CN116561603A - User matching method and device based on data analysis - Google Patents

User matching method and device based on data analysis Download PDF

Info

Publication number
CN116561603A
CN116561603A CN202310837078.8A CN202310837078A CN116561603A CN 116561603 A CN116561603 A CN 116561603A CN 202310837078 A CN202310837078 A CN 202310837078A CN 116561603 A CN116561603 A CN 116561603A
Authority
CN
China
Prior art keywords
user
users
product
feedback
class
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.)
Granted
Application number
CN202310837078.8A
Other languages
Chinese (zh)
Other versions
CN116561603B (en
Inventor
那木
皇甫霞
张存
钟承东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Ip Ruida Market Consulting Co ltd
Original Assignee
Shenzhen Ip Ruida Market Consulting Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Ip Ruida Market Consulting Co ltd filed Critical Shenzhen Ip Ruida Market Consulting Co ltd
Priority to CN202310837078.8A priority Critical patent/CN116561603B/en
Publication of CN116561603A publication Critical patent/CN116561603A/en
Application granted granted Critical
Publication of CN116561603B publication Critical patent/CN116561603B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Abstract

The present invention relates to the field of data collection, and in particular, to a user matching method and apparatus based on data analysis. The method comprises the following steps: setting pushing indexes and target pushing people; screening users from the database; selecting users participating in product trial as first-class users; reading feedback data of the first type of users aiming at the tried products; calculating and sequencing a priority value of an ith user in the first type of users according to feedback data of the first type of users; calculating the number H of people pushed by the first class of users 1 The method comprises the steps of carrying out a first treatment on the surface of the Calculating the number H of push people of second class users 2 The method comprises the steps of carrying out a first treatment on the surface of the From the ranking by a selected number H 1 Pushing the user of the device; randomly selecting a number H from the second class of users 2 Pushing the user of the device; wherein the second type of users are selected users except the first type of usersIs a user of (a). The invention can select proper user groups to effectively push, and provides more effective data for the marketing strategy of product trial.

