CN119273383A - User portrait construction method, system and medium for vending machines - Google Patents
User portrait construction method, system and medium for vending machines Download PDFInfo
- Publication number
- CN119273383A CN119273383A CN202411797164.1A CN202411797164A CN119273383A CN 119273383 A CN119273383 A CN 119273383A CN 202411797164 A CN202411797164 A CN 202411797164A CN 119273383 A CN119273383 A CN 119273383A
- Authority
- CN
- China
- Prior art keywords
- user
- historical
- transaction
- shopping cart
- commodity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
Landscapes
- Business, Economics & Management (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Control Of Vending Devices And Auxiliary Devices For Vending Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明涉及用户分析技术领域，并具体公开了应用于自动贩卖机的用户画像构建方法、系统及介质，其方法包括：获取用户的影响交易属性信息和用户与分析范围内的所有自动贩卖机的历史交互记录；将用户的影响交易属性信息与影响交易属性特征标签‑知识库进行匹配，确定出用户的所有影响交易属性特征标签；基于用户与分析范围内的所有自动贩卖机的历史交互记录分析出用户的所有个性化交易取向特征标签；基于用户的所有影响交易属性特征标签和所有个性化交易取向特征标签生成用户针对分析范围内的所有自动贩卖机的消费行为特征图谱画像；用以全面且精准地描绘了用户的消费行为模式，为精准营销和服务优化提供有力支持。
The present invention relates to the technical field of user analysis, and specifically discloses a method, system and medium for constructing a user portrait applied to a vending machine, wherein the method comprises: obtaining a user's transaction-influencing attribute information and a historical interaction record between the user and all vending machines within an analysis range; matching the user's transaction-influencing attribute information with a transaction-influencing attribute feature tag-knowledge base to determine all the user's transaction-influencing attribute feature tags; analyzing all the user's personalized transaction orientation feature tags based on the user's historical interaction records with all the vending machines within the analysis range; generating a consumption behavior feature map portrait of the user for all the vending machines within the analysis range based on all the user's transaction-influencing attribute feature tags and all the personalized transaction orientation feature tags; and comprehensively and accurately depicting the user's consumption behavior pattern to provide strong support for precision marketing and service optimization.
Description
Technical Field
The invention relates to the technical field of user analysis, in particular to a user portrait construction method, a user portrait construction system and a user portrait construction medium applied to a vending machine.
Background
At present, with the wide application of vending machines in the commercial field, in order to provide more accurate and personalized services and optimize commodity configuration, constructing user figures is an important means for improving the operation effect of vending machines. Currently, in the field of vending machines, there have been some attempts to construct consumer portraits. Some vending machine systems have begun to attempt to collect information about the user, such as purchase records, but the use of such information is often relatively simple and primary.
However, existing methods typically only acquire limited user transaction information, such as items and time of purchase, while ignoring other important attribute information that affects the transaction. Resulting in insufficient user portrayal base data being constructed. The determined feature labels are not accurate and comprehensive enough. The analysis of the historical interaction records of the user and the vending machine is not deep enough, and the personalized transaction orientation characteristics of the user are difficult to accurately mine. Multiple factors cannot be comprehensively considered, and the generated user image is not comprehensive and accurate enough and is difficult to accurately reflect the consumption behavior characteristics of the user.
Therefore, the invention provides a user portrait construction method, a user portrait construction system and a user portrait construction medium applied to a vending machine.
Disclosure of Invention
The invention provides a user portrait construction method, a system and a medium applied to a vending machine, which are used for comprehensively collecting data related to user consumption behaviors by acquiring transaction attribute information and historical interaction records, and providing rich materials for constructing accurate user portraits. The feature labels are determined by matching the influence transaction attribute information with the knowledge base, so that the accuracy and the efficiency of label determination are improved, and the understanding of the transaction attribute of the user is standardized and normalized. Based on the historical interaction record analysis personalized transaction orientation feature label, unique consumption preference and habit of the user can be deeply mined, so that the portrait is more personalized and targeted. And (3) generating a consumption behavior feature map portrait by integrating all the feature tags affecting the transaction attribute and the personalized transaction orientation feature tag, comprehensively and accurately describing the consumption behavior mode of the user, and providing powerful support for accurate marketing and service optimization. The method and the system are beneficial to better knowing the user demands of the vending machine operators, optimizing commodity supply and service strategies, improving user experience and increasing sales and user satisfaction.
The invention provides a user portrait construction method applied to a vending machine, which comprises the following steps:
S1, acquiring transaction attribute information of a user and historical interaction records of the user and all vending machines in an analysis range;
s2, matching the influence transaction attribute information of the user with the influence transaction attribute feature tag-knowledge base to determine all influence transaction attribute feature tags of the user;
s3, analyzing all personalized transaction orientation feature labels of the user based on historical interaction records of the user and all vending machines in an analysis range;
And S4, generating consumption behavior feature map portraits of the user aiming at all vending machines in the analysis range based on all the influence transaction attribute feature tags and all the personalized transaction orientation feature tags of the user.
Preferably, the user portrait construction method applied to the vending machine comprises the following steps of S1, obtaining the influence transaction attribute information of a user and the historical interaction records of the user and all vending machines in an analysis range, wherein the method comprises the following steps:
s101, acquiring historical interaction records of a user and all vending machines in an analysis range;
s102, acquiring online and offline interaction record information of the user and all vending machines in the analysis range based on the historical interaction records of the user and all vending machines in the analysis range;
And S103, extracting the transaction attribute information of the user from online and offline interaction record information of the user and all vending machines within the analysis range.
Preferably, the user portrait construction method applied to the vending machine comprises the following steps of S2, matching the influence transaction attribute information of a user with the influence transaction attribute feature tag-knowledge base, and determining all influence transaction attribute feature tags of the user, wherein the method comprises the following steps:
s201, calculating the matching degree between the influence transaction attribute information of the user and the knowledge sets corresponding to each influence transaction attribute feature tag in the influence transaction attribute feature tag-knowledge base;
s202, regarding all the influence transaction attribute feature tags with the matching degree not smaller than a matching degree threshold value in the influence transaction attribute feature tag-knowledge base as all the influence transaction attribute feature tags of the user.
Preferably, the user portrait construction method applied to the vending machine comprises the following steps of S3, analyzing all personalized transaction orientation feature labels of a user based on historical interaction records of the user and all vending machines within an analysis range, wherein the method comprises the following steps:
S301, extracting all sub-history interaction records of each history interaction commodity of the user from the history interaction records of all vending machines in the analysis range of the user;
S302, analyzing the comprehensive consumption intention index of the user on each historical interactive commodity based on all sub-historical interactive records of each historical interactive commodity;
S303, analyzing personalized transaction orientation feature labels of the user on commodity attribute dimensions based on comprehensive consumption intention indexes of the user on all the historical interactive commodities and inherent attributes of all the historical interactive commodities;
s304, performing interactive behavior feature analysis on the time dimension and the space dimension on the historical interactive records of the user and all vending machines in the analysis range respectively to obtain personalized transaction orientation feature labels of the user in the time dimension and personalized transaction orientation feature labels of the user in the space dimension.
