CN114945180A - Network high-order structure community generation and division method - Google Patents
Network high-order structure community generation and division method Download PDFInfo
- Publication number
- CN114945180A CN114945180A CN202210354871.8A CN202210354871A CN114945180A CN 114945180 A CN114945180 A CN 114945180A CN 202210354871 A CN202210354871 A CN 202210354871A CN 114945180 A CN114945180 A CN 114945180A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- network
- data
- database
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000002123 temporal effect Effects 0.000 claims abstract description 11
- 230000002457 bidirectional effect Effects 0.000 claims description 4
- 238000002360 preparation method Methods 0.000 claims description 4
- 238000012015 optical character recognition Methods 0.000 claims 2
- 230000000694 effects Effects 0.000 description 5
- 230000009182 swimming Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001680 brushing effect Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/18—Network planning tools
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method for generating and dividing a network high-order structure community, which comprises the following steps: connecting an Ethernet through a network interface, and logging in account information of the Ethernet; presetting a corresponding user preference database through information in the account; storing the internet browsing information of the user at different time periods and collecting the internet browsing information; training the collected data in a preset training model and adding the trained data into the user preference database; classifying the user preference database according to time, further generating a temporal personal database and updating the user preference database; pushing corresponding content within a fixed using time according to the personal database; during the use period of the user, the information browsed by the user is collected, and the collected information is input into the user preference database again through training to further improve the user data, so that the user can master the current preference of the user in real time, and the use experience of the user on the network is enhanced.
Description
Technical Field
The invention relates to the technical field of networks, in particular to a method for generating and dividing a network high-order structure community.
Background
Along with the technological progress, the dependence of people on electronic products is higher and higher, the network application condition is more and more, computers or other electronic products generally need to be connected through a network, in the network connection process, the interest and the hobbies and the use habits of a user need to be judged, and applications or information and the like frequently used by the user need to be pushed and displayed, so that the experience of the user is favorably improved; the current network structure community analyzes the data of the user in the big data so as to obtain the interests and habits of the user, but because the network interface has singleness in the community and the family, more than all the cases are that two or more people apply the same data port, in the network structure, it is difficult to distinguish that one of the people uses the network port, and then corresponding application and information are pushed according to the interests and habits of the user, so that the experience of the user can be reduced.
Therefore, the invention provides a network high-order structure community generation and division method.
Disclosure of Invention
In order to solve the above problems, the present invention provides a method for generating and dividing a network high-order structure community, so as to more exactly solve the problem of reducing the experience of a user using a network.
The invention is realized by the following technical scheme:
the invention provides a network high-order structure community generating and dividing method, which comprises the following steps:
connecting an Ethernet through a network interface, and logging in account information of the Ethernet;
presetting a corresponding user preference database through information in the account;
storing the browsing information of the user on the internet at different time periods and collecting the browsing information;
training the collected data in a preset training model and adding the trained data into the user preference database;
classifying the user preference database according to time, further generating a temporal personal database and updating the user preference database;
and pushing corresponding content according to the personal database within a fixed using time.
Further, the method for generating and dividing the network high-order structure community comprises the steps of connecting an Ethernet through a network interface and logging account information of the Ethernet;
the login account information comprises: account password login, short message verification login and face recognition login.
Further, the method for generating and dividing the network high-order structure community comprises the steps of presetting a corresponding user preference database through information in an account;
the Ethernet reads the information disclosed on the network, such as the age, sex, work, hobbies and the like of the user through the personal information in the account; and the picture disclosed by the user on the network is further scanned through an image recognition technology, and the information in the picture is read through an image training text.
Further, in the method for generating and dividing the network high-order structure community, the image training text is obtained by extracting characters in the image by adopting an OCR recognition technology, comparing the image with the image in the big data, finding out similar images and classifying the similar images into one class, and obtaining the content expressed by the image.
Further, in the method for generating and dividing the network high-order structure community, a corresponding user preference database is preset through information in an account;
the user preference database includes: the content browsed by the user, the common applications, the interested article content, the concerned information and the like.
