CN116662671A - Digital library data pushing method based on user preference - Google Patents
Digital library data pushing method based on user preference Download PDFInfo
- Publication number
- CN116662671A CN116662671A CN202310905305.6A CN202310905305A CN116662671A CN 116662671 A CN116662671 A CN 116662671A CN 202310905305 A CN202310905305 A CN 202310905305A CN 116662671 A CN116662671 A CN 116662671A
- Authority
- CN
- China
- Prior art keywords
- data
- pushing
- active
- time
- real
- 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 51
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000005065 mining Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000013528 artificial neural network Methods 0.000 claims description 21
- 238000007621 cluster analysis Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 4
- 238000013145 classification model Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000007418 data mining Methods 0.000 abstract description 30
- 238000011156 evaluation Methods 0.000 description 8
- 238000005457 optimization Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
-
- 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)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a digital library data pushing method based on user preference, which comprises the steps of obtaining historical data, real-time retrieval data and user information of a user in a digital library, correlating the user information with the historical data and the real-time retrieval data, preprocessing the historical data and the real-time retrieval data, obtaining active books according to the reading time of the preprocessed historical data, obtaining the active retrieval data according to the retrieval similar content times of the preprocessed historical data, extracting topics and feature keywords of the active books and the active retrieval data, performing correlation rule mining on the topics and the feature keywords, performing clustering analysis on the preprocessed historical data according to the feature keywords to obtain classification, inputting the preprocessed real-time retrieval data into a pushing model, obtaining preference data and pushing. The method not only can improve the data mining precision, but also has better interpretability.
Description
Technical Field
The invention relates to the field of data mining, in particular to a digital library data pushing method based on user preference.
Background
The preference data pushing technology is widely applied to the field of digital libraries, and can help a digital library manager to timely and efficiently acquire user preferences so as to realize accurate pushing of preference data. At present, a digital library has the characteristics of huge information quantity of users, various types of search data, high information density and the like, and the data pushing method of the digital library has more uncertain factors, so that the preference data pushing method of the digital library has larger uncertainty. Although some digital library data pushing methods have been invented, the problem of uncertainty of the digital library data pushing method is not effectively solved.
Disclosure of Invention
The invention aims to provide a digital library data pushing method based on user preference.
In order to achieve the above purpose, the invention is implemented according to the following technical scheme:
the invention comprises the following steps:
a, acquiring historical data, real-time retrieval data and user information of a user in a digital library, and associating the user information with the historical data and the real-time retrieval data, wherein the historical data comprises user information, historical retrieval data and historical reading data;
preprocessing the historical data and the real-time retrieval data, acquiring active books according to the preprocessed reading time of the historical data, acquiring active retrieval data according to the preprocessed retrieval similar content times of the historical data, and extracting topics and characteristic keywords of the active books and the active retrieval data;
c, carrying out association rule mining on the subject and the characteristic keywords, and carrying out cluster analysis on the preprocessed historical data according to the characteristic keywords to obtain classification;
and D, inputting the preprocessed real-time retrieval data into a pushing model, acquiring preference data and pushing the preference data, wherein the pushing model comprises an optimized deep neural network algorithm and a classified pushing algorithm, respectively predicting first pushing data and second pushing data by using the optimized deep neural network algorithm, calculating the confidence coefficient of the first pushing data and the second pushing data, sequencing the confidence coefficient from large to small, and pushing the pushing data corresponding to the first confidence coefficient as the preference data.
Further, the preprocessing method in the step B includes cleaning the historical data and the real-time search data, removing useless punctuation marks, special characters and labels, marking and word segmentation on the cleaned historical data and the real-time search data, removing stop words, deleting data with browsing time lower than 5 minutes in the historical data according to reading time, and deleting search data without browsing data according to whether browsing books.
Further, the method for extracting the theme and the characteristic keywords of the active books and the active retrieval data comprises the steps of extracting the theme and the characteristic keywords of the active books and the active retrieval data, counting frequently occurring words of the active books and the active retrieval data by word frequency, sequencing according to word occurrence frequency, taking the keywords with the first three frequencies as the characteristic keywords of the current retrieval, and determining the theme according to the content of the active books and the active retrieval data.
