CN117688243A - Keyword screening recommendation method and system based on big data - Google Patents
Keyword screening recommendation method and system based on big data Download PDFInfo
- Publication number
- CN117688243A CN117688243A CN202311752161.1A CN202311752161A CN117688243A CN 117688243 A CN117688243 A CN 117688243A CN 202311752161 A CN202311752161 A CN 202311752161A CN 117688243 A CN117688243 A CN 117688243A
- Authority
- CN
- China
- Prior art keywords
- keyword
- keywords
- search
- user
- ending
- 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 42
- 238000012216 screening Methods 0.000 title claims abstract description 33
- 230000006399 behavior Effects 0.000 claims description 93
- 238000004590 computer program Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 10
- 230000000694 effects Effects 0.000 claims description 9
- 230000009471 action Effects 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 241001122767 Theaceae Species 0.000 description 10
- 230000035622 drinking Effects 0.000 description 10
- 230000011218 segmentation Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a keyword screening recommendation method based on big data, which comprises the following steps: acquiring a first search behavior and an associated search behavior of a user group through big data; classifying the first search behavior and the associated search behavior of the user group according to the age group; extracting continuous keywords and ending keywords in the first search behavior and the associated search behavior according to the classification result to form a keyword set; screening and recommending keywords based on the formed keyword set; according to the method for screening and recommending the keywords based on the big data, text prediction of the keywords can be conducted based on the search results of the big data users, so that the recommended keywords can be guaranteed to better meet the real requirements of the search users.
Description
Technical Field
The invention relates to a keyword screening recommendation method and system based on big data.
Background
Searching is an important means for users to actively obtain information in internet applications, and can help users to quickly find out required information. When a user browses articles or initiates a search, the application system can predict the search behavior of the user and provide keyword recommendation, and the recommendation can effectively shorten the search path and inspire the search requirement of the user.
However, conventional search recommended words tend to build a recommendation system from only two perspectives of relevance and click through rate. In this case, the recommendation system mainly considers the text correlation between two keywords and predicts the click rate of the user. Although the scheme can effectively shorten the search path and improve the search efficiency of the user, the recommended keywords of the scheme cannot meet the real requirements of the searching user.
This is because some low quality false keywords tend to be more attractive and can attract more user clicks. And the quality of recommendation problems generated based on the predicted click rate often lead to user dissatisfaction and frustration with the search results. Therefore, a more intelligent search recommendation system is needed, which can better meet the real demands of users and avoid the interference of low-quality false keywords.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a method and a system for screening and recommending keywords based on big data, which can be used for predicting the text of the keywords based on the search result of the big data user, so as to ensure that the recommended keywords can better meet the real requirements of the search user.
The technical scheme adopted for solving the technical problems is as follows:
a method for keyword screening recommendation based on big data, comprising:
acquiring a first search behavior and an associated search behavior of a user group through big data;
classifying the first search behavior and the associated search behavior of the user group according to the age group;
extracting continuous keywords and ending keywords in the first search behavior and the associated search behavior according to the classification result to form a keyword set;
and carrying out screening recommendation of the keywords based on the formed keyword set.
Preferably, the first search behavior includes a search keyword or a search phrase that is first input by a user when information retrieval is performed; the associated search behavior includes search keywords or search phrases that the user continues to input after the first search behavior that are associated with the first input search keywords or search phrases.
Preferably, the method for classifying the first search behavior and the associated search behavior of the user group according to the age group comprises the following steps:
classifying the users according to age groups according to user registration information, historical behavior data or other reliable data sources, including teenagers aged 12-17 years old, young 18-35 years old, middle aged 36-55 years old and aged above 55 years old;
and associating the first search behavior and the associated search behavior with the age group of the corresponding classification.
Preferably, the continuous keyword is all keywords or search phrases occurring before the last associated search action, if only the first search action exists, the continuous keyword is 0, the ending keyword is keywords or search phrases occurring when the last associated search action exists, and if only the first search action exists, the ending keyword is keywords or search phrases occurring in the first search action.
Preferably, the method for extracting the continuous keywords and the ending keywords in the first search behavior and the associated search behavior according to the classification result to form a keyword set comprises the following steps:
combining the continuous keywords of each user and keywords appearing in the ending keywords into a lower keyword set;
combining each lower keyword set of users with the same age group into a middle keyword set;
the middle keyword sets with the same ending keywords are combined into an upper keyword set.
