CN109949065B - Method and device for analyzing attribute data - Google Patents

Method and device for analyzing attribute data Download PDF

Info

Publication number
CN109949065B
CN109949065B CN201711385752.4A CN201711385752A CN109949065B CN 109949065 B CN109949065 B CN 109949065B CN 201711385752 A CN201711385752 A CN 201711385752A CN 109949065 B CN109949065 B CN 109949065B
Authority
CN
China
Prior art keywords
similar
merchants
data
commodity
merchant
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.)
Active
Application number
CN201711385752.4A
Other languages
Chinese (zh)
Other versions
CN109949065A (en
Inventor
高宗
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Original Assignee
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Jingdong Century Trading Co Ltd, Beijing Jingdong Shangke Information Technology Co Ltd filed Critical Beijing Jingdong Century Trading Co Ltd
Priority to CN201711385752.4A priority Critical patent/CN109949065B/en
Publication of CN109949065A publication Critical patent/CN109949065A/en
Application granted granted Critical
Publication of CN109949065B publication Critical patent/CN109949065B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The embodiment of the invention provides a method and a device for attribute data analysis, which can be used for screening according to different dimensions to help merchants find competitors and lock competitive commodities, and can also be used for performing attribute data analysis, attribute value suggestion and attribute value simulation on key commodities in a targeted manner. The method comprises the following steps: acquiring similar merchants of the merchants according to the data signboards of the merchants; screening similar commodities of the merchant commodities by using the data signboards of the similar merchants; and calculating the suggested attribute value of the merchant commodity according to the attribute value interval of the similar commodity.