Further, the method for generating and dividing the network high-order structure community comprises the steps of storing the internet browsing information of the user at different time periods and collecting the internet browsing information; the method for collecting comprises the following steps:
collecting preparation: creating a database inside a cloud server, wherein information acquisition classification software runs inside the cloud server, an information acquisition end of the information acquisition classification software adopts a plurality of web crawlers, and each web crawler corresponds to at least one content parameter;
building a link: determining the type of network information data to be acquired, selecting a website or a network address suitable for acquiring the network information data, establishing a link with the corresponding website or network address through information acquisition classification software, and respectively setting a plurality of web crawlers according to the data types, wherein each web crawler is responsible for acquiring one type or two types of data;
data acquisition: the web crawler can directly enter a target list page and a paging page of a website or a network address, can capture longitudinal and transverse bidirectional data and information of network information, and then transmits corresponding information data back to the database;
and (4) classified storage: the inside of the database is divided into various classified catalogues in advance according to the classification requirements, the information data transmitted back by each web crawler is directly stored in the catalogues of the corresponding classification, and a user can select proper classification software to classify, display and output the data in the database again according to the requirements.
Further, according to the method for generating and dividing the network high-order structure community, in the data acquisition process, repeated information data are filtered and removed through special software, and similar information is combined.
Further, the method for generating and dividing the network high-order structure community comprises the steps of training collected data in a preset training model and adding the trained data into the user preference database;
the training model is used for splitting and classifying the keywords of the acquired data, a user contains a large number of words on the title or the content when browsing information, the keywords on the title or the content are trained, the meaning of the keywords expressed in the title or the content is deeply known, and the whole title and the content are analyzed in detail and put into a correct classification according to the expressed meaning.
Further, the method for generating and dividing the network high-order structure community comprises the steps of classifying the user preference databases according to time, further generating a temporal personal database and updating the user preference databases;
the time is the time when the user always uses the Ethernet regularly, and a temporal personal database is generated in the time, and the collected information is input into the user preference database to be updated and output.
Further, the method for generating and dividing the network high-order structure community comprises the step of pushing corresponding contents within a fixed using time according to a personal database;
and pushing the corresponding content into the classification content of the updated user preference database.
The invention has the beneficial effects that:
(1) during the use period of connecting the Ethernet through a network port, a user preference database is established according to the logged account information, meanwhile, during the use period of the user, information browsed by the user is collected, and the collected information is input into the user preference database again through training to further improve the user data, so that the current preference of the user can be mastered in real time, and the use experience of the user on the network can be enhanced;
(2) in the process of collecting data, a web crawler is adopted to collect and store the related data on the whole Ethernet, the content of the data is classified and stored in the collecting process, and meanwhile, the content irrelevant to the collected information is removed, so that the comprehensiveness of the collected information is ensured, the preference of a user can be further pushed and displayed, the collected coverage is wide, the preference of the user can be completely corresponded, and the experience of the user in using the network is improved;
(3) the user preference database is further classified into the personal database according to time, the fact that the user uses the network within corresponding time is guaranteed to be the same person, and the situation that pushed information does not accord with the preference of the user and further influences the experience of the user when different people in a family or a community use the same network port to connect the Ethernet to conduct network activities is prevented.
Drawings
FIG. 1 is a flow chart illustrating a method for generating and partitioning a network high-level structure community according to the present invention.
Detailed Description
In order to more clearly and completely describe the technical scheme of the invention, the invention is further described with reference to the accompanying drawings.
Referring to fig. 1, the present invention provides a method for generating and dividing a network high-order structure community;
in this embodiment, the present invention provides a method for generating and dividing a network high-order structure community, including the following steps:
connecting an Ethernet through a network interface, and logging in account information of the Ethernet;
presetting a corresponding user preference database through information in the account;
storing the browsing information of the user on the internet at different time periods and collecting the browsing information;
training the acquired data in a preset training model and adding the data into the user preference database;
classifying the user preference database according to time, further generating a temporal personal database and updating the user preference database;
and pushing corresponding content according to the personal database within a fixed using time.
