides a virtual reading trajectory map generating device, including:
the first conversion module is used for acquiring the existing information data of a user and the historical reading track in the existing information and constructing an information image according to the existing information data;
the second conversion module is used for constructing a track vector according to the historical reading track and marking the information image by using the track vector to obtain a first track image;
the first analysis module is used for carrying out reading track analysis on the first track image by utilizing a pre-constructed countermeasure generation network to obtain a second track image;
the coincidence degree calculation module is used for calculating the coincidence degree of the first track image and the second track image;
a parameter adjusting module, configured to adjust a parameter of the countermeasure generation network if the contact ratio is less than or equal to a preset threshold, and return to the step of performing reading trajectory analysis on the first trajectory image;
the network output module is used for outputting the confrontation generation network to obtain a reading track generation network if the contact ratio is greater than the preset threshold value;
and the second analysis module is used for acquiring information data to be analyzed, and performing reading track analysis on the information data to be analyzed by using the reading track generation network to obtain a virtual reading track graph of the user.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one instruction; and
and the processor executes the instructions stored in the memory to realize the virtual reading track map generation method.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, where at least one instruction is stored in the computer-readable storage medium, and the at least one instruction is executed by a processor in an electronic device to implement the virtual reading trajectory map generation method described above.
The track vector is generated through the historical reading track, the track vector is utilized to mark the information image generated by the existing information data to obtain the track image containing the reading track of the user, the efficiency of analyzing the information data is improved, the track image is utilized to train the pre-constructed countermeasure generation network, the trained network is utilized to analyze the reading track of the information data to be analyzed, the preference of the user on each data in the information data to be analyzed is obtained, and the accuracy of the network is utilized to realize the accurate analysis of the information. Therefore, the virtual reading trajectory graph generation method, the virtual reading trajectory graph generation device, the electronic equipment and the computer readable storage medium provided by the invention can solve the problem of low accuracy in analyzing the user preference information.
Drawings
Fig. 1 is a schematic flowchart illustrating a method for generating a virtual reading trace diagram according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating a process of converting an information image according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of generating an initial resource tag according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of a virtual reading trace map generating apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device for implementing the virtual reading track map generation method according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides a virtual reading track map generation method. The executing body of the virtual reading track map generating method includes, but is not limited to, at least one of electronic devices such as a server and a terminal, which can be configured to execute the method provided by the embodiment of the present application. In other words, the virtual reading trajectory graph generation method may be executed by software or hardware installed in the terminal device or the server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Fig. 1 is a schematic flow chart illustrating a method for generating a virtual reading trace diagram according to an embodiment of the present invention. In this embodiment, the method for generating a virtual reading trajectory diagram includes:
s1, acquiring the existing information data of the user and the historical reading track of the existing information, and constructing an information image according to the existing information data.
In the embodiment of the present invention, the existing information data is information (such as news, books, advertisements, etc. transmitted to the client) available to the user, and the information includes the total amount of the information, the number of the read information, etc.
For example, the information transmitted to the page at the client includes: a news item, a book item and an advertisement, and the total number of information is 3, and 2 information items among them are read.
In detail, the history reading track is information such as a name and browsing duration of information browsed by a user in the existing information data.
For example, the existing information data includes information a, information B, and information C, where the information B and the information C are browsed by the user, the browsing duration of the information B is 0.5 hour, and the browsing duration of the information C is 0.1 hour, and then the browsing durations corresponding to the information B, the information C, and the information B and the information C are the historical reading tracks of the user in the existing information data.
In the embodiment of the invention, the information calling instruction is generated and used for calling the existing information data and the historical reading track which are stored in the database, the block chain or the network cache in advance.
In the embodiment of the present invention, the acquiring of the existing information data of the user and the historical reading track in the existing information includes:
acquiring an information calling instruction, and extracting a target access address in the information calling instruction;
searching a storage database of the existing information data and the historical reading track according to the target access address;
and extracting the existing information data and the historical reading track from the storage database.
In detail, the information calling instruction can be generated through a pre-constructed graphical click button program or through an instruction operation platform.