Description

Method and device for analyzing attribute data
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for attribute data analysis.
Background
With the increasing market competition, merchants on the network trading platform face an increasingly complex sales competition environment. The method has the advantages that reasonable suggested attribute values are accurately and efficiently calculated, and attribute value simulation is implemented, so that the method is particularly important for accurately positioning competitors, fully exerting attribute advantages, effectively targeting and helping merchants obtain more users.
The prior art schemes for attribute value suggestion and attribute value simulation are roughly as follows: 1. adopting the existing online shopping attribute value to determine a model to realize attribute value suggestion; 2. and determining the tool service provider Feedvisor and the third-party attribute value optimizing tools repiers by utilizing the more commonly used attribute values abroad to automatically adjust the attribute values.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art: in the first attribute value suggestion scheme, the attribute value suggestion has a single function, only single-page attribute value suggestion can be realized, the suggestion rule is not clear enough, how pricing is set is not possible, in addition, only specific single products are analyzed, and deep analysis is not considered for competitive commodities and competitive merchants; the proposal related to the second attribute value proposal has larger risk of automatic price adjustment, no competitive analysis of other dimensions except attribute value analysis, and in addition, the analysis tool has no adaptability in domestic environment and thus has no universal applicability.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for attribute data analysis, which can help a merchant to find a competitor by screening according to different dimensions, lock a competitive commodity, and perform attribute value analysis, attribute value suggestion, and attribute value simulation on a key commodity in a targeted manner.
To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided a method of attribute data analysis.
The attribute data analysis method of the embodiment of the invention comprises the following steps: acquiring similar merchants of the merchants from data signboards of the merchants according to a preset similarity rule; screening similar commodities of the merchants by using the data billboard of the similar merchants; and calculating the suggested attribute value of the merchant commodity by using a preset suggested algorithm according to the attribute value interval of the similar commodity.
Optionally, the data billboard comprises at least one of the following information: commodity data, brand data, category data, daily average total volume of transaction data, daily average browsing volume data, key commodity data, commodity price elastic data and commodity price label data.
Optionally, the obtaining of similar merchants of the merchant from the data billboard of the merchant according to the preset similarity rule includes: according to the daily average total volume ranking of merchants under the same brand and/or category dimension, selecting a preset number of merchants from the merchants of the same brand and/or category as candidate similar merchants; and screening similar merchants from the candidate similar merchants according to a preset similarity rule.
Optionally, the screening similar commodities of the merchant commodity by using the data billboard of the similar merchant comprises: and screening the commodities similar to the key commodities of the merchants from the commodity data of the similar merchants to serve as the similar commodities.
Optionally, calculating the suggested attribute value of the merchant commodity by using a preset suggested algorithm according to the attribute value interval of the similar commodity includes: and calculating the suggested attribute value of the merchant commodity by utilizing a four-fencing algorithm and/or a dynamic optimization leading algorithm and/or a target optimization leading algorithm according to the maximum value and the minimum value of the attribute value interval of the similar commodity.
Optionally, the method further comprises: and simulating the predicted sales data of the merchant commodity according to the suggested attribute value.
To achieve the above object, according to another aspect of the embodiments of the present invention, another method for attribute data analysis is provided.
The attribute data analysis method of the embodiment of the invention comprises the following steps: acquiring similar merchants of the merchants from the data signboards of the merchants according to a preset similarity rule; screening similar commodities of the merchant commodities by using the data signboards of the similar merchants; and simulating the predicted sales data of the commodities according to the attribute value interval of the similar commodities.
Optionally, simulating the predicted sales data of the commodity according to the attribute value interval of the similar commodity includes: taking the maximum value of the attribute value interval of the similar commodities as a simulation maximum value, and multiplying the current sales attribute value of the commodities by a preset percentage as a simulation minimum value; and simulating the predicted sales data of the commodity by using a simulation interval consisting of the simulation maximum value and the simulation minimum value.
To achieve the above object, according to still another aspect of the embodiments of the present invention, there is provided an apparatus for attribute data analysis.
The attribute data analysis device of the embodiment of the invention comprises: the acquisition module is used for acquiring similar merchants of the merchants from the data signboards of the merchants according to a preset similarity rule; the screening module is used for screening similar commodities of the merchant commodities by using the data billboard of the similar merchant; and the calculation module is used for calculating the suggested attribute value of the merchant commodity by using a preset suggested algorithm according to the attribute value interval of the similar commodity.
Optionally, the data billboard comprises at least one of the following information: commodity data, brand data, category data, daily average total volume of transaction data, daily average browsing volume data, key commodity data, commodity price elastic data and commodity price label data.
Optionally, the obtaining module is further configured to: according to the daily average total volume ranking of merchants under the same brand and/or category dimension, selecting a preset number of merchants from the merchants of the same brand and/or category as candidate similar merchants; and screening similar merchants from the candidate similar merchants according to a preset similarity rule.
Optionally, the screening module is further configured to: and screening the commodities similar to the key commodities of the merchants from the commodity data of the similar merchants to serve as the similar commodities.
Optionally, the calculation module is further configured to: and calculating the suggested attribute value of the merchant commodity by utilizing a quarterback algorithm and/or a dynamic optimization leading algorithm and/or a target optimization leading algorithm according to the maximum value and the minimum value of the attribute value interval of the similar commodity.
Optionally, the apparatus further comprises: and the simulation module is used for simulating the predicted sales data of the merchant commodities according to the suggested attribute value.
To achieve the above object, according to still another aspect of the embodiments of the present invention, there is provided another attribute data analysis apparatus.
Another attribute data analysis device according to an embodiment of the present invention includes: the acquisition module is used for acquiring similar merchants of the merchants from the data signboards of the merchants according to a preset similarity rule; the screening module is used for screening similar commodities of the merchant commodities by using the data billboard of the similar merchant; and the simulation module is used for simulating the predicted sales data of the commodities according to the attribute value interval of the similar commodities.
Optionally, the simulation module is further configured to: taking the maximum value of the attribute value interval of the similar commodities as a simulation maximum value, and multiplying the current sales attribute value of the commodities by a preset percentage as a simulation minimum value; and simulating the predicted sales data of the commodity by using a simulation interval consisting of the simulation maximum value and the simulation minimum value.
To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided an electronic apparatus.
An electronic device of an embodiment of the present invention includes: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method for attribute data analysis of an embodiment of the present invention.
To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided a computer-readable medium.
A computer-readable medium of an embodiment of the present invention has stored thereon a computer program that, when executed by a processor, implements the method of attribute data analysis of an embodiment of the present invention.
One embodiment of the above invention has the following advantages or benefits: because the technical means that firstly a data billboard based on commodities helps a merchant to find a competitor, then the merchant is helped to lock competitive commodities for attribute value price ratio and attribute value optimization based on commodity brands and categories and attribute value suggestion is carried out, the technical problems that only single-item analysis is carried out, no competitive commodity and competitive commodity analysis is carried out, the automatic price adjustment risk is high and competitive analysis with other dimensions is not carried out are solved, and the technical effects that the merchant is assisted to reasonably calculate the suggested attribute value and deepen the competitive advantage of the attribute value are further achieved; in addition, by acquiring various data signboards, the embodiment of the invention can realize backtracking and drilling depth of the acquired data in the process of attribute value analysis; by selecting a preset number of merchants from the merchants of the same brand and/or category as candidate similar merchants, the commodities can be intelligently classified on the basis of industry competition, so that the competing merchants and the commodities can be accurately matched; the commodities similar to the key commodities of the merchants are screened from the commodity data of the similar merchants to serve as the similar commodities, so that attribute value suggestion can be accurately and efficiently carried out on the key commodities of the merchants, and the efficiency of attribute value development is improved; attribute value suggestion is carried out by using an intelligent suggestion algorithm, so that the attribute value suggestion can be accurately and flexibly carried out according to different pricing requirements of merchants; by using a simulation algorithm to predict commodity sales data including sales volume, gross profit, GMV and the like, the sales condition of the simulated commodity can be provided for reference of a merchant based on the result of the attribute value suggestion; in addition, in one embodiment of the invention, the predicted sales data of the commodities are simulated according to the attribute value interval of the similar commodities, so that the method can assist the merchant to know the sales conditions of other competitors in the same industry, and is beneficial to the merchant to make a correct decision.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of the main steps of a method of attribute data analysis according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a main flow of a method of attribute data analysis according to an embodiment of the present invention;
FIG. 3 is a logic diagram of obtaining a data billboard in a method of attribute data analysis in accordance with an embodiment of the invention;
FIG. 4 is a schematic diagram illustrating a commodity price band in a method for attribute data analysis according to an embodiment of the present invention;