Preferably, the user portrait construction method applied to the vending machine comprises the following steps of S302, analyzing the comprehensive consumption intention index of a user on each historical interactive commodity based on all sub-historical interactive records of each historical interactive commodity, wherein the method comprises the following steps:
determining the purchase frequency, the search frequency, the browsing depth of each search process, the shopping cart conversion rate and the after-sale evaluation of a user on each historical interactive commodity based on all sub-historical interactive records of each historical interactive commodity;
Based on the purchase frequency, search frequency, browsing depth of each search process, shopping cart conversion rate and all after-sales evaluations of the user on each historical interactive commodity, calculating the comprehensive consumption intention index of the user on each historical interactive commodity:
in the formula, For the user's comprehensive consumption intention index for the currently calculated historical interactive merchandise,For the user's frequency of purchase of the currently calculated historical interaction merchandise,For the user's search frequency for the currently calculated historical interaction merchandise,For the total number of searches the user has for the currently calculated historical interaction merchandise,For the user to interact with the current calculated historyThe depth of view of the secondary search process,Is an exponential function of the natural constant e,For the effective decay rate of the depth of view,For the current moment of time,For the user to interact with the current calculated historyThe time at which the secondary search process occurs,For the user's shopping cart conversion rate for the currently calculated historical interaction merchandise,The user is given a value for all after-market ratings of the currently calculated historical interactive merchandise.
Preferably, the user portrait construction method applied to the vending machine determines the shopping cart conversion rate of the user on each historical interactive commodity based on all sub-historical interactive records of each historical interactive commodity, and comprises the following steps:
Determining all shopping cart additional purchase records and shopping cart payment records of each historical interactive commodity based on all sub-historical interactive records of each historical interactive commodity;
Determining the total shopping cart additional purchase amount, the total shopping cart payment amount, the occurrence time of each shopping cart additional purchase record and the occurrence time of each shopping cart payment record of each historical interactive commodity based on all shopping cart additional purchase records and shopping cart payment records of each historical interactive commodity;
Calculating the shopping cart conversion rate of the user for each historical interactive commodity based on the total shopping cart number, the total shopping cart payment number, the occurrence time of each shopping cart number record and the occurrence time of each shopping cart payment record of each historical interactive commodity:
in the formula, For the user's shopping cart conversion rate for the currently calculated historical interaction merchandise,The total number of shopping carts for the currently calculated historical interactive merchandise,The total number of shopping carts paid for the currently calculated historical interactive merchandise,Item number of the currently calculated historical interaction merchandiseThe time of occurrence of the payment record for the secondary shopping cart,Item number of the currently calculated historical interaction merchandiseThe secondary shopping cart payment records the occurrence time of the corresponding shopping cart additional purchase record,The rate of decay of the validity of the payment record for the shopping cart,The correction parameters are preset.
Preferably, the user portrait construction method applied to the vending machine is used for analyzing personalized transaction orientation feature labels of the user in the commodity attribute dimension based on the comprehensive consumption intention index of the user on all the historical interaction commodities and the inherent attributes of all the historical interaction commodities, and comprises the following steps:
determining all common attribute items in the inherent attributes of all the historical interactive commodities of the user, and determining a common commodity set corresponding to each common attribute item;
calculating the average value of the comprehensive consumption intention indexes of all the historical interactive commodities in each shared commodity set, and taking the average value as the average consumption intention index of the corresponding shared commodity set;
Taking the product of the total number of commodities in the common commodity set corresponding to each common attribute item and the total number of all historical interactive commodities of the user and the average consumption intention index of the corresponding common commodity set as the generalization degree of the corresponding common attribute item in the historical interaction records of all vending machines in the user and analysis range;
Based on all the common attribute items with the generalization degree not less than the generalization degree threshold value in the historical interaction records of all the vending machines within the analysis range of the user, personalized transaction orientation feature labels of the user in the commodity attribute dimension are generated.
Preferably, the user portrait construction method applied to the vending machine is that S4, based on all the characteristic labels of the influence transaction attribute and all the personalized transaction orientation characteristic labels of the user, the consumption behavior characteristic map portraits of the user aiming at all the vending machine in the analysis range are generated, and the method comprises the following steps:
s401, acquiring a consumption behavior feature map template;
S402, based on all the characteristic labels of the influence transaction attribute, all the personalized transaction orientation characteristic labels and the consumption behavior characteristic spectrum template of the user, generating consumption behavior characteristic spectrum portraits of the user aiming at all vending machines in the analysis range.
The invention provides a user portrait construction system applied to a vending machine, which is used for executing a user portrait construction method applied to the vending machine, comprising the following steps:
the information acquisition module is used for acquiring the influence transaction attribute information of the user and the historical interaction records of the user and all vending machines in the analysis range;
The knowledge matching module is used for matching the influence transaction attribute information of the user with the influence transaction attribute feature tag-knowledge base to determine all influence transaction attribute feature tags of the user;
the label analysis module is used for analyzing all personalized transaction orientation feature labels of the user based on the historical interaction records of the user and all vending machines in the analysis range;
And the portrayal generation module is used for generating a consumption behavior characteristic atlas portrayal of the user aiming at all vending machines in the analysis range based on all the influence transaction attribute characteristic labels and all the personalized transaction orientation characteristic labels of the user.
The present invention provides a storage medium storing computer-executable instructions for causing a computer to execute the user portrait construction method applied to the vending machine.
Compared with the prior art, the method has the beneficial effects that the data related to the consumption behavior of the user can be comprehensively collected by acquiring the transaction attribute information and the history interaction record, so that rich materials are provided for constructing accurate user images. The feature labels are determined by matching the influence transaction attribute information with the knowledge base, so that the accuracy and the efficiency of label determination are improved, and the understanding of the transaction attribute of the user is standardized and normalized. Based on the historical interaction record analysis personalized transaction orientation feature label, unique consumption preference and habit of the user can be deeply mined, so that the portrait is more personalized and targeted. And (3) generating a consumption behavior feature map portrait by integrating all the feature tags affecting the transaction attribute and the personalized transaction orientation feature tag, comprehensively and accurately describing the consumption behavior mode of the user, and providing powerful support for accurate marketing and service optimization. The method and the system are beneficial to better knowing the user demands of the vending machine operators, optimizing commodity supply and service strategies, improving user experience and increasing sales and user satisfaction.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objects and other advantages of the application may be realized and obtained by means of the instrumentalities particularly pointed out in the specification.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flowchart of a user portrait construction method applied to a vending machine in an embodiment of the present invention;
FIG. 2 is a flowchart of a specific implementation method of step S1 in an embodiment of the present invention;
FIG. 3 is a flowchart of a specific implementation method of step S2 in an embodiment of the present invention;
FIG. 4 is a flowchart of a specific implementation method of step S3 in an embodiment of the present invention;
FIG. 5 is a flowchart of a specific implementation method of step S4 in an embodiment of the present invention;
FIG. 6 is a schematic diagram of a user portrayal construction system applied to a vending machine in accordance with an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Example 1:
The invention provides a user portrait construction method applied to a vending machine, referring to fig. 1, comprising the following steps:
S1, acquiring transaction attribute information of a user and historical interaction records of the user and all vending machines in an analysis range;
s2, matching the influence transaction attribute information of the user with the influence transaction attribute feature tag-knowledge base to determine all influence transaction attribute feature tags of the user;
s3, analyzing all personalized transaction orientation feature labels of the user based on historical interaction records of the user and all vending machines in an analysis range;
And S4, generating consumption behavior feature map portraits of the user aiming at all vending machines in the analysis range based on all the influence transaction attribute feature tags and all the personalized transaction orientation feature tags of the user.
