CN117114823A - Internet-based data mining method and system - Google Patents
Internet-based data mining method and system Download PDFInfo
- Publication number
- CN117114823A CN117114823A CN202311384486.9A CN202311384486A CN117114823A CN 117114823 A CN117114823 A CN 117114823A CN 202311384486 A CN202311384486 A CN 202311384486A CN 117114823 A CN117114823 A CN 117114823A
- Authority
- CN
- China
- Prior art keywords
- commodity
- consumer
- information
- search result
- page
- 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- Withdrawn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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000007418 data mining Methods 0.000 title claims abstract description 30
- 238000012512 characterization method Methods 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 10
- 230000006399 behavior Effects 0.000 description 14
- 235000013305 food Nutrition 0.000 description 5
- 235000013339 cereals Nutrition 0.000 description 3
- 239000003921 oil Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 235000015219 food category Nutrition 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 235000011888 snacks Nutrition 0.000 description 2
- 235000013311 vegetables Nutrition 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 239000008157 edible vegetable oil Substances 0.000 description 1
- 235000013312 flour Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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]
- G06Q30/0639—Item locations
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
- G06Q30/0256—User search
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the technical field of commodity data mining, in particular to a data mining method and system based on the Internet, comprising the following steps: acquiring category information of each different type of commodity on an internet shopping platform under different category levels, and acquiring browsing information and operation information of a consumer in each commodity search result, the inquiry condition of the consumer on the commodity and the reading speed of the consumer; acquiring global interest degree of a consumer on each commodity search result; obtaining local interest degree of a consumer on each commodity in each commodity search result; and obtaining the purchase intention of the consumer for each commodity according to the local interest degree of each commodity, the global interest degree of the corresponding type and the richness characterization value, and determining the commodity pushing scheme of the consumer according to the purchase intention of each commodity. The final commodity purchase recommendation scheme has a good effect.
Description
Technical Field
The application relates to the technical field of commodity data mining, in particular to a data mining method and system based on the Internet.
Background
With the continuous expansion of electronic commerce scale, the number and variety of commodities are rapidly increasing, and customers need to spend a great deal of time to find the commodities that they want to buy. Such browsing of large amounts of unrelated information and products is certainly subject to constant churn by consumers inundated with information overload problems. It can be seen that determining an adaptive commodity purchase recommendation based on consumer's willingness to purchase each commodity and the interest is important. The existing recommendation scheme only considers the interested analysis of the commodity by the consumer on the click content of the commodity, and the consideration factor is single, so that the effect of the commodity purchasing recommendation scheme is poor.
Disclosure of Invention
In order to solve the technical problem that the commodity purchasing recommendation scheme obtained by the existing method is poor in effect, the application aims to provide the data mining method based on the Internet, and the adopted technical scheme is as follows:
acquiring category information of each different type of commodity on an internet shopping platform under different category levels, and acquiring browsing information and operation information of a consumer in each commodity search result, the inquiry condition of the consumer on the commodity and the reading speed of the consumer;
obtaining the richness characterization value of each commodity according to the distribution condition of the class information of each commodity under different class grades; obtaining the global interest degree of the consumer on each commodity searching result according to the browsing information and the operation information of the consumer on the main page of each commodity searching result and the reading speed of the consumer;
obtaining the local interest degree of the consumer on each commodity in each commodity searching result according to the browsing information and the operation information of different information pages of each commodity in each commodity searching result of the consumer and the inquiry condition of the consumer on the commodity;
and obtaining the purchase intention of the consumer for each commodity according to the local interest degree of each commodity, the global interest degree of the corresponding type and the richness characterization value, and determining the commodity pushing scheme of the consumer according to the purchase intention of each commodity.
Preferably, the obtaining browsing information and operation information of each commodity search result of the consumer, the inquiry condition of the consumer on the commodity, and the reading speed of the consumer specifically includes:
acquiring the browsing time length of each main page and the browsed page length, the sliding times and the sliding amplitude of each main page in each commodity searching result of a consumer; acquiring the browsing time length of each information page of each commodity in each main page in each commodity searching result and the clicking times of each information page of a consumer; the reading speed of the consumer and the questioning times of each commodity are obtained.