Specifically, the present invention may utilize a preset resolver to resolve the information calling instruction to extract the target access address in the information calling instruction, where the resolver includes but is not limited to a json resolver and a python resolver; and then finding out a storage database for storing the existing information data and the historical reading track according to the target access address, and acquiring the existing information data and the historical reading track from the storage database.
Furthermore, since the existing information data is mostly text data and has a huge data volume, if the existing information data is directly processed, a large amount of computing resources are occupied, and the processing efficiency is reduced, therefore, the embodiment of the invention converts the existing information data into the information image according to the preset first unit time, so as to improve the efficiency of subsequently processing the existing information data.
In an embodiment of the present invention, referring to fig. 2, the constructing an information image according to the existing information data includes:
s21, dividing the existing information data according to a first unit time to obtain information subsets;
s22, determining the information reading quantity and the information total quantity of each information subset;
s23, constructing an information image according to the information reading quantity and the information total quantity of each information subset.
In one embodiment of the present invention, the first unit time may be a natural day (24 hours). The embodiment of the invention constructs the information image according to the information reading quantity and the information total quantity of the existing information data generated in each natural day.
For example, if the existing information data includes information available to the user from 3/1/3, the existing information data may be divided into a 3/1 daily news subset, a 3/2/3 daily news subset, and a 3/3 daily news subset.
Further, the number of information readings and the total number of information in each first unit time can be determined according to the information subsets, for example, when 3 months and 1 day, the existing information data includes news, books, advertisements and the like, and the total number of information in the information is 3, and when 2 information are read, the total number of information in the information subsets of 3 months and 1 day can be determined to be 3, and the number of information readings is 2. In another embodiment of the present invention, the constructing the information image according to the information reading quantity and the information total quantity of each information subset includes:
performing factorization on the total information quantity of the existing information data to obtain an information matrix;
performing a first operation on the information reading quantity of the information subset and a preset unit gray value to obtain a matrix gray;
and performing a second operation by using the matrix gray scale and the information matrix to obtain an information image.
In detail, assuming that the total information amount is Z, the total information amount can be factorized into Z ═ X · Y, wherein X, Y is a factor obtained by factoring Z, and the information matrix size corresponding to Z can be determined to be X · Y, wherein X is the number of rows and columns of the daily information matrix and Y is the number of columns of the daily information matrix.
For example, the total number of information is 3, the total number of information can be factorized into 3 ═ 1 · 3, and the scale of the information matrix corresponding to 3 can be determined to be 1 · 3, where 1 is the number of rows and columns of the day information matrix and 3 is the number of columns of the day information matrix.
In the embodiment of the present invention, the first operation includes, but is not limited to, a multiplication operation, a division operation, an addition operation, and a subtraction operation.
For example, the number of information reads is q, the unit gray scale value is e, and when the first operation is a multiplication operation, the matrix gray scale q × e can be obtained.
In detail, the second operation may be the same as the first operation.
For example, when the second operation is multiplicationDuring operation, information matrix (3, 1, 4) exists, matrix gray scale (9, 3, 12) exists, and information image can be obtained
S2, constructing a track vector according to the historical reading track, and marking the information image by using the track vector to obtain a first track image.
In one practical application scenario of the present invention, since the historical reading track is the same as the existing information data and is mostly text data, in order to improve the analysis efficiency of the historical reading track, the embodiment of the present invention constructs a track vector according to the historical reading track.
In an embodiment of the present invention, the constructing a track vector according to the historical reading track includes:
extracting the browsing duration of each information data in the historical reading track within a second unit time of the user;
and performing vector conversion on each information data in the historical reading track according to the browsing duration to obtain a track vector.
Wherein the second unit may be the same as the first unit time. In detail, the embodiment of the invention can extract the browsing duration of each existing information data in the historical reading track through the computer sentences (java sentences, python sentences and the like) with the data extraction function.
Specifically, the vector conversion of each existing information data in the historical reading track according to the browsing duration to obtain a track vector includes:
performing vector conversion on each existing information data in the historical reading track by using the following vector conversion algorithm:
wherein Bn is the browsing duration of the nth current information data in the historical reading track, Bn is the track vector of the nth current information data, min (Bn) is the minimum browsing duration in the historical reading track, and max (Bn) is the maximum browsing duration in the historical reading track.