Preferably, the method for selecting and recommending the keywords based on the formed keyword set comprises the following steps:
matching an upper keyword set of a corresponding age group according to the keyword index input by the user;
if more than one upper keyword set corresponding to the age group is matched, ranking and recommending are carried out according to the word frequency of the ending keywords;
if the upper keyword set of the corresponding age group is matched, recommending is directly performed by using the ending keywords obtained by the upper keyword set;
if the upper keyword set of the corresponding age group is not matched, the index is matched with the upper keyword sets of other adjacent age groups;
if more than one upper keyword set of other adjacent age groups is matched, ranking and recommending are carried out according to the word frequency of the ending keywords;
if the upper keyword set of other adjacent age groups is matched, recommending is directly performed by using the ending keywords obtained by the upper keyword set;
if the upper keyword sets of other adjacent age groups are not matched, indexing the upper keyword sets of the matched whole age groups;
if more than one upper keyword set of the whole age section is matched, ranking and recommending are carried out according to the word frequency of the ending keywords;
if the upper keyword set of the full-age segment is matched, recommending is directly performed by using the ending keywords obtained by the upper keyword set;
if the keyword sets of the upper layers of the whole age section are not matched, carrying out relevance analysis according to the relevance among calculated keywords, selecting the keyword set of the upper layer with the highest relevance, and carrying out sequencing recommendation according to the word frequency of the ending keywords or directly recommending the ending keywords obtained by the keyword set of the upper layer.
Preferably, the word frequency calculation method of the ending keyword is as follows: the number of middle level keyword sets/the total number of middle level keyword sets including the end keyword.
Another technical problem to be solved by the present invention is to provide a keyword screening recommendation system based on big data, comprising:
and the data acquisition and processing module is used for: the method comprises the steps of acquiring search behaviors and associated search behavior data of a user from a large data source, preprocessing and cleaning the acquired data, and extracting effective search keywords;
and a user classification module: classifying the first search behavior and the associated search behavior of the user group according to the age group;
keyword extraction module: extracting continuous keywords and ending keywords in the first search behavior and the associated search behavior of the user group according to the classification result to form a keyword set;
keyword screening recommendation module: screening and recommending keywords based on the formed keyword set;
a user interface module: and the keyword interaction module is used for interacting with the user and displaying the recommended keyword result.
Another technical problem to be solved by the present invention is to provide an electronic device, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for big data based keyword screening recommendation according to any one of the above when executing the computer program.
Another technical problem to be solved by the present invention is to provide a computer storage medium storing a computer program, which when executed by a processor, implements the steps of the method for big data based keyword screening recommendation as described in any one of the above.
The beneficial effects of the invention are as follows:
through careful classification of the user groups, interests and demands of users in different age groups can be better understood, and therefore targeted keyword recommendation is achieved. The personalized recommendation can improve user experience and increase the acceptance and satisfaction of users on recommended content; by acquiring user search behavior and extracting keyword sets through big data, keyword screening recommendation can be performed based on real data, rather than on hypothesis or sample data. Therefore, the interests and the demands of the users can be captured more accurately, and the recommended keywords are more targeted and effective.
Because the big data analysis has higher processing speed and real-time performance, the method can make adjustment in time when the search behavior of the user changes, and the timeliness and adaptability of keyword recommendation are maintained; by analyzing the search behavior of the user, the requirement and preference of the user can be better known, so that the user feels that own opinion is valued, and the trust feeling and the use willingness of the user to the recommendation system are increased; the method can be widely applied to the fields of search engines, electronic commerce platforms and the like, and provides more accurate keyword recommendation for users, so that the advertisement putting effect and the search result accuracy are improved, and the method has positive promotion effect on commercial operation.
Detailed Description
The present invention will be further described with reference to specific examples, which are not intended to be limiting, so that those skilled in the art will better understand the present invention and practice it.
