CN116894692A - Method and system for analyzing and monitoring potential demands of online network sales users - Google Patents
Method and system for analyzing and monitoring potential demands of online network sales users Download PDFInfo
- Publication number
- CN116894692A CN116894692A CN202311159542.9A CN202311159542A CN116894692A CN 116894692 A CN116894692 A CN 116894692A CN 202311159542 A CN202311159542 A CN 202311159542A CN 116894692 A CN116894692 A CN 116894692A
- Authority
- CN
- China
- Prior art keywords
- commodity
- potential
- recommendation
- user
- information
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012544 monitoring process Methods 0.000 title claims abstract description 33
- 238000011156 evaluation Methods 0.000 claims abstract description 61
- 238000006243 chemical reaction Methods 0.000 claims abstract description 49
- 230000003993 interaction Effects 0.000 claims abstract description 38
- 238000007405 data analysis Methods 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 15
- 230000014509 gene expression Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012512 characterization method Methods 0.000 claims description 2
- 238000013468 resource allocation Methods 0.000 abstract description 6
- 230000006399 behavior Effects 0.000 description 24
- 230000000694 effects Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 239000008267 milk Substances 0.000 description 2
- 210000004080 milk Anatomy 0.000 description 2
- 235000013336 milk Nutrition 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method and a system for analyzing and monitoring potential demands of online network sales users, and relates to the technical field of data analysis; the method comprises the following steps: the method comprises the steps of collecting commodity purchase conversion information and commodity purchase duration information of a user in an online network sales platform, generating potential demand indexes by the commodity purchase conversion information and the commodity purchase duration information, comparing the potential demand indexes with a set threshold value, classifying and marking the user according to a comparison result to realize resource allocation of different types of users, collecting attention commodity information including category interaction information and marketing characteristic information, generating commodity recommendation indexes, comparing the commodity recommendation indexes with a recommendation evaluation threshold value, generating recommendation commodity signals and standard recommendation signals, immediately marking commodities for generating recommendation commodity signals, establishing commodity recommendation index data sets, comprehensively analyzing commodity heat states, and therefore time for browsing commodities by the user is saved, and conversion of commodities and funds is accelerated.
Description
Technical Field
The application relates to the technical field of data analysis, in particular to a method and a system for analyzing and monitoring potential demands of online network sales users.
Background
The online network selling platform is a platform for providing goods and services through the Internet, so that users can make shopping, transaction and payment online, the platform can cover various product and service fields, from electronic products, fashion clothing to foods, household articles and the like, the users can browse and purchase goods anytime and anywhere without geographical limitation, and a large number of different types of goods and brands are available on the platform.
The prior art has the following defects: with the development of internet technology and electronic commerce, new changes are generated from analysis of shopping psychology and behaviors of consumers, in an online shopping environment, differences between potential shopping demands and explicit shopping demands of users influence shopping of users, explicit shopping demands are explicitly expressed by users and indicate that the users have buying intention, while the potential shopping demands are demands which are not explicitly expressed by the users but may develop into buying intention in the future, such as browsing behaviors of the users, message comments, social sharing and other data, and serious defects exist in analysis and monitoring of the potential shopping demands of the users, so that potential shopping intention of the users cannot be clearly analyzed, pushing of related goods or services is influenced, accurate recommendation of goods of the potential shopping demands of the users cannot be performed, more time is consumed for browsing and selecting when the users purchase goods, and shopping experience of the users is influenced.
The above information disclosed in the background section is only for enhancement of understanding of the background of the disclosure and therefore it may include information that does not form the prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
The application aims to provide a method and a system for analyzing and monitoring potential demands of online network sales users, which are used for solving the defects in the background technology.
In order to achieve the above object, the present application provides the following technical solutions: a potential demand analysis and monitoring method for online network sales users comprises the following steps;
collecting purchasing behavior information of a user in an online network sales platform, wherein the purchasing behavior information comprises commodity purchasing conversion information and commodity purchasing duration information, and generating potential demand indexes by the commodity purchasing conversion information and the commodity purchasing duration information;
comparing the generated potential demand index with a first threshold value of the potential evaluation and a second threshold value of the potential evaluation, and marking the user as an explicit user, a potential user and a browsing user according to the comparison result;
collecting commodity information of interest of a potential user, wherein the commodity information of interest comprises category interaction information and marketing characteristic information, and the category interaction information and the marketing characteristic information are combined to generate commodity recommendation indexes;
comparing the commodity recommendation index with a recommendation evaluation threshold value to generate a commodity recommendation signal and a standard recommendation signal;
and marking the commodity generating the commodity recommending signal in real time, marking commodity recommending indexes generated at the subsequent moment of the commodity, establishing a commodity recommending index data set for analysis, and recommending the commodity meeting the standard to the potential user.
Preferably, the commodity purchase conversion information comprises commodity click conversion coefficients and is calibrated asThe commodity purchase duration information comprises commodity ordering span duration value and is calibrated asThe category interaction information comprises commodity category click average ratio and commodity interaction sharing coefficient and is respectively calibrated as、Marketing-characterization information including area-purchase floating factor is calibrated to。
Preferably, the logic for acquiring commodity click conversion coefficient and time length value of next span is as follows:
acquiring the number of times that each commodity is clicked by a user and establishing pointsSet of strokesAcquiring actual purchase times corresponding to each commodity clicked and establishing a purchase time set,Calculating total click times of the click times set and total purchase times of the purchase times set as positive integers, respectively marking as、The calculation expressions are respectively:、calculating the total clicking times and the total purchasing times to obtain commodity clicking conversion coefficients, wherein the calculated expression is:;
acquiring all time of historical commodity browsing when a user places a commodity, wherein the time of browsing the commodity for the first time and the time of browsing the commodity for the last time are DSJ and ZSJ respectively, and acquiring the total browsing times LC of the commodity in all time of historical commodity browsing by the user, wherein the calculation expression of the single span duration value under the commodity is as follows:。
preferably, the commodity purchase conversion information and the commodity purchase duration information are used for generating potential demand indexes according to the following formula:in which, in the process,、respectively, commodity click conversion coefficientsTime length value of commodity ordering spanIs a preset proportionality coefficient of (1), and、are all greater than 0.