In this embodiment, the influence transaction attribute information refers to various kinds of related information capable of influencing transactions between the user and the vending machine, such as the age, sex, payment mode, and the like of the user. For example, a user often uses electronic payment and dislikes cash payment, and the payment mode preference is to influence transaction attribute information.
In this embodiment, all vending machines within the analysis range represent all vending machines covered within a particular analysis area or set condition. For example, if the analysis range is a business area of a city, then all vending machines within the business area are vending machines within the analysis range.
In this embodiment, the history of interactions refers to various records of past interactions of the user with the vending machine, including the type, quantity, time, location of purchased goods, behavior of browsing goods, and after-market ratings. For example, a user purchased a bottle of cola on a vending machine at 3 pm yesterday, which is a historical interaction record.
In this embodiment, the influence transaction attribute feature tag-knowledge base is a pre-established collection containing various influence transaction attribute feature tags and their associated knowledge and definitions. For example, there may be "young consumers", "high-consumer-ability" feature tags, etc., and each tag is described and explained in detail.
In this embodiment, the influencing transaction attribute feature tag is a short, explicit identification or description of the user influencing the transaction attribute. For example, a characteristic tag such as "male user" or "electronic payment user" affects the transaction attribute. Like "price sensitive users", "high frequency purchasers" are characteristic tags that affect transaction attributes.
In this embodiment, the personalized transaction orientation feature tag is a tag that reflects the unique transaction preferences and trends of the user, based on analysis of the user's interaction records with the vending machine. Examples are "preferred snack items", "apparent tendency to shopping at night", etc.
In the embodiment, the consumption behavior feature map portrait is a map or portrait which is formed by integrating all the feature tags affecting the transaction attribute and the personalized transaction orientation feature tags of the user and comprehensively and in detail describes the consumption behavior characteristics of the user in the vending machine. For example, a representation that includes features such as "young females like to purchase beverages in the afternoon, and" relatively price sensitive "is a representation of a consumer behavior profile.
The technology has the beneficial effects that the data related to the consumption behavior of the user can be comprehensively collected by acquiring the transaction attribute information and the history interaction record, so that rich materials are provided for constructing accurate user images. The feature labels are determined by matching the influence transaction attribute information with the knowledge base, so that the accuracy and the efficiency of label determination are improved, and the understanding of the transaction attribute of the user is standardized and normalized. Based on the historical interaction record analysis personalized transaction orientation feature label, unique consumption preference and habit of the user can be deeply mined, so that the portrait is more personalized and targeted. And (3) generating a consumption behavior feature map portrait by integrating all the feature tags affecting the transaction attribute and the personalized transaction orientation feature tag, comprehensively and accurately describing the consumption behavior mode of the user, and providing powerful support for accurate marketing and service optimization. The method and the system are beneficial to better knowing the user demands of the vending machine operators, optimizing commodity supply and service strategies, improving user experience and increasing sales and user satisfaction.
Example 2:
based on the embodiment 1, the user portrait construction method applied to the vending machine, S1, obtaining the influence transaction attribute information of the user and the historical interaction records of the user and all vending machines within the analysis range, referring to FIG. 2, comprises the following steps:
s101, acquiring historical interaction records of a user and all vending machines in an analysis range;
s102, acquiring online and offline interaction record information of the user and all vending machines in the analysis range based on the historical interaction records of the user and all vending machines in the analysis range;
And S103, extracting the transaction attribute information of the user from online and offline interaction record information of the user and all vending machines within the analysis range.
In this embodiment, the online-offline interaction record information refers to various records generated by interaction between the user and all vending machines in the analysis range on the network platform (online) and the physical vending machine (offline), including online browsing, ordering, payment and other behavior records, and offline purchasing, operation and other behavior records. Such as a record of the user's browsing of the merchandise in an online vending machine application and a record of the purchase of the merchandise prior to the physical vending machine.
In the embodiment, the influence transaction attribute information of the user is extracted from online and offline interaction record information of the user and all vending machines in the analysis range, namely, the user related attribute information which can influence the transaction is screened and acquired from all interaction records of the user and the vending machines in two scenes of a network and an entity. For example, attribute information which affects transactions, such as price sensitivity, preference for traditional payment mode, and the like, of a user is extracted from records of high-price commodities which are browsed on a user line for a plurality of times and are not purchased, cash payment is frequently used off line, and the like. For example, attribute information which affects transactions, such as price sensitivity, preference for traditional payment mode, and the like, of a user is extracted from records of high-price commodities which are browsed on a user line for a plurality of times and are not purchased, cash payment is frequently used off line, and the like.
The method has the beneficial effects that the history interaction record is firstly obtained, a foundation is laid for the subsequent extraction of key information, and the integrity and the originality of data are ensured. The online and offline interaction record information is acquired based on the history interaction record, so that the interaction condition of the user with the vending machine under different scenes is comprehensively covered. The transaction attribute information is extracted from the rich interaction record information, so that the pertinence and the effectiveness of the information are improved, and the interference of irrelevant data is eliminated. The method is beneficial to grasping key transaction attributes in the interaction process of the user and the vending machine more accurately, and provides powerful support for constructing accurate user portraits. The method can provide a more valuable data base for subsequent analysis and decision making, and improves the quality and efficiency of the service of the vending machine.
Example 3:
On the basis of embodiment 1, the user portrait construction method applied to the vending machine is provided with S2, wherein the method comprises the steps of matching the influence transaction attribute information of a user with the influence transaction attribute feature labels-knowledge base to determine all influence transaction attribute feature labels of the user, and referring to FIG. 3, the method comprises the following steps:
s201, calculating the matching degree between the influence transaction attribute information of the user and the knowledge sets corresponding to each influence transaction attribute feature tag in the influence transaction attribute feature tag-knowledge base;
s202, regarding all the influence transaction attribute feature tags with the matching degree not smaller than a matching degree threshold value in the influence transaction attribute feature tag-knowledge base as all the influence transaction attribute feature tags of the user.