For example, the historical reading tracks contained in Bn include: when B1 is 0.13 hour, B2 is 2.5 hours, B3 is 0.5 hours, B4 is 2.8 hours, B5 is 1.5 hours, B6 is 2.8 hours, B7 is 0.37 hours, B8 is 2.5 hours, and B9 is 1.25 hours, the trajectory vector B3 of the 3 rd existing information data and the trajectory vector B6 of the 6 th existing information data are calculated by the above-described vector conversion algorithm, it is possible to obtain:
in the embodiment of the invention, the track vector is calculated according to the browsing duration of each piece of information data in the existing information data by the user, so that the larger the value of the track vector is, the more carefully the user browses the existing information data corresponding to the track vector, and further, the information image can be marked by multiplying, adding and other operations on the track vector and the vector in the information image, so that the browsing track of the user is displayed in the information image, and the first track image is obtained.
And S3, performing reading track analysis on the first track image by using a pre-constructed confrontation generation network to obtain a second track image.
In an embodiment of the present invention, the countermeasure generation network is a deep learning model, and includes a generator and a discriminator, where the generator is a prediction result (second trajectory image) for generating input data, and the discriminator is used for discriminating a difference between the prediction result (second trajectory image) and a standard result (first trajectory image) corresponding to the input data.
In the embodiment of the present invention, referring to fig. 3, the analyzing a reading track of the first track image by using a pre-established countermeasure generating network to obtain a second track image includes:
s31, mapping the track vector in the first track map to a pre-constructed vector space by using a generator in the confrontation generation network to obtain a vector representation;
s32, constructing a target function by using a preset adjusting function and the vector representation;
and S33, calculating the first track image by using the objective function to obtain a second track image.
In detail, the generator may map the trajectory vector in the first trajectory graph to a pre-constructed vector space by using the following function, so as to obtain a vector characterization:
a(z)＝softmax(bn)
wherein bn is the track vector of the nth current information data, softmax () is a normalized exponential function, and a (z) is the vector representation corresponding to the track vector of the nth current information data.
Specifically, after the vector representation is obtained, a preset adjusting function and the vector representation can be used for constructing a target function.
Illustratively, the objective function is:
G(z)＝a(z)·g(z)
wherein a (z) is the vector characterization, g (z) is a preset adjustment function, and g (z) is the objective function.
In the embodiment of the present invention, the adjusting function includes, but is not limited to: linear kernel function, polymodal kernel function, Sigmoid kernel function.
S4, calculating the coincidence degree of the first track image and the second track image;
in the embodiment of the present invention, a discriminator in the confrontation generating network may be used to discriminate the coincidence degree of the first track image and the second track image.
In an embodiment of the present invention, the calculating a coincidence ratio of the first track image and the second track image includes:
calculating a loss value between each track vector in the first track image and the second track image by using a loss function of a discriminator in the countermeasure generating network;
and taking the average value of the loss values as the coincidence degree of the first track image and the second track image.
For example, if the first trajectory image includes trajectory vector a, trajectory vector B, and trajectory vector C, and the second trajectory image includes trajectory vector a, trajectory vector B, and trajectory vector C, the loss function of the discriminator in the countermeasure generation network may be used to calculate a loss value α between trajectory vector a and trajectory vector a, a loss value β between trajectory vector B and trajectory vector B, and a loss value γ between trajectory vector C and trajectory vector C, and the average of α, β, and γ is used as the coincidence degree of the first trajectory image and the second trajectory image.
S5, judging whether the contact ratio is greater than a preset threshold value;
if the contact ratio is less than or equal to the preset threshold, the following S6 is performed, and if the contact ratio is greater than the preset threshold, the following S7 is performed.
S6, adjusting parameters of the confrontation generation network, and returning to the step S3.
In the embodiment of the present invention, if the contact ratio is less than or equal to the preset threshold, it indicates that the accuracy of the countermeasure generating network is low, and therefore, the parameters of the countermeasure generating network need to be adjusted.