Further, the method for carrying out association rule mining on the theme and the feature keywords comprises the following steps:
scanning all the characteristic keywords to obtain a frequent item set, wherein the frequent item set comprises characteristic keywords, support degree and characteristic transaction set, and calculating the support degree of the item:
wherein the support degree of the characteristic key word X to the characteristic key word YThe number num (N) of total features including the number of feature keywords X and Y>；
And comparing the support degree of the feature keywords, deleting the feature keywords lower than the support degree threshold until all feature keywords are traversed to generate no frequent item sets, finding out all non-empty subsets meeting the support degree threshold, and sorting according to the support degree from large to small to generate association rules.
Further, the method for optimizing the deep neural network algorithm comprises the following steps:
a. given super parametersReadjusting the learning rate of each element in the objective function argument according to element operation:
wherein the learning rate isThe state variable at time t is +.>Constant for maintaining numerical stability>A small random gradient of +.>The independent variable at time t is +.>；
b. Setting the optimized learning rate and giving super parametersGiven superparameter->The study of each element in the model parametersReadjusting the learning rate according to element operation:
wherein the exponentially weighted moving average of the small batch random gradients of time steps at time t isA small batch random gradient exponentially weighted moving average at time t is +.>The small batch random gradient after correction at time t is +.>。
Further, the method for predicting the first push data by using the optimized deep neural network algorithm comprises the steps of inputting the preprocessed historical data into the optimized deep neural network, calculating the correlation degree between the first push data and the active books until the correlation degree reaches 80%, stopping training, and inputting the preprocessed real-time search data into the trained optimized deep neural network algorithm to obtain the first push data.
Further, the method for calculating the correlation degree between the first push data and the active book includes:
vectorizing the first push data and the active books, and calculating the relativity of the vectorized first push data and the active books:
wherein the vectorized ith first push data isThe ith vectorized active book is +.>The first push data C has a support for the active book E of +.>。
Further, the method for predicting the second push data by using the classified push algorithm comprises the following steps:
firstly, inputting the preprocessed historical data into a classified pushing algorithm, and performing cluster analysis on the preprocessed historical data according to a theme and characteristic keywords to obtain a plurality of types of reading books;
and secondly, inputting the real-time retrieval data into a classification model, matching the real-time retrieval data with a clustering analysis result to obtain a category, calculating the correlation degree of active books in the category, sequencing from large to small, and outputting the first active book as second pushing data.
Further, the method for calculating the confidence of the first push data and the second push data includes:
wherein the confidence of the real-time search data X to the push data Y is thatProbability of simultaneously including real-time search data X and push data Y>Probability of including real-time retrieval data>。
The beneficial effects of the invention are as follows:
the invention relates to a digital library data pushing method based on user preference, which has the following technical effects compared with the prior art:
1. according to the invention, through preprocessing, association rules mining and classification steps, the accuracy of pushing preference data can be improved, so that the accuracy of pushing preference data is improved, the pushing of preference data is automated, the labor and time cost can be greatly saved, the working efficiency is improved, the preference pushing of digital library data can be realized, the preference data of digital library users can be pushed in real time, the method has important significance for pushing the preference data of the digital library, and the method can adapt to the pushing requirements of different digital libraries and the digital library data preferred by different users, and has certain universality.
2. The method can comprehensively consider key parameters of the digital library data pushing based on user preference, converts the pushing problem into the prediction problem by utilizing the pushing model, and realizes accurate control of pushing by training the known preprocessing data. The method not only can improve the pushing precision, but also has better interpretability, and can be directly applied to a digital library data pushing system.
Drawings
FIG. 1 is a flow chart showing the steps of a method for pushing digital library data based on user preferences according to the present invention.
Detailed Description
The invention is further described below in the following description of specific embodiments, which are presented for purposes of illustration and description, but are not intended to be limiting.