Description

User matching method and device based on data analysis
Technical Field
The present invention relates to the field of data collection, and in particular, to a user matching method and apparatus based on data analysis.
Background
The product trial aims at attracting consumers to participate in trial of a certain product, so that potential customers can know and experience the product, trust and interest of the potential customers on the product are promoted, the potential customers are attracted to purchase, and finally sales are increased; the product trial is helpful for improving the awareness of the product, improving sales, collecting feedback comments and establishing a client relationship, and is a very effective marketing strategy.
The information of the product trial is to be pushed to the potential client, and social media is usually adopted, for example, the product trial pushing is carried out on a WeChat applet. At present, the product trial information is pushed in a wide and comprehensive way. If the pushing is performed for multiple times, the experience of the user who is not interested in the product is possibly reduced, the user is lost, each product is pushed by adopting the pushing method, the user who is not interested in the product can be pushed repeatedly, and bad experience is also caused for the user.
In such a way, a proper user group cannot be selected for effective pushing, so that the marketing strategy of product trial is greatly discounted.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a user matching method and apparatus based on data analysis.
The embodiment of the invention is realized in such a way that the user matching method based on data analysis comprises the following steps:
setting pushing indexes and target pushing people number S 1 ；
Screening users from a database according to the pushing index;
selecting users participating in product trial from the screened users to be marked as first-class users;
reading feedback data of the first type of users aiming at the tried products;
establishing a product classification tree diagram according to feedback data of a first user, and determining a correlation value A of a product tried by an ith user and a product to be tried according to the product classification tree diagram i ；
Respectively determining feedback time statistic values B of the ith user according to feedback data of the first user i Statistics of feedback times C i Feedback evaluation statistic D i ；
Determining feedback rate F of the jth tried product according to feedback data of the first class user j ；
According to A i 、B i 、C i D (D) i Calculating the priority value Q of the ith user in the first type of users i ；
According to Q i Sequencing the first class of users, and obtaining a feedback frequency statistical value sequence U corresponding to the users according to the sequencing result o ；
According to S 1 Presetting a first class user push proportion y and U o Calculating the number H of push people of the first class of users 1 ；
According to S 1 Y and F j Calculating the number H of push people of the second class of users 2 ；
From the ordering according to Q i The number H is selected from the order of big to small 1 Pushing the user of the device;
randomly selecting a number H from the second class of users 2 Pushing the user of the device;
the second type of users are the users except the first type of users in the screened users.
In one embodiment, the present invention provides a data analysis-based user matching apparatus, including:
the setting module is used for setting pushing indexes and target pushing people number S 1 ；
The screening module is used for screening users from the database according to the pushing index;
the selecting module is used for selecting users participating in product trial from the screened users to be marked as first-class users;
the reading module is used for reading feedback data of the first type of users aiming at the tried products;
the association value module is used for establishing a product classification tree diagram according to the feedback data of the first-class user, and determining an association value A of a product tried by the ith user and a product to be tried according to the product classification tree diagram i ；
A statistic value module for determining feedback time statistic value B of the ith user according to the feedback data of the first user i Statistics of feedback times C i Feedback evaluation statistic D i ；
A feedback rate module for determining the feedback rate F of the jth tested product according to the feedback data of the first class user j ；
A priority value module for according to A i 、B i 、C i D (D) i Calculating the priority value Q of the ith user in the first type of users i ；
A sorting module for sorting according to Q i Sequencing the first class of users, and obtaining a feedback frequency statistical value sequence U corresponding to the users according to the sequencing result o ；
A calculation module for according to S 1 Presetting a first class user push proportion y and U o Calculating the number H of push people of the first class of users 1 According to S 1 Y and F j Calculating the number H of push people of the second class of users 2 ；
A pushing module for sorting according to Q i The number H is selected from the order of big to small 1 Is pushed by users of the second class of users, and the number of users is randomly selected as H 2 Is pushed by the user of (a).
According to the user matching method based on data analysis, the priority values of the users meeting the set indexes in the database are calculated, the users are ranked from large to small according to the priority values, and then a part of users are selected from the ranking according to the calculated number of people to be pushed for product trial pushing; and selecting another part of users from the users which do not accord with the set index in the database according to the feedback data of the users which accord with the set index in the database to carry out product trial pushing.
According to the user matching method based on data analysis, the user population for product trial pushing and the number of people required for pushing are selected according to the feedback data of the user, so that proper user population can be selected for effective pushing, and more effective data is provided for marketing strategies for product trial.