In one embodiment of the present invention, the parameters of the countermeasure generation network may be adjusted by using a preset optimization algorithm, and the gradient descent algorithm includes but is not limited to: a batch gradient descent algorithm, a small batch gradient descent algorithm, and a random gradient descent algorithm.
For example, the current parameters of the countermeasure generating network are input into the optimization algorithm, the optimization algorithm is used to perform optimization calculation on the input current parameters, the optimized optimization parameters output by the optimization algorithm are obtained, and the optimization parameters are used to replace the current parameters of the countermeasure generating network, so as to adjust the parameters in the countermeasure generating network.
In detail, the adjusting parameters of the countermeasure generation network includes:
obtaining current parameters in the countermeasure generating network;
calculating the update gradient of the current parameter by using a preset optimization algorithm;
and updating the current parameters according to the updating gradient to obtain optimized parameters.
According to the embodiment of the invention, the current parameters can be extracted from the countermeasure generation network through the computer sentences with the parameter extraction function, and then the current parameters are updated by using the preset optimization algorithm.
When the current parameter is updated according to the update gradient, preset arithmetic operation can be performed by using the current parameter and the update gradient.
For example, the current parameter is 10, the current parameter is calculated by using a preset optimization algorithm, an update gradient of the current parameter is 0.1, and the current parameter may be updated to 10(1+0.1) ═ 11 according to the update gradient 0.1;
alternatively, the current parameter may be updated to 10+0.1 — 10.1 according to the update gradient 0.1.
After the parameters of the countermeasure generating network are adjusted, the step S3 is returned to, and the reading trajectory analysis is performed again on the first trajectory image.
S7, outputting the confrontation generation network to obtain a reading track generation network;
in the embodiment of the present invention, if the contact ratio is greater than the preset threshold, it indicates that the accuracy of the confrontation generating network meets the requirement, and the confrontation generating network may be output to obtain the reading track generating network.
And S8, acquiring the information data to be analyzed, and analyzing the reading track of the information data to be analyzed by using the reading track generation network to obtain the virtual reading track graph of the user.
In the embodiment of the present invention, the information data to be analyzed includes information data that is not shown to the user, and the information data to be analyzed can be captured from a database for storing the information data to be analyzed.
The embodiment of the invention utilizes the reading track generation network to analyze the reading track of the information data to be analyzed to obtain the virtual reading track graph, and the virtual reading track graph can be used for predicting the reading track of the user.
For example, if news a, news B, news C, and news D exist in the information data to be analyzed, the reading trajectory generation network is used to analyze the reading trajectory of the information data to be analyzed, so that it can be obtained that the user may read news a, news C, and news D, not read news B, read news a on-line, read news D, and finally read news C.
The embodiment of the invention generates the track vector through the historical reading track, and marks the information image generated by the existing information data by using the track vector to obtain the first track image containing the reading track of the user, thereby being beneficial to improving the efficiency of analyzing the information data. Therefore, the virtual reading track map generation method provided by the invention can solve the problem of low accuracy of analyzing the user preference information.
Fig. 4 is a functional block diagram of a virtual reading trace map generating apparatus according to an embodiment of the present invention.
The virtual reading trace map generating apparatus 100 according to the present invention may be installed in an electronic device. According to the implemented functions, the virtual reading trajectory diagram generating device 100 may include a first conversion module 101, a second conversion module 102, a first analysis module 103, a coincidence degree calculation module 104, a parameter adjustment module 105, a network output module 106, and a second analysis module 107. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the first conversion module 101 is configured to obtain existing information data of a user and a historical reading track in the existing information, and construct an information image according to the existing information data;
the second conversion module 102 is configured to construct a track vector according to the historical reading track, and mark the information image by using the track vector to obtain a first track image;
the first analysis module 103 is configured to perform reading track analysis on the first track image by using a pre-established countermeasure generation network to obtain a second track image;
the coincidence degree calculating module 104 is configured to calculate a coincidence degree of the first track image and the second track image;
the parameter adjusting module 105 is configured to adjust a parameter of the confrontation generating network if the contact ratio is less than or equal to a preset threshold, and return to the step of performing reading track analysis on the first track image;
the network output module 106 is configured to output the confrontation generating network as a reading track generating network if the contact ratio is greater than the preset threshold;
the second analysis module 107 is configured to obtain information data to be analyzed, and perform reading track analysis on the information data to be analyzed by using the reading track generation network to obtain a virtual reading track map of the user.