The digital library data pushing method based on user preference comprises the following steps:
as shown in fig. 1, in this embodiment, the steps include:
a, acquiring historical data, real-time retrieval data and user information of a user in a digital library, and associating the user information with the historical data and the real-time retrieval data, wherein the historical data comprises user information, historical retrieval data and historical reading data;
preprocessing the historical data and the real-time retrieval data, acquiring active books according to the preprocessed reading time of the historical data, acquiring active retrieval data according to the preprocessed retrieval similar content times of the historical data, and extracting topics and characteristic keywords of the active books and the active retrieval data;
c, carrying out association rule mining on the subject and the characteristic keywords, and carrying out cluster analysis on the preprocessed historical data according to the characteristic keywords to obtain classification;
inputting the preprocessed real-time retrieval data into a pushing model, acquiring preference data and pushing the preference data, wherein the pushing model comprises an optimized deep neural network algorithm and a classified pushing algorithm, respectively predicting first pushing data and second pushing data by using the optimized deep neural network algorithm, calculating the confidence coefficient of the first pushing data and the second pushing data, sequencing the confidence coefficient from large to small, and pushing the pushing data corresponding to the first confidence coefficient as the preference data;
in this embodiment, the preprocessing method in step B includes cleaning the historical data and the real-time search data, removing unnecessary punctuation marks, special characters and labels, marking and word segmentation on the cleaned historical data and the real-time search data, removing stop words, deleting data with browsing time lower than 5 minutes in the historical data according to reading duration, and deleting search data without browsing data according to whether browsing books;
in the actual evaluation, a certain digital library is taken as an experimental object, historical data and real-time retrieval data of a user in the digital library are obtained, the specific case description is carried out by taking the user as the experimental object, the user information in the historical data is Zhang San, 30 years old, men, 2023 month 6 and 17 th historical retrieval data are data mining, random HTML is allowed to be output by an output unit and used for rendering HTML codes, 2023 month 6 and 17 th historical reading data are 2 hours of data mining concept and technology reading, 3 minutes of data mining and predictive analysis reading, 10 minutes of data mining and predictive analysis reading, 2023 month 7 and 10 th real-time retrieval data are data mining actual combat, the preprocessed historical retrieval data of 2023 year 6 and 17 th month 17 is data/mining, allowed/output/unit/HTML, the preprocessed historical retrieval data of 2023 year 7 and 17 th is data mining/actual combat, the preprocessed historical retrieval data of 2023 month 6 and 17 th historical reading data of 2023 is data mining/actual combat, and the preprocessed historical reading data of 2023 month 6 and 17 th month 11 th is data mining and predictive analysis data of data and 10 minutes of data mining and predictive analysis.
In this embodiment, the method for extracting the topic and the feature keyword of the active book and the active search data includes extracting the topic and the feature keyword of the active book and the active search data, counting frequently occurring words of the active book and the active search data by using word frequency, sorting according to word occurrence frequency, taking keywords with first three frequencies as feature keywords of the current search, and determining the topic according to the content of the active book and the active search data;
in the actual evaluation, the processed theme of the historical data is data mining, the characteristic keywords are data mining and HTML, the preprocessed theme of the real-time retrieval data is data mining, and the characteristic keywords are data mining and actual combat.
In this embodiment, the method for performing association rule mining on the subject and the feature keyword includes:
scanning all the characteristic keywords to obtain a frequent item set, wherein the frequent item set comprises characteristic keywords, support degree and characteristic transaction set, and calculating the support degree of the item:
wherein the support degree of the characteristic key word X to the characteristic key word YThe number num (N) of total features including the number of feature keywords X and Y>；
Comparing the support degree of the feature keywords, deleting the feature keywords lower than the support degree threshold until all feature keywords are traversed to generate no frequent item sets, finding out all non-empty subsets meeting the support degree threshold, and sorting according to the support degree from large to small to generate association rules;
in actual evaluation, the HTML supported data mining was 0.651, the actual combat supported data mining was 0.803, the HTML supported actual combat was 0.597, and the association rules were actual combat, data mining, and HTML.
In this embodiment, the method for optimizing the deep neural network algorithm includes:
a. given super parametersReadjusting the learning rate of each element in the objective function argument according to element operation:
wherein the learning rate isThe state variable at time t is +.>Constant for maintaining numerical stability>A small random gradient of +.>The independent variable at time t is +.>；
b. Setting the optimized learning rate and giving super parametersGiven superparameter->Readjusting the learning rate of each element in the model parameters according to element operation:
wherein the exponentially weighted moving average of the small batch random gradients of time steps at time t isA small batch random gradient exponentially weighted moving average at time t is +.>The small batch random gradient after correction at time t is +.>；
In the actual evaluation, the preprocessed historical data are respectively input into an un-optimized deep neural network and an optimized deep neural network, and when the learning rate is 0.01 and other configuration parameters are the same, the time spent on un-optimization is 21s, and the time spent on optimization is 33s; when the learning rate is adjusted to 0.001, the time spent for optimization is 26s, the time spent for optimization is 7s, the learning rate of the optimized deep neural network is set to 0.001, and the response speed after optimization is faster.