In specific implementation, the Ethernet is connected through a network interface, and account information of the Ethernet is logged in; presetting a corresponding user preference database through information in the account; storing the internet browsing information of the user at different time periods and collecting the internet browsing information; training the collected data in a preset training model and adding the trained data into the user preference database; classifying the user preference database according to time, further generating a temporal personal database and updating the user preference database; and pushing corresponding content according to the personal database within a fixed using time. In one embodiment, a user logs in a home network port through an account password to perform network activities, the Ethernet pushes the content of the user through the content in a user preference database, if the user preference database has shooting classification, related information about a shooting method, a shooting place and a shooting appliance is pushed, when the user conducts activities such as video brushing or news reading at a certain time node, the user can collect and store the content into the user preference database again according to the content browsed by the user, renew the user preference database, push the related content after the renewal, generate different personal databases in a time node interval to reclassify the data, and finally push the classified content in the personal databases; the user preference database is established according to the logged account information during the use period when the Ethernet is connected through the network port, meanwhile, the information browsed by the user is collected during the use period of the user, and the collected information is input into the user preference database again through training to further improve the user data, so that the current preference of the user can be mastered in real time, and the use experience of the user on the network can be enhanced.
In another embodiment, three fixed Ethernet networks sharing a network port are connected, the time node of father is 10 to 11 pm, the time node of mother is 10 to 30 to 11 thirty, the time node of child is 8 to 9 pm, if someone uses Ethernet to perform network activities during 8 to 9 pm, the personal database of the child is automatically called out, the pushed content is the content of learning, sports and the like in the personal database of the child, in the using process of the child, if the father or the mother also uses the Ethernet, calling out the user preference database to push the content to the father or the mother, deducing whether the parent is interested according to the time for browsing the content, and calling a corresponding personal database of the father or the mother if the parent is interested to push the interested content for the father or the mother; the interest and hobbies of the users are distinguished under the condition that a plurality of people use the same Ethernet, and the purpose of improving the user experience is achieved.
In one embodiment, the method for generating and dividing the network high-order structure community comprises the steps of connecting an ethernet through a network interface and logging account information of the ethernet;
the login account information comprises: account password login, short message verification login and face recognition login.
In one embodiment, the method for generating and dividing the network high-order structure community comprises the steps of presetting a corresponding user preference database according to information in an account;
the Ethernet reads the information such as the age, sex, work, hobby and the like of the user, which is disclosed on the network, through the personal information in the account; and further scanning pictures disclosed by a user on the network through an image recognition technology, and reading information in the pictures through an image training text.
The image training text is to extract characters in the image by adopting an OCR recognition technology, compare the image with images in the big data, find out similar images and classify the similar images into a class, and obtain the content expressed by the image.
In specific implementation, the Ethernet preferentially reads the information which is disclosed on the network, such as the age, the sex, the work, the hobbies and the like of a user through the footprints left by the account on the network, the picture information including the pictures is scanned by adopting an image recognition technology, the information in the pictures is read through an image training text, in one embodiment, the user logs in through the account, the user is '23 years old', 'male', 'swimming, shooting, listening to songs' on the account information column, and a plurality of scenery pictures are published, the Ethernet saves the information of the user on the account information bar into the user preference database, and pushes the related contents of swimming, shooting and listening to songs, for the pictures, the pictures in the big data are preferably compared with the pictures to know the information of the places, seasons and the like, and the information is stored in the user preference database.
In an implementation example, in the step of presetting a corresponding user preference database according to information in an account, the network high-order structure community generation and division method includes the steps of generating a network high-order structure community by using a user preference database;
the user preference database includes: the content browsed by the user, the common applications, the interested article content, the concerned information and the like.
In one embodiment, the method for generating and dividing the network high-order structure community includes the steps of storing the internet browsing information of the user at different time periods and collecting the internet browsing information; the method for collecting comprises the following steps:
collecting preparation: creating a database inside a cloud server, wherein information acquisition classification software runs inside the cloud server, an information acquisition end of the information acquisition classification software adopts a plurality of web crawlers, and each web crawler corresponds to at least one content parameter;
building a link: determining the type of network information data to be acquired, selecting a website or a network address suitable for acquiring the network information data, establishing a link with the corresponding website or network address through information acquisition classification software, and respectively setting a plurality of web crawlers according to the data types, wherein each web crawler is responsible for acquiring one type or two types of data;
data acquisition: the web crawler can directly enter a target list page and a paging page of a website or a network address, can capture longitudinal and transverse bidirectional data and information of network information, and then transmits corresponding information data back to the database;
and (4) classified storage: the inside of the database is divided into various classified catalogues in advance according to the classification requirements, the information data transmitted back by each web crawler is directly stored in the catalogues of the corresponding classification, and a user can select proper classification software to classify, display and output the data in the database again according to the requirements.
In the data acquisition process, repeated information data are filtered and removed through special software, and similar information is merged.
In specific implementation, in the process of data acquisition, the acquisition preparation comprises the following steps: creating a database inside a cloud server, operating information acquisition classification software inside the cloud server, adopting a plurality of web crawlers at an information acquisition end of the information acquisition classification software, wherein each web crawler corresponds to at least one classification parameter, and determining a parameter value corresponding to each classification parameter; building a link: firstly, determining the type of network information data to be acquired, then selecting a website or a network address suitable for acquiring the network information data, establishing a link with the corresponding website or network address through information acquisition classification software, and respectively setting a plurality of web crawlers according to the data types, wherein each web crawler is responsible for acquiring one type or two types of data; data acquisition: the web crawler can directly enter a target list page and a paging page of a website or a network address, can capture longitudinal and transverse bidirectional data and information of network information, and then transmits corresponding information data back to the database; and (4) classified storage: the inside of the database is divided into various classified catalogues in advance according to the classification requirements, information data transmitted back by each web crawler is directly stored in the catalogues of the corresponding classification, and a user can select proper classification software to classify, display and output the data in the database again according to the requirements; in the data collecting process, the web crawler is adopted to collect and store relevant data on the whole Ethernet, the contents of the data are classified and stored in the collecting process, the contents irrelevant to the collected information are removed, the comprehensiveness of the collected information is guaranteed, further pushing and displaying of the user preference are facilitated, the collected coverage is wide, the user preference can be completely corresponded, and the user experience of using the network is improved.
In one embodiment, the method for generating and dividing a network high-order structure community includes the steps of training collected data in a preset training model and adding the trained data into the user preference database;
the training model is used for splitting and classifying the keywords of the acquired data, a user contains a large number of words on the title or the content when browsing information, the keywords on the title or the content are trained, the meaning of the keywords expressed in the title or the content is deeply known, and the whole title and the content are analyzed in detail and put into a correct classification according to the expressed meaning.
In specific implementation, the training model is used for further analyzing keywords on the collected information, so that the classification range of the collected information is convenient to determine, and if the collected new spring festival file is sold in advance for two hundred million: the title of the Mali is less than the title of the spring festival, the new movie, the zhang yinju, the movie and the mary is screened out by a training model, the keywords are placed in the training model for training to obtain the new movie and the movie, the famous star classification column is placed in the celebrity star classification column, the spring festival is placed in the folk custom column, after the keywords after training are classified, if the three types of columns do not exist before, the new movie classification column, the celebrity star classification column and the folk custom column are newly added in a user preference database, and related contents of the three types are pushed by Ethernet.
In one embodiment, the method for generating and dividing the network high-order structure community comprises the steps of classifying user preference databases according to time, further generating a temporal personal database and updating the user preference databases;
the time is the time when the user always uses the Ethernet regularly, and a temporal personal database is generated in the time, and the collected information is input into the user preference database to be updated and output.
In a specific implementation, within a certain time zone, the ethernet network pushes related content through the corresponding personal database, for example, between 20 o 'clock and 22 o' clock, where the content in the personal database includes photography and sports, and the user receives the relevant photography and sports content pushed by the ethernet network when performing network activities between 20 o 'clock and 22 o' clock using the ethernet network.
In one embodiment, the method for generating and dividing the network high-level structure community comprises the steps of pushing corresponding contents in a fixed using time according to a personal database;
and pushing the corresponding content into the classification content of the updated user preference database.
In particular, if the content in the initial user preference database includes: shooting and sports related contents, and adding game related contents to the updated user preference database, so that the Ethernet can timely push information and contents related to the game.
Of course, the present invention may have other embodiments, and based on the embodiments, those skilled in the art can obtain other embodiments without any creative effort, and all of them are within the protection scope of the present invention.
Claims (10)
1. A network high-order structure community generating and dividing method is characterized by comprising the following steps:
connecting an Ethernet through a network interface, and logging in account information of the Ethernet;
presetting a corresponding user preference database through information in the account;
storing the internet browsing information of the user at different time periods and collecting the internet browsing information;
training the collected data in a preset training model and adding the trained data into the user preference database;
classifying the user preference database according to time, further generating a temporal personal database and updating the user preference database;
and pushing corresponding content according to the personal database within a fixed using time.
2. The method for generating and dividing communities with network higher-order structures according to claim 1, wherein in the step of connecting the ethernet through the network interface and logging the account information thereof;
the login account information comprises: account password login, short message authentication login and face recognition login.
3. The method for generating and dividing the network high-order structure community according to claim 1, wherein before the step of presetting the corresponding user preference database through the information in the account;
the Ethernet reads the information disclosed on the network, such as the age, sex, work, hobbies and the like of the user through the personal information in the account; and the picture disclosed by the user on the network is further scanned through an image recognition technology, and the information in the picture is read through an image training text.
4. The method for generating and dividing a network high-order structure community according to claim 3, wherein the image training text is obtained by extracting characters in a picture by using an OCR (optical character recognition) technology, comparing the image with an image in big data, finding out similar images and classifying the similar images into one class, and obtaining the content expressed by the picture.
5. The method for generating and dividing the network high-order structure community according to claim 1, wherein in the step of presetting the corresponding user preference database through the information in the account number;
the user preference database includes: the content browsed by the user, the common applications, the interested article content, the concerned information and the like.
6. The method for generating and dividing the network high-order structure community according to claim 1, wherein in the step of storing the internet browsing information according to different periods of time of the user and collecting the internet browsing information; the method for collecting comprises the following steps:
collecting preparation: creating a database inside a cloud server, wherein information acquisition classification software runs inside the cloud server, an information acquisition end of the information acquisition classification software adopts a plurality of web crawlers, and each web crawler corresponds to at least one content parameter;
building a link: determining the type of network information data to be acquired, selecting a website or a network address suitable for acquiring the network information data, establishing a link with the corresponding website or network address through information acquisition classification software, and respectively setting a plurality of web crawlers according to the data types, wherein each web crawler is responsible for acquiring one type or two types of data;
data acquisition: the web crawler can directly enter a target list page and a paging page of a website or a network address, can capture longitudinal and transverse bidirectional data and information of network information, and then transmits corresponding information data back to the database;
and (4) classified storage: the inside of the database is divided into various classified catalogues in advance according to the classification requirements, the information data transmitted back by each web crawler is directly stored in the catalogues of the corresponding classification, and a user can select proper classification software to classify, display and output the data in the database again according to the requirements.
7. The method for generating and dividing the network high-order structure community according to claim 6, wherein in the data acquisition process, repeated information data are filtered and removed through special software, and similar information is combined.
8. The method for generating and dividing communities with network higher-order structures as claimed in claim 7, wherein said step of training the collected data in a preset training model and adding the trained data into the user preference database;
the training model is used for splitting and classifying the keywords of the acquired data, a user contains a large number of words on the title or the content when browsing information, the keywords on the title or the content are trained, the meaning of the keywords expressed in the title or the content is deeply known, and the whole title and the content are analyzed in detail and put into a correct classification according to the expressed meaning.
9. The method for generating and dividing web higher-order structure communities according to claim 7, wherein the step of classifying the user preference databases according to time, further generating a temporal personal database and updating the user preference database;
the time is the time when the user always uses the Ethernet regularly, and a temporal personal database is generated in the time, and the collected information is input into the user preference database to be updated and output.