Preferably, the obtaining the global interest degree of the consumer for each commodity search result according to the browsing information and the operation information of the consumer on the main page of each commodity search result and the reading speed of the consumer specifically includes:
for the searching result of any commodity, according to the sliding times and sliding amplitude of each main page and the browsed page length of the searching result of the commodity, the weight coefficient of the commodity on each main page is obtained; according to the sliding times and sliding amplitude of each main page in the commodity searching result of the consumer and the reading speed of the consumer, the interest coefficient of the commodity in each main page is obtained, and according to the browsing time length of each main page in the commodity searching result of the consumer, the weight coefficient and the interest coefficient, the global interest degree of the consumer on the commodity searching result is obtained.
Preferably, the calculation formula of the global interest degree is specifically:
；
wherein,indicating the global interest level of the consumer in the search result of item a,/for>Representing the number of main pages contained in the search result of the a-th commodity,/item>Representing the browsing time length of the ith main page in the search result of the a-th commodity by the consumer,/for the search result of the a-th commodity>Indicating the number of slides of the ith main page in the search result of the a-th commodity by the consumer,mean value representing the sliding amplitude of the ith main page in the search result of the consumer in the a-th commodity,/for>The page length of the ith main page in the search result of the a-th commodity is represented, and V represents the reading speed of a consumer; />As the weight coefficient of the light-emitting diode,is a coefficient of interest.
Preferably, the obtaining the local interest degree of the consumer on each commodity in each commodity search result according to the browsing information and the operation information of the different information pages of each commodity in each commodity search result of the consumer and the inquiry situation of the consumer on the commodity specifically includes:
for any commodity in any main page in the search result of any commodity, calculating the product of the browsing time length and the clicking times of a consumer on each information page of the commodity to obtain a first coefficient corresponding to each information page; acquiring the accumulation of browsing time lengths of all information pages of the commodity by a consumer and obtaining the global time length of the commodity; taking the sum of the first coefficients of all the information pages of the commodity and the sum of the global time length as the second coefficient of the commodity;
and determining the doubt coefficient of the commodity according to the questioning times of the consumer to the commodity, and taking the product of the doubt coefficient and the second coefficient as the local interest degree of the commodity.
Preferably, the determining the query coefficient of the commodity according to the questioning times of the consumer to the commodity specifically includes:
if the consumer does not have a questioning operation on the commodity, setting the query coefficient of the commodity as a first preset value;
if the consumer has a questioning operation on the commodity, taking the sum of the questioning times of the consumer on the commodity and the first preset value as the questioning coefficient of the commodity.
Preferably, the obtaining the richness characterization value of each commodity according to the distribution condition of the category information of each commodity under different category levels specifically includes:
and calculating the normalized value of the accumulated sum of the classification numbers of the commodity under each class level for any commodity to obtain the richness characterization value of each commodity.
Preferably, the obtaining the purchase intention of the consumer for each commodity according to the local interest degree of each commodity, the global interest degree of the corresponding category and the richness characterization value specifically includes:
for any commodity in any main page in the searching result of any commodity, obtaining the browsing richness of the consumer for the commodity according to the local interest degree corresponding to the commodity and the global interest degree of the corresponding type of commodity; the local interest degree and the global interest degree are in positive correlation with the browsing richness;
and taking the product of the browsing richness and the richness representation value corresponding to the commodity as the purchase intention of the consumer for the commodity.
Preferably, the determining a commodity pushing scheme of the consumer according to the purchase intention of each commodity specifically includes:
and arranging the commodities according to the purchasing wish from large to small to obtain a commodity pushing scheme of the consumer.
The application also provides an internet-based data mining system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, which when executed by the processor implements the steps of an internet-based data mining method.
The embodiment of the application has at least the following beneficial effects:
according to the application, the category information of each different type of commodity on the internet shopping platform under different category levels is firstly acquired, so that the behavior characteristics of the consumer on the commodity search result are analyzed based on the commodity category, and the interested condition of the consumer on different commodities is better acquired. And then analyzing the category information under the category level of each commodity to obtain the richness representation value of each commodity, reflecting the richness condition of the commodity category and representing the degree of the selectable operation of the commodity by the consumer. And further analyzing the browsing information and the operation information of the main page of each commodity search result and the reading speed of the consumer to obtain the global interest degree. The global interest level characterizes the interest level of the commodity in terms of the operational behavior information of the consumer on the main page of each commodity. Further, browsing information and operation information of different information pages of each commodity in each commodity searching result of a consumer and inquiry conditions of the consumer on the commodity are analyzed to obtain local interest degrees, the local interest degree consumers represent the interest degree of each commodity from the aspect of specific operation behavior information of each commodity in each commodity main page, and the richness representation value represents the variety richness of the commodity. The behavior characteristics and the commodity category characteristics of the two aspects are combined to obtain the buying intention of the consumer for each commodity, so that the consumer's consumption habit and buying demand can be more attached, and the finally determined commodity buying recommendation scheme has better effect.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a method flowchart of an internet-based data mining method according to an embodiment of the present application.