In this embodiment, the method for predicting the first push data by using the optimized deep neural network algorithm includes inputting the preprocessed historical data into the optimized deep neural network, calculating a correlation between the first push data and the active book until the correlation reaches 80%, stopping training, and inputting the preprocessed real-time search data into the trained optimized deep neural network algorithm to obtain the first push data;
in actual evaluation, the first push data was "python business data mining".
In this embodiment, the method for calculating the correlation between the first push data and the active book includes:
vectorizing the first push data and the active books, and calculating the relativity of the vectorized first push data and the active books:
wherein the vectorized ith first push data isThe ith vectorized active book is +.>The first push data C has a support for the active book E of +.>；
In the actual evaluation, the first push data is "python business data mining" data mining and predictive analysis ", the active book is" data mining and analysis ", the correlation between the first push data" python business data mining "and the active book is 0.89, and the correlation between the first push data" data mining and predictive analysis "and the active book is 0.83.
In this embodiment, the method for predicting the second push data by using the classified push algorithm includes:
firstly, inputting the preprocessed historical data into a classified pushing algorithm, and performing cluster analysis on the preprocessed historical data according to a theme and characteristic keywords to obtain a plurality of types of reading books;
secondly, inputting the real-time retrieval data into a classification model, matching the real-time retrieval data with a clustering analysis result to obtain a category, calculating the correlation degree of active books in the category, sorting from large to small, and outputting a first active book as second pushing data;
in the actual evaluation, the second push data is "data mining concept and technique".
In this embodiment, the method for calculating the confidence of the first push data and the second push data includes:
wherein the confidence of the real-time search data X to the push data Y is thatProbability of simultaneously including real-time search data X and push data Y>Probability of including real-time retrieval data>。
In the actual evaluation, the confidence of the real-time search data mining actual combat on the first push data python business data mining is 0.85, the confidence of the real-time search data mining actual combat on the second push data python business data mining is 0.78, and the first push data python business data mining is used as preference data for pushing.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (9)
1. A digital library data pushing method based on user preferences, comprising the steps of:
a, acquiring historical data real-time retrieval data and user information of a user in a digital library, and associating the user information with the historical data and the real-time retrieval data, wherein the historical data comprises historical retrieval data and historical reading data;
preprocessing the historical data and the real-time retrieval data, acquiring active books according to the preprocessed reading time of the historical data, acquiring active retrieval data according to the preprocessed retrieval similar content times of the historical data, and extracting topics and characteristic keywords of the active books and the active retrieval data;
c, carrying out association rule mining on the subject and the characteristic keywords, and carrying out cluster analysis on the preprocessed historical data according to the characteristic keywords to obtain classification;
and D, inputting the preprocessed real-time retrieval data into a pushing model, acquiring preference data and pushing the preference data, wherein the pushing model comprises an optimized deep neural network algorithm and a classified pushing algorithm, respectively predicting first pushing data and second pushing data by using the optimized deep neural network algorithm, calculating the confidence coefficient of the first pushing data and the second pushing data, sequencing the confidence coefficient from large to small, and pushing the pushing data corresponding to the first confidence coefficient as the preference data.
2. The method for pushing digital library data based on user preference according to claim 1, wherein the preprocessing method in step B comprises cleaning the historical data and the real-time search data, removing useless punctuation marks, special characters and labels, marking and word segmentation are carried out on the cleaned historical data and the real-time search data, stop words are removed, data with browsing time lower than 5 minutes in the historical data are deleted according to reading time, and search data without browsing data are deleted according to whether browsing books are browsed or not.
3. The method for pushing digital library data based on user preference according to claim 1, wherein the method for extracting the topic and the feature keyword of the active book and the active search data comprises extracting the topic and the feature keyword of the active book and the active search data, counting words frequently appearing in the active book and the active search data by word frequency, sorting according to word occurrence frequency, taking the keywords with the first three frequencies as the feature keyword of the current search, and determining the topic according to the content of the active book and the active search data.