In detail, when the modules in the virtual reading trajectory diagram generation apparatus 100 according to the embodiment of the present invention are used, the same technical means as the virtual reading trajectory diagram generation method described in fig. 1 to 3 are adopted, and the same technical effects can be produced, which is not described herein again.
Fig. 5 is a schematic structural diagram of an electronic device implementing a virtual reading trajectory diagram generation method according to an embodiment of the present invention.
The electronic device may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may further include a computer program, such as a front-end monitoring program, stored in the memory 11 and executable on the processor 10.
In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, a combination of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (e.g., executing a front end monitor 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, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable 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 Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and 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 to store application software installed in the electronic device and various types of data, such as codes of a front-end monitoring program, but also to temporarily store data that has been output or will be output.
The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
The communication interface 13 is used for communication between the electronic device and other devices, and includes 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.), which are 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), and optionally 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 device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.
Fig. 5 only shows an electronic device with components, and it will be 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 a combination of certain components, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply 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 realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The virtual reading trace map generation program stored in the memory 11 of the electronic device 1 is a combination of a plurality of instructions, and when running in the processor 10, can realize:
acquiring the existing information data of a user and a historical reading track in the existing information, and constructing an information image according to the existing information data;
constructing a track vector according to the historical reading track, and marking the information image by using the track vector to obtain a first track image;
performing reading track analysis on the first track image by using a pre-constructed confrontation generation network to obtain a second track image;
calculating the coincidence degree of the first track image and the second track image;
if the contact ratio is smaller than or equal to a preset threshold value, adjusting parameters of the confrontation generation network, and returning to the step of performing reading track analysis on the first track image;
if the contact ratio is larger than the preset threshold value, outputting the confrontation generation network to obtain a reading track generation network;
and acquiring information data to be analyzed, and analyzing the reading track of the information data to be analyzed by using the reading track generation network to obtain a virtual reading track graph of the user.
Specifically, the specific implementation method of the processor 10 for the instruction may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, 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, may implement:
acquiring the existing information data of a user and a historical reading track in the existing information, and constructing an information image according to the existing information data;
constructing a track vector according to the historical reading track, and marking the information image by using the track vector to obtain a first track image;
performing reading track analysis on the first track image by using a pre-constructed confrontation generation network to obtain a second track image;
calculating the coincidence degree of the first track image and the second track image;
if the contact ratio is smaller than or equal to a preset threshold value, adjusting parameters of the confrontation generation network, and returning to the step of performing reading track analysis on the first track image;
if the contact ratio is larger than the preset threshold value, outputting the confrontation generation network to obtain a reading track generation network;
and acquiring information data to be analyzed, and analyzing the reading track of the information data to be analyzed by using the reading track generation network to obtain a virtual reading track graph of the user.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
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 attributes 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 block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A virtual reading track map generation method is characterized by comprising the following steps:
acquiring the existing information data of a user and the historical reading track of the existing information, and constructing an information image according to the existing information data;
constructing a track vector according to the historical reading track, and marking the information image by using the track vector to obtain a first track image;
performing reading track analysis on the first track image by using a pre-constructed confrontation generation network to obtain a second track image;
calculating the coincidence degree of the first track image and the second track image;
if the contact ratio is smaller than or equal to a preset threshold value, adjusting parameters of the confrontation generation network, and returning to the step of performing reading track analysis on the first track image;
if the contact ratio is larger than the preset threshold value, outputting the confrontation generation network to obtain a reading track generation network;
and acquiring information data to be analyzed, and analyzing the reading track of the information data to be analyzed by using the reading track generation network to obtain a virtual reading track graph of the user.
2. The method of claim 1, wherein the constructing an information image according to the existing information data comprises:
dividing the existing information data according to a first unit time to obtain information subsets;
determining the information reading quantity and the information total quantity of each information subset;
and constructing an information image according to the information reading quantity and the information total quantity of each information subset.
3. The method as claimed in claim 2, wherein the step of constructing the information image according to the information reading quantity and the information total quantity of each information subset comprises:
performing factorization on the total information quantity of the existing information data to obtain an information matrix;
performing a first operation on the information reading quantity of each information subset and a preset unit gray value to obtain a matrix gray;
and performing a second operation by using the matrix gray scale and the information matrix to obtain an information image.
4. The virtual reading trajectory diagram generation method of claim 1, wherein the constructing a trajectory vector according to the historical reading trajectory diagram comprises:
extracting the browsing duration of each information data in the historical reading track within a second unit time of the user;
and performing vector conversion on each information data in the historical reading track according to the browsing duration to obtain a track vector.
5. The method as claimed in claim 4, wherein the vector conversion of each information data in the historical reading track according to the browsing duration to obtain a track vector comprises:
performing vector conversion on each existing information data in the historical reading track by using the following vector conversion algorithm:
wherein Bn is the browsing duration of the nth current information data in the historical reading track, Bn is the track vector of the nth current information data, min (Bn) is the minimum browsing duration in the historical reading track, and max (Bn) is the maximum browsing duration in the historical reading track.
6. The virtual reading trajectory diagram generation method of any one of claims 1 to 5, wherein the reading trajectory analysis of the first trajectory image by using a pre-constructed confrontation generation network to obtain a second trajectory image comprises:
mapping the track vector in the first track map to a pre-constructed vector space by using a generator in the countermeasure generation network to obtain a vector representation;
constructing a target function by using a preset adjusting function and the vector representation;
and calculating the first track image by using the target function to obtain a second track image.
7. The virtual reading trajectory map generation method of any one of claims 1 to 5, wherein the calculating the coincidence degree of the first trajectory image and the second trajectory image includes:
calculating a loss value between each track vector in the first track image and the second track image by using a loss function of a discriminator in the countermeasure generating network;
and taking the average value of the loss values as the coincidence degree of the first track image and the second track image.
8. An apparatus for generating a virtual reading trajectory diagram, the apparatus comprising:
the first conversion module is used for acquiring the existing information data of a user and the historical reading track of the existing information, and constructing an information image according to the existing information data;
the second conversion module is used for constructing a track vector according to the historical reading track and marking the information image by using the track vector to obtain a first track image;
the first analysis module is used for carrying out reading track analysis on the first track image by utilizing a pre-constructed countermeasure generation network to obtain a second track image;
the coincidence degree calculation module is used for calculating the coincidence degree of the first track image and the second track image;
a parameter adjusting module, configured to adjust a parameter of the countermeasure generation network if the contact ratio is less than or equal to a preset threshold, and return to the step of performing reading trajectory analysis on the first trajectory image;
the network output module is used for outputting the confrontation generation network to obtain a reading track generation network if the contact ratio is greater than the preset threshold value;
and the second analysis module is used for acquiring information data to be analyzed, and performing reading track analysis on the information data to be analyzed by using the reading track generation network to obtain a virtual reading track graph of the user.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of generating a virtual reading trajectory map as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the virtual reading trajectory map generation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110518009.1A CN113139129B (en) | 2021-05-12 | 2021-05-12 | Virtual reading trajectory graph generation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110518009.1A CN113139129B (en) | 2021-05-12 | 2021-05-12 | Virtual reading trajectory graph generation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113139129A true CN113139129A (en) | 2021-07-20 |