In this embodiment, the influencing transaction attribute feature tags are a brief identification or description of the attributes that the user has influenced during a transaction with the vending machine, for summarizing and categorizing certain transaction characteristics of the user. For example, tags such as "high frequency consumer", "impulse shopper", and the like.
In this embodiment, the knowledge set to which each transaction attribute-affecting feature tag corresponds is a series of detailed information and descriptions associated with each transaction attribute-affecting feature tag, possibly including definitions, typical performance, relevant data ranges, etc. of the tag. For example, the knowledge set corresponding to the tag of the "high frequency consumer" may contain specific information such as the number of times of purchase exceeds a certain value per week, and the variety of the purchased goods is rich.
In this embodiment, the matching degree between the user's attribute information of the influence transaction and the knowledge set corresponding to each attribute tag of the influence transaction attribute in the attribute tag-knowledge base is calculated, which means that the matching degree between the user's attribute information of the influence transaction and the knowledge set associated with each attribute tag in the knowledge base is measured by a specific algorithm or method. For example, if the purchase frequency of the user is high, the user is matched with the rule about the purchase frequency in the knowledge set of the 'high frequency consumer' tag, so as to calculate a value of the matching degree.
In this embodiment, the matching degree threshold is a preset standard value, which is used to determine whether the matching degree between the user's influence transaction attribute information and the knowledge set corresponding to the feature tag meets a certain requirement. For example, the matching degree threshold is set to 80%, and when the calculated matching degree is higher than 80%, the user is considered to have the corresponding characteristic label.
The method has the beneficial effects that the degree of association between the transaction attribute information and the tags in the knowledge base can be quantitatively influenced by calculating the degree of matching, so that the matching result is more accurate and measurable. And setting a matching degree threshold value, so that the screened characteristic tags affecting the transaction attribute have higher correlation and reliability, and the accuracy of tag determination is improved. The method is beneficial to more accurately selecting the feature labels which are consistent with the actual conditions of the users from the knowledge base, and avoids the introduction of errors or irrelevant labels. The method can provide more targeted and representative characteristic labels affecting transaction attributes for the user portrait, and enhance the credibility and practicability of the portrait. The scientificity and the effectiveness of user portrait construction are improved, and a more reliable basis is provided for accurate marketing and personalized services of the vending machine.
Example 4:
based on the embodiment 1, the user portrait construction method applied to the vending machine, S3, based on the historical interaction records of the user and all vending machines within the analysis range, analyzes all personalized transaction orientation feature labels of the user, and referring to FIG. 4, the method comprises the following steps:
S301, extracting all sub-history interaction records of each history interaction commodity of the user from the history interaction records of all vending machines in the analysis range of the user;
S302, analyzing the comprehensive consumption intention index of the user on each historical interactive commodity based on all sub-historical interactive records of each historical interactive commodity;
S303, analyzing personalized transaction orientation feature labels of the user on commodity attribute dimensions based on comprehensive consumption intention indexes of the user on all the historical interactive commodities and inherent attributes of all the historical interactive commodities;
s304, performing interactive behavior feature analysis on the time dimension and the space dimension on the historical interactive records of the user and all vending machines in the analysis range respectively to obtain personalized transaction orientation feature labels of the user in the time dimension and personalized transaction orientation feature labels of the user in the space dimension.
In this embodiment, the historical interactive merchandise refers to merchandise that the user has purchased, browsed or focused on in the past during interactions with the vending machine.
In this embodiment, the sub-historic interaction records are more finely divided interaction records for each historic interaction commodity, such as records that record a complete purchase transaction process.
In this embodiment, the comprehensive consumption intention index of the user for each historical interactive commodity is obtained through a series of related data and calculation, and is used for measuring the numerical index of the comprehensive consumption intention and tendency of the user for a specific historical interactive commodity. For example, if the purchase frequency of a certain chocolate by a user is high, the search frequency is high, the browsing depth is large, and the like, a high consumption intention index is comprehensively calculated.
In this embodiment, the inherent properties of the historical interactive merchandise refer to the fixed characteristics of the merchandise itself, such as category, brand, price, taste, etc. of the merchandise. For example, an inherent attribute of a chocolate may be a brand, milk chocolate taste, a price of 10 yuan, etc.
In this embodiment, the personalized transaction orientation feature tag for the user in the commodity attribute dimension is a tag generated based on the user's preferences and trends for the inherent attributes of the historically interacted with commodity, reflecting the unique transaction preferences of the user in terms of commodity attributes. Examples are "preference for well-known branded goods", "like low price goods", etc.
In this embodiment, the personalized transaction orientation feature tag of the user in the time dimension and the personalized transaction orientation feature tag in the space dimension reflect the consumption preference of the user in different time periods (such as day, night, weekend, etc.), and the tag in the space dimension reflects the consumption preference of the user in different places (such as schools, office buildings, communities, etc.).
For example, "night active" is a tag in the time dimension, and "frequent purchase near school" is a tag in the space dimension.
The technology has the beneficial effects that the sub-history interaction records of each history interaction commodity are extracted, the interaction condition of a user on a specific commodity can be carefully analyzed, and a rich data basis is provided for subsequent consumption intention analysis. And analyzing the comprehensive consumption intention index of the user on each historical interactive commodity, and being beneficial to quantifying the preference and demand degree of the user on different commodities. The personalized transaction orientation feature tag is determined based on the comprehensive consumption intention index and the inherent properties of the commodity, so that the consumption preference of the user can be known in depth from the dimension of the property of the commodity. And the interactive behavior feature analysis is carried out from the time dimension and the space dimension, so that the time and space rules of the consumption behavior of the user are comprehensively considered, and the personalized transaction orientation feature label is more comprehensive and accurate. The method is beneficial to providing more accurate user portraits for the vending machine, thereby realizing more accurate commodity recommendation, inventory management and marketing strategy formulation and improving user experience and operation benefits.
Example 5:
based on embodiment 4, the user portrait construction method applied to the vending machine, S302, based on all sub-historic interaction records of each historic interaction commodity, analyzes the comprehensive consumption intention index of the user for each historic interaction commodity, and comprises the following steps:
determining the purchase frequency, the search frequency, the browsing depth of each search process, the shopping cart conversion rate and the after-sale evaluation of a user on each historical interactive commodity based on all sub-historical interactive records of each historical interactive commodity;
Based on the purchase frequency, search frequency, browsing depth of each search process, shopping cart conversion rate and all after-sales evaluations of the user on each historical interactive commodity, calculating the comprehensive consumption intention index of the user on each historical interactive commodity:
in the formula, For the user's comprehensive consumption intention index for the currently calculated historical interactive merchandise,For the user's frequency of purchase of the currently calculated historical interaction merchandise,For the user's search frequency for the currently calculated historical interaction merchandise,For the total number of searches the user has for the currently calculated historical interaction merchandise,For the user to interact with the current calculated historyThe depth of view of the secondary search process,Is an exponential function of the natural constant e (e has a value of 2.72),For the effective decay rate of the depth of view,For the current moment of time,For the user to interact with the current calculated historyThe time at which the secondary search process occurs,For the user's shopping cart conversion rate for the currently calculated historical interaction merchandise,The user is given a value for all after-market ratings of the currently calculated historical interactive merchandise.
In this embodiment, the purchase frequency of each historical interaction product by the user refers to the average value of the number of times the user purchases a particular historical interaction product over a period of time. For example, if a user purchases a beverage 5 times in a month, the frequency of purchase is 5 times per month.
In this embodiment, the frequency of searching for each of the historical interactive items by the user is an average of the number of times the user searches for a certain historical interactive item within a particular period of time. For example, a user searches for a treat 3 times a week, with a frequency of 3 times/week.
In this embodiment, the browsing depth of each search process refers to the depth of viewing contents such as product details and related introduction each time a user performs a product search. For example, the browsing depth may be relatively high, as measured by the time the user stays on the merchandise page, the number of pages browsed, etc., such as stay for 2 minutes and having viewed 3 pages.
In this embodiment, shopping cart conversion refers to the conversion rate at which the user adds items to the shopping cart to ultimately complete the purchase process.
In this embodiment, the rate of decay of the effectiveness of the depth of view represents the rate at which the depth of view during a previous search gradually decreases in importance or effectiveness for subsequent analysis over time.
In this embodiment, the user assigns a value to all after-market ratings of the currently calculated historical interactive merchandise, which is a value obtained by quantifying all after-market ratings of a particular historical interactive merchandise. For example, it is possible to set a very satisfactory of 5 points, a satisfactory of 4 points, a dissatisfaction of 2 points, and a very dissatisfaction of 1 point. And then comprehensively calculating all after-sales evaluation of the commodity by the user to obtain a final assigned value, for example, the assigned value obtained after comprehensive calculation is 3.5 points.
The technology has the beneficial effects that the interest and consumption intention of the user on the specific commodity can be comprehensively known by considering the purchase frequency, the search frequency, the browsing depth of each search process, the shopping cart conversion rate, the after-sale evaluation and the like of the user on the historical interactive commodity. The multidimensional analysis can more accurately describe the consumption behavior mode of the user, and provides a more valuable basis for commodity recommendation and marketing strategies of the vending machine. The comprehensive consumption intention index is calculated by using a specific formula, and different types of user behavior data can be quantized and integrated. The index can be used as an important index of the user portrait, and helps the vending machine operator to better know the demands and preferences of the user, so that more accurate commodity recommendation and personalized service are realized, and shopping experience and satisfaction of the user are improved. The occurrence time of the search process and the effective decay rate of the browsing depth are considered in the formula, which means that the method can dynamically reflect the change of the user behavior with time. The recent searching behavior is given higher weight, so that the timeliness of the user interest is more met, and the comprehensive consumption intention index can more accurately reflect the current consumption intention of the user.
Example 6:
Based on embodiment 5, the user portrait construction method applied to the vending machine determines the shopping cart conversion rate of the user for each historical interactive commodity based on all sub-historical interaction records of each historical interactive commodity, including:
Determining all shopping cart additional purchase records and shopping cart payment records of each historical interactive commodity based on all sub-historical interactive records of each historical interactive commodity;
Determining the total shopping cart additional purchase amount, the total shopping cart payment amount, the occurrence time of each shopping cart additional purchase record and the occurrence time of each shopping cart payment record of each historical interactive commodity based on all shopping cart additional purchase records and shopping cart payment records of each historical interactive commodity;
Calculating the shopping cart conversion rate of the user for each historical interactive commodity based on the total shopping cart number, the total shopping cart payment number, the occurrence time of each shopping cart number record and the occurrence time of each shopping cart payment record of each historical interactive commodity:
in the formula, For the user's shopping cart conversion rate for the currently calculated historical interaction merchandise,The total number of shopping carts for the currently calculated historical interactive merchandise,The total number of shopping carts paid for the currently calculated historical interactive merchandise,Item number of the currently calculated historical interaction merchandiseThe time of occurrence of the payment record for the secondary shopping cart,Item number of the currently calculated historical interaction merchandiseThe secondary shopping cart payment records the occurrence time of the corresponding shopping cart additional purchase record,The rate of decay of the validity of the payment record for the shopping cart,To preset correction parametersThe value of (1).
In this embodiment, the shopping cart additional purchase record refers to a record formed by the operation of the user to add the merchandise to the shopping cart. For example, a user adds a piece of bread to a shopping cart at an online platform of a vending machine, which creates a record of shopping cart purchases.
In this embodiment, the shopping cart payment record is a record formed by an operation of a user for payment settlement of goods in the shopping cart. For example, when the user completes payment for a selected item within the shopping cart, a shopping cart payment record is generated.
In this embodiment, the total number of shopping cart purchases is the cumulative number of times the user adds items to the shopping cart over a period of time. For example, a user adds different items to a shopping cart 20 times a month, and the 20 times is the total number of shopping carts to be purchased.
In this embodiment, the total number of shopping cart payments refers to the cumulative number of times the user completed payment for the shopping cart commodity over a particular period of time. For example, in a week, the user has completed 8 payments for shopping cart merchandise, the 8 times being the total number of shopping cart payments.
In this embodiment, the rate of decay of the availability of the shopping cart payment record represents the rate at which the availability or impact of the shopping cart payment record for subsequent analysis and calculation gradually decreases over time.
The method has the beneficial effects that through analyzing all sub-history interaction records of each history interaction commodity, shopping cart additional purchase records and payment records are determined, and further the total number of shopping cartadditional purchases, the total number of payment and the occurrence time of corresponding records are obtained. By utilizing the detailed data and the specific formulas to calculate the shopping cart conversion rate, the conversion condition from adding goods into the shopping cart to actual payment of the user can be measured more accurately, and a more valuable user behavior index is provided for an operator of the vending machine. The validity decay rate of the shopping cart payment record is introduced into the formula, and the occurrence time of each shopping cart payment record and the relationship between the occurrence time of the corresponding shopping cart additional purchase record and the current moment are considered. The design can reflect the change trend of the user behavior along with time, gives higher weight to the recent shopping cart conversion behavior, is more in line with the actual user purchase decision process, and ensures that the calculated shopping cart conversion rate can more accurately reflect the purchase intention and behavior mode of the current user.
Example 7:
Based on embodiment 4, the user portrait construction method applied to the vending machine, S303, based on the comprehensive consumption intention index of the user to all the historical interactive commodities and the inherent attributes of all the historical interactive commodities, analyzes the personalized transaction orientation feature tag of the user in the commodity attribute dimension, comprises the following steps:
determining all common attribute items in the inherent attributes of all the historical interactive commodities of the user, and determining a common commodity set corresponding to each common attribute item;
calculating the average value of the comprehensive consumption intention indexes of all the historical interactive commodities in each shared commodity set, and taking the average value as the average consumption intention index of the corresponding shared commodity set;
Taking the product of the total number of commodities in the common commodity set corresponding to each common attribute item and the total number of all historical interactive commodities of the user and the average consumption intention index of the corresponding common commodity set as the generalization degree of the corresponding common attribute item in the historical interaction records of all vending machines in the user and analysis range;
Based on all the common attribute items with the generalization degree not less than the generalization degree threshold value in the historical interaction records of all the vending machines within the analysis range of the user, personalized transaction orientation feature labels of the user in the commodity attribute dimension are generated.
In this embodiment, the common attribute term refers to a certain attribute category commonly owned in at least two historically interactive merchandise. For example, such as "food category", "domestic commodity", etc., are common attribute items.
In this embodiment, the common commodity set corresponding to the common attribute item refers to a set of those history interactive commodities having the same common attribute item. For example, if the common attribute item is "food category," then the corresponding common merchandise set is all foods purchased by the user.
In this embodiment, the generalization degree of the common attribute item in the historical interaction records of all vending machines within the analysis range of the user is used as a measurement value for measuring the generalization degree and the importance degree of a certain common attribute item in all the historical interactions of the user. For example, a common attribute such as "food category" may be more generalized if most of the items purchased by the user are food.
In this embodiment, the generalization degree threshold is a preset standard value, which is used to determine whether the generalization degree of the common attribute item reaches a certain level. For example, setting the generalization threshold to 0.6 is considered important if the generalization of a common attribute item is greater than or equal to 0.6.
In this embodiment, based on all the common attribute items whose degree of generalization in the historical interaction records of all the vending machines within the analysis range of the user is not less than the threshold value of degree of generalization, the personalized transaction orientation feature tag of the user in the commodity attribute dimension is generated, which means that those attribute items whose degree of generalization reaches or exceeds the set threshold value are screened out from all the common attribute items, and feature tags capable of reflecting the personalized transaction tendency of the user in the commodity attribute aspect are created based on these attribute items. For example, if the generalization degree of the two common attribute items of "food category" and "low-sugar food" is not less than a threshold value, it is possible to generate personalized transaction orientation feature tags such as "preferred food-class merchandise" and "low-sugar diet focused".
The technology has the beneficial effects that all the common attribute items and the corresponding common commodity sets are determined, so that the commodity attributes can be classified and integrated, and analysis is more systematic. The average consumption intention index is calculated, so that the overall preference degree of the user to the specific common attribute commodity set can be comprehensively reflected. By calculating the generalization degree, the importance and the universality of the common attribute items in the historical interaction records of the user are quantified, and objective standards are provided for screening key attributes. And generating a personalized transaction orientation feature label based on the generalization degree threshold value, so that the label is ensured to have higher representativeness and pertinence, and the preference of the user on the commodity attribute dimension can be reflected more accurately. The method is beneficial to constructing more accurate and valuable user figures, provides more powerful support for commodity optimization, accurate marketing and service improvement of the vending machine, and improves user satisfaction and commercial benefit.
Example 8:
based on the embodiment 1, the user portrait construction method applied to the vending machine, S4, a consumption behavior feature map portrait of the user for all vending machines in the analysis range is generated based on all influence transaction attribute feature tags and all personalized transaction orientation feature tags of the user, and referring to FIG. 5, the method comprises the following steps:
s401, acquiring a consumption behavior feature map template;
S402, based on all the characteristic labels of the influence transaction attribute, all the personalized transaction orientation characteristic labels and the consumption behavior characteristic spectrum template of the user, generating consumption behavior characteristic spectrum portraits of the user aiming at all vending machines in the analysis range.
In this embodiment, the consumption behavior feature pattern template is a preset frame or format for integrating and presenting the consumption behavior feature information of the user. For example, it may include different modules, such as a transaction attribute module, a personalized orientation module, etc., each having a particular location and manner of presentation.
In this embodiment, based on all the transaction attribute feature tags and all the personalized transaction orientation feature tags of the user and the consumption behavior feature pattern template, the generation of the consumption behavior feature pattern image of the user for all the vending machines within the analysis range means that the related information such as the transaction attribute feature tags and the personalized transaction orientation feature tags of the user are filled and arranged according to the structure and the manner specified by the consumption behavior feature pattern template, so as to form a pattern image capable of comprehensively and systematically describing the consumption behavior features of the user for the vending machines within the specific range. For example, a template is provided with a main transaction attribute label for showing a user at one position, a personalized orientation label is shown at another position, and the collected user related labels are filled into the corresponding positions, so that a consumption behavior characteristic map portrait of the user is generated.
The technology has the beneficial effects that the consumption behavior feature pattern template is obtained, unified frames and standards are provided for generating the portrait, and the consistency and standardization of the structure and the content of the portrait are ensured. The portrait is generated based on all feature labels and templates of the user, and various information can be integrated, so that the portrait presents the consumption behavior features of the user more comprehensively and systematically. The method is beneficial to improving the efficiency and accuracy of image generation and reducing deviation and errors caused by human factors. Clear and visual consumer behavior insight can be provided for operators and decision makers of the vending machine, and more targeted strategies and measures can be formulated conveniently. The standardization and normalization of the user portrait are promoted, the user portrait can be applied and compared in different vending machine scenes, and the practicability and operability of the user portrait are improved.
Example 9:
the present invention provides a user portrayal construction system applied to a vending machine for executing the user portrayal construction method applied to a vending machine according to any one of embodiments 1 to 8, referring to fig. 6, comprising:
the information acquisition module is used for acquiring the influence transaction attribute information of the user and the historical interaction records of the user and all vending machines in the analysis range;
The knowledge matching module is used for matching the influence transaction attribute information of the user with the influence transaction attribute feature tag-knowledge base to determine all influence transaction attribute feature tags of the user;
the label analysis module is used for analyzing all personalized transaction orientation feature labels of the user based on the historical interaction records of the user and all vending machines in the analysis range;
And the portrayal generation module is used for generating a consumption behavior characteristic atlas portrayal of the user aiming at all vending machines in the analysis range based on all the influence transaction attribute characteristic labels and all the personalized transaction orientation characteristic labels of the user.
The technology has the beneficial effects that the data related to the consumption behavior of the user can be comprehensively collected by acquiring the transaction attribute information and the history interaction record, so that rich materials are provided for constructing accurate user images. The feature labels are determined by matching the influence transaction attribute information with the knowledge base, so that the accuracy and the efficiency of label determination are improved, and the understanding of the transaction attribute of the user is standardized and normalized. Based on the historical interaction record analysis personalized transaction orientation feature label, unique consumption preference and habit of the user can be deeply mined, so that the portrait is more personalized and targeted. And (3) generating a consumption behavior feature map portrait by integrating all the feature tags affecting the transaction attribute and the personalized transaction orientation feature tag, comprehensively and accurately describing the consumption behavior mode of the user, and providing powerful support for accurate marketing and service optimization. The method and the system are beneficial to better knowing the user demands of the vending machine operators, optimizing commodity supply and service strategies, improving user experience and increasing sales and user satisfaction.
Example 10:
The present invention provides a storage medium storing computer-executable instructions for causing a computer to execute the user portrait construction method applied to a vending machine according to any one of embodiments 1 to 8.
The technology has the beneficial effects that a convenient storage mode is provided, computer executable instructions related to the user portrait construction method are conveniently stored and managed, and the safety and stability of data are ensured. The user image construction method can be executed by the computer, so that the automatic application of the method is realized, and the complexity of manual operation and possible errors are reduced. The instructions in the storage medium can be used in different computer systems, have good universality and portability, and are convenient to popularize and apply the user portrait construction method. The method is helpful to ensure consistency and accuracy of method execution, and user portraits can be constructed according to established procedures and standards whenever and wherever the method is used. The method provides an efficient and reliable technical means for the vending machine industry, and can rapidly acquire the user portrait, thereby better meeting the market demand and improving the service quality and the operation benefit.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. The user portrait construction method applied to the vending machine is characterized by comprising the following steps:
S1, acquiring transaction attribute information of a user and historical interaction records of the user and all vending machines in an analysis range;
s2, matching the influence transaction attribute information of the user with the influence transaction attribute feature tag-knowledge base to determine all influence transaction attribute feature tags of the user;
s3, analyzing all personalized transaction orientation feature labels of the user based on historical interaction records of the user and all vending machines in an analysis range;
And S4, generating consumption behavior feature map portraits of the user aiming at all vending machines in the analysis range based on all the influence transaction attribute feature tags and all the personalized transaction orientation feature tags of the user.
2. The user portrayal construction method applied to the vending machine according to claim 1, wherein S1, obtaining the user 'S influence transaction attribute information and the user' S history interaction records with all vending machines within the analysis range, comprises:
s101, acquiring historical interaction records of a user and all vending machines in an analysis range;
s102, acquiring online and offline interaction record information of the user and all vending machines in the analysis range based on the historical interaction records of the user and all vending machines in the analysis range;
And S103, extracting the transaction attribute information of the user from online and offline interaction record information of the user and all vending machines within the analysis range.
3. The user portrait construction method applied to a vending machine as claimed in claim 1, wherein S2, matching the influence transaction attribute information of the user with the influence transaction attribute feature tag-knowledge base, determining all influence transaction attribute feature tags of the user comprises:
s201, calculating the matching degree between the influence transaction attribute information of the user and the knowledge sets corresponding to each influence transaction attribute feature tag in the influence transaction attribute feature tag-knowledge base;
s202, regarding all the influence transaction attribute feature tags with the matching degree not smaller than a matching degree threshold value in the influence transaction attribute feature tag-knowledge base as all the influence transaction attribute feature tags of the user.
4. The user portrait construction method applied to a vending machine as claimed in claim 1, wherein S3, analyzing all personalized transaction orientation feature tags of the user based on the historical interaction records of the user with all vending machines within the analysis range, comprises:
S301, extracting all sub-history interaction records of each history interaction commodity of the user from the history interaction records of all vending machines in the analysis range of the user;
S302, analyzing the comprehensive consumption intention index of the user on each historical interactive commodity based on all sub-historical interactive records of each historical interactive commodity;
S303, analyzing personalized transaction orientation feature labels of the user on commodity attribute dimensions based on comprehensive consumption intention indexes of the user on all the historical interactive commodities and inherent attributes of all the historical interactive commodities;
s304, performing interactive behavior feature analysis on the time dimension and the space dimension on the historical interactive records of the user and all vending machines in the analysis range respectively to obtain personalized transaction orientation feature labels of the user in the time dimension and personalized transaction orientation feature labels of the user in the space dimension.
5. The user portrayal construction method applied to the vending machine of claim 4, wherein S302, based on all sub-historic interaction records of each of the historic interaction products, analyzes the comprehensive consumption intention index of the user for each of the historic interaction products, comprises:
determining the purchase frequency, the search frequency, the browsing depth of each search process, the shopping cart conversion rate and the after-sale evaluation of a user on each historical interactive commodity based on all sub-historical interactive records of each historical interactive commodity;
Based on the purchase frequency, search frequency, browsing depth of each search process, shopping cart conversion rate and all after-sales evaluations of the user on each historical interactive commodity, calculating the comprehensive consumption intention index of the user on each historical interactive commodity:
in the formula, For the user's comprehensive consumption intention index for the currently calculated historical interactive merchandise,For the user's frequency of purchase of the currently calculated historical interaction merchandise,For the user's search frequency for the currently calculated historical interaction merchandise,For the total number of searches the user has for the currently calculated historical interaction merchandise,For the user to interact with the current calculated historyThe depth of view of the secondary search process,Is an exponential function of the natural constant e,For the effective decay rate of the depth of view,For the current moment of time,For the user to interact with the current calculated historyThe time at which the secondary search process occurs,For the user's shopping cart conversion rate for the currently calculated historical interaction merchandise,The user is given a value for all after-market ratings of the currently calculated historical interactive merchandise.
6. The user portrayal construction method applied to a vending machine of claim 5, wherein determining the shopping cart conversion rate of the user for each of the historically interactive merchandise based on all sub-historic interaction records of each of the historically interactive merchandise, comprises:
Determining all shopping cart additional purchase records and shopping cart payment records of each historical interactive commodity based on all sub-historical interactive records of each historical interactive commodity;
Determining the total shopping cart additional purchase amount, the total shopping cart payment amount, the occurrence time of each shopping cart additional purchase record and the occurrence time of each shopping cart payment record of each historical interactive commodity based on all shopping cart additional purchase records and shopping cart payment records of each historical interactive commodity;
Calculating the shopping cart conversion rate of the user for each historical interactive commodity based on the total shopping cart number, the total shopping cart payment number, the occurrence time of each shopping cart number record and the occurrence time of each shopping cart payment record of each historical interactive commodity:
in the formula, For the user's shopping cart conversion rate for the currently calculated historical interaction merchandise,The total number of shopping carts for the currently calculated historical interactive merchandise,The total number of shopping carts paid for the currently calculated historical interactive merchandise,Item number of the currently calculated historical interaction merchandiseThe time of occurrence of the payment record for the secondary shopping cart,Item number of the currently calculated historical interaction merchandiseThe secondary shopping cart payment records the occurrence time of the corresponding shopping cart additional purchase record,The rate of decay of the validity of the payment record for the shopping cart,The correction parameters are preset.
7. The user portrayal construction method applied to the vending machine according to claim 4, wherein S303, based on the comprehensive consumption intention index of the user to all the historical interactive commodities and the inherent attributes of all the historical interactive commodities, analyzes the personalized transaction orientation feature tag of the user in the commodity attribute dimension, comprises:
determining all common attribute items in the inherent attributes of all the historical interactive commodities of the user, and determining a common commodity set corresponding to each common attribute item;
calculating the average value of the comprehensive consumption intention indexes of all the historical interactive commodities in each shared commodity set, and taking the average value as the average consumption intention index of the corresponding shared commodity set;
Taking the product of the total number of commodities in the common commodity set corresponding to each common attribute item and the total number of all historical interactive commodities of the user and the average consumption intention index of the corresponding common commodity set as the generalization degree of the corresponding common attribute item in the historical interaction records of all vending machines in the user and analysis range;
Based on all the common attribute items with the generalization degree not less than the generalization degree threshold value in the historical interaction records of all the vending machines within the analysis range of the user, personalized transaction orientation feature labels of the user in the commodity attribute dimension are generated.
8. The user portrayal construction method applied to the vending machine according to claim 1, wherein S4, generating the consumer behavior feature map portrayal of the user for all vending machines within the analysis range based on all influencing transaction attribute feature tags and all personalized transaction orientation feature tags of the user comprises:
s401, acquiring a consumption behavior feature map template;
S402, based on all the characteristic labels of the influence transaction attribute, all the personalized transaction orientation characteristic labels and the consumption behavior characteristic spectrum template of the user, generating consumption behavior characteristic spectrum portraits of the user aiming at all vending machines in the analysis range.
9. A user portrayal construction system applied to a vending machine for performing the user portrayal construction method applied to a vending machine according to any one of claims 1 to 8, comprising:
the information acquisition module is used for acquiring the influence transaction attribute information of the user and the historical interaction records of the user and all vending machines in the analysis range;
The knowledge matching module is used for matching the influence transaction attribute information of the user with the influence transaction attribute feature tag-knowledge base to determine all influence transaction attribute feature tags of the user;
the label analysis module is used for analyzing all personalized transaction orientation feature labels of the user based on the historical interaction records of the user and all vending machines in the analysis range;
And the portrayal generation module is used for generating a consumption behavior characteristic atlas portrayal of the user aiming at all vending machines in the analysis range based on all the influence transaction attribute characteristic labels and all the personalized transaction orientation characteristic labels of the user.
10. A storage medium storing computer-executable instructions for causing a computer to execute the user portrayal construction method applied to a vending machine according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411797164.1A CN119273383A (en) | 2024-12-09 | 2024-12-09 | User portrait construction method, system and medium for vending machines |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411797164.1A CN119273383A (en) | 2024-12-09 | 2024-12-09 | User portrait construction method, system and medium for vending machines |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119273383A true CN119273383A (en) | 2025-01-07 |
Family
ID=94108805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411797164.1A Pending CN119273383A (en) | 2024-12-09 | 2024-12-09 | User portrait construction method, system and medium for vending machines |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119273383A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120524284A (en) * | 2025-05-07 | 2025-08-22 | 亿海蓝（北京）数据技术股份公司 | User portrait construction method and system, electronic device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115409577A (en) * | 2022-08-31 | 2022-11-29 | 拓元(广州)智慧科技有限公司 | Intelligent container repurchase prediction method and system based on user behavior and environmental information |
| CN116010700A (en) * | 2023-01-10 | 2023-04-25 | 读书郎教育科技有限公司 | Knowledge graph-based user portrayal method |
| CN117575648A (en) * | 2023-11-22 | 2024-02-20 | 四川中电启明星信息技术有限公司 | Mall user portrait construction method |
-
2024
- 2024-12-09 CN CN202411797164.1A patent/CN119273383A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115409577A (en) * | 2022-08-31 | 2022-11-29 | 拓元(广州)智慧科技有限公司 | Intelligent container repurchase prediction method and system based on user behavior and environmental information |
| CN116010700A (en) * | 2023-01-10 | 2023-04-25 | 读书郎教育科技有限公司 | Knowledge graph-based user portrayal method |
| CN117575648A (en) * | 2023-11-22 | 2024-02-20 | 四川中电启明星信息技术有限公司 | Mall user portrait construction method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120524284A (en) * | 2025-05-07 | 2025-08-22 | 亿海蓝（北京）数据技术股份公司 | User portrait construction method and system, electronic device and storage medium |
| CN120524284B (en) * | 2025-05-07 | 2025-12-23 | 亿海蓝（北京）数据技术股份公司 | User profile construction methods and systems, electronic devices and storage media |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11830053B2 (en) | Methods and systems for deriving a score with which item listings are ordered when presented in search results | |
| US12008593B2 (en) | System, method and computer program for varying affiliate position displayed by intermediary | |
| US20200005381A1 (en) | Method and system for selection, filtering or presentation of available sales outlets | |
| CN117670404B (en) | Intelligent retail management system and method for intelligent display terminal | |
| US10289736B2 (en) | Systems and methods for ranking results based on dwell time | |
| US10366435B2 (en) | Vehicle data system for rules based determination and real-time distribution of enhanced vehicle data in an online networked environment | |
| US20220253874A1 (en) | Product evaluation system and method of use | |
| KR101564824B1 (en) | Advertising system, advertising system control method, and information storage medium | |
| US20130254025A1 (en) | Item ranking modeling for internet marketing display advertising | |
| CN118552281A (en) | Intelligent commodity recommendation and personalized marketing tool monitoring method | |
| CN119273383A (en) | User portrait construction method, system and medium for vending machines | |
| US20150142782A1 (en) | Method for associating metadata with images | |
| CN119205271A (en) | Risk rating prediction system based on E-commerce big data analysis | |
| US9715708B2 (en) | Computerized systems and methods for anonymous collaborative auctions | |
| CN116611796A (en) | Exception detection method and device for store transaction data | |
| Król | The Application of Hedonic Methods in Quality-Adjusted Price Indices | |
| Hackl et al. | How to measure product differentiation | |
| CN118864014B (en) | Mobile phone advertising delivery method and system | |
| Hackl et al. | Measuring Product Differentiation by Observing Consumer Search | |
| CN117495430A (en) | A system and method for college student entrepreneurship based on data analysis | |
| KR20220163088A (en) | Shopping mall product exposure information provision system and method | |
| CN114663237A (en) | Data acquisition and analysis method and equipment based on online transaction platform and computer storage medium | |
| CN111523688A (en) | Computer hardware valuation system and method thereof | |
| WO2006134587A1 (en) | A system and method for delivering real-time information regarding dynamic content |
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 |