4. The method for pushing digital library data based on user preferences according to claim 1, wherein the method for performing association rule mining on the subject and the feature keyword comprises the following steps:
scanning all the characteristic keywords to obtain a frequent item set, wherein the frequent item set comprises characteristic keywords, support degree and characteristic transaction set, and calculating the support degree of the item:
wherein the support degree of the characteristic key word X to the characteristic key word YThe number num (N) of total features including the number of feature keywords X and Y>；
And comparing the support degree of the feature keywords, deleting the feature keywords lower than the support degree threshold until all feature keywords are traversed to generate no frequent item sets, finding out all non-empty subsets meeting the support degree threshold, and sorting according to the support degree from large to small to generate association rules.
5. The method for pushing digital library data based on user preferences according to claim 1, wherein the method for optimizing the deep neural network algorithm comprises the following steps:
a. given super parametersReadjusting the learning rate of each element in the objective function argument according to element operation:
wherein the learning rate isThe state variable at time t is +.>Constant for maintaining numerical stability>A small random gradient of +.>The independent variable at time t is +.>；
b. Setting the optimized learning rate and giving super parametersGiven superparameter->Readjusting the learning rate of each element in the model parameters according to element operation:
wherein the exponentially weighted moving average of the small batch random gradients of time steps at time t isA small batch random gradient exponentially weighted moving average at time t is +.>The small batch random gradient after correction at time t is +.>。
6. The method for pushing digital library data based on user preference according to claim 1, wherein the method for predicting first pushing data by using an optimized deep neural network algorithm comprises inputting the preprocessed historical data into the optimized deep neural network, calculating the correlation between the first pushing data and the active book until the correlation reaches 80%, stopping training, and inputting the preprocessed real-time retrieval data into the trained optimized deep neural network algorithm to obtain first pushing data.
7. The method of claim 6, wherein the method of calculating the correlation of the first push data and the active book comprises:
vectorizing the first push data and the active books, and calculating the relativity of the vectorized first push data and the active books:
wherein the vectorized ith first push data isThe ith vectorized active book is +.>The first push data C has a support for the active book E of +.>。
8. The method for pushing digital library data based on user preferences according to claim 1, wherein the method for predicting the second pushed data using the classified pushing algorithm comprises:
firstly, inputting the preprocessed historical data into a classified pushing algorithm, and performing cluster analysis on the preprocessed historical data according to a theme and characteristic keywords to obtain a plurality of types of reading books;
and secondly, inputting the real-time retrieval data into a classification model, matching the real-time retrieval data with a clustering analysis result to obtain a category, calculating the correlation degree of active books in the category, sequencing from large to small, and outputting the first active book as second pushing data.
9. The method for pushing digital library data based on user preferences according to claim 1, wherein the method for calculating the confidence of the first pushing data and the second pushing data comprises:
wherein the confidence of the real-time search data X to the push data Y is thatProbability of simultaneously including real-time search data X and push data Y>Probability of including real-time retrieval data>。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310905305.6A CN116662671B (en) | 2023-07-24 | 2023-07-24 | Digital library data pushing method based on user preference |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310905305.6A CN116662671B (en) | 2023-07-24 | 2023-07-24 | Digital library data pushing method based on user preference |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116662671A true CN116662671A (en) | 2023-08-29 |
| CN116662671B CN116662671B (en) | 2023-10-27 |
Family
ID=87710001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310905305.6A Active CN116662671B (en) | 2023-07-24 | 2023-07-24 | Digital library data pushing method based on user preference |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116662671B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117852717A (en) * | 2024-01-10 | 2024-04-09 | 中国气象局气象发展与规划院 | Typhoon disaster prediction method for optimizing back propagation neural network based on genetic algorithm |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102819555A (en) * | 2012-06-27 | 2012-12-12 | 北京奇虎科技有限公司 | Method and device for loading recommended information in read mode of webpage |