5 a-5 c are schematic diagrams illustrating different user transitions between commodity price bands in a method of attribute data analysis according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a system of commodity price labels according to a quarterward algorithm in a method of attribute data analysis according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a main flow of price suggestion based on a quarterward algorithm in a method of attribute data analysis according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a main flow of price proposal based on a dynamic optimization-dominated algorithm in a method of attribute data analysis according to an embodiment of the present invention;
FIG. 9 is a schematic diagram of a main flow of price proposing based on a target optimization-dominated algorithm in a method of attribute data analysis according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of the main modules of an apparatus for attribute data analysis according to an embodiment of the present invention;
FIG. 11 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 12 is a schematic structural diagram of a computer system suitable for implementing a terminal device or a server according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram of main steps of a method for attribute data analysis according to an embodiment of the present invention, and as shown in fig. 1, the method for attribute data analysis according to an embodiment of the present invention mainly includes the following steps:
step S101: and acquiring similar merchants of the merchants from the data signboards of the merchants according to a preset similarity rule. The step aims at screening similar merchants, and the specific process can comprise the following steps: according to the daily average total volume ranking of merchants under the same brand and/or category dimension, selecting a preset number of merchants from the merchants of the same brand and/or category as candidate similar merchants; and screening similar merchants from the candidate similar merchants according to a preset similarity rule.
Step S102: and screening similar commodities of the merchants by using the data billboard of the similar merchant.
Step S103: and calculating the suggested attribute value of the merchant commodity by using a preset suggested algorithm according to the attribute value interval of the similar commodity.
In the embodiment of the invention, the data billboard mainly comprises at least one of the following information: commodity data, brand data, category data, daily average total volume of transaction data, daily average browsing volume data, key commodity data, commodity price elastic data and commodity price label data.
The purpose of the statistics of the key commodity data is to mainly perform attribute data analysis and suggestion on key commodities of merchants in the process of performing attribute value suggestion on the commodities of the merchants. Such as data with sales ranking top 10. Of course, the number of the important commodities is not limited to 10. In the embodiment of the invention, the key commodity can be defined and selected based on a plurality of dimensions. For example, sales, Page View (hereinafter referred to as "PV"), shopping cart conversion, order generation conversion, etc. In the embodiment of the invention, the attribute value suggestion of 100 commodities can be supported at least, namely the key commodities can be selected to be 100, so that the requirement of a merchant for optimizing the attribute values of the commodities can be met to the maximum extent.
Therefore, in the embodiment of the present invention, the screening of similar products of the merchant products by using the data billboard of the similar merchant may further include: and screening the commodities similar to the key commodities of the merchants from the commodity data of the similar merchants to serve as the similar commodities.
In addition, the aforementioned calculating the suggested attribute value of the merchant commodity according to the attribute value interval of the similar commodity may further include: and calculating the suggested attribute value of the merchant commodity by utilizing a four-fencing algorithm and/or a dynamic optimization leading algorithm and/or a target optimization leading algorithm according to the maximum value and the minimum value of the attribute value interval of the similar commodity.
Based on the calculated suggested attribute value, the method for analyzing attribute data of the embodiment of the present invention may further include a step of simulating the predicted sales data of the merchant commodity according to the suggested attribute value. The primary purpose of this step is to predict expected sales data for the merchant's Merchandise, such as, but not limited to, Gross trades Volume (hereinafter "GMV"), PV, Gross profit, etc., over a period of time, based on the suggested attribute values.
In addition, in another embodiment of the present invention, the method for analyzing attribute data of the present invention can also directly perform attribute value simulation according to similar commodities of similar merchants, that is, simulate the expected sales data of the own commodity according to the attribute value distribution bands of similar commodities of other merchants. The method mainly comprises the following steps:
step S101: acquiring similar merchants of the merchants from data signboards of the merchants according to a preset similarity rule;
step S102: screening similar commodities of the merchants by using the data billboard of the similar merchants; and
step S104 (not shown in the figure): and simulating the predicted sales data of the commodities according to the attribute value interval of the similar commodities.
Specifically, step S104 may be performed by the following logic: taking the maximum value of the attribute value interval of the similar commodities as a simulation maximum value, and multiplying the current sales attribute value of the commodities by a preset percentage as a simulation minimum value; and simulating the predicted sales data of the commodity by using a simulation interval consisting of the simulation maximum value and the simulation minimum value.
In the embodiment of the invention, the attribute data analysis can be realized based on an attribute value open and simulated tracking system, and the system mainly comprises: the system comprises a merchant data billboard (which refers to the overall sales data overview of all the commodities of the merchant and can also comprise a trend chart compared with the commodities of similar merchants), a competitive merchant (which refers to the similar merchants) billboard, a competitive merchant screening module, a key commodity analysis module, an attribute value suggestion module and an attribute value simulation module. Fig. 2 is a schematic diagram of a main flow of a method of attribute data analysis according to an embodiment of the present invention. In the following, taking the analysis of the attribute data of the price of the commodity to obtain the proposed price of the commodity and performing price simulation as an example (of course, the technical solution of the present invention does not only relate to the analysis of the attribute data of the price, but also can propose and simulate other attribute data according to the actual analysis requirement), the details of the components of the system are described with reference to fig. 2:
(1) trade company data billboard module
The data billboard module mainly comprises the following information: the merchant mainly manages the contents such as brands, main management categories, commodity quantity, GMV (gross sales) in the near seven days, browsing volume PV in the near seven days, key commodities, key price bands, price sensitive distribution and the like.
Fig. 3 is a logic diagram of acquiring a data billboard in the method for attribute data analysis according to the embodiment of the invention. As shown in fig. 3, in the embodiment of the present invention, the kanban data, whether of a merchant or of a similar merchant, is obtained basically through the following processes: data to be acquired is synchronized through a timing task from a data storage module (in the embodiment of the present invention, the data storage module may be, but is not limited to, a data warehouse, and the selection of a specific storage module may be preselected based on the size of data volume and the requirement of processing), and whether the data is synchronized is judged by using a flag of a Redis (Redis is an open source, written in ANSI C language, supports a network, can be based on a log-type and Key-Value database which can also be persistent, and provides APIs in multiple languages). And if the Value of the flag is 1, the data is considered to be synchronously completed. At this time, the task scheduling tool Plumber of the data signboard determines, by judging the Value of Value, data that can schedule yesterday (that is, dt ═ sysdate (-1)) (here, for the data type that needs to acquire the data of the previous day, if the data that needs to be acquired in a month cycle, this is the previous month, and so on), otherwise, data of the previous day (that is, dt ═ sysdate (-2)) is used.
Which in turn may be subdivided into the following sub-modules:
a quantity of the commodity comprising: in the embodiment of the invention, the number of the SKUs can be understood as the number of commodities of one category or the number of the commodities individually, and in the embodiment of the invention, the SKU refers to a certain commodity), a major category sales ratio and a major brand sales ratio;
a near seven-day-averaged GMV comprising: yesterday shop total sales, yesterday GMV, yesterday VS previous GMV growth rate, yesterday sales crown military commodity), which is selected as a calculation unit, that is, the data billboard generally only needs to display data analysis of recent days, because a merchant basically logs in a network trading platform every day to pay attention to sales of the commodity of the merchant, including daily average browsing volume, a finer calculation granularity is set, which is helpful for the merchant to obtain a reasonable price suggestion;
a near seven day average PV comprising: yesterday shop UV (unique viewer, which refers to a natural person who accesses and browses the webpage through the internet, in the embodiment of the present invention, may be "independent visitor volume"), yesterday shop PV, PV growth rate before yesterday VS, yesterday PV champion commodity;
a price band consisting essentially of: the price band with the largest number of SKUs and the price band with the smallest number of SKUs in the shop;
a price sensitive distribution comprising: the number of highly elastic items in the store is proportional to the total number of items.
In the embodiment of the present invention, the determination of the elasticity level may be performed by the following logic:
first, the priority of the elastic value can be set according to the accuracy of the calculation as follows: the self elasticity of the commodity > the result with good quality of the random forest algorithm > the result with relatively poor quality > the elasticity of the affiliated brand > the elasticity of the affiliated class.
When calculating elasticity, the updating calculation is carried out by taking three months (the value can be flexibly adjusted according to the actual calculation requirement) as the rolling period. The median elasticity value of all SKUs under the category of the corresponding goods of the merchant is calculated. If the SKU elasticity is higher than the elasticity median value under the category of the shop, the commodity is high in elasticity; if the SKU elasticity is lower than the median elasticity under the category of the store, the merchandise is low elasticity.
In addition, the merchant data billboard module can further comprise the following modules:
industry trend module
And market industry trend analysis based on three-level categories, brands and a certain time range is provided for merchants. Visually displaying the overall trend of the item or the brand over time through flow (PV, UV) and sale month GMV;
merchant trend module
The development trend of the PV \ UV \ GMV of the merchant under the category or brand dimension is consistent with the analysis dimension of the industry trend according to the designated time range selected by the user;
sales scale sorting module
The module provides the marketer with trend analysis based on sales GMV and sales volume and considers GMV ranking to help the marketer know the competition ranking in the market at present;