Examples
A method for keyword screening recommendation based on big data, comprising:
acquiring a first search behavior and an associated search behavior of a user group through big data;
classifying the first search behavior and the associated search behavior of the user group according to the age group;
extracting continuous keywords and ending keywords in the first search behavior and the associated search behavior according to the classification result to form a keyword set;
and carrying out screening recommendation of the keywords based on the formed keyword set.
Data acquisition and processing: search behavior data of the user is collected, including a first search behavior of the user and associated search behaviors, and the data is integrated and cleaned.
User group classification: the search behavior data is classified according to the age groups of the users, and the age groups of the users are classified by using a statistical analysis method.
Extracting a keyword set: and extracting continuous keywords and ending keywords in the first search behavior and the associated search behavior of the user group of each age group to form a corresponding keyword set.
The first search behavior comprises search keywords or search phrases which are input by a user for the first time when information retrieval is carried out; the associated search behavior includes search keywords or search phrases that the user continues to input after the first search behavior that are associated with the first input search keywords or search phrases.
Based on word segmentation technology, the search phrase is extracted as a search keyword, for Chinese search phrase, the Chinese word segmentation technology can be used for decomposing the search phrase into single words, and for English search phrase, space or punctuation marks can be used for word segmentation, and the search keyword or the search phrase is uniformly changed into a keyword for extraction in the mode.
The method for classifying the first search behavior and the associated search behavior of the user group according to the age group comprises the following steps:
classifying the users according to age groups according to user registration information, historical behavior data or other reliable data sources, including teenagers aged 12-17 years old, young 18-35 years old, middle aged 36-55 years old and aged above 55 years old;
and associating the first search behavior and the associated search behavior with the age group of the corresponding classification.
Users of different age groups have different interests and demands, the preference and the interests of the users can be known more accurately through age group classification of the users, personalized keyword recommendation service is provided for the users, and keywords suitable for the users of different age groups can be recommended pertinently according to the characteristics of the users of different age groups through age group classification of the users. The method can improve the searching efficiency of the user, reduce the interference of irrelevant or uninteresting searching results and improve the searching experience of the user.
The continuous keywords are all keywords or search phrases which appear before the last associated search behavior, if only the first search behavior exists, the continuous keywords are 0, the ending keywords are keywords or search phrases which appear when the last associated search behavior exists, and if only the first search behavior exists, the ending keywords are keywords or search phrases which appear in the first search behavior.
In this scenario, the end keywords mentioned are keywords or search phrases that occur when the search activity is last associated, i.e., when the user terminates the search activity, which include keywords or search phrases that the user entered in the search bar, and keywords or search phrases that occur when the user clicks into the search page, such end keywords generally representing that the user has determined the search result through the search activity.
And the continuous keywords and the ending keywords are closely related with the search behavior of the user, so that the search behavior of the user can be more accurately described, and the user requirements and preferences are mastered. This helps to improve the recommendation of the search engine and the accuracy of the search results.
The method for extracting continuous keywords and ending keywords in the first search behavior and the related search behavior according to the classification result to form a keyword set comprises the following steps:
combining the continuous keywords of each user and keywords appearing in the ending keywords into a lower keyword set;
combining each lower keyword set of users with the same age group into a middle keyword set;
the middle keyword sets with the same ending keywords are combined into an upper keyword set.
By combining the keywords appearing in each user's continuous keywords and ending keywords into a lower set of keywords, data integration and generalization of the user's search behavior can be performed. This helps to clearly understand the user's search preferences and needs and to better provide personalized search results and recommendation services to the user.
And combining the lower keyword sets of users with the same age group into a middle keyword set, so that user group analysis can be performed. By analyzing the search behavior of different user groups, common interests, demands and preferences of the user groups can be found, and customized search services and recommended contents can be provided for the different user groups.
Whenever a middle-level keyword set of consistent end keywords is merged into an upper-level keyword set, the user's intent and needs can be better understood. This helps to optimize the search algorithm, improving the relevance and accuracy of the search results, and enabling the user to more quickly find information that meets his needs.
This hierarchical classification method has good scalability and applicability. New tiers can be added as needed, taking into account more search behavior features. Meanwhile, the classification method can be applied to data analysis and mining in other fields, and deeper insight and decision support are provided.