Preferably, the generated potential demand index is compared with a first threshold value of the potential evaluation and a second threshold value of the potential evaluation, and the users are marked as dominant users, potential users and browsing users according to the comparison result, and the specific process is as follows:
comparing the generated potential demand index with a first threshold value and a second threshold value of the potential evaluation, wherein the first threshold value of the potential evaluation is larger than the second threshold value of the potential evaluation, and classifying the marks of the users according to the comparison result;
if the potential demand index is smaller than or equal to the first threshold value of the potential evaluation and larger than the second threshold value of the potential evaluation, marking the user as a potential user;
if the potential demand index is greater than the first threshold value of the potential evaluation, marking the user as an explicit user;
and if the potential requirement index is less than or equal to the second threshold value of the potential evaluation, marking the user as a browsing user.
Preferably, the logic for acquiring commodity category click-to-average ratio, commodity interaction sharing coefficient and regional purchase floating coefficient is as follows:
acquiring the clicking times of the potential users on the commodity refers to the total clicking times of the potential users on the commodity, and acquiring the average clicking times of all the potential users on the commodity class refers to all the potential users on the commodityDividing the total clicking times on the category by the commodity category number, dividing the clicking times of the potential users on the commodity by the average clicking times of all the potential users on the commodity category as the commodity category clicking average ratio;
Acquiring the number of times of commodity marketing information received during the online time period of the potential user, marking the number as TN, acquiring the proportion of the potential user clicking the commodity marketing information as marketing weight Qz, acquiring the number of times of sharing the commodity during the online time period of the potential user, marking the number as FN, and acquiring the total number of times of ordering XN received by the commodity during the online time period of the potential user, wherein the expression of calculating the commodity interaction sharing coefficient is as follows:;
acquiring commodity sales quantity of each unit time in the regional time period of the potential user, and establishing a sales quantity set,Calculating sales average of sales quantity set as positive integerThe sales standard deviation of the sales quantity set is calculated as follows:the area purchase floating factor is calculated as:。
preferably, the category interaction information and the marketing feature information are combined to generate commodity recommendation indexes according to the following formula:in which, in the process,、、respectively, commodity category click average ratioCommodity interaction sharing coefficientArea purchase floatIs a preset proportionality coefficient of (1), and、、are all greater than 0.
Preferably, comparing the commodity recommendation index with a recommendation evaluation threshold to generate a recommended commodity signal and a standard recommendation signal, wherein the specific steps are as follows:
comparing the commodity recommendation index with a recommendation evaluation threshold;
if the commodity recommendation index is smaller than the recommendation evaluation threshold, generating a standard commodity signal;
and if the commodity recommendation index is greater than or equal to the recommendation evaluation threshold, generating a commodity recommendation signal.
Preferably, the method comprises the steps of immediately marking the commodity generating the commodity recommendation signal, marking the commodity recommendation index generated at the subsequent moment of the commodity, establishing a commodity recommendation index data set, and comprehensively analyzing the commodity heat state, wherein the specific steps are as follows:
marking the commodity generating the commodity recommending signal in real time, marking commodity recommending indexes generated at the subsequent moment of the commodity, and establishing a commodity recommending index data set;
calculating the average value and standard deviation of commodity recommendation indexes in the commodity recommendation index data set;
for each data, calculating the deviation value between the data and the mean value to obtain an outlier degree value, wherein the specific formula for obtaining the outlier degree value is as follows:whereinData points within the index data set are recommended for the commodity,a mean value of the index data set is recommended for the commodity,recommending standard deviation of an index data set for the commodity;
comparing the outlier degree value of the data in the commodity recommendation index data set with a set outlier threshold, and recording the data as an outlier when the outlier degree value of the data in the data set is smaller than or equal to a discrete threshold;
when the number of the outliers is smaller than or equal to the set number threshold, judging that the recommended heat degree of the commodity is stable and large, recommending the commodity to a potential user, and performing key monitoring on the commodity.
The application also provides an online network sales user potential demand analysis monitoring system which comprises a data acquisition module, a data processing module, a data analysis module and a monitoring recommendation module;
the data acquisition module acquires purchasing behavior information of a user, wherein the purchasing behavior information comprises commodity purchasing conversion information and commodity purchasing duration information, acquires attention commodity information of a potential user, and transmits acquired data to the data processing module, wherein the attention commodity information comprises category interaction information and marketing characteristic information;
the data processing module receives the data sent by the data acquisition module, generates potential demand indexes from commodity purchase conversion information and commodity purchase duration information, generates commodity recommendation indexes from category interaction information and marketing characteristic information, and sends the commodity recommendation indexes to the data analysis module;
the data analysis module receives the data sent by the data processing module, compares the potential demand index with a first threshold value of the potential evaluation and a second threshold value of the potential evaluation, marks the users as dominant users, potential users and browsing users, and sends commodity recommendation indexes and a recommendation evaluation threshold value to generate a recommendation commodity signal and a standard recommendation signal, and the data is sent to the monitoring recommendation module;
the monitoring recommendation module receives the data sent by the data analysis module, instantly marks the commodity generating the commodity recommendation signal, marks the commodity recommendation index generated at the subsequent moment of the commodity, establishes a commodity recommendation index data set for analysis, and recommends the commodity meeting the standard to the potential user.