Detailed Description
In order to further describe the technical means and effects adopted by the present application to achieve the preset purpose, the following detailed description refers to specific implementation, structure, features and effects of an internet-based data mining method and system according to the present application with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
The following specifically describes a specific scheme of the internet-based data mining method and system provided by the application with reference to the accompanying drawings.
An embodiment of a data mining method based on the Internet:
referring to fig. 1, a method flowchart of an internet-based data mining method according to an embodiment of the present application is shown, and the method includes the following steps:
step one, category information of each different type of commodity on the internet shopping platform under different category grades is obtained, and browsing information and operation information of a consumer in each commodity searching result, the inquiry condition of the consumer on the commodity and the reading speed of the consumer are obtained.
It should be noted that, various data of all activities inside the platform or the web page are contained on the internet shopping platform, so that platform merchants and platform staff can perform data analysis and optimization processing. Such platform data includes, but is not limited to, consumer search content, click-through content, duration of stay on a page, attention content, consumption content, and the like. The data can help the merchant and platform to know the current product types and brands in real time, and timely find out problems and process the problems, such as timely communication between the replenishment, the shop customer service and the clients, so that the stability of the platform and the reliability of the merchant are ensured. The method of collecting data may use a monitoring tool for collection. While in shopping platforms various items are often categorized.
For example, the commodity types include foods, clothes, ornaments, daily necessities and the like, and category information of various category levels is also contained under each commodity, for example, foods include grain and oil categories, drink categories, vegetable categories, fresh food categories, snack categories and the like, and the categories also contain data of the subordinate commodity categories.
Based on this, firstly, category information of each different category of commodity on the internet shopping platform under different category levels needs to be acquired, specifically, in this embodiment, the commodity category is a commodity category, namely food, clothing, ornaments, daily necessities and the like. The category information of different types of commodities under different category levels is specifically that the category information of foods under a first category level comprises grain and oil categories, beverage categories, vegetable categories, fresh food categories, snack categories and the like, the category information of foods under a second category level comprises subordinate commodity category data contained in each category under each first category level, namely grain and oil categories comprise rice, flour, edible oil and the like.
According to the same method, various category information corresponding to each commodity is obtained, and it is required to be noted that the category information under the second category level of each commodity is subordinate category data of the category information under the first category level, and various category information can be directly acquired by the internet shopping platform.
Further, the internet shopping platform may collect and obtain browsing information and operation information of each commodity searching result of the consumer, the inquiry condition of the consumer on the commodity and the reading speed of the consumer, which specifically includes: acquiring the browsing time length of each main page and the browsed page length, the sliding times and the sliding amplitude of each main page in each commodity searching result of a consumer; acquiring the browsing time length of each information page of each commodity in each main page in each commodity searching result and the clicking times of each information page of a consumer; the reading speed of the consumer and the questioning times of each commodity are obtained. Wherein it is understood that the sliding amplitude is the length of each sliding operation.
Step two, obtaining the richness characterization value of each commodity according to the distribution condition of the category information of each commodity under different category grades; and obtaining the global interest degree of the consumer in each commodity searching result according to the browsing information and the operation information of the consumer on the main page of each commodity searching result and the reading speed of the consumer.
In the process of purchasing commodities, a consumer searches the commodity type to be purchased to browse until a certain behavior exists between the purchasing of the commodities and the ordering of the commodities is confirmed, and a series of operation activities, such as commodity searching, commodity screening, commodity browsing and the like, generated by the consumer on target commodities have certain signs to reflect the possible consumption behavior of the consumer. However, different browsing actions may result in different purchasing results, or may not necessarily ultimately purchase the product, e.g., the consumer browses the electronic product type product only to learn about the relevant performance of the electronic product currently being sold. Based on the method, the operation behaviors of the consumer on the search result page can be subjected to data mining, so that the consumer's willingness to purchase goods can be known.