The method for screening and recommending the keywords based on the formed keyword set comprises the following steps:
matching an upper keyword set of a corresponding age group according to the keyword index input by the user;
if more than one upper keyword set corresponding to the age group is matched, ranking and recommending are carried out according to the word frequency of the ending keywords;
if the upper keyword set of the corresponding age group is matched, recommending is directly performed by using the ending keywords obtained by the upper keyword set;
if the upper keyword set of the corresponding age group is not matched, the index is matched with the upper keyword sets of other adjacent age groups;
if more than one upper keyword set of other adjacent age groups is matched, ranking and recommending are carried out according to the word frequency of the ending keywords;
if the upper keyword set of other adjacent age groups is matched, recommending is directly performed by using the ending keywords obtained by the upper keyword set;
if the upper keyword sets of other adjacent age groups are not matched, indexing the upper keyword sets of the matched whole age groups;
if more than one upper keyword set of the whole age section is matched, ranking and recommending are carried out according to the word frequency of the ending keywords;
if the upper keyword set of the full-age segment is matched, recommending is directly performed by using the ending keywords obtained by the upper keyword set;
if the keyword sets of the upper layers of the whole age section are not matched, carrying out relevance analysis according to the relevance among calculated keywords, selecting the keyword set of the upper layer with the highest relevance, and carrying out sequencing recommendation according to the word frequency of the ending keywords or directly recommending the ending keywords obtained by the keyword set of the upper layer.
The word frequency calculation method of the ending keywords comprises the following steps: the number of middle level keyword sets/the total number of middle level keyword sets including the end keyword.
By matching the keyword index input by the user with the upper keyword set of the corresponding age group, personalized recommendation can be performed according to the requirements of users of different age groups. Meanwhile, the ranking recommendation is carried out according to the word frequency of the ending keywords, so that the search preference and the requirement of the user can be reflected better.
When the upper keyword set of the corresponding age group is not matched, the upper keyword set of other adjacent age groups or full age groups can be indexed. Such cross-age-group recommendations can provide more options and possibilities for the user to better meet the user's needs.
Relevance analysis is performed by calculating the relevance among the keywords, and an upper keyword set with the highest relevance is selected for recommendation, so that more accurate search results and recommended contents can be provided, and a user can be helped to find required information more quickly.
By matching the upper keyword sets of the corresponding age groups according to the keyword indexes input by the user and performing sequencing recommendation according to the word frequency of the end keywords or directly recommending the end keywords obtained by the upper keyword sets, the efficiency and the accuracy of the user search can be improved, and the use experience of the user is improved.
For example, from the recorded data, a total of 5 users performed a search action, leaving the following record.
26 years old { cup, teacup, drinking cup, coffee cup }, 23 years old { cup, teacup, drinking cup, mug }, 24 years old { brew coffee, cup, coffee cup }, 46 years old { cup, thermos cup, teacup filter magnetic force, magneto-elastic tea cup }, 47 years old { cup, teacup filter }.
The lower keyword set is [ { cup, teacup, drinking cup, coffee cup } { cup, drinking cup } { mug coffee, cup, coffee cup } { cup, thermos cup, magnetic force of teacup filtration } { cup, teacup filtration, teacup filter } ];
the middle keyword sets are [ { cup, teacup, drinking cup, coffee cup } { cup, teacup, drinking cup, mug } { coffee, cup, coffee cup } ], and [ { cup, thermos cup, teacup filtration magnetic force, magnetic spring tea cup } { cup, teacup filtration, magnetic spring tea cup } ];
the upper keyword sets are [ { cup, teacup, drinking cup, coffee cup } { make coffee, cup, coffee cup } ], [ { cup, teacup, drinking cup, mug } ], and [ { cup, thermos cup, teacup filtration magnetic force, magnetic spring tea cup } { cup, teacup filtration, magnetic spring tea cup } ].
When the user marked as young searches for the "teacup", the set of upper keywords according to the matching is [ { cup, teacup, drinking cup, coffee cup } { brew coffee, cup, coffee cup } ] and [ { cup, teacup, drinking cup, mug } ], wherein the word frequency of the coffee cup is high Yu Make cup, so the keyword recommendation sequence is "coffee cup, mug } ], while when the user marked as young searches for the" teacup filter ", the set of upper keywords according to the matching is [ { cup, thermos cup, filtering magnetic force, magnetic spring tea cup } ], cup { cup, teacup filter, magnetic spring tea cup } ], and when the user marked as middle-aged searches for the" cup ", the set of upper keywords according to the matching is [ { cup, filtering magnetic spring tea cup }, the set of upper keywords according to the matching is }, the set of upper keywords of [ { cup, filtering magnetic spring tea cup }, magnetic spring cup }, and cup }, so the set of tea cup }.
