CN112819540A - Method and device for predicting commodity sales of vending machine and computer-readable storage medium - Google Patents
Method and device for predicting commodity sales of vending machine and computer-readable storage medium Download PDFInfo
- Publication number
- CN112819540A CN112819540A CN202110170458.1A CN202110170458A CN112819540A CN 112819540 A CN112819540 A CN 112819540A CN 202110170458 A CN202110170458 A CN 202110170458A CN 112819540 A CN112819540 A CN 112819540A
- Authority
- CN
- China
- Prior art keywords
- sales
- data
- commodity
- longitudinal
- predicted
- 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 61
- 238000004140 cleaning Methods 0.000 claims description 32
- 230000015654 memory Effects 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 230000007787 long-term memory Effects 0.000 claims description 3
- 230000006403 short-term memory Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 4
- 230000002457 bidirectional effect Effects 0.000 abstract description 3
- 238000013277 forecasting method Methods 0.000 abstract 1
- 230000008569 process Effects 0.000 description 6
- 238000007726 management method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000014171 carbonated beverage Nutrition 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000020510 functional beverage Nutrition 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 235000020124 milk-based beverage Nutrition 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000010295 mobile communication Methods 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
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 235000013616 tea Nutrition 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Control Of Vending Devices And Auxiliary Devices For Vending Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method and a device for predicting commodity sales of a vending machine and a computer readable storage medium, belonging to the field of data processing, wherein the method for predicting commodity sales of the vending machine comprises the following steps: acquiring commodity data; performing transverse prediction and longitudinal prediction on the commodity data to obtain a transverse prediction value and a longitudinal prediction value of a first unit time; and obtaining the predicted sales volume of the first unit time according to the transverse predicted value and the longitudinal predicted value. According to the commodity sales amount forecasting method for the vending machine, the forecasting sales amount is obtained through transverse forecasting and longitudinal forecasting and according to bidirectional forecasting, and the forecasting result is more accurate and reliable; the manager of the vending machine can scientifically analyze and judge the replenishment quantity or the stocking quantity of each commodity by predicting the sales quantity.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for predicting commodity sales of a vending machine, and a computer-readable storage medium.
Background
With the wider and wider market release of the vending machine, the increase of market competition causes that the merchants have to give consideration to the use and management of the vending machine, and the vending machine can stand for a long time only if the vending machine has advantages in all aspects. The general management method is that when the shortage of goods in the vending machine reaches a set threshold value, the management system of the vending machine sends a prompt, then the manager sends out vehicles to add goods, and when the goods are added, the detailed goods adding is detailed, such as which kind of goods are added specifically, the adding amount of each kind of goods is large, and the manager can only guess by experience, and can not predict scientifically and effectively.
Disclosure of Invention
The application aims to solve at least one technical problem in the prior art, and provides a method for predicting commodity sales of a vending machine, which can predict the sales of each commodity of the vending machine so as to be beneficial to scientific and effective goods adding.
According to the method for predicting the commodity sales amount of the vending machine in the embodiment of the first aspect of the application, the method comprises the following steps:
acquiring commodity data;
performing transverse prediction and longitudinal prediction on the commodity data to obtain a transverse prediction value and a longitudinal prediction value of a first unit time; the transverse prediction is carried out according to the commodity data of a corresponding historical first unit time in a plurality of historical unit periods, and the longitudinal prediction is carried out according to the commodity data of a unit time period before the first unit time;
and obtaining the predicted sales volume of the first unit time according to the transverse predicted value and the longitudinal predicted value.
According to the method for predicting the commodity sales of the vending machine, at least the following technical effects are achieved: through transverse prediction and longitudinal prediction, the prediction sales volume is obtained according to bidirectional prediction, and the prediction result is more accurate and reliable; the manager of the vending machine can scientifically analyze and judge the replenishment quantity or the stocking quantity of each commodity by predicting the sales quantity.
According to some embodiments of the present application, the performing lateral prediction and longitudinal prediction on the commodity data to obtain a lateral prediction value and a longitudinal prediction value of a first unit time includes:
acquiring the commodity data of each day in unit time period before the first unit time to obtain a longitudinal data group;
inputting the longitudinal data group into an autoregressive moving average model to obtain a longitudinal predicted value of the first unit time;
acquiring commodity data of a plurality of historical first unit times corresponding to the historical unit periods to obtain a transverse data group, wherein commodity data sales contained in the transverse data group and the commodity data sales contained in the longitudinal data are the same;
and inputting the transverse data group into an autoregressive moving average model to obtain a transverse predicted value of the first unit time.
According to some embodiments of the present application, the integrating the lateral prediction value and the longitudinal prediction value to obtain the predicted sales per unit time includes:
acquiring transverse predicted values, longitudinal predicted values and actual values of a plurality of corresponding historical first unit times in the historical unit periods to obtain transverse predicted value groups, longitudinal predicted value groups and actual value groups;
calculating to obtain a transverse weight and a longitudinal weight according to the transverse predicted value set, the longitudinal predicted value set and the actual value set;
and integrating the transverse predicted value and the longitudinal predicted value according to the transverse weight and the longitudinal weight to obtain the predicted sales volume of the first unit time.