Firstly, analyzing the distribution condition of category information of each commodity under different category levels, and obtaining the richness characterization value of each commodity. In the searching process before purchasing, consumers often directly generate consumption behaviors without selecting a large class of a certain commodity, and can conduct fine viewing under a certain class of the commodity to select the class of interest. And consumers often suffer from influence of commodity merchants, such as sales volume, related activities and the like, on a certain wanted product, such as directly searching, which is not beneficial to screening wanted commodities.
For example, the types of fashion items of women's clothing are classified into spring-autumn clothing, summer clothing and winter clothing by seasons; the age classification category of women's clothes mainly comprises children's clothes, puberty clothes, young people's clothes, middle-aged clothes and old people's clothes; the position grading type of the women's dress mainly comprises a coat, trousers, a one-piece coat and the like; the style of women's dress mainly comprises casual dress, professional dress, sportswear, national costume, and the like; the style classification of the women's dress mainly comprises a skirt, a shirt, a short sleeve, shorts and the like by taking spring and autumn dress as an example. There are a number of hierarchical categories under this main category of women's clothing.
When a certain commodity is required to be purchased, a consumer may choose to view detailed information under each category in order to search for the commodity of the heart instrument, and further the more the commodity category of the commodity is, the greater the degree of screening the commodity. Based on the above, for any commodity, calculating the normalized value of the accumulated sum of the classification numbers of the commodity under each class level to obtain the richness characterization value of each commodity. The category richness of the commodity is obtained by analyzing the category characteristics of the commodity, namely the richness representation value of the commodity reflects the category richness of the commodity and is used for analyzing the preference and purchase willingness of the consumer.
Further, the stay time and the sliding times of the consumer in the main page in the commodity search result reflect the approximate satisfaction of the consumer on the commodity in the current page. When a consumer browses a certain main page, if the consumer is not satisfied with the commodity of the search result of the current main page, the consumer can slide quickly and repeatedly. If the consumer is interested in a certain commodity or a certain commodity in the current main page, the stay time of the consumer in the current main page is longer, and the sliding times are correspondingly smaller.
Based on the above, the global interest degree of the consumer in each commodity search result is obtained by analyzing the browsing information and the operation information of the consumer on the main page of each commodity search result and the reading speed of the consumer. Specifically, for any commodity searching result, according to the sliding times and sliding amplitude of each main page and the browsed page length of the searching result of the commodity, obtaining the weight coefficient of the commodity on each main page; according to the sliding times and sliding amplitude of each main page in the commodity searching result of the consumer and the reading speed of the consumer, the interest coefficient of the commodity in each main page is obtained, and according to the browsing time length of each main page in the commodity searching result of the consumer, the weight coefficient and the interest coefficient, the global interest degree of the consumer on the commodity searching result is obtained.
In this embodiment, taking the article a as an example for explanation, the calculation formula of the global interest degree of the consumer on the article a search result may be expressed as follows:
；
wherein,indicating the global interest level of the consumer in the search result of item a,/for>Representing the number of main pages contained in the search result of the a-th commodity,/item>Representing the browsing time length of the ith main page in the search result of the a-th commodity by the consumer,/for the search result of the a-th commodity>Indicating the number of slides of the ith main page in the search result of the a-th commodity by the consumer,mean value representing the sliding amplitude of the ith main page in the search result of the consumer in the a-th commodity,/for>The page length of the ith main page in the search result of the a-th commodity is represented, and V represents the reading speed of a consumer; />As the weight coefficient of the light-emitting diode,is a coefficient of interest.
The length of the total sliding operation of the consumer on the ith main page is represented, and the weight coefficient further represents the ratio of the sliding operation length of the consumer on the ith main page, and the larger the value of the weight coefficient is, the greater the possibility that the consumer performs the sliding operation on the current page is indicated, and the smaller the commodity interest degree of the consumer on the current main page is indicated, the weight coefficient is used for weighting the interest coefficient, so that the corresponding global interest degree is smaller.