flow scale sequencing module
Consistent with the sales scale ordering dimension, the module provides PV and UV based trend analysis for the merchants and considers traffic ranking to help the merchants know the competitive ranking in the market at present;
intelligent classification label module for commodities
Based on the intelligent classification labels of the commodities obtained based on the dimensionalities of all SKU traffic (PV, UV and the like), elasticity and the like under the shop, the merchants are informed of the price labels of all the commodities in the shop and the corresponding SKU quantity through unified display; such as: the high-elasticity high-strength.
In the embodiment of the invention, the calculation method for judging the price label of the commodity SKU through the flow and the elasticity comprises the following steps:
1. the judgment flow is high or low:
and selecting all SKUs under the stores of the merchants, and calculating the distribution condition of the total PV of the stores to each SKU by taking the week as a calculation period. The actual PV duty cycles for each SKU are then calculated, taking those above a certain threshold (which may be defined herein as 90 deciles) that are considered high traffic and those below that threshold that are considered low traffic.
2. And (3) judging the elasticity:
selecting all SKUs under the shop of the merchant, taking the elasticity of the SKUs, sorting the SKUs from low to high, taking the value at the 3/4 quantile as the elasticity median, wherein the value greater than the elasticity median is high elasticity, and the value smaller than the elasticity median is low elasticity)
(2) Competitive merchant billboard and competitive merchant screening module
The module provides the merchant with a similar merchant data billboard derived based on a similarity learning algorithm.
In the embodiment of the present invention, according to the main brand or category of the merchant commodity, it may be determined that the merchant with the highest GMV rank (for example, but not limited to, 20 th rank) under the same brand or category is used as the candidate similar merchant set, and then the similar merchants are screened from the candidate similar merchant set based on the following four similarity learning algorithms:
and (3) replacing: calculating the click and jump probability of a user in a store, and listing a list of alternative merchants most likely to form merchant access competition in the same brand or category range;
superposing: calculating the coincidence degree of in-store commodities of the merchant and other merchants, and giving a similar merchant list with high coincidence degree in the range of the same brand or category;
scale: giving out a similar merchant list with the closest sale scale within the same brand or category range by calculating the monthly sale scale of merchants;
height: the union of results is derived based on three dimensions (substitution, coincidence, scale).
In the tracking system with opened and simulated prices in the embodiment of the invention, each similarity learning algorithm can correspond to one screening function, similar merchants in different ranges can be customized by merchants through the screening function, and the system displays a list of the similar merchants based on the selection of the merchants and provides a basic interval of prices for the next key commodity analysis.
In addition, the competitive merchant billboard and the competitive merchant screening module can also comprise an overview of the price bands of the merchants. The merchant price band is mainly used for showing price bands based on item classes and brand dimensions for merchants, and showing the number ratio of SKUs on different price bands in a chart mode through time dimensions, merchant ranking and the like.
The price band is an important information window facing consumers of a brand merchant, a reasonable price band positioning and the richness of the types of commodities on the important price band, and influences the selection preference and consumption cognition of the consumers to a great extent, thereby influencing the brand loyalty. After finding similar merchants, analyzing brand locations of the similar merchants, and regarding whether the similar merchants and the distribution of the similar merchants on the price locations directly conflict or not, whether the similar merchants need to make adjustments on the price belts or not, such as supplement or weakening, and the like.
And analyzing the competition situation by using the price bands, and comparing and analyzing whether the two price bands are consistent or not by displaying the main price bands of the merchant brand and the price bands of similar merchants. And for the consistent price bands existing on both sides, deeply analyzing the competitive relationship between the merchants with GMV ranking close in the price bands. And analyzing the jump relation of the user on different brands and different price bands for the inconsistent price bands, thereby calculating the effect of the price bands on the selection preference of the user.
Fig. 4 is a schematic diagram illustrating a commodity price band in the method for analyzing attribute data according to the embodiment of the present invention. As shown in FIG. 4, the presentation of the merchant's price bands may be based on the price bands of the item class or brand dimension, represented by a bar chart, representing the ratio of the number of SKUs on the different price bands. At the moment, the merchant can also select a plurality of merchants in front of the market and a plurality of merchants in front of and behind the merchant through the function of 'exhibition merchant' to compare and inquire. In the embodiment of the present invention, the price bands of three merchants are displayed as an example.
Fig. 5a to 5c are schematic diagrams illustrating different jumping situations between commodity price bands by a user in the method for analyzing attribute data according to the embodiment of the present invention. FIG. 5a is a schematic diagram of a user jumping between different price bands under the same brand, which can be used to help a merchant to comb the problem of own price structure. FIG. 5b is a schematic diagram of a user jumping between different brands and the same price band, which is used to help merchants combing out the competitive strength of the key price band, thereby assisting in deciding whether the conditions should be improved by adjusting the price or changing the shop layout on the price band. FIG. 5c is a schematic diagram of a user jumping between different brands and under different price bands to help merchants combing out the competitive strengths and weaknesses of the key price bands, so as to assist in deciding whether the conditions should be improved by adjusting the prices or changing the layout of the shops on the price bands or by adjusting the marketing means of the brands.
(3) Key commodity analysis module
The module is used for providing the detailed item-focused list with sales of the shops ranked in the top several digits (as mentioned above, the embodiment of the present invention may actually support more than 100 items-focused items) in the last period of time (for example, but not limited to, 1 month), and the module supports the operations of item sorting, item-focused list export, jumping to the price suggestion module, and the like.
Here, the highlight product may include, but is not limited to, the following information: SKUID, current page price, sales volume, GMV, browsing volume (PV), sensitivity (high sensitivity if price elasticity is high and low sensitivity if price elasticity is low), order conversion rate (the order conversion rate is the number of orders of the SKU in the current day and the payment is completed within 24h after the SKU is successfully placed in the current day), shopping cart conversion rate (the number of orders of the SKU in the current day and the number of times the SKU is added into the shopping cart after the SKU is added into the shopping cart in 24 h), and price label. The data of page price, bargain price, order conversion rate and shopping cart conversion rate are usually based on the latest data, and the sales volume, GMV and browsing volume are usually based on the average of the latest month.
(4) Price suggestion module
The module displays the sales trend analysis of the commodity in the last month according to the input key commodity number (namely SKUID), for example, the overall trend of the commodity developing along with the time is displayed through the flow, the bargain price and the page price. And meanwhile, filtering out a similar commodity list with competitive matching degree from the commodities of similar merchants according to the key commodities.
And then inputting the cost of the key commodity according to the filtered similar commodities so as to calculate the suggested price of the commodity.
In the embodiment of the invention, three suggested price calculation modes are set for merchants to select, wherein the three suggested price calculation modes comprise three dimensions which are respectively as follows: market competition leading (based on a four-component algorithm), dynamic optimization leading and target optimization leading);
the first method comprises the following steps: market competition dominance (four fencing algorithm based)
Fig. 6 is a system diagram illustrating that the price label of the product according to the quarterwise algorithm corresponds to the price interval of the similar product in the method for analyzing the attribute data according to the embodiment of the present invention; the main flow diagram of price suggestion based on the four-fencing algorithm in the grid analysis method is shown. The market competition dominated price proposal algorithm is described in detail below with reference to fig. 6 and 7.
According to the similar goods (competitive goods) selected and confirmed by the merchant, the price range of the goods is firstly determined. And taking the lowest market price of the similar commodities as a left end point and the highest market price as a right end point.
And then carrying out correspondence between the commodity price label classification and the similar commodity price interval classification. Firstly, the distribution situation of the price is checked, and abnormal values are filtered by combining statistical indexes such as variance and the like when the deviation value of the price point is large.
Next, the number of similar products of the product is judged. If the number of the similar commodities is more than or equal to 10, sorting the prices of all the similar commodities from low to high, and dividing 25%, 50%, 75% and 100% according to the positions in the statistical sense to be used as corresponding price points of different price labels (explosive money, high elasticity, potential and long tail); and if the number of the similar commodities is less than 10, carrying out average quartering segmentation on the interval from the maximum value max to the minimum value min of the price range, and determining 25%, 50%, 75% and 100% of the following bisecting positions as corresponding price points of different price labels (explosive money, high elasticity, potential and long tail).
And thirdly, determining the price label system of the commodity according to the flow height and the elasticity height, and further allocating a reasonable price label to each commodity. There are four price labels: respectively high flow and high elasticity (explosion), high flow and low elasticity (potential), low flow and low elasticity (long tail), high elasticity and low flow (high elasticity).
The four price labels are respectively positioned on different grades, namely low grade, middle grade and high grade, in the range of subtracting the minimum value from the maximum value of the market price. For example, if [ min, max ] is [ 80, 100 ], then the quartile is performed for 20 (20/4 is 5), so that the positions are 85, 90, 95, and 100, respectively, and are located at different positions, i.e., low, middle, and high. The corresponding relation between the specific price label and the price interval of the similar commodity is as follows:
high flow and high elasticity: generally, the price strategy is generally positioned on a low price section on the market, and the default of the system is 25% quantile and is close to the Min value.
High flow and low elasticity: generally, the competitive pressure of small commodities in the mass market, such as apple vinegar in beverages, is relatively small, and the commodities have a good price-rising space due to the fact that the commodities are mass-beverages and have a default of a middle-high position of 75% of decimals in a market price range, which is close to a max value.
Low flow and low elasticity: generally, the product is a newly-demanded product in the market of the small people, such as a middle-high-end brand in a shaver, the competition is less, the price is insensitive, and at the moment, the high price is kept in the market price range, and 100 percent of the price is taken.
High elasticity and low flow: the method has the advantages that the increment space is provided in the market of the young people, such as a hammer mobile phone of the old Rou, the flow at first rarely belongs to the relatively small goods, but the product quality is good, the sales volume can be improved through price reduction, more people are attracted to pay attention, and at the moment, the moderate price reduction strategy is appropriate and can adopt a 50% quantile median.
As shown in fig. 6, the proposed price can be obtained by appropriately increasing the price of the commodity in the high-flow low-elasticity middle/high price range, and the price can be converted into high-flow high-elasticity commodity. Or the commodity in the middle price range with high elasticity and low flow rate can obtain the suggested price through price reduction, so that the commodity is converted into the commodity with high elasticity and high flow rate.
And the second method comprises the following steps: dynamic optimization leading algorithm
Fig. 8 is a schematic main flow chart of price suggestion based on a dynamic optimization-dominated algorithm in the method for attribute data analysis according to the embodiment of the invention. As shown in fig. 8, the algorithm is obtained based on elasticity and replacement efficiency learning, and an optimal price for balancing sales and gross profit within a certain price interval can be calculated by using a relatively mature pricing engine in the prior art and combining the indexes of the elasticity and the replacement efficiency of the commodity (i.e. gamma, which is used for measuring the proportion of the GMV change rate and the gross profit change rate).
And the third is that: target optimization leader
FIG. 9 is a goal-based optimization in a method of attribute data analysis according to an embodiment of the present inventionAnd optimizing a main flow diagram of the dominant algorithm for price suggestion by the algorithm target. As shown in fig. 9, this algorithm is an early algorithm for referring to mackentin, and is a calculation model based on price elasticity, and provides a maximum sales volume (salePrice) weight of 30% and a maximum GMV (gmvpprice ═ e-1) × P0V. (2 × e), where e represents the elasticity of the similar SKU, P0Representing the SKU page price of the resemblance, i.e. red price) weight 40%, maximum profit (gpPrice ═ e-1+ e cost/P0)*Q0And e represents the elasticity of the similar SKU, P0Page price representing a likeness SKU, cost: representing the cost price, Q, of the commodity to be simulated for calculation0: representing the sale amount of SKU in the last 7 days to be simulated and calculated) under the three scenes of weighting 30%, and combining with a quantity-price model to give price suggestions according to three targets of maximizing the sale amount, maximizing the GMV and maximizing the profit, wherein the three prices are respectively set by taking 30%, 40% and 30% as default proportions, and the suggested price is calculated.
(3) Price simulation
For a given price proposal, the system provides a price simulator, and provides a predicted sales data derived based on an algorithm model for the merchant according to the existing elasticity, such as but not limited to sales predicted value, profit predicted value, GMV predicted value and the like, for the merchant to refer to.
In addition, in the embodiment of the invention, price simulation can be directly performed on the commodity according to the obtained price interval of the similar commodity. Namely, the expected sales condition of the commodity is simulated directly according to the data billboard of the similar merchant without price suggestion, and the expected sales condition comprises a sales predicted value, a profit predicted value and a GMV predicted value. The method specifically comprises the following steps:
(1) the maximum page price of a similar merchant SKU is obtained as the maximum value of the simulated price. It should be noted that: abnormal values of the maximum page prices of similar merchant SKUs are required to be filtered, namely data beyond fifty percent of the page prices of similar merchant SKU lists are filtered out), and if the maximum value is null, the maximum value of the simulation price is set to be 10% higher than the page price of the current commodity SKU to be simulated.
(2) A minimum value for the simulated price is defined, which is set to 50% of the price of the SKU page for the item currently being simulated.
(3) After the minimum value and the maximum value of the price to be simulated are obtained, the chart trend simulation of the sales volume, the GMV and the gross profit is carried out between the two price areas, namely the trend situation of the sales volume, the GMV and the gross profit corresponding to the simulated price, and the specific simulation principle is as follows:
1) and (4) according to the existing price and sales volume, flexibly predicting the sales volume when the price is equal to the simulated price manually input by the merchant. The algorithm is as follows: q1 × ec (p1-p2)/p1+ q1 (note: if the calculation result is less than 0, 0 is taken, otherwise, the actual calculation result), wherein q 1: a total weekly sales representative of the current SKU to be simulated; ec: the elasticity of the currently simulated SKU (this is a positive value after negative number x-1); p 1: currently, simulating the current page price of the SKU; p 2: representing minimum and maximum price interval values;
2) simulating the GMV according to the simulated price and the predicted sales volume manually input by the merchant, wherein the algorithm is as follows: manually inputting price and sales volume of the current simulation SKU;
3) simulating the gross profit according to the simulated price and the predicted sales volume manually input by the merchant, wherein the algorithm is as follows: (x-cost) sale, wherein x: represents the minimum and maximum price interval values, cost: currently, to simulate SKU manually entered prices, sale: the amount of sales simulated.
In summary, in an embodiment of the present invention, taking the merchant a as an example, the main flow of the method for analyzing the attribute data includes:
1. and acquiring merchants with GMV ranking of top 20 (which can be flexibly defined according to the requirements of similar merchants) under the category of the merchant A (taking the dimension of the merchant A belonging to the consumer goods and the primary category of the household living department as an example) as a candidate similar merchant set. The category of the merchant is judged as follows: if the merchant only has one category or brand, directly carrying out GMV sequencing; if the merchant has a plurality of categories, respectively calculating the scale ranks corresponding to the plurality of categories, and taking the category with the highest GMV ratio as the final rank; if the merchant has a plurality of brands, respectively calculating scale ranks corresponding to the brands, and taking the brand with the highest GMV ratio as the final rank;
2. calculating similar merchants according to a similarity learning algorithm, for example, learning by using a substitution algorithm, selecting a merchant-1 similar to A from the candidate similar merchant set, learning by using a superposition algorithm, selecting a merchant-2 similar to A from the candidate similar merchant set, learning by using a scale algorithm, selecting a merchant-3 similar to A from the candidate similar merchant set, and forming a similar merchant pool by using the three results. In practical operation, based on the consideration of calculation accuracy, an alternative algorithm and a coincidence algorithm are usually selected. In addition, a height algorithm can be used, and all similar merchants are used as final similar merchants in a similar merchant pool obtained by taking and combining the three results. Of course, in the embodiment of the present invention, for efficient calculation, similar merchants in the above-mentioned pool of similar merchants may be filtered based on experience and preference of the merchant a, for example, an intersection is formed by free combination, and the filtered similar merchants serve as the similar merchants. There is also another scenario involved here, namely: if an intersection exists after the free combination, the intersection is used as a similar merchant, and if the intersection does not exist after the free combination, the obtained candidate similar merchant set can be directly used as a similar merchant;
3. matching similar commodities of key commodity SKUs with top 10 of A (which can be flexibly defined according to the requirements of similar merchants, as described above, the embodiment of the invention can support the matching of more than 100 SKUs) from the similar merchant range of A;
4. and proposing the price through the price interval of the similar commodity, and carrying out price simulation according to the proposed price, or directly carrying out price simulation according to the price interval of the similar commodity, namely carrying out sales data prediction of the merchant A according to commodities of competing merchants. In the embodiment of the invention, similar commodities used for price suggestion or price simulation can be screened and confirmed based on experience and preference of a merchant A so as to meet different suggestion and simulation requirements of the merchant.
According to the technical scheme of the attribute data analysis, the technical means that a data billboard based on commodities is adopted to help a merchant to find a competitor, then the merchant is helped to lock competitive commodities with optimized attribute values and optimized attribute values based on commodity brands and categories, and attribute value suggestion is carried out is adopted, so that the technical problems that only single-item analysis is adopted, no competitive product and competitive commodity analysis is carried out, the automatic price adjustment risk is high, and competitive analysis with other dimensions is not carried out are solved, and the technical effects that the merchant is assisted to reasonably calculate the suggested attribute values and deepen the competitive advantages of the attribute values are achieved; in addition, by acquiring various data signboards, the embodiment of the invention can realize backtracking and drilling depth of the acquired data in the process of analyzing the attribute data; by selecting a preset number of merchants from the merchants of the same brand and/or category as candidate similar merchants, the commodities can be intelligently classified on the basis of industry competition, so that the competing merchants and the commodities can be accurately matched; the commodities similar to the key commodities of the merchants are screened from the commodity data of the similar merchants to serve as the similar commodities, so that attribute value suggestion can be accurately and efficiently carried out on the key commodities of the merchants, and the efficiency of attribute value development is improved; attribute value suggestion is carried out by using an intelligent suggestion algorithm, so that the attribute value suggestion can be accurately and flexibly carried out according to different pricing requirements of merchants; by using a simulation algorithm to predict commodity sales data including sales volume, gross profit, GMV and the like, the sales condition of the simulated commodity can be provided for reference of a merchant based on the result of the attribute value suggestion; in addition, in one embodiment of the invention, the predicted sales data of the commodities are simulated according to the attribute value interval of the similar commodities, so that the method can assist the merchant to know the sales conditions of other competitors in the same industry, and is beneficial to the merchant to make a correct decision.
Fig. 10 is a schematic diagram of main blocks of an apparatus for attribute data analysis according to an embodiment of the present invention. As shown in fig. 10, the attribute data analysis device 1000 according to the embodiment of the present invention mainly includes the following modules: an acquisition module 1001, a screening module 1002, and a calculation module 1003. The obtaining module 1001 may be configured to obtain similar merchants of a merchant according to a preset similarity rule and from a data billboard of the merchant; the screening module 1002 may be configured to screen similar products of the merchant's products using the data billboard of the similar merchant; the calculating module 1003 may be configured to calculate, according to the attribute value interval of the similar product, a suggested attribute value of the merchant product by using a preset suggested algorithm.
Wherein, the data billboard comprises at least one of the following information: commodity data, brand data, category data, daily average total volume of transaction data, daily average browsing volume data, key commodity data, commodity price elastic data and commodity price label data.
In this embodiment of the present invention, the obtaining module 1001 may further be configured to: according to the daily average total volume ranking of the merchants under the same brand and/or category dimension, selecting a preset number of merchants from the merchants of the same brand and/or category as candidate similar merchants; and screening similar merchants from the candidate similar merchants according to a preset similarity rule.
The screening module 1002 may also be configured to: and screening the commodities similar to the key commodity of the merchant from the commodity data of the similar merchants to serve as the similar commodities. The calculation module 1003 may also be configured to: and calculating the suggested attribute value of the merchant commodity by utilizing a quarterback algorithm and/or a dynamic optimization leading algorithm and/or a target optimization leading algorithm according to the maximum value and the minimum value of the attribute value interval of the similar commodity.
In this embodiment of the present invention, the apparatus 1000 may further include: a simulation module (not shown) for simulating the predicted sales data for the merchant commodity in accordance with the suggested attribute value.
In addition, the attribute data analysis device 1000 according to the embodiment of the present invention may further be configured to, according to a preset similarity rule, obtain, by the obtaining module 1001, similar merchants of the merchant from the data billboard of the merchant; screening similar commodities of the merchants by using the data billboard of the similar merchants through a screening module 1002; and simulating the predicted sales data of the commodity according to the attribute value interval of the similar commodity by using a simulation module.
Wherein the simulation module is further operable to: taking the maximum value of the attribute value interval of the similar commodity as a simulation maximum value, and multiplying the current sales attribute value of the commodity by a preset percentage to be taken as a simulation minimum value; and simulating the predicted sales data of the commodity by using a simulation interval consisting of the simulation maximum value and the simulation minimum value.
From the above description, it can be seen that the technical means that the merchant is helped to find competitors by adopting the data billboard based on the commodity firstly, then the merchant is helped to lock competitive commodities for attribute value price ratio and attribute value optimization based on commodity brands and categories, and attribute value suggestion is carried out is overcome, so that the technical problems that only single item analysis is adopted, no competitive commodity and competitive commodity analysis is available, the automatic price adjustment risk is large, and no competitive analysis with other dimensions is available are solved, and the technical effects that the merchant is helped to reasonably calculate the suggested attribute value and deepen the competitive advantage of the attribute value are achieved; in addition, by acquiring various data signboards, the embodiment of the invention can realize backtracking and drilling depth of the acquired data in the process of analyzing the attribute data; by selecting a preset number of merchants from the merchants of the same brand and/or category as candidate similar merchants, the commodities can be intelligently classified on the basis of industry competition, so that the competing merchants and the commodities can be accurately matched; the commodities similar to the key commodities of the merchants are screened from the commodity data of the similar merchants to serve as the similar commodities, so that attribute value suggestion can be accurately and efficiently carried out on the key commodities of the merchants, and the efficiency of attribute value development is improved; attribute value suggestion is carried out by using an intelligent suggestion algorithm, so that the attribute value suggestion can be accurately and flexibly carried out according to different pricing requirements of merchants; by using a simulation algorithm to predict commodity sales data including sales volume, gross profit, GMV and the like, the sales condition of the simulated commodity can be provided for reference of a merchant based on the result of the attribute value suggestion; in addition, in one embodiment of the invention, the predicted sales data of the commodities are simulated according to the attribute value interval of the similar commodities, so that the method can assist the merchant to know the sales conditions of other competitors in the same industry, and is beneficial to the merchant to make a correct decision.
Fig. 11 shows an exemplary system architecture 1100 to which the attribute data analysis method or the attribute data analysis apparatus of the embodiment of the present invention can be applied.
As shown in fig. 11, the system architecture 1100 may include terminal devices 1101, 1102, 1103, a network 1104, and a server 1105. The network 1104 is a medium to provide communication links between the terminal devices 1101, 1102, 1103 and the server 1105. Network 1104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
A user may use terminal devices 1101, 1102, 1103 to interact with a server 1105 over a network 1104 to receive or send messages or the like. Various messaging client applications, such as shopping applications, web browser applications, search applications, instant messaging tools, mailbox clients, social platform software, etc. (examples only) may be installed on the terminal devices 1101, 1102, 1103.
The terminal devices 1101, 1102, 1103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 1105 may be a server that provides various services, such as a backend management server (for example only) that provides support for shopping-like websites browsed by users using the terminal devices 1101, 1102, 1103. The backend management server may analyze and perform other processing on the received data such as the product information query request, and feed back a processing result (for example, target push information, product information — just an example) to the terminal device.
It should be noted that the attribute data analysis method provided in the embodiment of the present invention is generally executed by the server 1105, and accordingly, the attribute data analysis device is generally provided in the server 1105.
It should be understood that the number of terminal devices, networks, and servers in fig. 11 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 12, shown is a block diagram of a computer system 1200 suitable for use with a terminal device implementing an embodiment of the present invention. The terminal device shown in fig. 12 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 12, the computer system 1200 includes a Central Processing Unit (CPU)1201, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)1202 or a program loaded from a storage section 1208 into a Random Access Memory (RAM) 1203. In the RAM 1203, various programs and data necessary for the operation of the system 1200 are also stored. The CPU 1201, ROM 1202, and RAM 1203 are connected to each other by a bus 1204. An input/output (I/O) interface 1205 is also connected to bus 1204.
The following components are connected to the I/O interface 1205: an input section 1206 including a keyboard, a mouse, and the like; an output portion 1207 including a display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 1208 including a hard disk and the like; and a communication section 1209 including a network interface card such as a LAN card, a modem, or the like. The communication section 1209 performs communication processing via a network such as the internet. A driver 1210 is also connected to the I/O interface 1205 as needed. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like, is mounted on the drive 1210 as necessary, so that a computer program read out therefrom is mounted into the storage section 1208 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 1209, and/or installed from the removable medium 1211. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 1201.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes an acquisition module, a screening module, and a computation module. The names of these modules do not in some cases form a limitation on the module itself, for example, the acquiring module may also be described as a module for acquiring similar merchants of the merchant from the data billboard of the merchant according to preset similarity rules.
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: acquiring similar merchants of the merchants from data signboards of the merchants according to a preset similarity rule; screening similar commodities of the merchants by using the data billboard of the similar merchants; and calculating the suggested attribute value of the merchant commodity according to the attribute value interval of the similar commodity.
According to the technical scheme of the embodiment of the invention, the technical means that the merchant is helped to find a competitor based on the data billboard of the commodity at first, then the merchant is helped to lock competitive commodities with optimized attribute values and price ratios based on the brand and the category of the commodity, and the attribute value suggestion is carried out, so that the technical problems that only single item analysis is adopted, no competitive products and competitive commodity analysis is available, the automatic price adjustment risk is high, and no competitive analysis with other dimensions is available are solved, and the technical effects of assisting the merchant to reasonably calculate the suggested attribute values and deepen the competitive advantages of the attribute values are achieved; in addition, by acquiring various data signboards, the embodiment of the invention can realize backtracking and drilling depth of the acquired data in the process of attribute value attribute data analysis; by selecting a preset number of merchants from the merchants of the same brand and/or category as candidate similar merchants, the commodities can be intelligently classified on the basis of industry competition, so that the competing merchants and the commodities can be accurately matched; the commodities similar to the key commodities of the merchants are screened from the commodity data of the similar merchants to serve as the similar commodities, so that attribute value suggestion can be accurately and efficiently carried out on the key commodities of the merchants, and the efficiency of attribute value development is improved; attribute value suggestion is carried out by using an intelligent suggestion algorithm, so that the attribute value suggestion can be accurately and flexibly carried out according to different pricing requirements of merchants; by using a simulation algorithm to predict commodity sales data including sales volume, gross profit, GMV and the like, the sales condition of the simulated commodity can be provided for reference of a merchant based on the result of the attribute value suggestion; in addition, in one embodiment of the invention, the predicted sales data of the commodities are simulated according to the attribute value interval of the similar commodities, so that the method can assist the merchant to know the sales conditions of other competitors in the same industry, and is beneficial to the merchant to make a correct decision.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (14)

1. A method of attribute data analysis, comprising:
according to the daily average total volume ranking of merchants under the same brand and/or category dimension, selecting a preset number of merchants from the merchants of the same brand and/or category as candidate similar merchants, and screening the similar merchants from the candidate similar merchants according to a preset similarity rule, wherein the similarity rule comprises the following steps: substitution, coincidence, scale and height;
screening similar commodities of the merchants by using the data billboard of the similar merchants;
calculating the suggested attribute value of the merchant commodity by using a preset suggested algorithm according to the attribute value interval of the similar commodity;
wherein, the data billboard comprises at least one of the following information: commodity data, brand data, category data, daily average total volume of transaction data, daily average browsing volume data, key commodity data, commodity price elastic data and commodity price label data.
2. The method of claim 1, wherein screening the merchant items for similar items using the similar merchant's data billboard comprises:
and screening the commodities similar to the key commodity of the merchant from the commodity data of the similar merchants to serve as the similar commodities.
3. The method of claim 1, wherein calculating the suggested attribute value of the merchant commodity according to the attribute value interval of the similar commodity by using a preset suggestion algorithm comprises:
and calculating the suggested attribute value of the merchant commodity by utilizing a quarterback algorithm and/or a dynamic optimization leading algorithm and/or a target optimization leading algorithm according to the maximum value and the minimum value of the attribute value interval of the similar commodity.
4. The method of claim 1, further comprising: and simulating the predicted sales data of the merchant commodities according to the suggested attribute values.
5. A method of attribute data analysis, comprising:
according to the daily average total volume ranking of merchants under the same brand and/or category dimension, selecting a preset number of merchants from the merchants of the same brand and/or category as candidate similar merchants, and screening the similar merchants from the candidate similar merchants according to a preset similarity rule, wherein the similarity rule comprises the following steps: substitution, coincidence, scale and height;
screening similar commodities of the merchants by using the data billboard of the similar merchants;
and simulating the predicted sales data of the commodities according to the attribute value interval of the similar commodities.
6. The method of claim 5, wherein simulating the forecasted sales data for the good based on the range of attribute values for the similar good comprises:
taking the maximum value of the attribute value interval of the similar commodity as a simulation maximum value, and multiplying the current sales attribute value of the commodity by a preset percentage to be taken as a simulation minimum value;
and simulating the predicted sales data of the commodity by using a simulation interval consisting of the simulation maximum value and the simulation minimum value.
7. An apparatus for attribute data analysis, comprising:
the acquisition module is used for selecting a preset number of merchants from the merchants of the same brand and/or category as candidate similar merchants according to the daily average transaction total ranking of the merchants under the same brand and/or category dimension, and screening the candidate similar merchants according to a preset similarity rule, wherein the similarity rule comprises: substitution, coincidence, scale and height;
the screening module is used for screening similar commodities of the merchant commodities by using the data billboard of the similar merchant;
the calculation module is used for calculating the suggested attribute value of the merchant commodity by using a preset suggested algorithm according to the attribute value interval of the similar commodity;
wherein, the data billboard comprises at least one of the following information: commodity data, brand data, category data, daily average total volume of transaction data, daily average browsing volume data, key commodity data, commodity price elastic data and commodity price label data.
8. The apparatus of claim 7, wherein the screening module is further configured to:
and screening the commodities similar to the key commodity of the merchant from the commodity data of the similar merchants to serve as the similar commodities.
9. The apparatus of claim 7, wherein the computing module is further configured to:
and calculating the suggested attribute value of the merchant commodity by utilizing a quarterback algorithm and/or a dynamic optimization leading algorithm and/or a target optimization leading algorithm according to the maximum value and the minimum value of the attribute value interval of the similar commodity.
10. The apparatus of claim 7, further comprising: and the simulation module is used for simulating the predicted sales data of the merchant commodities according to the suggested attribute value.
11. An apparatus for attribute data analysis, comprising:
the acquisition module is used for selecting a preset number of merchants from the merchants of the same brand and/or category as candidate similar merchants according to the daily average transaction total ranking of the merchants under the same brand and/or category dimension, and screening the candidate similar merchants according to a preset similarity rule, wherein the similarity rule comprises: substitution, coincidence, scale and height;
the screening module is used for screening similar commodities of the merchant commodities by using the data billboard of the similar merchant;
and the simulation module is used for simulating the predicted sales data of the commodities according to the attribute value interval of the similar commodities.
12. The apparatus of claim 11, wherein the simulation module is further configured to:
taking the maximum value of the attribute value interval of the similar commodity as a simulation maximum value, and multiplying the current sales attribute value of the commodity by a preset percentage to be taken as a simulation minimum value;
and simulating the predicted sales data of the commodity by using a simulation interval consisting of the simulation maximum value and the simulation minimum value.
13. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.
14. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-6.
CN201711385752.4A 2017-12-20 2017-12-20 Method and device for analyzing attribute data Active CN109949065B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711385752.4A CN109949065B (en) 2017-12-20 2017-12-20 Method and device for analyzing attribute data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711385752.4A CN109949065B (en) 2017-12-20 2017-12-20 Method and device for analyzing attribute data

Publications (2)

Publication Number Publication Date
CN109949065A CN109949065A (en) 2019-06-28
CN109949065B true CN109949065B (en) 2021-10-12

Family

ID=67004260

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711385752.4A Active CN109949065B (en) 2017-12-20 2017-12-20 Method and device for analyzing attribute data

Country Status (1)

Country Link
CN (1) CN109949065B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210090106A1 (en) * 2019-09-23 2021-03-25 Coupang, Corp. Systems and methods for outbound forecasting
JP2021103444A (en) * 2019-12-25 2021-07-15 株式会社野村総合研究所 Demand forecasting system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106886934A (en) * 2016-12-30 2017-06-23 北京三快在线科技有限公司 Method, system and apparatus for determining merchant categories
CN107038190A (en) * 2016-10-28 2017-08-11 厦门大学 A kind of intelligent promotion plan modeling method applied to Taobao

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160086222A1 (en) * 2009-01-21 2016-03-24 Truaxis, Inc. Method and system to remind users of targeted offers in similar categories

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107038190A (en) * 2016-10-28 2017-08-11 厦门大学 A kind of intelligent promotion plan modeling method applied to Taobao
CN106886934A (en) * 2016-12-30 2017-06-23 北京三快在线科技有限公司 Method, system and apparatus for determining merchant categories

Also Published As

Publication number Publication date
CN109949065A (en) 2019-06-28

Similar Documents

Publication Publication Date Title
CN108205768B (en) Database establishing method, data recommending device, equipment and storage medium
US11127032B2 (en) Optimizing and predicting campaign attributes
CN108280749B (en) Method and device for displaying service function entry
CN107465741A (en) Information-pushing method and device
US20230196219A1 (en) Systems and methods for report generation
US20200234218A1 (en) Systems and methods for entity performance and risk scoring
CN107679103B (en) Attribute analysis method and system for entity
CN110348921B (en) Method and device for selecting store articles
CN112528153B (en) Content recommendation method, device, apparatus, storage medium, and program product
CN109213936B (en) Commodity searching method and device
CN112215448A (en) Method and device for distributing customer service
CN108932625A (en) Analysis method, device, medium and the electronic equipment of user behavior data
CN112598472A (en) Product recommendation method, device, system, medium and program product
CN109949065B (en) Method and device for analyzing attribute data
CN104572775A (en) Advertisement classification method, device and server
CN115147144A (en) Data processing method and electronic equipment
CN110570271A (en) information recommendation method and device, electronic equipment and readable storage medium
JP2022066769A (en) Information processing apparatus, information processing method, program, application program, and information processing system
CN112348590A (en) Method and device for determining value of article, electronic equipment and storage medium
CN116452299A (en) Intelligent recommendation system and method for electronic commerce
Chen et al. Pricing Decisions on Reward-Based Crowdfunding with Bayesian Review System Facing Strategic Consumers
CN116050569A (en) Visual prediction decision method and processing system for transaction data of high-fidelity electronic commerce platform
CN110490682A (en) The method and apparatus for analyzing item property
US20200286104A1 (en) Platform for In-Memory Analysis of Network Data Applied to Profitability Modeling with Current Market Information
CN113421148A (en) Commodity data processing method and device, electronic equipment and computer storage medium

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