In the technical scheme, the application has the technical effects and advantages that:
according to the method, the purchasing behavior information of the user in the online network sales platform is analyzed, commodity purchasing conversion information and commodity purchasing duration information in the purchasing behavior information are combined to generate potential demand indexes, the generated potential demand indexes are compared with a first threshold value and a second threshold value of potential evaluation, the user is classified according to comparison results, shopping habits of the user are obtained through analysis, the user has more definite resource allocation, commodity recommendation is carried out on the potential user, various types of commodities are analyzed, proper commodities are selected for pushing, category interaction information of the commodities is collected and combined with marketing feature information to generate commodity recommendation indexes, the commodity recommendation indexes are compared with recommendation evaluation threshold values, different recommendation signals are generated according to comparison results, real-time recording is carried out on the generated recommendation signals as recommendation commodity signals, and the overall heat state of the commodities is determined, so that the accurate pushing of the commodities of the potential user is achieved, the time of browsing the commodities of the potential user is saved, and the conversion of commodities and funds is accelerated.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings for those skilled in the art.
Fig. 1 is a schematic flow chart of a method and a system for analyzing and monitoring potential demands of online network sales users according to the present application.
Fig. 2 is a schematic structural diagram of a method and a system for analyzing and monitoring potential demands of online network sales users according to the present application.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.
Example 1: the application provides a method for analyzing and monitoring potential demands of online network sales users, which is shown in fig. 1, and comprises the following steps:
in an online shopping environment, users present diversified habits on the purchasing behavior of commodities, the habit differences reflect different physical attitudes and behavior patterns of the users in purchasing decisions, and particularly, a part of users present firmer purchasing decisions, the purchasing goals of the commodities are quite clear, the users tend to quickly decide to purchase after a relatively short browsing process, the users do not need excessive comparison and hesitation, and the users pay more attention to the characteristics of the commodities, and once the demands of the users are met, the users do not hesitate to purchase.
On the other hand, some users tend to make judicious purchases, they show relatively high hesitation in purchase decisions, such users can make multiple commodity comparisons, different factors such as product parameters, prices, quality and the like can play an important role in their decision process, they can make multiple browses on a network sales platform, and collect relevant commodity information to ensure that they make the most intelligent purchase choices, and such careful attitude may mean that they pay more attention to the long-term value of the purchase, i.e. the potential purchase intention of the users is strong, and more knowledge about the commodities is needed.
At the same time, some users tend to limit shopping behavior to the browsing phase of merchandise, they may browse multiple merchandise pages, focusing on merchandise characteristics and prices, but not as urgent as purchasing decisions may be made because they are in the cognitive phase of merchandise or browsing for entertainment and exploration purposes only, and such users' browsing behavior of merchandise may help to enhance understanding of market trends and new merchandise, an important potential browsing user.
The buying behavior habits of different users in the online shopping environment cover a wide range from the fast decision buying to the cautious comparison to the pure browsing, the behavior difference can help online merchants to better meet the demands of the users, optimize the user experience and marketing strategies, analyze the potential shopping demands of the users of the online sales platform, classify the users according to analysis results, and allocate corresponding pushing resources to the users of different classifications, so that the commodity pushing mode among the users is defined.
And acquiring purchasing behavior information of the user in the online network sales platform, wherein the purchasing behavior information comprises commodity purchasing conversion information and commodity purchasing duration information, and analyzing different potential demand degrees of the user through the acquired information.
The commodity purchase conversion information comprises commodity click conversion coefficients, the commodity purchase time length information comprises commodity ordering span time length values, and after acquisition, the commodity click conversion coefficients and the commodity ordering span time length values are respectively calibrated as、。
The commodity click conversion coefficient in the commodity purchase conversion information plays an important role in analyzing the potential demands of the user, and the commodity click conversion coefficient represents the situation that the user clicks between a specific commodity and the final actually purchased commodity, and has the following roles in the analysis user:
personalized recommendation: analyzing click-through conversion coefficients can understand the user's purchasing preferences, for a broken purchaser, can recommend items that fit their interests to promote purchasing behavior, while for a discreet purchaser, providing more detailed comparison and assessment information;
purchasing decision style identification: by analyzing the commodity click conversion coefficient, the purchase decision styles of different users can be distinguished, and for users with higher click conversion coefficients, the judgment is more prone to breaking purchase without multiple comparisons, and for users with lower click conversion coefficients, comparison and consideration are possibly more focused;
marketing strategy optimization: knowing the purchase decision style of the user optimizes marketing strategies, for broken purchasers, time-limited offers and urgency can be emphasized, causing them to purchase faster, while for discreet purchasers, more commodity comparisons and evaluations can be provided, reducing hesitation before purchase.
The acquisition logic of commodity click conversion coefficient is as follows:
acquiring the times of clicking each commodity by a user and establishing a clicking times setAcquiring actual purchase times corresponding to each commodity clicked and establishing a purchase time set,Calculating total click times of the click times set and total purchase times of the purchase times set as positive integers, respectively marking as、The calculation expressions are respectively:、calculating the total clicking times and the total purchasing times to obtain commodity clicking conversion coefficients, wherein the calculated expression is:。
the number of times of clicking each commodity by the user is acquired in a set time period, and the number of times of clicking each commodity and the number of times of purchasing each commodity in the set time period are recorded.
The commodity ordering span duration value in the commodity purchasing duration information plays an important role in analyzing the potential demands of users, and the commodity ordering span duration value represents the time length condition of the user after browsing or clicking the commodity and the commodity ordering purchase actually has the following roles in the analysis users:
purchase decision path: the span length may reveal the user's steps on the purchase decision path, some users may need to browse and compare multiple times, while others may make decisions in a short time;
purchase intent intensity: the value of the commodity ordering span duration can also reflect the purchase intention intensity of the user, a shorter duration can suggest that the purchase intention of the user is higher, the purchase satisfaction requirement is strong, and conversely, a longer duration can indicate that the purchase intention is not strong and more time is needed to consider whether to purchase the commodity or not;
purchase decision speed: the value of the time span for the merchandise may reveal the user's decision making speed for purchase after clicking the merchandise, a shorter time period may indicate that the user's decision making for purchase is quicker, and a longer time period may mean that the user needs more time to consider and compare.