The interest coefficient represents the total duration of the sliding operation of the consumer on the ith main page, and the longer the duration is, the longer the operation time of the consumer on the current page is, and the shorter the reading time is, the smaller the corresponding interest degree is, namely the smaller the value of the global interest degree of the corresponding commodity is.
The difference value between the total browsing time of the consumer on the ith main page and the total sliding operation time of the consumer on the ith main page is represented, the stay time of the consumer on the ith main page is reflected, and the larger the value is, the more interested the consumer is in the commodities in the ith main page, and the larger the value is, the global interested degree of the corresponding commodities is. The global interest degree of each commodity reflects the interest condition of the consumer on the commodity, and can reflect the buying desire of the consumer on the commodity.
And thirdly, obtaining the local interest degree of the consumer on each commodity in each commodity searching result according to the browsing information and the operation information of the different information pages of each commodity in each commodity searching result of the consumer and the inquiry condition of the consumer on the commodity.
In the search results of each commodity, each main page contains a large number of commodities, each commodity contains a detail page, when a consumer is more interested in a certain commodity, the consumer clicks the detail page entering the commodity to conduct detailed browsing operation, and the more detailed the consumer browses the internal information of the commodity, the longer the time spent, the more satisfied the consumer has.
In the detail page of the article, the consumer may look at the main introduction of the article, for example, while browsing a skirt of a certain style of the female dress, may want to know the material of the article, the effect of the model upper body, the delivery place, evaluation detail information such as a good score, poor evaluation detail, etc. The higher the richness of the browsing, the more detailed it is, indicating that the consumer is interested in the commodity.
Based on the information, browsing information and operation information of different information pages of each commodity in each commodity searching result of the consumer and inquiry conditions of the consumer on the commodity are analyzed, and local interest degree of the consumer on each commodity in each commodity searching result is obtained.
Specifically, for any commodity in any main page in the search result of any commodity, determining a query coefficient of the commodity according to the number of times the consumer asks for the commodity, namely if the consumer does not have a query operation on the commodity, setting the query coefficient of the commodity as a first preset value; if the consumer has a questioning operation on the commodity, taking the sum of the questioning times of the consumer on the commodity and the first preset value as the questioning coefficient of the commodity.
In this embodiment, the first preset value is 1. When a consumer requests a question about a commodity, the consumer is informed about the detailed use of the commodity or about the related information, and the consumer is interested in the commodity more, so that the consumer needs to give a higher value to the query coefficient.
Calculating the product of the browsing time length and the clicking times of a consumer on each information page of the commodity to obtain a first coefficient corresponding to each information page; acquiring the accumulation of browsing time lengths of all information pages of the commodity by a consumer and obtaining the global time length of the commodity; taking the sum of the first coefficients of all the information pages of the commodity and the sum of the global time length as the second coefficient of the commodity; the product of the doubt coefficient and the second coefficient is taken as the local interest level of the commodity.
In this embodiment, taking the mth commodity of any one of the main pages in the search results of the mth commodity as an example for explanation, the calculation formula of the local interest degree of the consumer on the mth commodity of any one of the main pages in the search results of the mth commodity may be expressed as:
；
wherein,representing the local interest degree of the consumer in the mth commodity of any main page in the search result of the mth commodity,/the consumer>A question factor representing the mth article, +.>And->Respectively representing the browsing time length and the clicking times of the consumer on the nth information page of the mth commodity,/or->Showing the sum of the browsing time lengths of all information pages of the mth commodity by the consumer, namely the global time length of the mth commodity,/the user can select the user to browse the mth commodity>Indicating all information pages contained by the mth article,for the first coefficient corresponding to the nth information page,/->Is the second coefficient.
The larger the value of (c) is, the more the consumer has a question about the mth commodity, and the more interested the mth commodity is, the larger the value of the corresponding local interested degree is. The first coefficient reflects that the more the operation information of the current information page of the consumer under the mth commodity is, the longer the stay time is, which indicates that the more interested the consumer is in the commodity, the larger the purchase will is, and the larger the corresponding local interested degree value is.
The total residence time of the consumer under the information page of the mth commodity is represented, wherein the residence time comprises the reading time and the operation time of the consumer in the detail page of the mth commodity, and the larger the value is, the higher the interest degree of the consumer in the mth commodity is, the larger the purchase intention is, and the larger the corresponding local interest degree value is.