A keyword screening recommendation system based on big data comprises:
and the data acquisition and processing module is used for: the method comprises the steps of acquiring search behaviors and associated search behavior data of a user from a large data source, preprocessing and cleaning the acquired data, and extracting effective search keywords;
and a user classification module: classifying the first search behavior and the associated search behavior of the user group according to the age group;
keyword extraction module: extracting continuous keywords and ending keywords in the first search behavior and the associated search behavior of the user group according to the classification result to form a keyword set;
keyword screening recommendation module: screening and recommending keywords based on the formed keyword set;
a user interface module: and the keyword interaction module is used for interacting with the user and displaying the recommended keyword result.
The user group is classified by the user classification module, and personalized keyword recommendation can be performed according to user search behaviors and associated search behaviors of different age groups. Thus, the requirements of different user groups can be better met, and the user experience is improved; through the data acquisition and processing module, the system can acquire search behaviors and associated search behavior data of the user from a large data source, and preprocess and clean the data. Therefore, the system can make decisions and recommends based on the real user behavior data, and the accuracy and effectiveness of the decisions are improved.
The keyword extraction module can effectively extract continuous keywords and ending keywords in the first search behavior and the associated search behavior of the user group to form a keyword set. The system is favorable for realizing accurate keyword recommendation, and the relevance and accuracy of search results are improved; the user interface module can interact with a user to display recommended keyword results. Through a friendly user interface, a user can intuitively know recommended keywords, so that the user can find the required information more quickly; : because the system is based on a big data source, the latest user search behavior data can be acquired in real time, and keywords are screened and recommended according to the latest data. Therefore, timeliness and latest keyword recommended by the system can be guaranteed.
The embodiment also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the big data based keyword screening recommendation method as described in any one of the above when executing the computer program.
The present embodiment also provides a computer storage medium storing a computer program which, when executed by a processor, implements the steps of the big data based keyword screening recommendation method as described in any of the above.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program, which may be stored on a non-transitory computer readable storage medium and which, when executed, may comprise the steps of the above-described embodiments of the methods. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the system is divided into different functional units or modules to perform all or part of the above-described functions.
The above-mentioned embodiments of the present invention are not intended to limit the scope of the present invention, and the embodiments of the present invention are not limited thereto, and all kinds of modifications, substitutions or alterations made to the above-mentioned structures of the present invention according to the above-mentioned general knowledge and conventional means of the art without departing from the basic technical ideas of the present invention shall fall within the scope of the present invention.
Claims (10)
1. A method for keyword screening recommendation based on big data, comprising:
acquiring a first search behavior and an associated search behavior of a user group through big data;
classifying the first search behavior and the associated search behavior of the user group according to the age group;
extracting continuous keywords and ending keywords in the first search behavior and the associated search behavior according to the classification result to form a keyword set;
and carrying out screening recommendation of the keywords based on the formed keyword set.
2. The method of claim 1, wherein the first search action comprises a search keyword or search phrase first entered by a user when information retrieval is performed; the associated search behavior includes search keywords or search phrases that the user continues to input after the first search behavior that are associated with the first input search keywords or search phrases.
3. The method for filtering recommendations based on keywords of big data according to claim 1 or 2, wherein the method for classifying the first search behavior and the associated search behavior of the user population by age group is as follows:
classifying the users according to age groups according to user registration information, historical behavior data or other reliable data sources, including teenagers aged 12-17 years old, young 18-35 years old, middle aged 36-55 years old and aged above 55 years old;
and associating the first search behavior and the associated search behavior with the age group of the corresponding classification.
4. The method of claim 3, wherein the continuous keyword is all keywords or search phrases occurring before the last associated search activity, the continuous keyword is 0 if only the first search activity exists, the end keyword is the keyword or search phrase occurring when the last associated search activity exists, and the end keyword is the keyword or search phrase occurring when the first search activity exists only.
5. The method for big data based keyword screening recommendation of claim 4, wherein the method for extracting consecutive keywords and ending keywords in the first search behavior and the associated search behavior according to the classification result to form a keyword set comprises:
combining the continuous keywords of each user and keywords appearing in the ending keywords into a lower keyword set;
combining each lower keyword set of users with the same age group into a middle keyword set;
the middle keyword sets with the same ending keywords are combined into an upper keyword set.
6. The method of claim 5, wherein the method of performing keyword screening recommendation based on the formed keyword set is as follows:
matching an upper keyword set of a corresponding age group according to the keyword index input by the user;
if more than one upper keyword set corresponding to the age group is matched, ranking and recommending are carried out according to the word frequency of the ending keywords;
if the upper keyword set of the corresponding age group is matched, recommending is directly performed by using the ending keywords obtained by the upper keyword set;
if the upper keyword set of the corresponding age group is not matched, the index is matched with the upper keyword sets of other adjacent age groups;
if more than one upper keyword set of other adjacent age groups is matched, ranking and recommending are carried out according to the word frequency of the ending keywords;
if the upper keyword set of other adjacent age groups is matched, recommending is directly performed by using the ending keywords obtained by the upper keyword set;
if the upper keyword sets of other adjacent age groups are not matched, indexing the upper keyword sets of the matched whole age groups;
if more than one upper keyword set of the whole age section is matched, ranking and recommending are carried out according to the word frequency of the ending keywords;
if the upper keyword set of the full-age segment is matched, recommending is directly performed by using the ending keywords obtained by the upper keyword set;
if the keyword sets of the upper layers of the whole age section are not matched, carrying out relevance analysis according to the relevance among calculated keywords, selecting the keyword set of the upper layer with the highest relevance, and carrying out sequencing recommendation according to the word frequency of the ending keywords or directly recommending the ending keywords obtained by the keyword set of the upper layer.
7. The method for keyword screening recommendation based on big data according to claim 6, wherein the word frequency calculation method for ending keywords is as follows: the number of middle level keyword sets/the total number of middle level keyword sets including the end keyword.
8. The keyword screening recommendation system based on big data is characterized by comprising the following components:
and the data acquisition and processing module is used for: the method comprises the steps of acquiring search behaviors and associated search behavior data of a user from a large data source, preprocessing and cleaning the acquired data, and extracting effective search keywords;
and a user classification module: classifying the first search behavior and the associated search behavior of the user group according to the age group;
keyword extraction module: extracting continuous keywords and ending keywords in the first search behavior and the associated search behavior of the user group according to the classification result to form a keyword set;
keyword screening recommendation module: screening and recommending keywords based on the formed keyword set;
a user interface module: and the keyword interaction module is used for interacting with the user and displaying the recommended keyword result.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the big data based keyword screening recommendation method of any of claims 1-7 when the computer program is executed.
10. A computer storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the steps of the big data based keyword screening recommendation method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311752161.1A CN117688243A (en) | 2023-12-19 | 2023-12-19 | Keyword screening recommendation method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311752161.1A CN117688243A (en) | 2023-12-19 | 2023-12-19 | Keyword screening recommendation method and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117688243A true CN117688243A (en) | 2024-03-12 |
Family
ID=90133337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311752161.1A Pending CN117688243A (en) | 2023-12-19 | 2023-12-19 | Keyword screening recommendation method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117688243A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598607A (en) * | 2015-01-29 | 2015-05-06 | 百度在线网络技术（北京）有限公司 | Method and system for recommending search phrase |
| CN104933100A (en) * | 2015-05-28 | 2015-09-23 | 北京奇艺世纪科技有限公司 | Keyword recommendation method and device |
| CN109190049A (en) * | 2018-11-02 | 2019-01-11 | 北京字节跳动网络技术有限公司 | Keyword recommendation method, system, electronic equipment and computer-readable medium |
| CN109634991A (en) * | 2018-12-12 | 2019-04-16 | 安徽讯呼信息科技有限公司 | A kind of searching method based on big data |
| CN109871483A (en) * | 2019-01-22 | 2019-06-11 | 珠海天燕科技有限公司 | A kind of determination method and device of recommendation information |
| CN111639255A (en) * | 2019-03-01 | 2020-09-08 | 北京字节跳动网络技术有限公司 | Search keyword recommendation method and device, storage medium and electronic equipment |
| CN114265981A (en) * | 2021-12-22 | 2022-04-01 | 北京字节跳动网络技术有限公司 | Recommendation word determining method, device, equipment and storage medium |
| CN114417221A (en) * | 2022-01-24 | 2022-04-29 | 周丽萍 | Big data operation system based on Internet and implementation method thereof |
| KR102552849B1 (en) * | 2022-07-27 | 2023-07-10 | (주)유밥 | Apparatus and method for recommending contents |
-
2023
- 2023-12-19 CN CN202311752161.1A patent/CN117688243A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598607A (en) * | 2015-01-29 | 2015-05-06 | 百度在线网络技术（北京）有限公司 | Method and system for recommending search phrase |
| CN104933100A (en) * | 2015-05-28 | 2015-09-23 | 北京奇艺世纪科技有限公司 | Keyword recommendation method and device |
| CN109190049A (en) * | 2018-11-02 | 2019-01-11 | 北京字节跳动网络技术有限公司 | Keyword recommendation method, system, electronic equipment and computer-readable medium |
| CN109634991A (en) * | 2018-12-12 | 2019-04-16 | 安徽讯呼信息科技有限公司 | A kind of searching method based on big data |
| CN109871483A (en) * | 2019-01-22 | 2019-06-11 | 珠海天燕科技有限公司 | A kind of determination method and device of recommendation information |
| CN111639255A (en) * | 2019-03-01 | 2020-09-08 | 北京字节跳动网络技术有限公司 | Search keyword recommendation method and device, storage medium and electronic equipment |
| CN114265981A (en) * | 2021-12-22 | 2022-04-01 | 北京字节跳动网络技术有限公司 | Recommendation word determining method, device, equipment and storage medium |
| CN114417221A (en) * | 2022-01-24 | 2022-04-29 | 周丽萍 | Big data operation system based on Internet and implementation method thereof |
| KR102552849B1 (en) * | 2022-07-27 | 2023-07-10 | (주)유밥 | Apparatus and method for recommending contents |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10366119B2 (en) | Customized content stream utilizing dwelltime-based machine learning | |
| US8868570B1 (en) | Selection and display of online content items | |
| CN110019943B (en) | Video recommendation method and device, electronic equipment and storage medium | |
| CA2940843C (en) | Method and system for targeted advertising based on topical memes | |
| US20140067535A1 (en) | Concept-level User Intent Profile Extraction and Applications | |
| KR101453382B1 (en) | Recommended search terms providing system and method for each user and computer readable medium processing the method | |
| CN102929928A (en) | Multidimensional-similarity-based personalized news recommendation method | |
| Marine-Roig | Online travel reviews: A massive paratextual analysis | |
| Bailey et al. | Mining historic query trails to label long and rare search engine queries | |
| CN104462336A (en) | Information pushing method and device | |
| CN105338408B (en) | Video recommendation method based on time factor | |
| Chiny et al. | Netflix recommendation system based on TF-IDF and cosine similarity algorithms | |
| CN109241451A (en) | A kind of content combined recommendation method, apparatus and readable storage medium storing program for executing | |
| US20160048575A1 (en) | System and method for topics extraction and filtering | |
| CN110910207A (en) | Method and system for improving commodity recommendation diversity | |
| CN112784141A (en) | Search result quality determination method and device, storage medium and computer equipment | |
| CN112989824A (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN111914079A (en) | Topic recommendation method and system based on user tags | |
| CN110598126B (en) | Cross-social network user identity recognition method based on behavior habits | |
| JP5548900B2 (en) | Web page recommendation method using multiple attributes | |
| Ashraf et al. | Personalized news recommendation based on multi-agent framework using social media preferences | |
| WO2018042179A1 (en) | Method and system for providing content | |
| CN117688243A (en) | Keyword screening recommendation method and system based on big data | |
| CN115408618B (en) | Point-of-interest recommendation method based on social relation fusion position dynamic popularity and geographic features | |
| KR100900467B1 (en) | Personal media search service system and method |
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 |