CN115221267A - Consumer portrait generation method and device - Google Patents
Consumer portrait generation method and device Download PDFInfo
- Publication number
- CN115221267A CN115221267A CN202210777151.2A CN202210777151A CN115221267A CN 115221267 A CN115221267 A CN 115221267A CN 202210777151 A CN202210777151 A CN 202210777151A CN 115221267 A CN115221267 A CN 115221267A
- Authority
- CN
- China
- Prior art keywords
- game
- consumer
- label information
- representation
- algorithm
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/316—Indexing structures
- G06F16/319—Inverted lists
-
- 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
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a consumer portrait generation method and a device, which are applied to the technical field of data processing, and the technical scheme is as follows: obtaining first label information of the game based on the label labeled to the game by the consumer and the keyword; extracting second label information of the game based on a TF-IDF (Trans-digital IDF) feature extraction technology, acquiring first label information and second label information through a big data technology, and determining a game portrait for representing the game according to the first label information and the second label information; has the technical effects that: and pushing the corresponding game to realize the personalized recommendation of the consumer, and meeting the requirement of accurate marketing of the game website to the crowd.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a consumer portrait generation method and device.
Background
The user portrait is also called a user role and is an effective tool for delineating target users and connecting user appeal and design direction, and the user portrait is widely applied to various fields. In the practical operation process, the attributes and behaviors of the user are often combined with expected data conversion by the utterances with the most shallow and close to life. As a virtual representation of an actual user, the user role formed by the user image is not constructed outside the product and the market, and the formed user role needs to be representative and can represent the main audience and the target group of the product.
Aiming at the prior art, when the existing game website recommends games for consumers, a collaborative filtering algorithm is adopted, but the collaborative filtering algorithm has the defects that the games or the attributes of the consumers are not completely utilized, the recommendations are realized only by utilizing the interactive information of the games and the consumers, and because a series of consumer characteristics and game characteristics such as age, sex, game description and game are not effectively introduced, the omission of effective information is caused, other characteristic data cannot be fully utilized, and the game recommendation information cannot be accurately pushed.
Disclosure of Invention
The invention aims to provide a consumer portrait generation method and a consumer portrait generation device, which have the advantages that: and pushing corresponding games to realize personalized recommendation to consumers and meet the requirement of accurate marketing of game websites to crowds.
The technical purpose of the invention is realized by the following technical scheme: a consumer representation generation method, comprising the steps of:
s1, obtaining first label information of a game based on labels and keywords labeled to the game by a consumer; extracting second label information of the game based on a TF-IDF (Trans-digital IDF) feature extraction technology, acquiring first label information and second label information through a big data technology, and determining a game portrait for representing the game according to the first label information and the second label information;
s2, collecting game demand information of consumers, wherein the game demand information comprises static characteristics, behavior characteristics, habit characteristics and hobby characteristics; constructing a consumer representation representing a consumer based on the game demand information;
and S3, performing traversal algorithm analysis on the portrait of the consumer to obtain a label, analyzing the keyword and the label recorded in the inverted index table through a weighting algorithm, summing the obtained game weights finally on the basis that different labels correspond to different game weights, and recommending the consumer on the basis that the final game weight corresponds to a game name.
By the technical scheme, more accurate consumer figures can be obtained, the obtained consumer data have real-time performance and high efficiency, the consumer data can be better mined, the mined consumer data are further analyzed and then compared with game information in the game database, and corresponding games are pushed to realize personalized recommendation of consumers, so that the demand of accurate marketing of game websites to crowds is met.
The invention is further configured to: the step S1 further includes:
s11: establishing a Dictionary through the first label information and the second label information, and counting the word frequency of each word through a Dictionary function;
s12: the word frequencies are arranged in descending order, the obtained front word frequency is used as a game portrait, and an inverted index table is established based on the game portrait, wherein the inverted index table corresponds tags to game names.
The invention is further configured to: static characteristics in step S2 include the age, sex and the academic calendar of the game player, the behavior characteristics include the game duration and the game time period, the habit characteristics include the game memory and the game purchase information, and the hobby characteristics include the type of the game played, the price of the game and the game comments.
The invention is further configured to: the weighting algorithm in the step S3 comprises a single-domain weighting algorithm, a multi-domain weighting algorithm and a comparison topology algorithm.
The invention is further configured to: the single domain weighting algorithm is as follows: the single domain weighting algorithm = the total number of word frequencies/the total number of entries, when the number of word frequencies of the game is larger than the single field weighting coefficient, the game is associated with the consumer portrait and stored; the multi-domain weighting algorithm is as follows: multi-field weighting algorithm = number of times/total number of fields of occurrence of the outcome associated with the consumer representation and the game, the consumer representation being associated with the game when the number of times of occurrence of the outcome associated with the consumer representation is greater than the multi-field weighting factor.
The invention is further configured to: the comparative topology algorithm performs the topology in a clustering manner by analyzing the consumer representation and the game representation in the game database, starting from the game representation, the analysis result will be a topology analysis graph comprising an N-layer structure, wherein N is greater than 3.
The invention is further configured to: and performing data modeling on the behavior characteristics and the preference characteristics, wherein the data modeling adopts frequency graph model analysis, and potential consumption data of the consumers are obtained through the frequency graph model.
The invention is further configured to: a consumer representation generation apparatus, the storage module for storing game categories, in particular, the game categories including role playing games, action games, shooting games, music games and sports games, the consumer representation including player modules for recording player types including achievement roles, exploration roles, social roles and killer roles.
The invention is further configured to: the storage module is connected with the player module through an analysis module, and the analysis module matches the game types with the player types based on a similarity algorithm.
In conclusion, the invention has the following beneficial effects: more accurate consumer figures can be obtained, the obtained consumer data have real-time performance and high efficiency, the consumer data can be better mined, the mined consumer data are further analyzed and compared with game information in a game database, corresponding games are pushed to realize personalized recommendation of consumers, and the requirement of accurate marketing of game websites to crowds is met.
Detailed Description
The present invention will be described in further detail below.
Example (b): a consumer representation generation method and apparatus, comprising the steps of:
s1, obtaining first tag information of a game based on tags and keywords labeled to the game by a consumer; extracting second label information of the game based on a TF-IDF (Trans-digital IDF) feature extraction technology, acquiring first label information and second label information through a big data technology, and determining a game portrait for representing the game according to the first label information and the second label information;
s2, collecting game demand information of the consumer, wherein the game demand information comprises static characteristics, behavior characteristics, habit characteristics and hobby characteristics; constructing a consumer representation representing a consumer based on the game demand information;
and S3, performing traversal algorithm analysis on the consumer portrait to obtain a label, analyzing the keywords and the label recorded in the inverted index table through a weighting algorithm, summing the obtained game weights on the basis that different labels correspond to different game weights, and recommending the consumer on the basis that the final game weights correspond to game names.
Specifically, more accurate consumer figures can be obtained, the obtained consumer data have real-time performance and high efficiency, the consumer data can be better mined, the mined consumer data are further analyzed, and then compared with game information in a game database, the corresponding game is pushed to realize personalized recommendation of the consumer, and the requirement of accurate marketing of a game website to crowds is met.
Further, step S1 further includes:
s11: establishing a Dictionary through the first label information and the second label information, and counting the word frequency of each word through a Dictionary function;
s12: the word frequencies are arranged in descending order, the obtained front word frequency is used as a game portrait, an inverted index table is established based on the game portrait, and the inverted index table corresponds tags to game names.
Further, in step S2, the static characteristics include the age, sex and academic calendar of the game player, the behavior characteristics include the game duration and the game time period, the habit characteristics include the game memory and the game purchase information, and the game preference characteristics include the type of the game played, the price of the game and the game comments.
The invention is further configured to: the weighting algorithm in the step S3 comprises a single-domain weighting algorithm, a multi-domain weighting algorithm and a comparison topology algorithm.
Further, the single domain weighting algorithm is: the single domain weighting algorithm = word frequency total number/total number of entries, and when the game word frequency number is larger than a single field weight coefficient, the game and the consumer portrait are associated and stored; the multi-domain weighting algorithm is as follows: multi-field weighting algorithm = number of times/total number of fields of occurrence of the outcome associated with the consumer representation and the game, the consumer representation being associated with the game when the number of times of occurrence of the outcome associated with the consumer representation is greater than the multi-field weighting factor.
Further, by comparing the topology algorithm, by analyzing the consumer representation and the game representation within the game database, starting with the game representation, the single domain weighting algorithm performs the topology in a clustering manner, the analysis result will be a topology analysis graph comprising a N-level structure, N >3.
Furthermore, data modeling is carried out on the behavior characteristics and the preference characteristics, the data modeling adopts frequency graph model analysis, and potential consumption data of the consumers are obtained through the frequency graph model.
Further, a consumer representation generating device, the storage module is used for storing game types, specifically, the game types comprise role playing games, action games, shooting games, music games and competitive games, the consumer representation comprises a player module, the player module is used for recording player types, and the player types comprise achievement roles, exploration roles, social roles and killer roles.
Further, the storage module is connected with the player module through the analysis module, and the analysis module matches the game types with the player types based on a similarity algorithm.
The present embodiment is only for explaining the present invention, and it is not limited to the present invention, and those skilled in the art can make modifications of the present embodiment without inventive contribution as needed after reading the present specification, but all of them are protected by patent law within the scope of the claims of the present invention.
Claims (9)
1. A consumer representation generation method, comprising the steps of:
s1, obtaining first label information of a game based on labels and keywords labeled to the game by a consumer; extracting second label information of the game based on a feature extraction technology of TF-IDF, acquiring first label information and second label information through a big data technology, and determining a game portrait for representing the game according to the first label information and the second label information;
s2, collecting game demand information of the consumer, wherein the game demand information comprises static characteristics, behavior characteristics, habit characteristics and hobby characteristics; constructing a consumer representation representing a consumer based on the game demand information;
and S3, performing traversal algorithm analysis on the portrait of the consumer to obtain a label, analyzing the keyword and the label recorded in the inverted index table through a weighting algorithm, summing the obtained game weights finally on the basis that different labels correspond to different game weights, and recommending the consumer on the basis that the final game weight corresponds to a game name.
2. A consumer representation generation method as claimed in claim 1, wherein said step S1 further comprises:
s11: establishing a Dictionary through the first label information and the second label information, and counting the word frequency of each word through a Dictionary function;
s12: and performing descending arrangement on the word frequency to obtain the previous word frequency as the game portrait, and establishing an inverted index table based on the game portrait, wherein the inverted index table corresponds the tags to the game names.
3. A consumer representation generation method as claimed in claim 1, wherein: static characteristics in step S2 include the age, sex and the academic calendar of the game player, the behavior characteristics include the game duration and the game time period, the habit characteristics include the game memory and the game purchase information, and the hobby characteristics include the type of the game played, the price of the game and the game comments.
4. A consumer representation generation method as claimed in claim 1, wherein: the weighting algorithm in the step S3 comprises a single-domain weighting algorithm, a multi-domain weighting algorithm and a comparison topology algorithm.
5. A consumer representation generation method as claimed in claim 4, wherein: the single domain weighting algorithm is as follows: the single domain weighting algorithm = word frequency total number/total number of entries, when the game word frequency number is larger than the single field weight coefficient, the game is associated and stored with the consumer portrait; the multi-domain weighting algorithm is as follows: multi-field weighting algorithm = number of times/total number of fields of occurrence of the outcome associated with the consumer representation and the game, the consumer representation being associated with the game when the number of times of occurrence of the outcome associated with the consumer representation is greater than the multi-field weighting factor.
6. A consumer representation generation method as claimed in claim 4, wherein: the comparative topology algorithm performs the topology in a clustering manner by analyzing the consumer representation and the game representation within the game database, starting from the game representation, the analysis result will be a topology analysis graph comprising an N-layer structure, where N >3.
7. A consumer representation generation method as claimed in claim 3, wherein: and performing data modeling on the behavior characteristics and the preference characteristics, wherein the data modeling adopts frequency graph model analysis, and potential consumption data of the consumers are obtained through the frequency graph model.
8. A consumer representation generation apparatus, comprising: the game representation comprises a storage module, the storage module is used for storing game types, specifically, the game types comprise role playing games, action games, shooting games, music games and competitive games, the consumer representation comprises a player module, the player module is used for recording player types, and the player types comprise achievement roles, exploration roles, social roles and killer roles.
9. A consumer representation generation apparatus as claimed in claim 8, wherein: the storage module is connected with the player module through an analysis module, and the analysis module matches the game types with the player types based on a similarity algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210777151.2A CN115221267A (en) | 2022-07-04 | 2022-07-04 | Consumer portrait generation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210777151.2A CN115221267A (en) | 2022-07-04 | 2022-07-04 | Consumer portrait generation method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115221267A true CN115221267A (en) | 2022-10-21 |
Family
ID=83610855
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210777151.2A Withdrawn CN115221267A (en) | 2022-07-04 | 2022-07-04 | Consumer portrait generation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115221267A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116091112A (en) * | 2022-12-29 | 2023-05-09 | 江苏玖益贰信息科技有限公司 | Consumer portrait generating device and portrait analyzing method |
-
2022
- 2022-07-04 CN CN202210777151.2A patent/CN115221267A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116091112A (en) * | 2022-12-29 | 2023-05-09 | 江苏玖益贰信息科技有限公司 | Consumer portrait generating device and portrait analyzing method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110941740B (en) | Video recommendation method and computer-readable storage medium | |
US20210271975A1 (en) | User tag generation method and apparatus, storage medium, and computer device | |
US20210056571A1 (en) | Determining of summary of user-generated content and recommendation of user-generated content | |
Cheng et al. | Personalized click prediction in sponsored search | |
CN106372249B (en) | A kind of clicking rate predictor method, device and electronic equipment | |
Dave et al. | Learning the click-through rate for rare/new ads from similar ads | |
US8346701B2 (en) | Answer ranking in community question-answering sites | |
US20170132230A1 (en) | Systems and methods for recommending temporally relevant news content using implicit feedback data | |
CN108363821A (en) | A kind of information-pushing method, device, terminal device and storage medium | |
US20090265290A1 (en) | Optimizing ranking functions using click data | |
US20120066073A1 (en) | User interest analysis systems and methods | |
WO2018040069A1 (en) | Information recommendation system and method | |
CN105095187A (en) | Search intention identification method and device | |
CN109511015B (en) | Multimedia resource recommendation method, device, storage medium and equipment | |
CN109509033A (en) | A kind of user buying behavior big data prediction technique under consumer finance scene | |
US20170199930A1 (en) | Systems Methods Devices Circuits and Associated Computer Executable Code for Taste Profiling of Internet Users | |
CN112612951B (en) | Unbiased learning sorting method for income improvement | |
CN112288471A (en) | Advertisement click rate prediction method based on user historical behavior sequence | |
US20190065611A1 (en) | Search method and apparatus | |
CN111400609A (en) | User recommendation method and device, storage medium and server | |
CN115439139A (en) | User interest analysis method based on E-commerce big data | |
CN110795613A (en) | Commodity searching method, device and system and electronic equipment | |
CN110175892B (en) | Bidirectional thermal ball recommendation method and system based on consumer behaviors | |
CN115221267A (en) | Consumer portrait generation method and device | |
CN108287902B (en) | Recommendation system method based on data non-random missing mechanism |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20221021 |