According to the same method, the local interest degree of each commodity is obtained, the interest degree of the consumer on each commodity is reflected in the aspect of behavior information of the commodity detail page, and the purchase intention of each commodity is further reflected.
And step four, obtaining the purchase intention of the consumer for each commodity according to the local interest degree of each commodity, the global interest degree of the corresponding type and the richness characterization value, and determining the commodity pushing scheme of the consumer according to the purchase intention of each commodity.
Because consumers may not only singly view a certain commodity in detail but also compare among the same type of commodity when searching for and purchasing the commodity, different commodities on different main pages may be viewed. Therefore, in analyzing the interest level of each commodity, it is necessary to consider the consumer's intention to purchase each commodity in combination with factors of various aspects.
The global interest degree characterizes the interest degree of the commodity from the aspect of the operation behavior information of the consumer on the main page of each commodity, the local interest degree consumer characterizes the interest degree of each commodity from the aspect of the operation behavior information of each commodity in the main page of each commodity, and the richness characterization value characterizes the variety richness of the commodity. And combining the behavior characteristics of the two aspects and the commodity type characteristics to obtain the purchase intention of the consumer for each commodity.
Specifically, for any commodity in any main page in the searching result of any commodity, obtaining the browsing richness of the consumer on the commodity according to the local interest degree corresponding to the commodity and the global interest degree corresponding to the commodity; the local interest degree and the global interest degree are in positive correlation with the browsing richness; and taking the product of the browsing richness and the richness representation value corresponding to the commodity as the purchase intention of the consumer for the commodity.
In this embodiment, taking the mth commodity of any one of the main pages in the search results of the mth commodity as an example for explanation, the calculation formula of the purchase intention of the consumer for the mth commodity of any one of the main pages in the search results of the mth commodity may be expressed as:
wherein,the consumer's purchase intention of the mth commodity of any one main page in the search result of the mth commodity,/for>Representing the local interest degree of the consumer in the mth commodity of any main page in the search result of the mth commodity,/the consumer>Representation of the eliminationGlobal interest level of the search result of the a-th commodity by the fee,/th>The richness indicating value of the mth commodity corresponding to the commodity category, exp () indicates an exponential function based on a natural constant e.
For the consumer to browse the m-th commodity, represent the pair +.>And carrying out normalization processing, wherein the larger the value of the interested degree of the consumer on the mth commodity is, the larger the value of the corresponding browsing richness is, and the larger the purchasing will of the consumer on the commodity is. />The larger the value of the item is, the larger the richness of the category of the item is, and further, the more the information that a consumer can search and compare is when searching and purchasing the item, so that the information is used as a weight to weight the browsing behavior information of the consumer on the mth item, and the buying intention of the final consumer on the mth item can be obtained.
And finally, determining a commodity pushing scheme of the consumer according to the purchase intention of each commodity. According to the operation behavior information of different consumers during purchase searching, the interested condition of the consumers on each commodity is analyzed, and the intensity of corresponding purchase will is further determined. Based on the method, each commodity is arranged in order from big to small according to purchase intention, and a commodity pushing scheme of a consumer is obtained.
An internet-based data mining system embodiment:
the present embodiment provides an internet-based data mining system comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, which when executed by the processor, implements the steps of an internet-based data mining method. Since an internet-based data mining method has been described in detail, it will not be described in detail.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application and are intended to be included within the scope of the application.
Claims (10)
1. An internet-based data mining method, comprising the steps of:
acquiring category information of each different type of commodity on an internet shopping platform under different category levels, and acquiring browsing information and operation information of a consumer in each commodity search result, the inquiry condition of the consumer on the commodity and the reading speed of the consumer;
obtaining the richness characterization value of each commodity according to the distribution condition of the class information of each commodity under different class grades; obtaining the global interest degree of the consumer on each commodity searching result according to the browsing information and the operation information of the consumer on the main page of each commodity searching result and the reading speed of the consumer;
obtaining the local interest degree of the consumer on each commodity in each commodity searching result according to the browsing information and the operation information of different information pages of each commodity in each commodity searching result of the consumer and the inquiry condition of the consumer on the commodity;
and obtaining the purchase intention of the consumer for each commodity according to the local interest degree of each commodity, the global interest degree of the corresponding type and the richness characterization value, and determining the commodity pushing scheme of the consumer according to the purchase intention of each commodity.