| CN109408600A (en) * | 2018-09-25 | 2019-03-01 | 浙江工业大学 | A kind of books based on data mining recommend purchaser's method |
| CN109657140A (en) * | 2018-12-13 | 2019-04-19 | 平安普惠企业管理有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN110163703A (en) * | 2018-02-12 | 2019-08-23 | 阿里巴巴集团控股有限公司 | A kind of disaggregated model method for building up, official documents and correspondence method for pushing and server |
| CN111882361A (en) * | 2020-07-31 | 2020-11-03 | 苏州云开网络科技有限公司 | Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium |
| CN111881343A (en) * | 2020-07-07 | 2020-11-03 | Oppo广东移动通信有限公司 | Information pushing method and device, electronic equipment and computer readable storage medium |
| CN114238618A (en) * | 2021-12-21 | 2022-03-25 | 掌阅科技股份有限公司 | Information pushing method, electronic equipment and storage medium |
| WO2023272516A1 (en) * | 2021-06-29 | 2023-01-05 | Siemens Aktiengesellschaft | A method, device, system and storage medium for scheme recommendation |
| CN116188120A (en) * | 2023-04-28 | 2023-05-30 | 北京华阅嘉诚科技发展有限公司 | Method, device and system for recommending audio books and storage medium |
-
2023
- 2023-07-24 CN CN202310905305.6A patent/CN116662671B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102819555A (en) * | 2012-06-27 | 2012-12-12 | 北京奇虎科技有限公司 | Method and device for loading recommended information in read mode of webpage |
| CN110163703A (en) * | 2018-02-12 | 2019-08-23 | 阿里巴巴集团控股有限公司 | A kind of disaggregated model method for building up, official documents and correspondence method for pushing and server |
| CN109408600A (en) * | 2018-09-25 | 2019-03-01 | 浙江工业大学 | A kind of books based on data mining recommend purchaser's method |
| CN109657140A (en) * | 2018-12-13 | 2019-04-19 | 平安普惠企业管理有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN111881343A (en) * | 2020-07-07 | 2020-11-03 | Oppo广东移动通信有限公司 | Information pushing method and device, electronic equipment and computer readable storage medium |
| CN111882361A (en) * | 2020-07-31 | 2020-11-03 | 苏州云开网络科技有限公司 | Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium |
| WO2023272516A1 (en) * | 2021-06-29 | 2023-01-05 | Siemens Aktiengesellschaft | A method, device, system and storage medium for scheme recommendation |
| CN114238618A (en) * | 2021-12-21 | 2022-03-25 | 掌阅科技股份有限公司 | Information pushing method, electronic equipment and storage medium |
| CN116188120A (en) * | 2023-04-28 | 2023-05-30 | 北京华阅嘉诚科技发展有限公司 | Method, device and system for recommending audio books and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117852717A (en) * | 2024-01-10 | 2024-04-09 | 中国气象局气象发展与规划院 | Typhoon disaster prediction method for optimizing back propagation neural network based on genetic algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116662671B (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107577688B (en) | Original article influence analysis system based on media information acquisition | |
| CN109933670B (en) | Text classification method for calculating semantic distance based on combined matrix | |
| CN111832289B (en) | Service discovery method based on clustering and Gaussian LDA | |
| CN109165294B (en) | Short text classification method based on Bayesian classification | |
| CN110826320B (en) | Sensitive data discovery method and system based on text recognition | |
| CN110413764B (en) | Long text enterprise name recognition method based on pre-built word stock | |
| CN111860981B (en) | Enterprise national industry category prediction method and system based on LSTM deep learning | |
| CN104199965A (en) | Semantic information retrieval method | |
| CN116662671B (en) | Digital library data pushing method based on user preference | |
| JP2020512651A (en) | Search method, device, and non-transitory computer-readable storage medium | |
| CN109033066B (en) | Abstract forming method and device | |
| CN104573130A (en) | Entity resolution method based on group calculation and entity resolution device based on group calculation | |
| CN112395881B (en) | Material label construction method and device, readable storage medium and electronic equipment | |
| CN108897754A (en) | Recognition methods, system and the calculating equipment of work order type based on big data | |
| CN114003721A (en) | Construction method, device and application of dispute event type classification model | |
| CN112069307B (en) | Legal provision quotation information extraction system | |
| CN116756347A (en) | Semantic information retrieval method based on big data | |
| CN114491062B (en) | Short text classification method integrating knowledge graph and topic model | |
| CN115146062A (en) | Intelligent event analysis method and system fusing expert recommendation and text clustering | |
| CN116629716A (en) | Intelligent interaction system work efficiency analysis method | |
| CN114943285B (en) | Intelligent auditing system for internet news content data | |
| CN111339783B (en) | RNTM-based topic mining method and device | |
| CN113688633A (en) | Outline determination method and device | |
| CN109359161A (en) | Address date recognition methods and device | |
| CN113807429B (en) | Enterprise classification method, enterprise classification device, computer equipment and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |