CN114493673A - Commodity price changing method, system, device and storage medium based on user behavior - Google Patents
Commodity price changing method, system, device and storage medium based on user behavior Download PDFInfo
- Publication number
- CN114493673A CN114493673A CN202111659411.8A CN202111659411A CN114493673A CN 114493673 A CN114493673 A CN 114493673A CN 202111659411 A CN202111659411 A CN 202111659411A CN 114493673 A CN114493673 A CN 114493673A
- Authority
- CN
- China
- Prior art keywords
- commodity
- selling
- selling price
- sales
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000006399 behavior Effects 0.000 claims abstract description 32
- 238000006243 chemical reaction Methods 0.000 claims abstract description 11
- 230000009471 action Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 21
- 230000008859 change Effects 0.000 description 10
- 230000001186 cumulative effect Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
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
- G06Q30/0206—Price or cost determination based on market factors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
- G06K17/0029—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device the arrangement being specially adapted for wireless interrogation of grouped or bundled articles tagged with wireless record carriers
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a commodity price changing method, a commodity price changing system, a commodity price changing device and a storage medium based on user behaviors. The method comprises the following steps: acquiring accumulated sales records according to the commodity collection data, acquiring N selling price intervals according to the accumulated sales records, and acquiring the average gross profit of each selling price interval; acquiring the accumulated number of picking people according to the commodity collection data, and predicting the predicted number of picking people corresponding to each selling price interval in the next selling period by using a smooth index time sequence model; acquiring accumulated sales conversion rate according to the accumulated sales records and the accumulated number of the selected persons, and acquiring predicted sales number corresponding to each sales price interval in the next sales period according to the accumulated sales conversion rate and the predicted number of the selected persons; and selecting a target selling price interval from the N selling price intervals according to the average gross profit corresponding to each selling price interval and the estimated selling quantity corresponding to each selling price interval in the next selling period, and acquiring target pricing according to the target selling price interval. The invention can effectively increase the commodity sales volume of stores.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a commodity price changing method, a system, a device and a storage medium based on vibration induction.
Background
Price planning for off-line stores is still in the infancy stage, often with variations lagging behind market changes. In the process from the time when a user enters a store to the time when money is selected for consumption, how a customer interacts with a commodity is lack of data acquisition and analysis, and an enterprise is often unable to accurately attribute the current situation of poor sales data, and the price change of the commodity is only based on past sales data and often lags behind the change of the market, so that the pricing is inaccurate, and the commodity sales volume is influenced.
Disclosure of Invention
The technical problem to be solved by the invention is that the selling quantity of the commodity is influenced by inaccurate pricing, and aiming at the defects in the prior art, the commodity price changing method, the commodity price changing system, the commodity price changing device and the commodity price storing medium based on the user behaviors are provided, so that the proper pricing can be obtained in advance, and the selling quantity of stores can be improved.
The technical scheme adopted by the invention for solving the technical problems is as follows: the commodity price changing method based on the user behavior comprises the following steps:
acquiring an original data table, wherein the original data table comprises original event data of each customer selecting commodities in a store, and commodity collection data of each customer in the store is acquired according to the original event data, and the commodity collection data comprises at least one of commodity selecting codes, commodity selecting sales, commodity selecting times, commodity selecting historical retail prices, commodity actual selling prices and commodity gross profits;
acquiring accumulated sales records of a target commodity style according to the commodity collection data, acquiring N selling price intervals of the target commodity style according to the accumulated sales records, and acquiring average gross profit of each selling price interval, wherein N is an integer greater than or equal to 1;
acquiring the accumulated number of picked people of the target commodity style according to the commodity collection data, and predicting the predicted number of picked people of the target commodity style in each selling price interval in the next selling period by using a smooth exponential time sequence model;
acquiring an accumulated sales conversion rate according to the accumulated sales record and the accumulated number of the selected persons, and acquiring a predicted sales number corresponding to the target commodity style in each selling price interval in the next selling period according to the accumulated sales conversion rate and the predicted number of the selected persons;
and selecting a target selling price interval from the N selling price intervals according to the average gross profit corresponding to each selling price interval and the predicted selling quantity corresponding to each selling price interval in the next selling period, and obtaining target pricing of the target commodity style in the next selling period according to the target selling price interval.
The technical scheme adopted by the invention for solving the technical problems is as follows: provided is a commodity price changing system based on user behavior, comprising:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring an original data form, the original data form comprises original event data of each customer for selecting commodities in a store, and commodity collection data of each customer in the store is acquired according to the original event data, and the commodity collection data comprises at least one of commodity selecting codes, commodity retail price selecting, actual commodity selling price selecting, commodity cost selecting and commodity gross profit selecting;
the average module is used for acquiring accumulated sales records of target commodity styles according to the commodity collection data, acquiring N selling price intervals of the target commodity styles according to the accumulated sales records, and acquiring the average gross profit of each selling price interval, wherein N is an integer greater than or equal to 1;
the selection module is used for acquiring the accumulated selection number of the target commodity style according to the commodity collection data and predicting the predicted selection number of the target commodity style in each selling price interval in the next selling period by using a smooth exponential time sequence model;
the sales module is used for obtaining the expected sales quantity of the target commodity style in each sales price interval in the next sales period according to the accumulated sales record and the accumulated number of the selected people;
and the pricing module is used for selecting a target selling price interval from the N selling price intervals according to the average gross profit corresponding to each selling price interval in the next selling period and the estimated selling quantity.
The technical scheme adopted by the invention for solving the technical problems is as follows: there is provided a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the method as described above.
The technical scheme adopted by the invention for solving the technical problems is as follows: a storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the method as described above.
The invention has the advantages that compared with the prior art, the invention acquires the commodity collection data of each customer in the store, acquires the accumulated sales record of the target commodity style according to the commodity collection data, acquires N selling price intervals of the target commodity style according to the accumulated sales record, acquires the average gross profit of each selling price interval, acquires the corresponding estimated sales quantity of each selling price interval in the next selling period according to the accumulated sales record, selects the target selling price interval from the N selling price intervals according to the average gross profit corresponding to each selling price interval and the corresponding estimated sales quantity of each selling price interval in the next selling period, acquires the target pricing interval of the target commodity style in the next selling period according to the target selling price interval, can accurately analyze the behavior of the user when selecting commodities, and acquires the target pricing of the next selling period of the target style by combining the gross profit and the sales quantity, and proper pricing can be obtained in advance, and the sales volume of stores is promoted.
Drawings
The invention will be further described with reference to the following drawings and examples, in which:
FIG. 1 is a flowchart illustrating a commodity price changing method based on user behavior according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of an application scenario of the commodity price changing method based on user behavior according to the present invention;
FIG. 3 is a diagram of a data structure of event _ data;
FIG. 4 is a flowchart illustrating a commodity price changing method based on user behavior according to a second embodiment of the present invention;
FIG. 5 is a data structure diagram of one embodiment of counter data provided by the present invention;
FIG. 6 is a data structure diagram of one embodiment of an initial set of pick events for a customer in a store provided by the present invention;
FIG. 7 is a data structure diagram of an embodiment of the merchandise collection data provided by the present invention;
FIG. 8 is a data structure diagram of one embodiment of rating record data;
FIG. 9 is a data structure diagram of an embodiment of merchandise sales data provided by the present invention;
FIG. 10 is a diagram illustrating an exemplary data structure of merchandise category data provided by the present invention;
FIG. 11 is a schematic structural diagram of an embodiment of a commodity price changing system based on user behavior according to the present invention;
FIG. 12 is a schematic block diagram of an embodiment of a computer device provided in the present invention;
fig. 13 is a schematic structural diagram of an embodiment of a storage medium provided in the present invention.
Detailed Description
The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
Referring to fig. 1 and fig. 2, fig. 1 is a flowchart illustrating a commodity price changing method based on user behavior according to a first embodiment of the present invention. Fig. 2 is a schematic view of an application scenario of the commodity price changing method based on user behavior provided by the invention.
As shown in fig. 2, an intelligent tag 11 is arranged on a commodity, the intelligent tag 11 is wirelessly connected with a bluetooth gateway 12, the bluetooth gateway 12 sends original data collected by the intelligent tag 11 to a cloud server 13 through the internet, and the cloud server 13 includes a service server, a database server and an algorithm server, and is used for performing data processing on the original data. When a commodity customer selects, such as touches, picks up or tries on, the intelligent tag 11 arranged on the commodity can feel corresponding vibration, and the sensor vibration data corresponding to the vibration is collected. The intelligent tag 11 transmits the sensor vibration data to the cloud server 13 through the bluetooth gateway 12. The cloud server 13 performs data processing and data analysis on the received sensor vibration data, acquires the selection operation information of the user, and stores the selection operation information. And generating an original data table according to the stored operation information.
The commodity price changing method based on the user behavior comprises the following steps:
s101: the method comprises the steps of obtaining an original data table, wherein the original data table comprises original event data of each customer selecting commodities in a store, and obtaining commodity collection data of each customer in the store according to the original event data, and the commodity collection data comprises at least one of a commodity selecting code, a commodity selecting sales volume and a commodity selecting gross profit.
In a specific implementation scenario, an original data table within a preset duration is obtained and recorded as event _ data. The preset time duration may be one sale period, or several sale periods, or other time durations defined by the user. Referring to fig. 3 in combination, fig. 3 is a diagram illustrating a data structure of event _ data. As shown in fig. 3, each of the event _ data means a pick event triggered by a customer in the store. As shown in fig. 3, one event _ data includes customer pick goods original event data, for example, pick store code, pick goods code, pick event start-stop time, pick type. In the implementation scene, the commodity is clothes, and the selection types comprise touch and try-on. In other implementations, the pick type may include one or more of pick up, global touch, local touch, view swing.
The original data table comprises data of selected commodities of a plurality of customers, classification is carried out according to the original event data, and commodity collection data of each customer in a store are obtained, wherein the commodity collection data comprises at least one of a commodity selection code, a commodity selection sales volume, a commodity selection actual sale price and a commodity selection gross profit. Specifically, the selected commodity cost and the selected commodity actual selling price may be obtained from the selected commodity code, and the selected commodity gross profit may be obtained from the selected commodity cost and the selected commodity actual selling price. And inquiring an ERP (Enterprise Resource Planning) system according to the selected commodity code to obtain the sales volume of the selected commodity.
S102: and acquiring the accumulated sales record of the target commodity style according to the commodity collection data, acquiring N selling price intervals of the target commodity style according to the accumulated sales record, and acquiring the average gross profit of each selling price interval, wherein N is an integer greater than or equal to 1.
In a specific implementation scenario, commodity collection data of each customer is acquired, so that a commodity sales amount corresponding to each commodity code is acquired, and a target commodity code corresponding to a commodity style of goods in the ERP system is inquired. The method comprises the steps of obtaining a selected commodity code matched with a target commodity code from commodity collection data of each customer, obtaining a selected commodity sales volume, a selected commodity actual sales price and a selected commodity gross profit corresponding to the selected commodity code matched with the target commodity code, and obtaining an accumulated sales record according to the obtained selected commodity sales volume, selected commodity historical retail price, selected commodity actual sales price and selected commodity gross profit.
And acquiring N selling price intervals of the target commodity style according to the actual selling price of the selected commodity corresponding to each selected commodity code in the accumulated selling records and the historical retail price of the selected commodity, wherein N is an integer greater than or equal to 1. The N selling price intervals may be obtained according to a preset pricing interval, for example, one selling price interval every 5 yuan, or one selling price interval every 50 yuan. The size of N may also be limited, for example, 5 selling price intervals are obtained, and the actual selling price range of the selected commodity is divided into 5 selling price intervals. The price span of each selling price interval can be equal or unequal and is set according to the actual demand of the user. And obtaining the gross profit of the selected commodities corresponding to the actual selling price of the selected commodities in each selling price interval, and calculating the average gross profit of each selling price interval.
At one isIn the implementation scenario, for the ith selling price interval (i e [1, n ]]) All the goods which were put on the shelf at the selling price within the selling price interval are marked as miAll the goods with selling price in the selling price interval are recorded as a set
Wherein the total display time of the jth commodity placed on the shelf is di，jBy deltai，j(0, 1) indicates whether the item is sold, when deltai，jWhen the value is 0, the commodity is not sold, and when the value is deltai，jWhen the price is 1, the commodity is sold, and the selling price is mui，j. At this time, the average gross profit in the ith selling price interval is recorded as:
the total showing time of each commodity can be obtained by inquiring the ERP system, and whether the commodity is sold or not can also be obtained by inquiring the ERP system.
S103: and acquiring the accumulated number of the selected persons of the target commodity style according to the commodity collection data, and predicting the predicted number of the selected persons corresponding to the target commodity style in each selling price interval in the next selling period by using a smooth exponential time series model.
In a specific embodiment, the number of persons picked up for each picked-up product code is obtained based on the number of picked-up product selections in the product collection data of each customer, for example, when the product collection data of customer a includes a picked-up product code B, C, D, and the product collection data of customer E includes a picked-up product code B, D, the number of persons picked up for product code B is 2, the number of persons picked up for product code C is 1, and the number of persons picked up for product code D is 2.
And selecting the commodity code corresponding to the target commodity style in each selling price interval and the preset selling period duration according to the number of the selected people of each selected commodity code. And acquiring the number of the selected commodity selection persons corresponding to the selected commodity code corresponding to the target commodity style in each selling price interval in the historical time corresponding to the commodity collection data in each selling period. For example, the picked-up commodity historical retail price and the picked-up commodity actual selling price of the picked-up commodity code B, C, D are acquired, and it is determined to which selling price section the picked-up commodity historical retail price and the picked-up commodity actual selling price of the picked-up commodity code B, C, D belong respectively. For example, the selected commodity historical retail price B1 of the selected commodity code B belongs to the selling price section M, the selected commodity actual selling price B2 of the selected commodity code B belongs to the selling price section N, the selected commodity code C does not select the commodity historical retail price, the selected commodity actual selling price C1 of the selected commodity code C belongs to the selling price section N, the selected commodity historical retail price D1 of the selected commodity code D belongs to the selling price section M, the selected commodity historical retail price D2 belongs to the selling price section N, and the selected commodity actual selling price D3 belongs to the selling price section N. And the data is data in one sales cycle. Further, in order to improve the accuracy of the data, the corresponding number of picking persons of each picked commodity code when the historical retail price of each picked commodity and the actual sales price of the picked commodity are put on shelf is obtained, the number of picking persons corresponding to B1 is 1, the number of picking persons corresponding to B2 is 1, the cumulative number of picking persons corresponding to the selling price interval M is 2, and the cumulative number of picking persons corresponding to the selling price interval N is 3 in one selling period. And predicting the predicted number of picking people corresponding to each selling price interval in the next selling period according to the accumulated number of picking people corresponding to each selling price interval in the current selling period by using a smooth exponential time series model.
In one implementation scenario, assume that the merchandise is partitioned into t sales cycles in the historical sales record for a predetermined period of time (e.g., 14 days), and the merchandise has a total of N sales price intervals for the ith sales price interval (i e [1, N)]) The jth sales cycle (j e [1, t ]]) All the goods put on the shelf at the selling price within the selling price interval are marked as mi，jAll the goods with selling price in the selling price interval are recorded as a set
Wherein the total display time of the kth commodity placed on the shelf is di，j，kAll once in the selling price areaThe total number of the selected commodities generated by the commodities with selling prices put on the shelves in the room is recorded as mui，jAt this time, the average number of picked commodities in the jth time period in the ith selling price interval is recorded as
Respectively aiming at the ith selling price interval, the { P _ B is divided intoi，j}(j∈[1，t]) Introducing a smooth index time series model, and predicting the predicted number P _ B of the pickers corresponding to each selling price interval in the next selling period t +1i，t+1Thereby obtaining a vector { P _ B }i，t+1}。
S104: and acquiring the accumulated sales conversion rate according to the accumulated sales records and the accumulated number of the selected persons, and acquiring the expected sales number of the target commodity style in each sales price interval in the next sales period according to the accumulated sales conversion rate and the expected number of the selected persons.
In a specific implementation scenario, according to the accumulated sales records, whether the commodity corresponding to each selected commodity code corresponding to the target commodity style is sold in a sales cycle or not and the actual sales price of each selected commodity code when the commodity code is sold can be obtained, so that the quantity of the commodities corresponding to the selected commodity code in each sales price interval in a sales cycle and the sales quantity of the selected commodities sold in each sales price interval in a sales cycle are obtained. And dividing the sold quantity corresponding to one selling price interval by the commodity quantity to obtain the accumulated selling conversion rate corresponding to the selling price interval.
In one implementation scenario, for the ith price interval (i e [1, n ]]) In the t-th time period, the total number of the picking people corresponding to the picking commodity codes in all the selling price intervals in the selling period is recorded as mui，tIn the selling period, the number of sold commodities corresponding to the selected commodity codes in all the selling price intervals is recorded as si，tThen the cumulative sales conversion can be recorded as
The expected sales number corresponding to each selling price interval in the next period can be calculated by multiplying the accumulated sales conversion rate of each selling price interval in one period by the expected picking number of the corresponding selling price interval obtained in the step S104.
S105: and selecting a target selling price interval from the N selling price intervals according to the average gross profit corresponding to each selling price interval and the predicted selling quantity corresponding to each selling price interval in the next selling period, and obtaining the target pricing of the target commodity style in the next selling period according to the target selling price interval.
In a specific implementation scenario, a target selling price interval is selected from the N selling price intervals according to the expected selling quantity corresponding to each selling price interval in the next selling period and the average gross profit obtained from each selling price interval obtained in step S102. The N target selling price intervals may be screened according to a preset screening criterion, such as a preset sales volume threshold and a preset profit threshold, m selectable selling price intervals meeting the preset screening criterion are selected, and then the selling price interval with the highest average gross profit or the highest selling quantity is selected from the selectable selling price intervals as the target selling price interval.
In other implementation scenarios, the predicted sales quantity of each selling price interval may be multiplied by the average gross profit to obtain the predicted total profit of each selling price interval, and the selling price interval with the largest predicted total profit may be selected as the target selling price interval.
In other implementation scenarios, the N selling price intervals can be further divided into N selling price intervals according to the corresponding average gross profit P _ AiSorting from big to small to obtain profit Rank { Rank _ A) of each selling price intervalkWhere k denotes the kth selling price interval of the N selling price intervals, Rank _ AkThe value of (b) represents the size ranking of the kth selling price interval, and Rank _ Ak∈[1，n]. N selling price intervals are divided into N selling price intervals according to the corresponding predicted selling amount S _ BiSorting from big to small to obtain the sales ranking { Rank _ B ] of each selling price intervalkWhere k denotes a k-th selling price section among the N selling price sections, Rank _ BkThe value of (d) represents the size ranking of the kth selling price interval, and Rank _ Bk∈[1，n]. Ranking profit and sales according to each selling price intervalAnd selecting a target selling price interval from the N selling price intervals. For example, a selling price interval in which both the profit rank and the selling rank are within a preset ranking threshold (e.g., the top three) is selected as the target selling price interval.
In other implementation scenarios, the profit weight and the sales weight are obtained, and the profit weight and the sales weight can be set according to the needs of the user, and if the profit is more emphasized, the profit weight is set to be greater than the sales weight, and if the sales volume is more emphasized, the sales weight is set to be greater than the profit weight. And multiplying the profit rank of each selling price interval by the profit weight to obtain a profit value, multiplying the sales rank of each selling price interval by the sales weight to obtain a sales value, and adding the profit value and the sales value of each selling price interval to obtain a comprehensive value. And taking the selling price interval with the minimum comprehensive value as a target selling price interval.
And obtaining the target pricing of the target commodity style in the next sale period according to the target sale price interval. For example, one selling price may be randomly selected as the target selling price in the target selling price interval, or the most frequently used selling price in the target selling price interval may be selected as the target selling price according to the past pricing history, or the highest selling price in the target selling price interval may be selected as the target selling price according to the profit demand, for example.
As can be seen from the above description, in this embodiment, the commodity collection data of each customer in the store is obtained, the accumulated sales record of the target commodity style is obtained according to the commodity collection data, the N selling price intervals of the target commodity style are obtained according to the accumulated sales record, the average gross profit of each selling price interval is obtained, the expected sales quantity corresponding to each selling price interval in the next selling period is obtained according to the accumulated sales record, the target selling price interval is selected from the N selling price intervals according to the average gross profit corresponding to each selling price interval and the expected sales quantity corresponding to each selling price interval in the next selling period, the target pricing of the target commodity style in the next selling period is obtained according to the target selling price interval, the behavior of the user in selecting commodities can be accurately analyzed, and the target pricing of the target profit of the next selling period of the target commodity style is obtained by combining the gross and the sales quantities, and proper pricing can be obtained in advance, and the sales volume of stores is promoted.
Referring to fig. 4, fig. 4 is a flowchart illustrating a commodity price changing method based on user behavior according to a second embodiment of the present invention. The commodity price changing method based on the user behavior provided by the invention comprises the following steps:
s201: a raw data form is obtained that includes raw event data for each customer picking a product at the store.
In a specific implementation scenario, step S201 is substantially the same as the "acquiring original data table" in step S101 of the method for changing prices of commodities based on user behaviors provided by the present invention in the first embodiment, where the original data table includes original event data for each customer to select a commodity in a store, "and details are not repeated here.
In this implementation scenario, the original event data includes data such as a selection store identifier (store code), a selection product code (product code), a selection event start time (start time), a selection event end time (end time), a duration, and a selection event type, where the selection event start time is a time when the selection event starts, the selection event end time is a time when the selection event ends, and the duration is a time length during which the selection event continues.
S202: and acquiring a selection event initial set of each customer in the store according to the original event data, wherein the selection event initial set comprises selection commodity codes.
In a specific implementation scenario, counter data is obtained from the raw event data, and the counter data is all possible combinations of store numbers and commodity codes, denoted as bar _ set. Referring to fig. 5, fig. 5 is a schematic diagram of a data structure of an embodiment of counter data provided by the present invention. And taking the store number as a target store identification, and taking the counter data of which the commodity code is the target commodity code as a target store parameter.
And acquiring original data matched with the target commodity code in the target store parameter as target original event data, namely acquiring original event data with the store number and the commodity code consistent with the target store parameter as the target original event data. And sequencing the obtained target original data from small to large according to respective selection event starting time to obtain an original event sequence.
And acquiring the time difference of the selected events of every two adjacent target original event data in the original event sequence, wherein the time difference of the selected events can be the difference between the end time of the selected event in the previous target original event data and the start time of the selected event in the next target original event data. It is determined whether each pickevent time difference meets a preset requirement, which may be less than a preset duration threshold (e.g., 300 s). When the time difference of the picking events is smaller than a preset threshold, it can be determined that two target original event data corresponding to the time difference of the picking events correspond to the same customer, and the two target original event data are added to the initial set of the picking events of the customer, so that the initial set of the picking events of each customer in the store is obtained and recorded as person _ data. Referring to fig. 6, fig. 6 is a data structure diagram of an embodiment of the present invention for selecting an initial set of events for a customer in a store.
After acquiring the initial picking event set person _ data, acquiring the original event data event _ data in the initial picking event set person _ data, acquiring the duration and picking event type in the original event data event _ data, wherein in the implementation scenario, there are two types of trying-on and touching, which are respectively denoted as type _1 and type _2, and acquiring the sum duration _1 of the duration in all the original event data event _ data with the picking event type of type _1 and the sum duration _2 of the duration in the original event data event _ data with the picking event type of type _2 in the initial picking event set person _ data. And acquiring the earliest time of the picking event starting times in all original event data event _ data in the picking event initial set person _ data as a behavior starting time start, and acquiring the earliest time of the picking event ending times in all original event data event _ data as a behavior ending time end. And according to the selection event types type _1 and type _2, the time sequence duration sum duration _1 and duration _2 corresponding to each selection event type, the action starting time start and the action ending time end and the selection commodity code, commodity collection data of each customer are formed and are recorded as person _ data _ collection. Referring to fig. 7, fig. 7 is a data structure diagram of an embodiment of the commodity collection data provided by the present invention.
S203: and acquiring price changing record data, wherein the price changing record data comprises at least one of a price changing commodity code, an old retail price and a new retail price.
In a specific implementation scenario, the price change record data is stored in a sales system or an ERP system, and a user can obtain the price change record data by querying, and the obtained price change record data is recorded as change _ price _ data. Referring to fig. 8, fig. 8 is a data structure diagram of an embodiment of rating change recording data. As shown in fig. 8, the change-price record data change _ price _ data includes at least one of a change-price goods code, an old retail price, a new retail price, and a price-adjusted validation time.
S204: and obtaining historical retail prices of the selected commodities and actual sales prices of the selected commodities according to the old retail prices and the new retail prices corresponding to the price-changed commodity codes matched with the selected commodity codes.
In a specific implementation scenario, a price-changing commodity code consistent with the code content of a selected commodity code included in original event data event _ data included in a selected event initial set person _ data is acquired, an old retail price and a new retail price corresponding to the price-changing commodity code with the code content consistent with the selected commodity code in price-changing record data change _ price _ data are acquired, and a history retail price of the selected commodity and an actual sales price of the selected commodity are acquired according to the old retail price and the new retail price. For example, the actual selling price of the selected article may be a new retail price, and the historical retail price of the selected article may be an old retail price.
In other implementation scenarios, the commodity sales data is obtained from a sales-related system such as ERP, and is recorded as sample _ data, please refer to fig. 9, and fig. 9 is a data structure diagram of an embodiment of the commodity sales data provided by the present invention. Please refer to fig. 10, in which fig. 10 is a schematic diagram of a data structure of an embodiment of the data of the commodity category according to the present invention, wherein the data of the commodity category is obtained from the warehousing system and is marked as stock _ data. The commodity sales data comprises a sales commodity code, a sales commodity actual price and a sales cost, and the sales commodity actual price and the sales cost corresponding to the sales commodity code matched with the selected commodity code are respectively used as the selected commodity actual sales price and the selected commodity cost. And calculating the gross profit of the selected commodity according to the actual selling price and the cost of the selected commodity.
According to the above description, in this embodiment, the old retail price and the new retail price corresponding to the code of the selected commodity are obtained according to the initial set of the selection event and the price change record data of each customer in the store, the historical retail price and the actual sales price of the selected commodity are obtained according to the old retail price and the new retail price, and the gross profit of the selected commodity is calculated according to the actual sales price and the cost of the selected commodity, so that the gross profit of the selected commodity can be accurately obtained, and the accuracy and the reliability of the target pricing are improved.
Referring to fig. 11, fig. 11 is a schematic structural diagram of a commodity price changing system based on user behavior according to an embodiment of the present invention. The commodity price changing system 20 based on user behavior includes an acquisition module 21, an averaging module 22, a choosing module 23, a selling module 24, and a pricing module 25.
The obtaining module 21 is configured to obtain an original data table, where the original data table includes original event data of each customer selecting a commodity in a store, and obtain commodity collection data of each customer in the store according to the original event data, where the commodity collection data includes at least one of a commodity selection code, a commodity retail price, an actual commodity sales price, a commodity cost, and a commodity gross profit. The average module 22 is configured to obtain a cumulative sales record of the target commodity style according to the commodity collection data, obtain N selling price intervals of the target commodity style according to the cumulative sales record, and obtain an average gross profit of each selling price interval, where N is an integer greater than or equal to 1. The selecting module 23 is configured to obtain an accumulated number of selected persons of the target commodity style according to the commodity collection data, and predict a predicted number of selected persons of the target commodity style in each selling price interval in the next selling period by using the smooth exponential time series model. The selling module 24 is used for obtaining the expected selling quantity of the target commodity style in each selling price interval in the next selling period according to the accumulated selling records and the accumulated number of people selected. The pricing module 25 is configured to select a target selling price interval from the N selling price intervals according to the average gross profit corresponding to each selling price interval in the next selling period and the predicted selling quantity.
The pricing module 25 is further configured to sort the N selling price intervals from large to small according to the corresponding average gross profit thereof, and obtain a profit rank of each selling price interval; sorting the N selling price intervals from large to small according to the corresponding predicted selling amount to obtain the selling rank of each selling price interval; and selecting a target selling price interval from the N selling price intervals according to the profit ranking and the selling ranking of each selling price interval.
The pricing module 25 is further configured to obtain profit weights and sales weights, multiply the profit ranking of each selling price interval by the profit weights to obtain profit values, multiply the sales ranking of each selling price interval by the sales weights to obtain sales values, and add the profit values and the sales values of each selling price interval to obtain comprehensive values; and taking the selling price interval with the minimum comprehensive value as a target selling price interval.
The obtaining module 21 is further configured to obtain an initial set of selection events of each customer in the store according to the original event data, where the initial set of selection events includes a selection commodity code; acquiring price changing record data, wherein the price changing record data comprises at least one of a price changing commodity code, an old retail price and a new retail price; and acquiring the historical retail price and the actual sales price of the selected commodity according to the old retail price and the new retail price corresponding to the price-changed commodity code matched with the selected commodity code.
The obtaining module 21 is further configured to obtain commodity sales data, where the commodity sales data includes a commodity sales code, a commodity sales actual price, and a sales cost; taking the actual selling price and the selling cost of the sales commodity corresponding to the sales commodity code matched with the selected commodity code as the actual selling price and the selected commodity cost of the selected commodity respectively; and calculating the gross profit of the selected commodity according to the actual selling price and the cost of the selected commodity.
The original event data comprises a picking commodity code and a picking store identifier, and further comprises a picking event starting time and a picking event ending time. The obtaining module 21 is further configured to obtain target store parameters, where the target store parameters include a target store identifier and a target commodity code; acquiring target original event data matched with the target store identification and the target commodity code, and sequencing the target original event data from small to large according to the initial time of the selected event to acquire an original event sequence; judging whether the time difference of the selected events of two adjacent target original event data in the original event sequence meets a preset requirement or not; and if the time difference of the selected events of the two adjacent target original event data meets the preset requirement, classifying the two adjacent target original event data into the selected events of the same customer.
The raw event data includes a pick event type and a pick duration. The obtaining module 21 is further configured to obtain, according to original event data of a selection event of the same customer, a selection event type of each product coded for each selected product by each customer in the store; acquiring the selection duration corresponding to the selection event type and the action starting time and the action ending time of each customer according to the selection event starting time and the selection event ending time; and forming commodity collection data of each customer according to the action starting time, the action ending time, the selection event type and the selection duration corresponding to the selection event type.
As can be seen from the above description, in this embodiment, the commodity price changing system based on user behavior obtains the commodity collection data of each customer in the store, obtains the accumulated sales record of the target commodity style according to the commodity collection data, obtains N selling price intervals of the target commodity style according to the accumulated sales record, obtains the average gross profit of each selling price interval, obtains the expected sales number corresponding to each selling price interval in the next selling period according to the accumulated sales record, selects the target selling price interval from the N selling price intervals according to the average gross profit corresponding to each selling price interval and the expected sales number corresponding to each selling price interval in the next selling period, obtains the target price of the target commodity style in the next selling period according to the target selling price interval, can accurately analyze the behavior of the user when selecting commodities, and obtains the target price of the next selling period of the target commodity style by combining gross profit and sales volume, and proper pricing can be obtained in advance, and the sales volume of stores is promoted.
Referring to fig. 12, fig. 12 is a schematic structural diagram of a computer device according to an embodiment of the present invention. The image processing device 30 includes a processor 31, a memory 32. The processor 31 is coupled to the memory 32. The memory 32 has stored therein a computer program which is executed by the processor 31 when in operation to implement the method as shown in fig. 1 and 4. The detailed methods can be referred to above and are not described herein.
Referring to fig. 13, fig. 13 is a schematic structural diagram of a storage medium according to an embodiment of the present invention. The storage medium 40 stores at least one computer program 41, and the computer program 41 is used for being executed by a processor to implement the method shown in fig. 1 and 4, and the detailed method can be referred to above and is not described herein again. In one embodiment, the computer readable storage medium 40 may be a memory chip in a terminal, a hard disk, or other readable and writable storage tool such as a removable hard disk, a flash disk, an optical disk, or the like, and may also be a server or the like.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, and the program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.
Claims (10)
1. A commodity price changing method based on user behaviors is characterized by comprising the following steps:
acquiring an original data table, wherein the original data table comprises original event data of each customer selecting commodities in a store, and commodity collection data of each customer in the store is acquired according to the original event data, and the commodity collection data comprises at least one of commodity selecting codes, commodity selecting sales, commodity selecting times, commodity selecting historical retail prices, commodity actual selling prices and commodity gross profits;
acquiring accumulated sales records of a target commodity style according to the commodity collection data, acquiring N selling price intervals of the target commodity style according to the accumulated sales records, and acquiring average gross profit of each selling price interval, wherein N is an integer greater than or equal to 1;
acquiring the accumulated number of the selected persons of the target commodity style according to the commodity collection data, and predicting the predicted number of the selected persons of the target commodity style in each selling price interval in the next selling period by using a smooth exponential time series model;
acquiring an accumulated sales conversion rate according to the accumulated sales record and the accumulated number of the selected persons, and acquiring a predicted sales number corresponding to the target commodity style in each selling price interval in the next selling period according to the accumulated sales conversion rate and the predicted number of the selected persons;
and selecting a target selling price interval from the N selling price intervals according to the average gross profit corresponding to each selling price interval and the predicted selling quantity corresponding to each selling price interval in the next selling period, and obtaining target pricing of the target commodity style in the next selling period according to the target selling price interval.
2. The method as claimed in claim 1, wherein the step of selecting a target selling price interval from the N selling price intervals according to the expected picking number and the expected selling number corresponding to each selling price interval in the next selling period comprises:
sorting the N selling price intervals from large to small according to the average gross profit corresponding to the N selling price intervals, and obtaining the profit ranking of each selling price interval;
sorting the N selling price intervals from large to small according to the corresponding predicted selling amount, and obtaining the selling rank of each selling price interval;
selecting a target selling price interval from the N selling price intervals according to the profit ranking and the selling ranking of each selling price interval.
3. The user behavior-based merchandise re-pricing method according to claim 2, wherein the step of selecting a target selling price interval from the N selling price intervals according to the profit ranking and the selling ranking of each selling price interval comprises:
obtaining profit weight and sales weight, multiplying the profit ranking of each selling price interval by the profit weight to obtain profit value, multiplying the sales ranking of each selling price interval by the sales weight to obtain sales value, and adding the profit value and the sales value of each selling price interval to obtain comprehensive value;
and taking the selling price interval with the minimum comprehensive value as the target selling price interval.
4. The commodity price changing method based on user behavior as claimed in claim 1, wherein the step of obtaining commodity collection data of each customer in the store according to the original event data comprises:
acquiring a selection event initial set of each customer in a store according to the original event data, wherein the selection event initial set comprises the selection commodity code;
acquiring price changing record data, wherein the price changing record data comprises at least one of a price changing commodity code, an old retail price and a new retail price;
and acquiring the historical retail price of the selected commodity and the actual sales price of the commodity according to the old retail price and the new retail price corresponding to the price-changing commodity code matched with the selected commodity code.
5. The commodity price changing method based on user behavior as claimed in claim 4, wherein the step of obtaining commodity collection data of each customer in the store according to the original event data comprises:
acquiring commodity sales data, wherein the commodity sales data comprises a commodity sales code, a commodity sales actual price and a commodity sales cost;
taking the actual selling price and the selling cost corresponding to the selling goods code matched with the selected goods code as the actual selling price and the selected goods cost respectively;
and calculating the gross profit of the selected commodity according to the actual selling price and the cost of the selected commodity.
6. The user behavior-based commodity re-pricing method of claim 4, wherein the original event data comprises the pick commodity code and a pick store identifier, further comprising a pick event start time and a pick event end time;
the step of obtaining an initial set of pick events for each customer in the store based on the raw event data comprises:
acquiring target store parameters, wherein the target store parameters comprise target store identification and target commodity codes;
acquiring target original event data matched with the target store identification and the target commodity code, and sequencing the target original data from small to large according to the starting time of the selection event to acquire an original event sequence;
judging whether the time difference of the selected events of two adjacent target original event data in the original event sequence meets a preset requirement or not;
and if the time difference of the selected events of the two adjacent target original event data meets the preset requirement, classifying the two adjacent target original event data into the selected events of the same customer.
7. The user behavior-based commodity re-pricing method of claim 6, wherein the raw event data includes a pick event type and a pick duration;
the step of obtaining a selected event initial set of each customer in the store according to the original event data, wherein the selected event initial set comprises the selected commodity code, and comprises the following steps:
acquiring the selection event type of each product coded for each selected product by each customer in a store according to the original event data of the selection event of the same customer;
acquiring the picking duration corresponding to the picking event type and the action starting time and the action ending time of each customer according to the picking event starting time and the picking event ending time;
and forming the commodity collection data of each customer according to the behavior starting time, the behavior ending time, the selection event type and the selection duration corresponding to the selection event type.
8. A commodity price changing system based on user behavior, comprising:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring an original data form, the original data form comprises original event data of each customer for selecting commodities in a store, and commodity collection data of each customer in the store is acquired according to the original event data, and the commodity collection data comprises at least one of commodity selecting codes, commodity retail price selecting, actual commodity selling price selecting, commodity cost selecting and commodity gross profit selecting;
the average module is used for acquiring the accumulated sales record of the target commodity style according to the commodity collection data, acquiring N selling price intervals of the target commodity style according to the accumulated sales record and acquiring the average gross profit of each selling price interval, wherein N is an integer greater than or equal to 1;
the selection module is used for acquiring the accumulated selection number of the target commodity style according to the commodity collection data and predicting the predicted selection number of the target commodity style in each selling price interval in the next selling period by using a smooth exponential time sequence model;
the sales module is used for obtaining the expected sales number of the target commodity style in each sales price interval in the next sales period according to the accumulated sales records and the accumulated number of the selected people;
and the pricing module is used for selecting a target selling price interval from the N selling price intervals according to the average gross profit corresponding to each selling price interval in the next selling period and the estimated selling quantity.
9. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method of any one of claims 1 to 7.
10. A storage medium, in which a computer program is stored which, when being executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111659411.8A CN114493673A (en) | 2021-12-30 | 2021-12-30 | Commodity price changing method, system, device and storage medium based on user behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111659411.8A CN114493673A (en) | 2021-12-30 | 2021-12-30 | Commodity price changing method, system, device and storage medium based on user behavior |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114493673A true CN114493673A (en) | 2022-05-13 |
Family
ID=81507714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111659411.8A Pending CN114493673A (en) | 2021-12-30 | 2021-12-30 | Commodity price changing method, system, device and storage medium based on user behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114493673A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115619507A (en) * | 2022-12-05 | 2023-01-17 | 阿里健康科技(杭州)有限公司 | Method, device and equipment for determining target resource exchange amount of data object |
-
2021
- 2021-12-30 CN CN202111659411.8A patent/CN114493673A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115619507A (en) * | 2022-12-05 | 2023-01-17 | 阿里健康科技(杭州)有限公司 | Method, device and equipment for determining target resource exchange amount of data object |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mostard et al. | Forecasting demand for single-period products: A case study in the apparel industry | |
| US20100138273A1 (en) | Repeatability index to enhance seasonal product forecasting | |
| US20140278778A1 (en) | Method, apparatus, and computer-readable medium for predicting sales volume | |
| CN114219412B (en) | Automatic replenishment method and replenishment system based on intelligent commodity system sales prediction | |
| Herbon | Optimal piecewise-constant price under heterogeneous sensitivity to product freshness | |
| CN112581182A (en) | Sales management method and system for automatic vending equipment | |
| JP6576043B2 (en) | Product demand forecast system | |
| CN111652653A (en) | Price determination and prediction model construction method, device, equipment and storage medium | |
| CN113763035A (en) | Advertisement delivery effect prediction method and device, computer equipment and storage medium | |
| CN111861605A (en) | Business object recommendation method | |
| CN113837617A (en) | Anti-bill-swiping risk management method and device | |
| CN110189164B (en) | Commodity-store recommendation scheme based on information entropy measurement and random feature sampling | |
| CN114493673A (en) | Commodity price changing method, system, device and storage medium based on user behavior | |
| CN115082153A (en) | Merchant quality evaluation method and device, electronic equipment and storage medium | |
| CN117350766A (en) | Data processing method, system and storage medium based on private domain e-commerce platform | |
| CN103597485A (en) | Pattern extraction device and method | |
| KR101658714B1 (en) | Method and system for predicting online customer action based on online activity history | |
| Raman | Managing inventory for fashion products | |
| CN110222881B (en) | Purchase data prediction method and device, storage medium and terminal | |
| JP2001134643A (en) | Device and method for predicting demand | |
| CN115860865A (en) | Commodity combination construction method and device, equipment, medium and product thereof | |
| US20220343395A1 (en) | User interface for showing availability of orders for concierge shopping service | |
| JP2019046183A (en) | Information processing method and program | |
| CN113139835A (en) | Data processing method, data processing device, nonvolatile storage medium and processor | |
| US20210142348A1 (en) | Multi-layered system for heterogeneous pricing decisions by continuously learning market and hotel dynamics |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240520 Address after: Room 1035, Building 2, No. 7 Jiaogezhuang Street, Nanfaxin District, Shunyi District, Beijing, 100000 Applicant after: Beijing Xiaoma Youshu Technology Co.,Ltd. Country or region after: China Address before: 100000 415-60, 4th floor, building 5, bitongyuan, Haidian District, Beijing Applicant before: BEIJING MATITIE SCIENCE & TECHNOLOGY Co.,Ltd. Country or region before: China |