2. The internet-based data mining method according to claim 1, wherein the obtaining browsing information and operation information of each commodity search result of the consumer, the inquiry condition of the consumer on the commodity, and the reading speed of the consumer specifically includes:
acquiring the browsing time length of each main page and the browsed page length, the sliding times and the sliding amplitude of each main page in each commodity searching result of a consumer; acquiring the browsing time length of each information page of each commodity in each main page in each commodity searching result and the clicking times of each information page of a consumer; the reading speed of the consumer and the questioning times of each commodity are obtained.
3. The internet-based data mining method according to claim 2, wherein the obtaining the global interest degree of the consumer for each commodity search result according to the browsing information and the operation information of the consumer on the main page of each commodity search result and the reading speed of the consumer specifically comprises:
for the searching result of any commodity, according to the sliding times and sliding amplitude of each main page and the browsed page length of the searching result of the commodity, the weight coefficient of the commodity on each main page is obtained; according to the sliding times and sliding amplitude of each main page in the commodity searching result of the consumer and the reading speed of the consumer, the interest coefficient of the commodity in each main page is obtained, and according to the browsing time length of each main page in the commodity searching result of the consumer, the weight coefficient and the interest coefficient, the global interest degree of the consumer on the commodity searching result is obtained.
4. The internet-based data mining method according to claim 3, wherein the calculation formula of the global interest level is specifically:
；
wherein,indicating the global interest level of the consumer in the search result of item a,/for>Representing the number of main pages contained in the search result of the a-th commodity,/item>Representing the browsing time length of the ith main page in the search result of the a-th commodity by the consumer,/for the search result of the a-th commodity>Indicating the number of slides of the ith main page in the search result of the a-th commodity by the consumer,mean value representing the sliding amplitude of the ith main page in the search result of the consumer in the a-th commodity,/for>The page length of the ith main page in the search result of the a-th commodity is represented, and V represents the reading speed of a consumer; />Is a weight coefficient>Is a coefficient of interest.
5. The internet-based data mining method according to claim 2, wherein the obtaining the local interest degree of the consumer for each commodity in each commodity search result according to the browsing information and the operation information of the consumer on the different information page of each commodity in each commodity search result and the inquiry condition of the consumer for the commodity specifically comprises:
for any commodity in any main page in the search result of any commodity, calculating the product of the browsing time length and the clicking times of a consumer on each information page of the commodity to obtain a first coefficient corresponding to each information page; acquiring the accumulation of browsing time lengths of all information pages of the commodity by a consumer and obtaining the global time length of the commodity; taking the sum of the first coefficients of all the information pages of the commodity and the sum of the global time length as the second coefficient of the commodity;
and determining the doubt coefficient of the commodity according to the questioning times of the consumer to the commodity, and taking the product of the doubt coefficient and the second coefficient as the local interest degree of the commodity.
6. The internet-based data mining method according to claim 5, wherein the determining the query coefficient of the commodity according to the number of questions of the consumer about the commodity comprises:
if the consumer does not have a questioning operation on the commodity, setting the query coefficient of the commodity as a first preset value;
if the consumer has a questioning operation on the commodity, taking the sum of the questioning times of the consumer on the commodity and the first preset value as the questioning coefficient of the commodity.
7. The internet-based data mining method according to claim 1, wherein the obtaining the richness characterization value of each commodity according to the distribution condition of the category information of each commodity under different category levels specifically comprises:
and calculating the normalized value of the accumulated sum of the classification numbers of the commodity under each class level for any commodity to obtain the richness characterization value of each commodity.
8. The internet-based data mining method according to claim 1, wherein the obtaining the purchase intention of the consumer for each commodity according to the local interest degree of each commodity, the global interest degree of the corresponding type and the richness characterization value specifically comprises:
for any commodity in any main page in the searching result of any commodity, obtaining the browsing richness of the consumer for the commodity according to the local interest degree corresponding to the commodity and the global interest degree of the corresponding type of commodity; the local interest degree and the global interest degree are in positive correlation with the browsing richness;
and taking the product of the browsing richness and the richness representation value corresponding to the commodity as the purchase intention of the consumer for the commodity.
9. The internet-based data mining method according to claim 1, wherein the determining a commodity pushing scheme of the consumer according to the purchase intention of each commodity specifically comprises:
and arranging the commodities according to the purchasing wish from large to small to obtain a commodity pushing scheme of the consumer.
10. An internet-based data mining system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the computer program when executed by the processor implements the steps of an internet-based data mining method as claimed in any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311384486.9A CN117114823A (en) | 2023-10-25 | 2023-10-25 | Internet-based data mining method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311384486.9A CN117114823A (en) | 2023-10-25 | 2023-10-25 | Internet-based data mining method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117114823A true CN117114823A (en) | 2023-11-24 |
Family
ID=88795249
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311384486.9A Withdrawn CN117114823A (en) | 2023-10-25 | 2023-10-25 | Internet-based data mining method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117114823A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110895778A (en) * | 2018-09-12 | 2020-03-20 | 北京科杰信息技术有限公司 | Method for grading classification interests in electric commercial user images |
| CN113608651A (en) * | 2021-08-11 | 2021-11-05 | 北京字跳网络技术有限公司 | Data interaction method, device, equipment and storage medium |
| CN113689259A (en) * | 2021-08-09 | 2021-11-23 | 青岛海尔科技有限公司 | Commodity personalized recommendation method and system based on user behaviors |
| CN116579819A (en) * | 2023-04-10 | 2023-08-11 | 北京泉喜科技有限公司 | Machine learning-based commodity accurate and comprehensive display method and device |
-
2023
- 2023-10-25 CN CN202311384486.9A patent/CN117114823A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110895778A (en) * | 2018-09-12 | 2020-03-20 | 北京科杰信息技术有限公司 | Method for grading classification interests in electric commercial user images |
| CN113689259A (en) * | 2021-08-09 | 2021-11-23 | 青岛海尔科技有限公司 | Commodity personalized recommendation method and system based on user behaviors |
| CN113608651A (en) * | 2021-08-11 | 2021-11-05 | 北京字跳网络技术有限公司 | Data interaction method, device, equipment and storage medium |
| CN116579819A (en) * | 2023-04-10 | 2023-08-11 | 北京泉喜科技有限公司 | Machine learning-based commodity accurate and comprehensive display method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Su et al. | A method for discovering clusters of e-commerce interest patterns using click-stream data | |
| CN108335137B (en) | Sorting method and device, electronic equipment and computer readable medium | |
| US8762226B2 (en) | Item discovery tools and methods for shopping in an electronic commerce environment | |
| KR101034101B1 (en) | System and Method for providing product recommendation service | |
| CN108108380B (en) | Search sorting method, search sorting device, search method and search device | |
| US20130226743A1 (en) | Multilevel silhouettes in an online shopping environment | |
| US20090043665A1 (en) | Method and system of providing recommendations during online shopping | |
| KR20200101068A (en) | A method of providing a fashion item recommendation service using a body shape and purchase history | |
| WO2008134707A2 (en) | Product affinity engine and method | |
| JP2012529122A (en) | System and method for learning user genre and style and matching products to user preferences | |
| US20200134694A1 (en) | Automatic fashion outfit composition and recommendation system and method | |
| US20090037292A1 (en) | Intelligent shopping search system | |
| KR102309373B1 (en) | System for building the contents automatically for planning sales and method therefor | |
| Serrano-Cinca et al. | Internet positioning and performance of e-tailers: An empirical analysis | |
| KR102109338B1 (en) | Customized clothing analysis and recommendation system | |
| Hino | Antecedents of supermarket formats’ adoption and usage: A study in the context of non-western customers | |
| CN116894709A (en) | Advertisement commodity recommendation method and system | |
| CN110378770A (en) | A kind of method and device that e-commerce operation selects money to recommend | |
| KR101707660B1 (en) | An e-commerce system based on interest category using related keywords | |
| Yuan et al. | Walmart online grocery personalization: Behavioral insights and basket recommendations | |
| CN116894692A (en) | Method and system for analyzing and monitoring potential demands of online network sales users | |
| Verhallen et al. | Retail attribute sensitivity and shopping patronage | |
| CN117114823A (en) | Internet-based data mining method and system | |
| Łapczyński et al. | Discovering patterns of users' behaviour in an e-shop-comparison of consumer buying behaviours in poland and other european countries | |
| Gupta et al. | Research Article Private Brands Waiting to Be Purchased-the Store Image Story |
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: 20231124 |