The logic for acquiring the commodity ordering single span duration value is as follows:
acquiring all time of historical commodity browsing when a user places a commodity, wherein the time of browsing the commodity for the first time and the time of browsing the commodity for the last time are DSJ and ZSJ respectively, and acquiring the total browsing times LC of the commodity in all time of historical commodity browsing by the user, wherein the calculation expression of the single span duration value under the commodity is as follows:。
it should be noted that, the time of browsing the commodity for the first time and the time of browsing the commodity for the last time represent the time of contacting the commodity for the first time and the time of ordering the commodity.
Comprehensively analyzing shopping habits of users according to commodity purchase conversion information and commodity purchase duration information, and obtaining user attribute classification types according to analysis results;
the obtained commodity click conversion coefficient and commodity single span duration value are subjected to dimensionless treatment, a potential demand index is generated after a unit is removed, and the potential demand index is calibrated as followsThe formula according to is:in which, in the process,、respectively, commodity click conversion coefficientsTime length value of commodity ordering spanIs a preset proportionality coefficient of (1), and、greater than 0.
As can be seen from the formula, the larger the commodity click conversion coefficient is, the smaller the single span duration value under the commodity is, namely the potential demand indexThe larger the expression value of the commodity is, the higher the potential demand index shows that the purchasing decision of the user is broken and the purchasing speed is high, the purchasing demand is relatively high, the smaller the commodity click conversion coefficient is, the larger the commodity ordering span duration value is, namely the potential demand indexThe smaller the performance value of (c), the more careful and slower the user purchase decision, and the weaker the user purchase demand.
Comparing the potential demand index with a preset potential evaluation threshold value, classifying the users into different classifications, and further knowing the purchasing behavior mode and demand characteristics of the users according to classification results so as to optimize marketing strategies;
comparing the generated potential demand index with a first threshold value and a second threshold value of the potential evaluation, wherein the first threshold value of the potential evaluation is larger than the second threshold value of the potential evaluation, and classifying users according to the comparison result;
after the generated potential demand index is obtained, the generated potential demand index is respectively compared with a first threshold value of the potential evaluation and a second threshold value of the potential evaluation, if the potential demand index is smaller than or equal to the first threshold value of the potential evaluation and larger than the second threshold value of the potential evaluation, the user is marked as a potential user, the purchasing decision of the user is relatively cautious, more time and comparison are needed to make the purchasing decision, a higher hesitation state is held for purchasing behavior, and the user is more monitored for resource allocation;
if the potential demand index is greater than the first threshold value of the potential evaluation, marking the user as an explicit user, which indicates that the decision speed and the fragility of the user when purchasing goods are higher, and the user is more prone to rapidly complete purchasing, and normally monitoring resource allocation is carried out on the user;
and if the potential demand index is smaller than or equal to the second threshold value of the potential evaluation, marking the user as a browsing user, indicating that the user belongs to more browsing behaviors, and carrying out normal monitoring resource allocation on the user.
It should be noted that, marking a user as a potential user does not mean that the user does not purchase intent or does not purchase goods, but rather, simply means that the user's purchase decision is relatively cautious, and requires more information and time to make a decision, and in multiple time windows, the potential user may become an explicit user due to different categories of goods purchased in different time windows, and the explicit user may also be converted to a potential user, for example, the first user may be classified as a potential user when purchasing a commodity, and the first user may be classified as an explicit user when purchasing an electronic product.
According to the method, the purchasing behavior information of the user in the online network sales platform is analyzed, commodity purchasing conversion information and commodity purchasing duration information in the purchasing behavior information are combined to generate potential demand indexes, the generated potential demand indexes are compared with a first threshold value of potential evaluation and a second threshold value of potential evaluation, the user is classified according to the comparison result, shopping habits of the user are obtained through analysis, and the method has more definite resource allocation to the user.
Example 2: when a potential user buys goods in advance, a certain degree of hesitation is generated on a purchase decision, and the hesitation may be caused by various factors including uncertainty, purchase risk, comparison of different options, personal preference and the like.
Collecting focused commodity information of a potential user, wherein the focused commodity information comprises category interaction information and marketing characteristic information, and the category interaction information comprisesThe commodity category click-to-average ratio, the commodity interaction sharing coefficient and the marketing characteristic information comprise regional purchase floating coefficients, and after acquisition, the commodity category click-to-average ratio, the commodity interaction sharing coefficient and the regional purchase floating coefficients are respectively calibrated as、、。
The commodity class click average ratio has an important influence on the popularity of the analyzed commodity, and the commodity class click average ratio represents the ratio of the number of clicks of the potential user on the commodity to the average number of clicks of all the potential users on the commodity class, and the commodity class click average ratio plays the following roles in commodity analysis:
personalized recommendation: the commodity category clicking average value ratio is used for identifying the relative preference of the potential user to the specific commodity category, and the platform can customize and recommend commodities which are more in line with the interests of the user, so that the purchase conversion rate is improved;
market segment: by analyzing the commodity category click average ratio, the potential users can be subdivided into groups with different interest degrees in different commodity categories, so that the marketing activities can be developed more pertinently, and the requirements of the potential users with different interests can be met.
The acquisition logic of the commodity category click average ratio is as follows:
the method comprises the steps of obtaining the clicking times of potential users on commodities refers to the total clicking times of the potential users on the commodities, obtaining the average clicking times of all the potential users on commodity categories refers to the total clicking times of all the potential users on the commodity categories divided by the commodity category number, and dividing the clicking times of the potential users on the commodities by the average clicking times of all the potential users on the commodity categories to be used as the commodity category clicking average ratio。
It should be noted that the number of clicks of the commodity and the total number of clicks on the commodity category are the same commodity and the category of the upper level thereof, for example, the commodity is defatted pure milk, the upper level commodity category is pure milk, and the number of clicks of the commodity and the total number of clicks on the commodity category are obtained through user data stored in an online network sales platform.
The commodity interaction sharing coefficient represents the relationship between the potential users and commodity interaction sharing, influences the purchase intention of the potential users, and has the following effects on commodity analysis:
interest and preference: the high commodity interactive sharing coefficient generally indicates that the commodity induces great interests and favorites of users, and the users are willing to purchase the commodity with multiple sharing times, so that the purchasing demands of masses can be met;
recommendation and public praise: the commodity interaction sharing coefficient is considered as a sort of public praise and recommendation, and users introduce friends, family or attention to commodities worth purchasing, and the generation of the public praise effect has positive effects on attracting new potential users and increasing sales conversion rate.
The acquisition logic of the commodity interaction sharing coefficient is as follows:
acquiring the number of times of commodity marketing information received during the online time period of the potential user, marking the number as TN, acquiring the proportion of the potential user clicking the commodity marketing information as marketing weight Qz, acquiring the number of times of sharing the commodity during the online time period of the potential user, marking the number as FN, and acquiring the total number of times of ordering XN received by the commodity during the online time period of the potential user, wherein the expression of calculating the commodity interaction sharing coefficient is as follows:。
when the concurrent power supply balance value and the data linkage conflict rate are obtained, data acquisition can be performed according to divided data acquisition time periods, the specific data acquisition time periods are divided according to actual conditions, and analog analysis can be performed on each data acquisition time period.
The regional purchase floating coefficient represents sales floating conditions of commodities in the region where the potential user is located and is used for evaluating sales and marketing conditions of the commodities in the region, the regional purchase floating coefficient influences purchase intention of the potential user, the number of the potential user purchases in the region is large, the potential user can generate more interests on the commodities and has more purchase tendency, and the regional purchase floating coefficient has the following effects on analysis of the commodities:
marketing strategy optimization: the regional purchase floating coefficient can guide the formulation and adjustment of marketing strategies, a lower floating coefficient can mean that the sales volume of the commodity is stable, the commodity is in a stable sales state, and a higher floating coefficient means that the sales volume is increased in the region, and the commodity is in a hot sales state;
demand fluctuation prediction: by analyzing the change trend of the regional purchasing floating coefficient, the fluctuation of commodity demand in different regions can be predicted, so that the marketing planning, the production arrangement and the purchasing decision are made.
The acquisition logic for the region purchase floating coefficients is as follows:
acquiring commodity sales quantity of each unit time in the regional time period of the potential user, and establishing a sales quantity set,Calculating sales average of sales quantity set as positive integerThe sales standard deviation of the sales quantity set is calculated as follows:the area purchase floating factor is calculated as:。
it should be noted that, each unit time in the regional time period is divided according to actual conditions, and can be adjusted in unit time, and the commodity sales number is counted according to the region where the user receiving address is located in the online network sales platform.
The obtained commodity category click average value ratio, commodity interaction sharing coefficient and regional purchase floating coefficient are subjected to dimensionless processing, and after units are removed, commodity recommendation indexes are generated and calibrated asThe formula according to is:
in which, in the process,、、respectively, commodity category click average ratioCommodity interaction sharing coefficientArea purchase floatIs a preset proportionality coefficient of (1), and、、are all greater than 0.
As can be seen from the formula, the larger the commodity category click-through average ratio is, the larger the commodity interaction sharing coefficient is, the larger the regional purchase floating coefficient is, namely the commodity recommendation indexThe larger the expression value of (2)The larger the probability that the commodity meets the requirement of the potential user is, the smaller the commodity class click average ratio is, the smaller the commodity interaction sharing coefficient is, the smaller the regional purchase floating coefficient is, namely the commodity recommendation index isThe smaller the performance value of (c), the less likely that the item meets the needs of the potential user.
Comparing the commodity recommendation index with a recommendation evaluation threshold, wherein the specific process is as follows:
if the commodity recommendation index is smaller than the recommendation evaluation threshold, generating a standard commodity signal, wherein the probability of meeting the shopping requirement of the potential user is small, wherein the probability is that the commodity purchase heat is lower;
if the commodity recommendation index is greater than or equal to the recommendation evaluation threshold, a recommendation commodity signal is generated, the commodity is indicated to be high in purchasing heat, and the probability of meeting the shopping requirement of the potential user is high.
Marking the commodity generating the commodity recommending signal in real time, marking commodity recommending indexes generated at the subsequent moment of the commodity, establishing a commodity recommending index data set, calculating the mean value and standard deviation in the data set to obtain outlier degree values of the commodity recommending indexes, and determining the commodity recommending heat state;
calculating the mean value and standard deviation of commodity recommendation indexes in the data set;
for each data, calculating the deviation value between the data and the mean value to obtain an outlier degree value, wherein the specific formula for obtaining the outlier degree value is as follows:whereinData points within the index data set are recommended for the commodity,a mean value of the index data set is recommended for the commodity,recommending index data sets for goodsStandard deviation of the sum;
comparing the outlier degree value of the data in the commodity recommendation index data set with a set outlier threshold, when the outlier degree value of the data in the data set is smaller than or equal to the discrete threshold, indicating that the outlier degree of the commodity recommendation index of the commodity is small, recording the data as outliers, and when the number of the outliers is smaller than or equal to the set number threshold, judging that the recommended heat degree of the commodity is stable and large, and recommending the commodity to a potential user.
According to the application, the potential user carries out commodity recommendation, analyzes various types of commodities, selects proper commodities to push, generates commodity recommendation indexes by collecting class interaction information and marketing characteristic information of the commodities and combining the commodity recommendation indexes with a recommendation evaluation threshold value, generates different recommendation signals according to comparison results, and carries out real-time recording on the generated recommendation signals as recommendation commodity signals to determine the overall heat state of the commodities, thereby realizing accurate pushing of the commodities of the potential user, saving the time of browsing the commodities by the potential user and accelerating the conversion of the commodities and funds.
Example 3: the application provides an online network sales user potential demand analysis monitoring system as shown in fig. 2, which comprises a data acquisition module, a data processing module, a data analysis module and a monitoring recommendation module;
the data acquisition module acquires purchasing behavior information of a user, wherein the purchasing behavior information comprises commodity purchasing conversion information and commodity purchasing duration information, acquires attention commodity information of a potential user, and transmits acquired data to the data processing module, wherein the attention commodity information comprises category interaction information and marketing characteristic information;
the data processing module receives the data sent by the data acquisition module, generates potential demand indexes from commodity purchase conversion information and commodity purchase duration information, generates commodity recommendation indexes from category interaction information and marketing characteristic information, and sends the commodity recommendation indexes to the data analysis module;
the data analysis module receives the data sent by the data processing module, compares the potential demand index with a first threshold value of the potential evaluation and a second threshold value of the potential evaluation, marks the users as dominant users, potential users and browsing users, and sends commodity recommendation indexes and a recommendation evaluation threshold value to generate a recommendation commodity signal and a standard recommendation signal, and the data is sent to the monitoring recommendation module;
the monitoring recommendation module receives the data sent by the data analysis module, instantly marks the commodity generating the commodity recommendation signal, marks commodity recommendation indexes generated at the subsequent moment of the commodity, establishes a commodity recommendation index data set and comprehensively analyzes the commodity heat state.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
While certain exemplary embodiments of the present application have been described above by way of illustration only, it will be apparent to those of ordinary skill in the art that modifications may be made to the described embodiments in various different ways without departing from the spirit and scope of the application. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive of the scope of the application, which is defined by the appended claims.
It is noted that relational terms such as first and second, and the like, if any, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. The method for analyzing and monitoring the potential demands of online network sales users is characterized by comprising the following steps of;
collecting purchasing behavior information of a user in an online network sales platform, wherein the purchasing behavior information comprises commodity purchasing conversion information and commodity purchasing duration information, and generating potential demand indexes by the commodity purchasing conversion information and the commodity purchasing duration information;
comparing the generated potential demand index with a first threshold value of the potential evaluation and a second threshold value of the potential evaluation, and marking the user as an explicit user, a potential user and a browsing user according to the comparison result;
collecting commodity information of interest of a potential user, wherein the commodity information of interest comprises category interaction information and marketing characteristic information, and the category interaction information and the marketing characteristic information are combined to generate commodity recommendation indexes;
comparing the commodity recommendation index with a recommendation evaluation threshold value to generate a commodity recommendation signal and a standard recommendation signal;
and marking the commodity generating the commodity recommending signal in real time, marking commodity recommending indexes generated at the subsequent moment of the commodity, establishing a commodity recommending index data set for analysis, and recommending the commodity meeting the standard to the potential user.
2. According to claim 1The method is characterized in that commodity purchase conversion information comprises commodity click conversion coefficients and is calibrated asThe commodity purchase duration information comprises a commodity ordering span duration value and is marked as +.>The category interaction information comprises commodity category click average ratio and commodity interaction sharing coefficient and is respectively calibrated as +.>、/>Marketing-characterization information includes area purchase floating factor calibrated +.>。
3. The method for analyzing and monitoring potential needs of online network sales users according to claim 2, wherein the acquiring logic of commodity click conversion coefficient and next span duration value is as follows:
acquiring the times of clicking each commodity by a user and establishing a clicking times setAcquiring actual purchase times corresponding to clicking each commodity and establishing a purchase times set +.>,/>Calculating total click times of the click times set and total purchase times of the purchase times set as positive integers, respectively marked as +.>、/>The calculation expressions are respectively: />、/>Calculating the total clicking times and the total purchasing times to obtain commodity clicking conversion coefficients, wherein the calculated expression is: />;
Acquiring all time of historical commodity browsing when a user places a commodity, wherein the time of browsing the commodity for the first time and the time of browsing the commodity for the last time are DSJ and ZSJ respectively, and acquiring the total browsing times LC of the commodity in all time of historical commodity browsing by the user, wherein the calculation expression of the single span duration value under the commodity is as follows:。
4. the method for analyzing and monitoring potential needs of online network sales users according to claim 3, wherein the commodity purchase conversion information and the commodity purchase duration information are used for generating potential needs indexes according to the following formula:
wherein->、/>Respectively, commodity click conversion coefficients/>Time length value of commodity order>Is a preset proportionality coefficient of>、/>Are all greater than 0.
5. The method for analyzing and monitoring the potential demand of online network sales users according to claim 4, wherein the generated potential demand index is compared with a first threshold value for potential evaluation and a second threshold value for potential evaluation, and the users are marked as dominant users, potential users and browsing users according to the comparison result, and the specific process is as follows:
comparing the generated potential demand index with a first threshold value and a second threshold value of the potential evaluation, wherein the first threshold value of the potential evaluation is larger than the second threshold value of the potential evaluation, and classifying the marks of the users according to the comparison result;
if the potential demand index is smaller than or equal to the first threshold value of the potential evaluation and larger than the second threshold value of the potential evaluation, marking the user as a potential user;
if the potential demand index is greater than the first threshold value of the potential evaluation, marking the user as an explicit user;
and if the potential requirement index is less than or equal to the second threshold value of the potential evaluation, marking the user as a browsing user.
6. The method for analyzing and monitoring potential needs of online sales users according to claim 5, wherein the logic for acquiring commodity category click-to-average ratio, commodity interaction sharing coefficient and regional purchase floating coefficient is as follows:
acquiring the clicking times of potential users on commoditiesThe average clicking times of all the potential users on the commodity category are obtained by dividing the total clicking times of all the potential users on the commodity category by the commodity category number, and the average clicking times of all the potential users on the commodity category is divided by the clicking times of all the potential users on the commodity category as the commodity category clicking average value ratio;
Acquiring the number of times of commodity marketing information received during the online time period of the potential user, marking the number as TN, acquiring the proportion of the potential user clicking the commodity marketing information as marketing weight Qz, acquiring the number of times of sharing the commodity during the online time period of the potential user, marking the number as FN, and acquiring the total number of times of ordering XN received by the commodity during the online time period of the potential user, wherein the expression of calculating the commodity interaction sharing coefficient is as follows:;
acquiring commodity sales quantity of each unit time in the regional time period of the potential user, and establishing a sales quantity set,/>Calculating sales mean of sales set as +.>The sales standard deviation of the sales quantity set is calculated as follows: />The area purchase floating factor is calculated as: />。
7. The method for analyzing and monitoring potential demands of online network sales users according to claim 6, wherein category interaction information and marketing feature information are combined to generate commodity recommendation indexes according to the following formula:
wherein->、/>、/>Click mean ratio of commodity categories respectively +.>Commodity interaction sharing coefficient->Zone purchase float +.>Is a preset proportionality coefficient of (1), and、/>、/>are all greater than 0.
8. The method for analyzing and monitoring potential demands of online network sales users according to claim 7, wherein comparing commodity recommendation indexes with recommendation evaluation thresholds, generating recommended commodity signals and standard recommendation signals comprises the following specific steps:
comparing the commodity recommendation index with a recommendation evaluation threshold;
if the commodity recommendation index is smaller than the recommendation evaluation threshold, generating a standard commodity signal;
and if the commodity recommendation index is greater than or equal to the recommendation evaluation threshold, generating a commodity recommendation signal.
9. The method for analyzing and monitoring potential demands of online network sales users according to claim 8, wherein the method is characterized by marking the commodity generating the recommended commodity signal in real time, marking commodity recommendation indexes generated at the subsequent time of the commodity, establishing a commodity recommendation index data set for analysis, and recommending the commodity meeting the standard to the potential users, and comprises the following specific steps:
marking the commodity generating the commodity recommending signal in real time, marking commodity recommending indexes generated at the subsequent moment of the commodity, and establishing a commodity recommending index data set;
calculating the average value and standard deviation of commodity recommendation indexes in the commodity recommendation index data set;
for each data, calculating the deviation value between the data and the mean value to obtain an outlier degree value, wherein the specific formula for obtaining the outlier degree value is as follows:wherein->Recommending data points in an index data set for a commodity, +.>Recommending an average value of the index data set for the commodity, +.>Recommending standard deviation of an index data set for the commodity;
comparing the outlier degree value of the data in the commodity recommendation index data set with a set outlier threshold, and recording the data as an outlier when the outlier degree value of the data in the data set is smaller than or equal to a discrete threshold;
and when the number of the outliers is smaller than or equal to the set number threshold, judging that the recommended heat stability of the commodity is large, and recommending the commodity to the potential user.
10. An online network sales user potential demand analysis monitoring system for implementing the method of any one of claims 1-9, comprising a data acquisition module, a data processing module, a data analysis module, and a monitoring recommendation module;
the data acquisition module acquires purchasing behavior information of a user, wherein the purchasing behavior information comprises commodity purchasing conversion information and commodity purchasing duration information, acquires attention commodity information of a potential user, and transmits acquired data to the data processing module, wherein the attention commodity information comprises category interaction information and marketing characteristic information;
the data processing module receives the data sent by the data acquisition module, generates potential demand indexes from commodity purchase conversion information and commodity purchase duration information, generates commodity recommendation indexes from category interaction information and marketing characteristic information, and sends the commodity recommendation indexes to the data analysis module;
the data analysis module receives the data sent by the data processing module, compares the potential demand index with a first threshold value of the potential evaluation and a second threshold value of the potential evaluation, marks the users as dominant users, potential users and browsing users, and sends commodity recommendation indexes and a recommendation evaluation threshold value to generate a recommendation commodity signal and a standard recommendation signal, and the data is sent to the monitoring recommendation module;
the monitoring recommendation module receives the data sent by the data analysis module, instantly marks the commodity generating the commodity recommendation signal, marks the commodity recommendation index generated at the subsequent moment of the commodity, establishes a commodity recommendation index data set for analysis, and recommends the commodity meeting the standard to the potential user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311159542.9A CN116894692B (en) | 2023-09-11 | 2023-09-11 | Method and system for analyzing and monitoring potential demands of online network sales users |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311159542.9A CN116894692B (en) | 2023-09-11 | 2023-09-11 | Method and system for analyzing and monitoring potential demands of online network sales users |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116894692A true CN116894692A (en) | 2023-10-17 |
CN116894692B CN116894692B (en) | 2023-11-24 |
Family
ID=88312374
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311159542.9A Active CN116894692B (en) | 2023-09-11 | 2023-09-11 | Method and system for analyzing and monitoring potential demands of online network sales users |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116894692B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117237024A (en) * | 2023-11-14 | 2023-12-15 | 深圳市诚王创硕科技有限公司 | Popularization method and system for marketing |
CN117273863A (en) * | 2023-11-03 | 2023-12-22 | 零一创造欢乐(深圳)科技有限公司 | Information pushing method based on user demand prediction and electronic commerce system |
CN117670404A (en) * | 2024-02-02 | 2024-03-08 | 深圳市卖点科技股份有限公司 | Intelligent retail management system and method for intelligent display terminal |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106708821A (en) * | 2015-07-21 | 2017-05-24 | 广州市本真网络科技有限公司 | User personalized shopping behavior-based commodity recommendation method |
CN107895299A (en) * | 2017-11-08 | 2018-04-10 | 浙江执御信息技术有限公司 | The exposure sort method and device of a kind of commodity |
CN109685631A (en) * | 2019-01-10 | 2019-04-26 | 博拉网络股份有限公司 | A kind of personalized recommendation method based on big data user behavior analysis |
CN110222272A (en) * | 2019-04-18 | 2019-09-10 | 广东工业大学 | A kind of potential customers excavate and recommended method |
CN111724235A (en) * | 2020-06-09 | 2020-09-29 | 清华大学深圳国际研究生院 | Online commodity recommendation method based on user novelty |
CN112288549A (en) * | 2020-11-18 | 2021-01-29 | 杭州拼便宜网络科技有限公司 | Commodity recommendation list generation method, device and equipment and readable storage medium |
WO2023071404A1 (en) * | 2021-10-29 | 2023-05-04 | 花瓣云科技有限公司 | Recommendation method, electronic device, and storage medium |
CN116308562A (en) * | 2023-02-09 | 2023-06-23 | 重庆商社电子商务有限公司 | Off-line retail user intelligent screening method |
-
2023
- 2023-09-11 CN CN202311159542.9A patent/CN116894692B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106708821A (en) * | 2015-07-21 | 2017-05-24 | 广州市本真网络科技有限公司 | User personalized shopping behavior-based commodity recommendation method |
CN107895299A (en) * | 2017-11-08 | 2018-04-10 | 浙江执御信息技术有限公司 | The exposure sort method and device of a kind of commodity |
CN109685631A (en) * | 2019-01-10 | 2019-04-26 | 博拉网络股份有限公司 | A kind of personalized recommendation method based on big data user behavior analysis |
CN110222272A (en) * | 2019-04-18 | 2019-09-10 | 广东工业大学 | A kind of potential customers excavate and recommended method |
CN111724235A (en) * | 2020-06-09 | 2020-09-29 | 清华大学深圳国际研究生院 | Online commodity recommendation method based on user novelty |
CN112288549A (en) * | 2020-11-18 | 2021-01-29 | 杭州拼便宜网络科技有限公司 | Commodity recommendation list generation method, device and equipment and readable storage medium |
WO2023071404A1 (en) * | 2021-10-29 | 2023-05-04 | 花瓣云科技有限公司 | Recommendation method, electronic device, and storage medium |
CN116308562A (en) * | 2023-02-09 | 2023-06-23 | 重庆商社电子商务有限公司 | Off-line retail user intelligent screening method |
Non-Patent Citations (1)
Title |
---|
王腾宇;: "大数据时代下电子商务个性化推荐系统的分析与设计", 智库时代, no. 08, pages 136 - 137 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117273863A (en) * | 2023-11-03 | 2023-12-22 | 零一创造欢乐(深圳)科技有限公司 | Information pushing method based on user demand prediction and electronic commerce system |
CN117273863B (en) * | 2023-11-03 | 2024-05-28 | 零一创造欢乐(深圳)科技有限公司 | Information pushing method based on user demand prediction and electronic commerce system |
CN117237024A (en) * | 2023-11-14 | 2023-12-15 | 深圳市诚王创硕科技有限公司 | Popularization method and system for marketing |
CN117237024B (en) * | 2023-11-14 | 2024-02-20 | 深圳市诚王创硕科技有限公司 | Popularization method and system for marketing |
CN117670404A (en) * | 2024-02-02 | 2024-03-08 | 深圳市卖点科技股份有限公司 | Intelligent retail management system and method for intelligent display terminal |
CN117670404B (en) * | 2024-02-02 | 2024-05-28 | 深圳市卖点科技股份有限公司 | Intelligent retail management system and method for intelligent display terminal |
Also Published As
Publication number | Publication date |
---|---|
CN116894692B (en) | 2023-11-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116894692B (en) | Method and system for analyzing and monitoring potential demands of online network sales users | |
US11587116B2 (en) | Predictive recommendation system | |
US11587123B2 (en) | Predictive recommendation system using absolute relevance | |
KR102213768B1 (en) | Customer-specific product recommendation system that exposes products with high purchase conversion rate based on customer information by artificial intelligence based on big data | |
JP6325745B2 (en) | Information processing apparatus, information processing method, and information processing program | |
JP6045750B1 (en) | Information processing apparatus, information processing method, and information processing program | |
Lim et al. | Impact of satisfaction with e-retailers’ touch points on purchase behavior: the moderating effect of search and experience product type | |
CN111709813B (en) | Commodity recommendation method based on big data line | |
Chen et al. | Analysis of review helpfulness based on consumer perspective | |
JP5824602B1 (en) | Information processing apparatus, information processing method, and information processing program | |
CN116894709A (en) | Advertisement commodity recommendation method and system | |
CN112085549A (en) | Commodity recommendation method for E-commerce platform based on data processing technology | |
Mykhalchuk et al. | Development of recommendation system in e-commerce using emotional analysis and machine learning methods | |
US10713260B2 (en) | Apparatus, method, and computer-readable recording medium for providing information based on information elements identified by using user history information and estimated viewing duration information | |
JP6914313B2 (en) | Information processing equipment, information processing methods, and programs | |
JP6980573B2 (en) | Information processing equipment, information processing methods, and programs | |
Sekarlingga et al. | Analysis of factors that influence purchase intentions for skintific products using Tiktok shop Indonesia with online trust as mediator variable | |
Nalchigar et al. | A large-scale study of online shopping behavior | |
JP6679705B1 (en) | Information processing apparatus, information processing method, and information processing program | |
Gao et al. | Modeling shopping cart decisions with heterogeneous product involvement and reviews | |
JP7261967B1 (en) | Program, information processing device, and method | |
Tabak Kizgin et al. | Random Forest Based Hybrid Approaches to Analysis of Retail Stores | |
Gangewatta et al. | Factors Affecting Urban Consumer Intention towards Online Purchasing of Agricultural Commodities in Sri Lanka | |
Lunde et al. | How does dynamic pricing affect customer perceived fairness across product necessities? | |
Gao et al. | Modeling Shopping Cart Decisions |
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 |