Drawings
FIG. 1 is a flow diagram of a user matching method based on data analysis in one embodiment;
FIG. 2 is an exemplary diagram of a product classification tree diagram in one embodiment;
FIG. 3 is a block diagram of a user matching device based on data analysis in one embodiment;
FIG. 4 is a block diagram of the internal architecture of a computer device in one embodiment.
Description of the embodiments
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
It will be understood that the terms "first," "second," and the like, as used herein, may be used to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another element. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script, without departing from the scope of this disclosure.
As shown in fig. 1, in one embodiment, a user matching method based on data analysis is provided, which specifically includes the following steps:
setting pushing indexes and target pushing people number S 1 ；
Screening users from a database according to the pushing index;
selecting users participating in product trial from the screened users to be marked as first-class users;
reading feedback data of the first type of users aiming at the tried products;
establishing a product classification tree diagram according to feedback data of a first user, and determining a correlation value A of a product tried by an ith user and a product to be tried according to the product classification tree diagram i ；
Respectively determining feedback time statistic values B of the ith user according to feedback data of the first user i Statistics of feedback times C i Feedback evaluation statistic D i ；
Determining feedback rate F of the jth tried product according to feedback data of the first class user j ；
According to A i 、B i 、C i D (D) i Calculating the priority value Q of the ith user in the first type of users i ；
According to Q i Sequencing the first class of users, and obtaining a feedback frequency statistical value sequence U corresponding to the users according to the sequencing result o ；
According to S 1 Presetting a first class user push proportion y and U o Calculating the number H of push people of the first class of users 1 ；
According to S 1 Y and F j Calculating the number H of push people of the second class of users 2 ；
From the ordering according to Q i The number H is selected from the order of big to small 1 Pushing the user of the device;
randomly selecting a number H from the second class of users 2 Pushing the user of the device;
the second type of users are the users except the first type of users in the screened users.
In this embodiment, the pushing index is set according to the purpose of pushing, for example, the index may be region, gender, age group, and the like.
In this embodiment, the push index may be set in one layer or multiple layers, for example: beijing, beijing-Male, and Beijing-Male-20-30 years old.
In this embodiment, the target pushing number is the total number of people for which feedback information is needed in the current pushing, and the actual pushing number includes the target pushing number and the number of people without feedback information.
In this embodiment, the feedback data of the first type of users for the products tried includes the products tried by the users, the time required for the users to return to the questionnaire, the number of times the users receive feedback of the push information, the evaluation of the users, the feedback rate of the products, and the like.
In this embodiment, the product classification tree diagram may classify products according to different standards.
In this embodiment, the feedback time statistic B is calculated based on the time required for the user to return to the questionnaire i 。
In this embodiment, the feedback frequency statistic value C is calculated according to the frequency of receiving feedback of push information by the user i 。
In the present embodiment, the feedback evaluation statistic value D is calculated from the evaluation of the user i 。
In the present embodiment, F j Is the ratio of the feedback number of the j-th tested product to the push number of the j-th tested product.
In the present embodiment, according to Q i When ordering the first class of users, if Q i The values of (a) are the same and can be as in A i If A is the order of the sizes of i The values of (a) are also the same and can be determined as B i If B i The values of (C) are also the same and can be determined by C i If C i The values of (2) are also the same and can be as in D i Is a size ordering of (2).
In this embodiment, when the first user selects the push user, the push user is selected according to the order of the order, and at this time, C corresponding to the ith user i The user is not necessarily in the ith order, so that the feedback frequency statistical value sequence U corresponding to the user is needed to be obtained according to the ordering result of the first type of user o O is the sequence U o Is a sequence number of (c).
In this embodiment, the preset first-class user push proportion y is the number of people and target push of the first-class user that need feedback information in the current pushNumber of people S 1 So 1-y is the number of people needing feedback information for the second class user to push and the target push number S 1 Is a ratio of (2).
In this embodiment, the value of y ranges from 0 to 1, and the larger the value is, the better.
In this embodiment, if the number of the first type of users reaches the target pushing number, the user may not be selected from the second type of users, so that the value of y is 1.
In the present embodiment, H 1 Is the actual number of people pushed by the first class user, and comprises the number S of people needing feedback information for the first class user pushing this time 2 And the number of people for whom the first type of user does not feed back information.
In the present embodiment, H 2 Is the actual number of people pushed by the second class user, and comprises the number S of people needing feedback information for the second class user pushing this time 3 And the number of people for whom the second type of user does not feed back information.
According to the user matching method based on data analysis, the user population for product trial pushing and the number of people required for pushing are selected according to feedback data of the users, so that proper user population can be selected for effective pushing, and more effective data is provided for marketing strategies for product trial.
In one embodiment, the product classification tree diagram is built according to the feedback data of the first class user, and the association value A of the product tried by the ith user and the product to be tried is determined according to the product classification tree diagram i Comprising:
establishing product classification according to the standard classification catalogue of international trade products;
increasing and decreasing product classification according to products to be tried and products tried by a first class user to obtain a product classification tree diagram, wherein each product is positioned on the lowest node of the product classification tree diagram in the product classification tree diagram;
finding out paths from products to be tried to each product tried by a first class user, determining the number of nodes passing through each path, and marking the maximum number of nodes as P;
for the ith user, determine toThe number of nodes p traversed by the path of the trial product and the product tried by the user i ；
From the following componentsObtaining the association value A of the product tried by the ith user and the product to be tried i 。
In this embodiment, as shown in fig. 2, each box represents a node, and the node may be a product classification or a specific product.
In this embodiment, the product classification level of the product classification tree is from large to small, for example, as shown in fig. 2, the product classification level is from large to small, which is represented by daily necessities-toiletries-solid detergents-high-efficiency detergent-X detergent.
In this embodiment, the last node of each branch of the product classification tree is the lowest node, and the lowest node must have a product, for example, as shown in fig. 2, the lowest node must be a specific product.
In this embodiment, the nodes except the lowest node are all intermediate nodes, and the intermediate nodes are not a specific product, for example, as shown in fig. 2, the intermediate nodes are all product categories, and are not specific products.
In this embodiment, each product shares at least one intermediate node with another product, and at least two parallel products or one product or two nodes are arranged under each intermediate node, for example, as shown in fig. 2, the E perfume and the F perfume share one intermediate node perfume, the product X detergent and the product Y detergent are arranged under the intermediate node high-efficiency detergent, the intermediate node high-efficiency detergent and the product Z detergent are arranged under the intermediate node solid detergent, and the intermediate node solid detergent and the intermediate node liquid detergent are arranged under the intermediate node toilet article.
In this embodiment, the path from the product to be tried to each product tried by the first class user is the shortest path in the product classification tree diagram; for example, as shown in fig. 2, the path from the G lipstick to the H lipstick is the G lipstick-H lipstick, the path from the G lipstick to the C lipstick is the G lipstick-matte lipstick-C lipstick, and the path from the G lipstick to the E perfume is the G lipstick-matte lipstick-perfume-E perfume.
In this embodiment, the nodes through which the path passes do not include a start node and a stop node, i.e., the nodes through which the path passes are all intermediate nodes; for example, as shown in fig. 2, the path from the G lipstick to the H lipstick is not through the intermediate node, and the node number is 0; the intermediate node through which the path from the G lipstick to the C lipstick is used for trial is a matte lipstick, the number of nodes is 1, and the intermediate node through which the path from the G lipstick to the E perfume is used for trial is a matte lipstick, a lipstick and a perfume, and the number of nodes is 3.
In this embodiment, there are multiple paths with the maximum node number P, for example, as shown in fig. 2, the paths are G lipstick-matte lipstick-cosmetics and perfume-toiletries-solid detergent-high-efficiency detergent-X detergent/Y detergent, and the intermediate nodes of the two paths are 6,6 and the maximum node number P in fig. 2.
In this embodiment, if the product to be tried and the product tried by the ith user are located below the same node, the association value a of the product tried by the ith user and the product to be tried i 1, for example, as shown in FIG. 2, the products to be tested, G and H, are located under the intermediate node matte lipstick, at which point P i Is 0, P is 6, made ofObtainable A i 1.
In this embodiment, each user may have a plurality of products tried, and only the products tried with the least number of nodes passing through the path of the product to be tried need to be selected for calculation, for example, as shown in fig. 2, the ith user tries the H lipstick and the C lipstick, and only the H lipstick needs to be selected for calculation.
In one embodiment, feedback time statistics B for the ith user are determined based on feedback data for the first type of user i Comprising:
acquiring the ith user from receiving in the kth pushThe time period t that it takes to push information back to the questionnaire ik ；
Obtaining the maximum time length T from receiving push information to returning questionnaire for the user in the same push ik ；
From the following componentsObtaining feedback time statistic value b of kth pushing of ith user ik ；
Calculating b of each push of ith user ik Obtaining feedback time statistic value B of ith user by average value of (2) i 。
In this embodiment, when feedback is pushed only once, the value of k is 1.
In this embodiment, only one of the users need to be selected as the maximum duration for which there may be multiple users.
In one embodiment, the feedback frequency statistic value C of the ith user is determined according to the feedback data of the first user i Comprising:
obtain the total number of times N pushed to the ith user i The number of times of the user feedback n i ；
From the following componentsObtaining feedback frequency statistic value C of ith user i 。
In the present embodiment, n i The value of (2) may be 0.
In one embodiment, feedback rating statistic D of the ith user is determined based on feedback data of the first type of user i Comprising:
for the j-th trial product, acquiring the evaluation of all users, and setting W according to the occurrence frequency of words in the evaluation j A keyword;
identifying keywords appearing in feedback evaluation of ith user on jth trial product, and calculating number w of the keywords appearing ij ；
From the following componentsObtaining feedback evaluation statistical value d of jth trial product of ith user ij ；
Calculating d for each tested product for the ith user ij Obtaining feedback evaluation statistical value D of ith user by average value of (2) i 。
In this embodiment, the words selected are to represent the enthusiasm and the positivity of the user.
In this embodiment, the keywords are mainly single words, two words, three words, and the like, and are adjectives or other words having adjective properties.
In this embodiment, the value of j may be 1, indicating that the user has only tried one product.
In one embodiment, the method according to A i 、B i 、C i D (D) i Calculating the priority value Q of the ith user in the first type of users i Comprising:
for the ith user, byObtaining Q i ；
Wherein x is 1 ~x 4 For setting corresponding A i 、B i 、C i D (D) i Coefficient of x 1 、x 2 、x 3 And x 4 The addition is equal to 1.
In the present embodiment, x 1 ~x 4 Setting according to actual conditions, for example, if the relation between the product to be tested and the product tried by the user is the main, increasing x 1 If the feedback time of the user is the main value, x is increased 2 If the number of user feedback is the main value, x is increased 3 If the value of (2) is based on the enthusiasm and the degree of care of the user feedback, x is increased 4 Is a value of (2).
In one embodiment, the method according to S 1 Presetting a first class user push proportion y and U o Calculating the number H of push people of the first class of users 1 Comprising:
from the formulaSolving the number H of the pushed people of the first type of users 1 。
In the present embodiment, S 1 Multiplying y to obtain the number S of people needing feedback information for the current push of the first class user 2 。
In the present embodiment, U o The accumulated value and the number H of the push people of the first class user 1 The ratio of (2) is the feedback frequency statistic value of each push user.
In the present embodiment, S 2 Can only be an integer, so H 1 The ratio of the average feedback frequency statistics value of each push user is rounded to obtain S 2 。
In the present embodiment, the number of first class users is limited, so H can be obtained by using the exhaustion method 1 。
In one embodiment, the method according to S 1 Y and F j Calculating the number H of push people of the second class of users 2 Comprising:
from the formulaObtaining push person H of second class user 2 ；
Wherein R is the number of products tried by the first class of users.
In the present embodiment of the present invention, in the present embodiment,represent S 1 Subtracting the number S of people needing feedback information for the current push of the first class user 2 The obtained number S of people needing feedback information for the current push of the second class user 3 。
In the present embodiment, F j The ratio of the accumulated value to the number of the products tried by the first class user is the average feedback rate of each product tried.
In the present embodiment, S 3 Can only be an integer, so H 2 The ratio of the feedback rate of each tested product is averaged to obtain S 3 。
In the present embodiment, R is a definite integer in practice, so F j The number of (2) is also determined, so that H can be solved 2 。
As shown in fig. 3, in one embodiment, a user matching device based on data analysis is provided, which may specifically include:
the setting module is used for setting pushing indexes and target pushing people number S 1 ；
The screening module is used for screening users from the database according to the pushing index;
the selecting module is used for selecting users participating in product trial from the screened users to be marked as first-class users;
the reading module is used for reading feedback data of the first type of users aiming at the tried products;
the association value module is used for establishing a product classification tree diagram according to the feedback data of the first-class user, and determining an association value A of a product tried by the ith user and a product to be tried according to the product classification tree diagram i ；
A statistic value module for determining feedback time statistic value B of the ith user according to the feedback data of the first user i Statistics of feedback times C i Feedback evaluation statistic D i ；
A feedback rate module for determining the feedback rate F of the jth tested product according to the feedback data of the first class user j ；
A priority value module for according to A i 、B i 、C i D (D) i Calculating the priority value Q of the ith user in the first type of users i ；
A sorting module for sorting according to Q i Sequencing the first class of users, and obtaining a feedback frequency statistical value sequence U corresponding to the users according to the sequencing result o ；
A calculation module for according to S 1 Presetting a first class user push proportion y and U o Calculating the number H of push people of the first class of users 1 According to S 1 Y and F j Calculating the number H of push people of the second class of users 2 ；
A pushing module for sorting according to Q i The number H is selected from the order of big to small 1 Is pushed by users of the second class of users, and the number of users is randomly selected as H 2 Is pushed by the user of (a).
In this embodiment, each module of the user matching device based on data analysis is modularized in the method portion of the present invention, and for specific explanation of each module, please refer to the corresponding content in the method portion of the present invention, and the embodiments of the present invention are not described herein again.
FIG. 4 illustrates an internal block diagram of a computer device in one embodiment. As shown in fig. 4, the computer device includes a processor, a memory, a network interface, an input device, and a display screen connected by a system bus. The memory includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system, and may also store a computer program, where the computer program when executed by a processor may cause the processor to implement the user matching method based on data analysis provided by the embodiment of the present invention. The internal memory may also store a computer program, which when executed by the processor, causes the processor to execute the user matching method based on data analysis provided by the embodiment of the present invention. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by persons skilled in the art that the architecture shown in fig. 4 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, the user matching apparatus based on data analysis provided in the embodiment of the present invention may be implemented as a computer program, which may be executed on a computer device as shown in fig. 4. The memory of the computer device may store various program modules constituting the data analysis-based user matching apparatus, such as a setting module, a screening module, a selecting module, a reading module, an association value module, a statistics module, a feedback rate module, a priority value module, a sorting module, a calculating module, and a pushing module, as shown in fig. 3. The computer program of each program module causes the processor to carry out the steps in the user matching method based on data analysis of each embodiment of the present invention described in the present specification.
For example, the computer apparatus shown in fig. 4 may perform step S001 through a setting module in the user matching device based on data analysis as shown in fig. 3; the computer equipment can execute the step S002 through the screening module; the computer equipment can execute the step S003 through the selection module; the computer device may execute step S004 through the reading module; the computer device may execute step S005 through the association value module; the computer device may execute step S006 through the statistics module; the computer device may perform step S007 through the feedback rate module; the computer device may execute step S008 through the priority value module; the computer equipment can execute the step S009 through a sequencing module; the computer device may execute step S010 and step S011 through the calculation module; the computer device may perform step S012 and step S013 through the push module.
In one embodiment, a computer device is presented, the computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
setting pushing indexes and target pushing people number S 1 ；
Screening users from a database according to the pushing index;
selecting users participating in product trial from the screened users to be marked as first-class users;
reading feedback data of the first type of users aiming at the tried products;
establishing a product classification tree diagram according to feedback data of a first user, and determining a correlation value A of a product tried by an ith user and a product to be tried according to the product classification tree diagram i ；
Respectively determining feedback time statistic values B of the ith user according to feedback data of the first user i Statistics of feedback times C i Feedback evaluation statistic D i ；
Determining feedback rate F of the jth tried product according to feedback data of the first class user j ；
According to A i 、B i 、C i D (D) i Calculating the priority value Q of the ith user in the first type of users i ；
According to Q i Sequencing the first class of users, and obtaining a feedback frequency statistical value sequence U corresponding to the users according to the sequencing result o ；
According to S 1 Presetting a first class user push proportion y and U o Calculating the number H of push people of the first class of users 1 ；
According to S 1 Y and F j Calculating the number H of push people of the second class of users 2 ；
From the ordering according to Q i The number H is selected from the order of big to small 1 Pushing the user of the device;
randomly selecting a number H from the second class of users 2 Pushing the user of the device;
the second type of users are the users except the first type of users in the screened users.
In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, which when executed by a processor causes the processor to perform the steps of:
setting pushing indexes and target pushing people number S 1 ；
Screening users from a database according to the pushing index;
selecting users participating in product trial from the screened users to be marked as first-class users;
reading feedback data of the first type of users aiming at the tried products;
establishing a product classification tree diagram according to feedback data of a first user, and determining a correlation value A of a product tried by an ith user and a product to be tried according to the product classification tree diagram i ；
Respectively determining feedback time statistic values B of the ith user according to feedback data of the first user i Statistics of feedback times C i Feedback evaluation statistic D i ；
Determining feedback rate F of the jth tried product according to feedback data of the first class user j ；
According to A i 、B i 、C i D (D) i Calculating the priority value Q of the ith user in the first type of users i ；
According to Q i Sequencing the first class of users, and obtaining a feedback frequency statistical value sequence U corresponding to the users according to the sequencing result o ；
According to S 1 Presetting a first class user push proportion y and U o Calculating the number H of push people of the first class of users 1 ；
According to S 1 Y and F j Calculating the number H of push people of the second class of users 2 ；
From the ordering according to Q i The number H is selected from the order of big to small 1 Pushing the user of the device;
randomly selecting a number H from the second class of users 2 Pushing the user of the device;
the second type of users are the users except the first type of users in the screened users.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.

Claims (9)

1. The user matching method based on the data analysis is characterized by comprising the following steps of:
setting pushing indexes and target pushing people number S 1 ；
Screening users from a database according to the pushing index;
selecting users participating in product trial from the screened users to be marked as first-class users;
reading feedback data of the first type of users aiming at the tried products;
establishing a product classification tree diagram according to feedback data of a first user, and determining a correlation value A of a product tried by an ith user and a product to be tried according to the product classification tree diagram i ；
Respectively determining feedback time statistic values B of the ith user according to feedback data of the first user i Statistics of feedback times C i Feedback evaluation statistic D i ；
Determining feedback rate F of the jth tried product according to feedback data of the first class user j ；
According to A i 、B i 、C i D (D) i Calculating the priority value Q of the ith user in the first type of users i ；
According to Q i Sequencing the first class of users, and obtaining a feedback frequency statistical value sequence U corresponding to the users according to the sequencing result o ；
According to S 1 Presetting a first class user push proportion y and U o Calculating the number H of push people of the first class of users 1 ；
According to S 1 Y and F j Calculating the number H of push people of the second class of users 2 ；
From the ordering according to Q i The number H is selected from the order of big to small 1 Pushing the user of the device;
randomly selecting a number H from the second class of users 2 Pushing the user of the device;
the second type of users are the users except the first type of users in the screened users.
2. The method for matching users based on data analysis according to claim 1, wherein a product classification tree diagram is established according to the feedback data of the first type of users, and the association value A of the product tried by the ith user and the product to be tried is determined according to the product classification tree diagram i Comprising:
establishing product classification according to the standard classification catalogue of international trade products;
increasing and decreasing product classification according to products to be tried and products tried by a first class user to obtain a product classification tree diagram, wherein each product is positioned on the lowest node of the product classification tree diagram in the product classification tree diagram;
finding out paths from products to be tried to each product tried by a first class user, determining the number of nodes passing through each path, and marking the maximum number of nodes as P;
for the ith user, determining the number p of nodes passed by the paths of the product to be tried and the product tried by the user i ；
From the following componentsObtaining the association value A of the product tried by the ith user and the product to be tried i 。
3. The data analysis-based user matching method of claim 1, wherein the feedback time statistic B of the ith user is determined based on feedback data of the first type of user i Comprising:
acquiring the ith user in the kth pushThe time period t from receiving the push information to returning the questionnaire ik ；
Obtaining the maximum time length T from receiving push information to returning questionnaire for the user in the same push ik ；
From the following componentsObtaining feedback time statistic value b of kth pushing of ith user ik ；
Calculating b of each push of ith user ik Obtaining feedback time statistic value B of ith user by average value of (2) i 。
4. The data analysis-based user matching method as claimed in claim 1, wherein the feedback count value C of the ith user is determined based on the feedback data of the first type of user i Comprising:
obtain the total number of times N pushed to the ith user i The number of times of the user feedback n i ；
From the following componentsObtaining feedback frequency statistic value C of ith user i 。
5. The data analysis-based user matching method of claim 1, wherein the feedback evaluation statistic D of the ith user is determined based on feedback data of the first type of user i Comprising:
for the j-th trial product, acquiring the evaluation of all users, and setting W according to the occurrence frequency of words in the evaluation j A keyword;
identifying keywords appearing in feedback evaluation of ith user on jth trial product, and calculating number w of the keywords appearing ij ；
From the following componentsObtaining the ith user and the jth userFeedback evaluation statistic d of trial product ij ；
Calculating d for each tested product for the ith user ij Obtaining feedback evaluation statistical value D of ith user by average value of (2) i 。
6. The data analysis-based user matching method according to claim 1, wherein the data according to a i 、B i 、C i D (D) i Calculating the priority value Q of the ith user in the first type of users i Comprising:
for the ith user, byObtaining Q i ；
Wherein x is 1 ~x 4 For setting corresponding A i 、B i 、C i D (D) i Coefficient of x 1 、x 2 、x 3 And x 4 The addition is equal to 1.
7. The data analysis-based user matching method according to claim 1, wherein the step of matching is performed according to S 1 Presetting a first class user push proportion y and U o Calculating the number H of push people of the first class of users 1 Comprising:
from the formulaSolving the number H of the pushed people of the first type of users 1 。
8. The data analysis-based user matching method according to claim 1, wherein the step of matching is performed according to S 1 Y and F j Calculating the number H of push people of the second class of users 2 Comprising:
from the formulaObtaining push person H of second class user 2 ；
Wherein R is the number of products tried by the first class of users.
9. A data analysis-based user matching apparatus, comprising:
the setting module is used for setting pushing indexes and target pushing people number S 1 ；
The screening module is used for screening users from the database according to the pushing index;
the selecting module is used for selecting users participating in product trial from the screened users to be marked as first-class users;
the reading module is used for reading feedback data of the first type of users aiming at the tried products;
the association value module is used for establishing a product classification tree diagram according to the feedback data of the first-class user, and determining an association value A of a product tried by the ith user and a product to be tried according to the product classification tree diagram i ；
A statistic value module for determining feedback time statistic value B of the ith user according to the feedback data of the first user i Statistics of feedback times C i Feedback evaluation statistic D i ；
A feedback rate module for determining the feedback rate F of the jth tested product according to the feedback data of the first class user j ；
A priority value module for according to A i 、B i 、C i D (D) i Calculating the priority value Q of the ith user in the first type of users i ；
A sorting module for sorting according to Q i Sequencing the first class of users, and obtaining a feedback frequency statistical value sequence U corresponding to the users according to the sequencing result o ；
A calculation module for according to S 1 Presetting a first class user push proportion y and U o Calculating the number H of push people of the first class of users 1 According to S 1 Y and F j Calculating a second class of usePush number H of users 2 ；
A pushing module for sorting according to Q i The number H is selected from the order of big to small 1 Is pushed by users of the second class of users, and the number of users is randomly selected as H 2 Is pushed by the user of (a).
CN202310837078.8A 2023-07-10 2023-07-10 User matching method and device based on data analysis Active CN116561603B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310837078.8A CN116561603B (en) 2023-07-10 2023-07-10 User matching method and device based on data analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310837078.8A CN116561603B (en) 2023-07-10 2023-07-10 User matching method and device based on data analysis

Publications (2)

Publication Number Publication Date
CN116561603A true CN116561603A (en) 2023-08-08
CN116561603B CN116561603B (en) 2023-09-01

Family

ID=87496909

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310837078.8A Active CN116561603B (en) 2023-07-10 2023-07-10 User matching method and device based on data analysis

Country Status (1)

Country Link
CN (1) CN116561603B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009018228A1 (en) * 2007-07-27 2009-02-05 Digital River, Inc. Trial optimization system and method
US20180101576A1 (en) * 2016-10-10 2018-04-12 Alibaba Group Holding Limited Content Recommendation and Display
CN108074122A (en) * 2016-11-18 2018-05-25 腾讯科技（深圳）有限公司 Product beta test recommends method, apparatus and server
CN109635200A (en) * 2018-12-18 2019-04-16 南京邮电大学 A kind of Collaborative Filtering Recommendation Algorithm based on MMTD and user
CN113672797A (en) * 2020-05-13 2021-11-19 腾讯科技（深圳）有限公司 Content recommendation method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009018228A1 (en) * 2007-07-27 2009-02-05 Digital River, Inc. Trial optimization system and method
US20180101576A1 (en) * 2016-10-10 2018-04-12 Alibaba Group Holding Limited Content Recommendation and Display
CN108074122A (en) * 2016-11-18 2018-05-25 腾讯科技（深圳）有限公司 Product beta test recommends method, apparatus and server
CN109635200A (en) * 2018-12-18 2019-04-16 南京邮电大学 A kind of Collaborative Filtering Recommendation Algorithm based on MMTD and user
CN113672797A (en) * 2020-05-13 2021-11-19 腾讯科技（深圳）有限公司 Content recommendation method and device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
焦明海 等: "基于贝叶斯网络认知反馈的协同过滤推荐", 控制工程, vol. 24, no. 07, pages 1310 - 1317 *

Also Published As

Publication number Publication date
CN116561603B (en) 2023-09-01

Similar Documents

Publication Publication Date Title
Wan et al. Item recommendation on monotonic behavior chains
JP7104244B2 (en) User tag generation method and its devices, computer programs and computer equipment
Christakopoulou et al. Local item-item models for top-n recommendation
Zhang et al. Dissonance between human and machine understanding
Tang et al. Ensemble contextual bandits for personalized recommendation
Elsalamony Bank direct marketing analysis of data mining techniques
CN109241427A (en) Information-pushing method, device, computer equipment and storage medium
CN108491511B (en) Data mining method and device based on graph data and model training method and device
CN112559900B (en) Product recommendation method and device, computer equipment and storage medium
Yakhchi et al. Enabling the analysis of personality aspects in recommender systems
CN114282054A (en) Video recommendation method and device, computer equipment and storage medium
Levy et al. Combining forecasts in the presence of ambiguity over correlation structures
US7562063B1 (en) Decision support systems and methods
Truyen et al. Preference networks: Probabilistic models for recommendation systems
Shams et al. Cluster-based bandits: Fast cold-start for recommender system new users
CN111639696A (en) User classification method and device
Dunker et al. Random coefficients in static games of complete information
Zhu et al. Simultaneous estimation and group identification for network vector autoregressive model with heterogeneous nodes
Zhang Enhancing diversity in top-n recommendation
Guan et al. Enhanced SVD for collaborative filtering
CN116561603B (en) User matching method and device based on data analysis
Sharma et al. SPLIT-DOOR CRITERION
CN110264364B (en) Recommendation method for investor
CN111667298A (en) User personalized demand prediction method and system
WO2013063524A2 (en) Identifying people likely to respond accurately to survey questions

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
GR01 Patent grant
GR01 Patent grant