10. The method for generating and dividing communities with higher network level structures as claimed in claim 1, wherein in the step of pushing the corresponding contents according to the personal database within a fixed usage time;
and pushing the corresponding content into the classification content of the updated user preference database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210354871.8A CN114945180A (en) | 2022-04-06 | 2022-04-06 | Network high-order structure community generation and division method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210354871.8A CN114945180A (en) | 2022-04-06 | 2022-04-06 | Network high-order structure community generation and division method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114945180A true CN114945180A (en) | 2022-08-26 |
Family
ID=82908089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210354871.8A Pending CN114945180A (en) | 2022-04-06 | 2022-04-06 | Network high-order structure community generation and division method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114945180A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102946590A (en) * | 2012-10-31 | 2013-02-27 | 北京众思铭信息技术有限公司 | Method and system for information issue by wifi (wireless fidelity) network |
| CN105243103A (en) * | 2015-09-19 | 2016-01-13 | 杭州电子科技大学 | Content based push time determination method |
| CN111160942A (en) * | 2018-11-08 | 2020-05-15 | 蒋伟杰 | Advertisement putting method based on target crowd |
| CN112632356A (en) * | 2020-12-25 | 2021-04-09 | 深圳市高德信通信股份有限公司 | Network information data classification collection method |
| CN114051054A (en) * | 2022-01-13 | 2022-02-15 | 深圳市赢向量科技有限公司 | Method and system for acquiring information by adopting wireless communication network |
-
2022
- 2022-04-06 CN CN202210354871.8A patent/CN114945180A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102946590A (en) * | 2012-10-31 | 2013-02-27 | 北京众思铭信息技术有限公司 | Method and system for information issue by wifi (wireless fidelity) network |
| CN105243103A (en) * | 2015-09-19 | 2016-01-13 | 杭州电子科技大学 | Content based push time determination method |
| CN111160942A (en) * | 2018-11-08 | 2020-05-15 | 蒋伟杰 | Advertisement putting method based on target crowd |
| CN112632356A (en) * | 2020-12-25 | 2021-04-09 | 深圳市高德信通信股份有限公司 | Network information data classification collection method |
| CN114051054A (en) * | 2022-01-13 | 2022-02-15 | 深圳市赢向量科技有限公司 | Method and system for acquiring information by adopting wireless communication network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111143610B (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN106528693B (en) | Educational resource recommended method and system towards individualized learning | |
| JP6487201B2 (en) | Method and apparatus for generating recommended pages | |
| CN104462573B (en) | A kind of video search result methods of exhibiting and device | |
| KR102034346B1 (en) | Method and Device for Detecting Slang Based on Learning | |
| KR20160055930A (en) | Systems and methods for actively composing content for use in continuous social communication | |
| WO2016095576A1 (en) | Method, device and system for pushing information to user on barrage carrier | |
| CN109903127A (en) | A kind of group recommending method, device, storage medium and server | |
| US20190095444A1 (en) | Voice driven analytics | |
| CN106980651B (en) | Crawling seed list updating method and device based on knowledge graph | |
| CN104462376A (en) | Information providing method and device for barrage media | |
| CN111954087B (en) | Method and device for intercepting images in video, storage medium and electronic equipment | |
| CN103605808A (en) | Search-based UGC (user generated content) recommendation method and search-based UGC recommendation system | |
| Trevisiol et al. | Image ranking based on user browsing behavior | |
| CN104615627A (en) | Event public sentiment information extracting method and system based on micro-blog platform | |
| CN111177559A (en) | Text travel service recommendation method and device, electronic equipment and storage medium | |
| Spiro et al. | Shifting stakes: Understanding the dynamic roles of individuals and organizations in social media protests | |
| Nasraoui et al. | Performance of recommendation systems in dynamic streaming environments | |
| US20190095499A1 (en) | Data reporting system and method | |
| JP2009116519A (en) | Personal history development device | |
| US20140019545A1 (en) | Social Graph Expanding Method, Program and System | |
| CN109670047B (en) | Abstract note generation method, computer device and readable storage medium | |
| WO2010131013A1 (en) | Collaborative search engine optimisation | |
| CN114945180A (en) | Network high-order structure community generation and division method | |
| CN115965439A (en) | Data recall method, data recall device, electronic 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 |