| CN113139129B CN113139129B (en) | 2024-02-09 |
Family
ID=76817551
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110518009.1A Active CN113139129B (en) | 2021-05-12 | 2021-05-12 | Virtual reading trajectory graph generation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113139129B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113887384A (en) * | 2021-09-29 | 2022-01-04 | 平安银行股份有限公司 | Pedestrian trajectory analysis method, device, equipment and medium based on multi-trajectory fusion |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107031227A (en) * | 2017-06-13 | 2017-08-11 | 成都艾体验科技有限公司 | Intelligent bookmark and its implementation |
| US20180040056A1 (en) * | 2016-08-04 | 2018-02-08 | Linkedin Corporation | Maximizing the propensity of content consumption according to content complexity and content consumption time |
| CN112733023A (en) * | 2020-12-30 | 2021-04-30 | 平安科技（深圳）有限公司 | Information pushing method and device, electronic equipment and computer readable storage medium |
-
2021
- 2021-05-12 CN CN202110518009.1A patent/CN113139129B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180040056A1 (en) * | 2016-08-04 | 2018-02-08 | Linkedin Corporation | Maximizing the propensity of content consumption according to content complexity and content consumption time |
| CN107031227A (en) * | 2017-06-13 | 2017-08-11 | 成都艾体验科技有限公司 | Intelligent bookmark and its implementation |
| CN112733023A (en) * | 2020-12-30 | 2021-04-30 | 平安科技（深圳）有限公司 | Information pushing method and device, electronic equipment and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 张磊;高强;朱珍民;叶剑;: "面向移动阅读平台的资源推荐算法", 计算机工程, no. 08, pages 69 - 73 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113887384A (en) * | 2021-09-29 | 2022-01-04 | 平安银行股份有限公司 | Pedestrian trajectory analysis method, device, equipment and medium based on multi-trajectory fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113139129B (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112380859A (en) | Public opinion information recommendation method and device, electronic equipment and computer storage medium | |
| CN112883190A (en) | Text classification method and device, electronic equipment and storage medium | |
| CN115423535B (en) | Product purchasing method, device, equipment and medium based on market priori big data | |
| CN114186132B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN114781832A (en) | Course recommendation method and device, electronic equipment and storage medium | |
| CN115002200A (en) | User portrait based message pushing method, device, equipment and storage medium | |
| CN112306835A (en) | User data monitoring and analyzing method, device, equipment and medium | |
| CN113868528A (en) | Information recommendation method and device, electronic equipment and readable storage medium | |
| CN114612194A (en) | Product recommendation method and device, electronic equipment and storage medium | |
| CN113868529A (en) | Knowledge recommendation method and device, electronic equipment and readable storage medium | |
| CN114398560B (en) | Marketing interface setting method, device, equipment and medium based on WEB platform | |
| CN113886708A (en) | Product recommendation method, device, equipment and storage medium based on user information | |
| CN115018588A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN111930897A (en) | Patent retrieval method, device, electronic equipment and computer-readable storage medium | |
| CN114187096A (en) | Risk assessment method, device and equipment based on user portrait and storage medium | |
| CN113486238A (en) | Information pushing method, device and equipment based on user portrait and storage medium | |
| CN113139129B (en) | Virtual reading trajectory graph generation method and device, electronic equipment and storage medium | |
| CN116401602A (en) | Event detection method, device, equipment and computer readable medium | |
| CN113706019B (en) | Service capability analysis method, device, equipment and medium based on multidimensional data | |
| CN115238179A (en) | Project pushing method and device, electronic equipment and computer readable storage medium | |
| CN115098644A (en) | Image and text matching method and device, electronic equipment and storage medium | |
| CN114780688A (en) | Text quality inspection method, device and equipment based on rule matching and storage medium | |
| CN114461630A (en) | Intelligent attribution analysis method, device, equipment and storage medium | |
| CN114240560A (en) | Product ranking method, device, equipment and storage medium based on multidimensional analysis | |
| CN113704407A (en) | Complaint amount analysis method, device, equipment and storage medium based on category analysis |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220916 Address after: Room 2601 (Unit 07), Qianhai Free Trade Building, No. 3048, Xinghai Avenue, Nanshan Street, Qianhai Shenzhen-Hong Kong Cooperation Zone, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Ping An Smart Healthcare Technology Co.,Ltd. Address before: 1-34 / F, Qianhai free trade building, 3048 Xinghai Avenue, Mawan, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong 518000 Applicant before: Ping An International Smart City Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |