TWI629652B - Intelligent network marketing analysis and judgment method - Google Patents

Abstract

A smart network marketing analysis and judgment method includes at least the steps of: embedding a code on at least one cooperation website; collecting, by the code, information of at least one user browsed on the cooperation website, the user's data Include a message (Cookie); analyze the user's data through the word meaning judgment rule; establish a user database for the user's data analysis result; establish a total weight value compared with the user database; Deciding to sell at least one line of information based on the user database, time factor, date factor, page viewed, total weighted value, or any combination thereof; and outputting the marketing information to the user. Through the above method, this creation cross-checks and analyzes each cookie browsing record, and according to factors such as browsing date, browsing time, and website visited, can provide the marketing information that is most likely to cause interest to the user.

Description

Intelligent network marketing analysis and judgment method

This creation involves a smart network marketing analysis and judgment method, especially for each user (cookie), analyzing its browsing behavior and calculating a weight value through which to provide the marketing that is most likely to cause interest. Smart network marketing analysis and judgment methods for data.

Press, with the advent of high-speed computers and broadband networks, people are accustomed to getting information on the Internet and friends to keep in touch and share information. In addition, with the popularity of online shopping, bringing huge online shopping opportunities, many physical stores have joined the battlefield of e-commerce, making online shopping and auction platforms booming to facilitate consumers to consume through their online stores. .

In addition, in order to stimulate buying and attracting consumers, online store owners often buy sites from websites, place advertisements to attract consumers to click, and enter their online stores to shop. Since the traffic of the website directly reflects the probability of clicking on the advertisement, the portal with higher traffic is often the first choice for the advertiser to purchase the advertisement field. However, the portal site with higher traffic has a relatively high price for advertising, and long-term purchase is a very large burden for online store owners. Therefore, it is a concept of an advertising network that extends the pricing model that is priced by the number of clicks on advertisements.

In the dazzling array of advertising products and limited advertising fields, how to grasp the moment when consumers' desire for purchase surges, recommend the relevant products that are most likely to attract their attention to attract consumers to click, and have become a researcher of online advertising network manufacturers. The direction is also of great help to the increase in consumer buying. Most of the current online marketing recommendation models can be divided into three types: remarketing, interest marketing, and content marketing.

Remarketing is a record of the websites that consumers have visited, and the marketing information of the website is continuously delivered to the consumer, causing the attention of the consumer. However, since many advertisers adopt a remarketing scheme, many websites may have many advertisements of the same advertiser on the same page.

Interest marketing is aimed at the categories and characteristics of the websites that consumers have visited, and compares them with the categories of advertisements through the categories of the websites, and then delivers advertisements of this category to attract consumers' attention. However, the purpose of consumers going to the website at different time points may be different, and the types are also different, so interest marketing has the disadvantage of low precision.

Content marketing is a kind of creative that directly provides high relevance to the content of the webpage being browsed. The advantage is that it does not need to understand the consumer's interest and browsing history, and can directly deliver marketing information related to browsing the webpage to the consumer. However, due to the large amount of vocabulary of webpage content, the precision of the comparison is not high through the machine, and it is easy to judge the misleading marketing information.

Therefore, how to deliver marketing information that is easy to attract consumers' attention, and then attract consumers to click, has become the goal of related manufacturers and related R&D personnel, and it must become a topic of future trends.

The main purpose of this creation is to improve the shortcomings of the prior art in the promotion of online marketing information, the inability to accurately grasp the consumer's intentions, the low accuracy of the marketing information provided, etc., and actively proceed to develop, in order to improve the above There are disadvantages, and after continuous trial and effort, the present invention has finally been developed.

In order to achieve the above objectives, the present invention is achieved by the following technical means. The intelligent network marketing analysis and judgment method of the present invention includes at least the following steps: embedding a code on at least one cooperation website; The code collects information of at least one user browsed on the cooperation website, the user's information includes a message (cookie), the information includes the number of pages viewed, the browsing time and the content of the browsed webpage; The user's data, the word meaning judgment rule includes: word frequency analysis, word context analysis, word matrix cluster analysis, or any combination of the above; a user database is established for the user's data analysis result Establishing a total weighted value compared to the user database; determining at least one line of sales information based on the user database, time factor, date factor, page viewed, total weighted value, or Determined by any combination; and output the marketing information to the user.

By the above method, the author uses cross-matching analysis to analyze each cookie browsing record, and calculates a weighting value, and through the weighting value, provides the most interesting interest according to factors such as browsing date, browsing time, and website visited. The marketing information is given to the user, and the user is attracted to click on the marketing information.

In order to achieve the above objectives and effects, the technical means and structure adopted by the present invention are described in detail in the preferred embodiment of the present creation, and the features and functions are as follows.

Please refer to FIG. 1 and FIG. 2 at the same time, which is a flowchart and a schematic diagram of a preferred embodiment of the creative intelligent network marketing analysis and judgment method. The intelligent network marketing analysis and judgment method of this creation is applied to the information transmission of the Internet, and at least includes the following steps:

Step 110: Embed a code (11, 11a, 11b) on at least one of the cooperation websites (10, 10a, 10b). The code (11, 11a, 11b) is a computer program code. When a user 4 browses on the cooperation website, the user 4 can browse and record the browsing history of the user 4. The user 4 can be defined as one. Browsing unit (personal computer, mobile device).

Step 120: Collect, through the code (11, 11a), at least one user's data (12, 12a) browsed on the cooperation website (10, 10a), the user's data (12, 12a) contains a message (12, 12a) Cookie), this information includes the number of pages viewed, the time of browsing, and the content of the pages viewed. When a user 4 browses the website through the Internet, the code (11, 11a) can capture and collect information about the behavior of the user 4 browsing the webpage, and the user's data (12, 12a) includes a message (Cookie), the information including the number of pages viewed by the user 4 when browsing the website, the length of the browsing, the content of the browsed webpage, and the actions performed, such as inputting words for searching, etc. .

Step 130: Analyze the user's data (12, 12a) by using the word meaning judgment rule, the word meaning judgment rule includes: word frequency analysis 211, word context analysis 212, word matrix cluster analysis 213, or Any combination of the above. After the code (11, 11a) collects the user's data (12, 12a), the user's data (12, 12a) can be transmitted to a processing device 2 via the Internet. The processing device 2 The analysis unit 21, a user database 22, a database 23, and a smart delivery unit 24, the analysis unit 21 is electrically connected to the user database 22, the smart delivery unit 24 and the analysis unit 21. The user database 22 and the database 23 are electrically connected. The processing device 2 can perform integration and analysis on the data of the user 4 on different cooperation websites (10, 10a), which can be a remote server for analyzing the data of the user (12, 12a) . In this embodiment, the analyzing unit 21 first screens out meaningful words for the content of the webpage in the user's data (12, 12a), and then selects a meaningful word, wherein the analyzing unit 21 performs the screening element. Includes: content analysis, browsing behavior, and community impact, but not limited to this. The content analysis includes: content word segmentation analysis, word-of-speech comparison of word-breaking words, word-of-speech analysis of word-breaking words, and classification of the title and internal word segmentation of the browsing page. The browsing behavior includes: browsing the online (crawling) time of the webpage, browsing the number of webpages viewed, the time of browsing the webpage, browsing the current time of the webpage (including the year, day, hour, minute), browsing the webpage bounce rate, browsing the webpage staying point User interest pipe map and user view article relevance value. This community impact includes the number of shares, likes, and responses for the social networking site. Then, the analyzing unit 21 analyzes the user's data (12, 12a) by using a word-and-speech rule, and the word-study rule includes at least: a word frequency analysis 211, a word context analysis 212, and a word matrix cluster. Analysis 213, or any combination of the above.

The term frequency analysis 211 refers to the analysis and statistics according to the part-of-speech part-of-speech, the number of words and the frequency of occurrence. For example, the words are classified by nouns, verbs or artificial settings, and the frequency and frequency of occurrence are counted. Presented in the form of tables, statistical charts, etc. The word context analysis 212 refers to the calculation and analysis based on the mutual correlation between words to find the topic that is most suitable for the words. The word matrix cluster analysis 213 refers to classifying and summarizing according to the mutual relevance and category of words to distinguish different blocks. For example, the words are classified into a matrix cluster table by classifying the correlations and categories between words, and the higher the similarity, the more closely the words are arranged, and vice versa.

Step 140: Establish a user database 22 for the analysis result of the user (12, 12a). The processing device 2 creates and stores the analysis result of the user's data (12, 12a) in the user database 22, wherein the user database 22 includes: browsing date, browsing website address, IP address, browsing Classification, page title, keyword words, word vocabulary analysis results, or any combination of the above.

Step 150: Establish a total weight value compared with the user database, and determine at least one line of sales information (25, 25a), the marketing information (25, 25a) is based on the user database 22, time factor, Date factor, page viewed, or any combination of the above. After the user database 22 is created, when the user 4 enters any of the cooperation websites (10, 10a, 10b), the smart delivery unit 24 determines the marketing information most suitable for the user 4 according to the following factors ( 25, 25a): The article goes online (crawling) time, which provides instant and up-to-date content to avoid delivering the content that the user 4 has seen. The number of articles viewed, which refers to the article, the more people browse (the more views the author crawls through the code (11, 11a)), the more representative the current affairs. Article categorization, which delivers the same category of articles that users have seen, can help improve clickthrough rates. The word comparison is used to analyze the result of the word and the meaning of the rule, and the keyword of the user 4 can be clearly determined. The article stays in time, which can clearly determine the readability of the article content. The number of community recommendations, through the number of recommendations on social networking sites such as facebook, Weibo, Twitter, etc., can clearly determine the horizontal development of the article. The article bounce rate, which can clearly determine the accuracy of the content between the article and the title. The article stays at a point in time, which can clearly determine the proportion of articles that the user 4 viewed when leaving the web page. The user interest map, which can clearly understand the associations of the users before they read the articles and categories. The user can view the relevance value of the article, which can clearly understand the association between the article viewed by the user and the article viewed before and after, and the time of browsing the current time and the date of browsing. Based on the above factors, the smart delivery unit 24 can analyze the marketing information (25, 25a) that the user 4 is most likely to be interested in at the moment.

The marketing information (25, 25a) is stored in the database 23, and the database 23 can store at least one advertisement, at least one community recommendation mechanism, at least one preferential message, and at least one activity information, but is not limited thereto. The marketing information (25, 25a) may be any of the above or any combination thereof. And the database 23 is updated dynamically, automatically, scheduled or periodically, and the manager can update the database 23 dynamically, automatically, scheduled or periodically according to customer needs.

It is worth mentioning that the database 23 can classify the marketing information (25, 25a) according to different factors, and the classification considerations are as follows: product information, product browsing materials and product marketing materials. The product information includes: product price, product classification, product title, product keyword, the quantity ratio of the product in the category, and the time when the product was launched. The product browsing data includes: the average stay time of the product page (all traffic), the bounce rate after the product page is imported (all traffic), the exit rate of the product page (all traffic), the number of checkouts of the product page (all traffic) ), the product is thrown into the shopping cart but there is no proportion of checkout (all traffic), the purchase of the product, the proportion of other products purchased (all traffic), click on the product advertisement to enter the website, but buy other products proportion. The product marketing information includes: the number of past advertisement clicks of the product (the statistical flow of the creation), the past advertisement exposure of the product (the statistical flow of the creation), the past advertisement click rate of the product (the statistical flow of the creation), the product The average stay time after the previous click (the statistical flow of the creation), the bounce rate of the product after the past click (the statistical flow of the creation), the departure rate of the product after the past click (the statistical flow of the creation), and the past click of the product. The number of checkouts (the statistical traffic of this creation), the proportion of the product that was clicked in the past and dropped into the shopping cart but not settled (the statistical traffic of this creation), and the proportion of the purchase of the product after the previous click, and the purchase of other goods at the same time (this creation statistics) flow).

The database 23 calculates six weight values for all marketing information (25, 25a) for the above factors, namely: intensity traction, diffusion tension, correlation difference, classification logic, vector distribution, and sparse dispersion. degree. After substituting the mathematical formula, the total weighting value of each marketing information (25, 25a) can be obtained. After the total weighting value is integrated with the analysis result of the smart delivery unit 24, at least one line of sales information (25, 25a) with the highest fitness can be determined. Among them, the statistical methods for calculating the six weight values include: nonlinear regression, grey theory, joint analysis method, mediation variable analysis method, deterministic decision method, and generalized estimating equation (GEE) analysis, but Not limited to this.

For example, based on the analysis result, the smart delivery unit 24 determines that the user 4 is interested in the marketing information (25, 25a) of the food when browsing on the sports news website at 4:30 pm on Friday. The probability value is the highest. Further, the smart delivery unit 24 can compare the marketing information (25, 25a) in the database 23, and the comparison result indicates that the marketing information (25, 25a) with the highest total weight value of the user 4 is a bubble. Fu. Therefore, the smart delivery unit 24 decides to recommend marketing information related to the puff to the user 4.

Step 160: Output the marketing information (25, 25a) to the user 4. After the smart delivery unit 24 determines the marketing information (25, 25a) to be recommended, the marketing information (25, 25a) can be transmitted to the cooperation website 10b browsed by the user 4 via the Internet, and the The cooperation website 10b can display the marketing information (25, 25a) on the browsing screen to attract the attention and click of the consumer.

In summary, the intelligent network marketing analysis and judgment method proposed by this creation has the following advantages compared with the conventional technology: (1) The intelligent network marketing analysis and judgment method of this creation can increase the marketing information to be used by users. The number of clicks. (2) The intelligent network marketing analysis and judgment method of this creation can avoid the advertisement of the same advertiser on the same page. (3) The intelligent network marketing analysis and judgment method of this creation analyzes the user's browsing history through multiple factors, and can provide high-precision marketing information to attract consumers to click.

Therefore, it can fully demonstrate that the purpose and efficacy of this creation are both progressive in implementation, highly exploitable in the industry, and are new inventions that have never been seen before on the market, fully comply with the requirements of invention patents, and apply in accordance with the law. .

The above description is only the preferred embodiment of the present invention, and is not intended to limit the scope of the invention. All changes and modifications made in accordance with the scope of the invention shall fall within the scope covered by the patent of the invention. I would like to ask your review committee to give a clear explanation and pray for it.

10,10a,10b‧‧‧Cooperative website
11,11a,11b‧‧‧code
12,12a‧‧‧ User information
2‧‧‧Processing device
21‧‧‧Analysis unit
211‧‧‧ frequency analysis of words
212‧‧‧word analysis
213‧‧‧Word matrix cluster analysis
22‧‧‧User database
23‧‧‧Database
24‧‧‧Smart Delivery Unit
25,25a‧‧‧Marketing Information
4 ‧ ‧ User Steps 110 ‧ ‧ bury a code on at least one partner website Step 120 ‧ ‧ Collect the information of at least one user viewed on the partner website through the code Step 130‧‧‧ The term meaning analysis rule analyzes the user's data. Step 140‧‧ Establish a user database for the user's data analysis. Step 150‧‧ Establish a total weighting value compared to the user database, and Decide to sell at least one line of information. Step 160‧‧‧ Export the marketing information to the user

1 is a flow chart of a preferred embodiment of a smart network marketing analysis and determination method. FIG. 2 is a schematic diagram of a preferred embodiment of a smart network marketing analysis and determination method.

Claims (7)

A smart network marketing analysis and judgment method includes at least the steps of: embedding a code on at least one cooperation website; collecting, by the code, information of at least one user browsed on the cooperation website, the user's data Contains a message (Cookie), the information includes the number of pages viewed, the time of browsing, and the content of the webpage being browsed; the data of the user is analyzed by the word-for-study rule, and the word-meaning rule of thumb includes: word frequency analysis, Word context analysis, word matrix cluster analysis, or any combination of the above; establishing a user database for the user's data analysis result; establishing a total weight value compared with the user database, wherein the total The weighting value considerations include: intensity traction, diffusion tension, correlation difference, classification logic, vector distribution, and sparse dispersion; determining at least one line of information, the marketing information is based on the user database, time factor, date factor, browsed a web page, the total weighting value, or any combination of the above; and outputting the marketing information to the ambassador By. For example, the smart network marketing analysis and judgment method described in claim 1 wherein the user database includes: browsing date, browsing website address, IP address, browsing category, web page title, keyword word, word Words are intended to analyze the results of the analysis of the results, at least one of the above. For example, the intelligent network marketing analysis and judgment method described in claim 1 wherein the word frequency analysis is based on the part of speech, the number of words, and the frequency of occurrence after the sentence is broken. Conduct analysis and statistics. For example, the intelligent network marketing analysis and judgment method described in claim 1 wherein the word context analysis is based on the relationship between the words after the word segmentation is performed on the content of the browsed webpage. Perform calculations and analysis. For example, the intelligent network marketing analysis and judgment method described in claim 1 wherein the word matrix cluster analysis is based on the relationship between the words after the word segmentation is performed on the content of the browsed webpage. Sex and categories are classified and summarized to distinguish between different blocks. For example, the smart network marketing analysis and judgment method described in claim 1 is wherein the marketing information is an advertisement or a community recommendation mechanism. The smart network marketing analysis and judgment method described in claim 1, wherein the marketing information is stored in a database, the database storing at least one advertisement, at least one community recommendation mechanism, at least one The offer, at least one event, or any combination of the above, is updated dynamically, automatically, scheduled, or periodically.