According to some embodiments of the present application, the calculating a lateral weight and a longitudinal weight according to the set of lateral predictors, the set of longitudinal predictors, and the set of actual values includes:
establishing a relational expression of the transverse predicted value, the transverse weight, the longitudinal predicted value, the longitudinal weight and the actual value according to a least square method;
inputting the horizontal prediction value set, the vertical prediction value set and the actual value set into a relational expression to obtain a minimum value of the relational expression;
and obtaining the transverse weight and the longitudinal weight corresponding to the minimum value according to the minimum value of the relational expression.
According to some embodiments of the application, the obtaining the commodity data comprises:
acquiring original sales data;
and cleaning the original sales data to obtain the commodity data.
According to some embodiments of the present application, the cleaning the raw sales data to obtain the commodity data comprises:
classifying the original sales data according to the trade names and sales volumes in the original sales data;
respectively carrying out max and min function screening on the price, the cost and the actual payment amount in the original sales data of the same type to obtain the original sales data after one-time cleaning;
obtaining the order state in the primary cleaned sales data;
filtering the original sales data with abnormal order states to obtain original sales data after secondary cleaning;
filtering data with information missing in the original sales data after the secondary cleaning to obtain original sales data after the tertiary cleaning;
and obtaining the commodity data according to the original sales data after the three times of cleaning.
According to some embodiments of the application, the commodity data includes a commodity name, a sales amount, and a time.
According to some embodiments of the application, further comprising:
inputting the commodity data into a long-term and short-term memory artificial neural network to obtain the predicted sales volume of the commodity in the second unit time; wherein the second unit time comprises a plurality of the first unit times;
obtaining a total prediction amount according to the predicted sales amount of a plurality of first unit time;
comparing the predicted total amount with a corresponding predicted sales amount for the second unit of time;
and if the error between the total prediction amount and the predicted sales amount of the second unit time is within an error range, judging that the predicted sales amount of the first unit time is effective.
An operation control apparatus according to an embodiment of a second aspect of the present application includes: at least one control processor, and a memory communicatively coupled to the at least one control processor;
wherein the memory stores instructions executable by the at least one control processor to enable the at least one control processor to perform the method of predicting vending machine item sales as described in the first aspect.
According to the third aspect of the present application, there is provided a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the method for predicting commodity sales of vending machines according to the first aspect.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The present application is further described with reference to the following figures and examples;
FIG. 1 is a schematic flow chart illustrating a method for predicting sales of goods in a vending machine according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart illustrating a process of obtaining a longitudinal predicted value and a lateral predicted value of a first unit time according to an embodiment of the present application;
fig. 3 is a schematic flow chart illustrating a process of obtaining a predicted sales amount according to a lateral predicted value and a longitudinal predicted value according to an embodiment of the present application;
fig. 4 is a schematic flowchart of acquiring commodity data according to an embodiment of the present application;
FIG. 5 is a schematic flow chart illustrating the process of obtaining the commodity sales amount by cleaning the original sales amount data according to the embodiment of the present application;
fig. 6 is a schematic view of an operation control device according to another embodiment of the present application.
Fig. 7 is a flowchart illustrating a process of determining a predicted sales amount per first unit time using a predicted sales amount per second unit time according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the present embodiments of the present application, preferred embodiments of which are illustrated in the accompanying drawings, which are for the purpose of visually supplementing the description with figures and detailed description, so as to enable a person skilled in the art to visually and visually understand each and every feature and technical solution of the present application, but not to limit the scope of the present application.
In the description of the present application, it is to be understood that the positional descriptions, such as the directions of up, down, front, rear, left, right, etc., referred to herein are based on the directions or positional relationships shown in the drawings, and are only for convenience of description and simplification of description, and do not indicate or imply that the referred device or element must have a specific direction, be constructed and operated in a specific direction, and thus, should not be construed as limiting the present application.
In the description of the present application, the meaning of a plurality is one or more, the meaning of a plurality is two or more, and larger, smaller, larger, etc. are understood as excluding the present number, and larger, smaller, inner, etc. are understood as including the present number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the sales of the indicated technical features or implicitly indicating the precedence of the indicated technical features.
In the description of the present application, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.
The following describes a method for predicting commodity sales of a vending machine according to an embodiment of the present application with reference to the accompanying drawings.
As shown in fig. 1, a method for predicting commodity sales of a vending machine according to an embodiment of the present application includes:
s110: acquiring commodity data;
s120: performing transverse prediction and longitudinal prediction on the commodity data to obtain a transverse prediction value and a longitudinal prediction value of a first unit time; the transverse prediction is carried out according to commodity data of a corresponding historical first unit time in a plurality of historical unit periods, and the longitudinal prediction is carried out according to the commodity data of a unit time period before the first unit time;
s130: and obtaining the predicted sales amount of the first unit time according to the transverse predicted value and the longitudinal predicted value.
The commodity data comprises commodity names, sales volumes and time, the commodity names are used as the basis for classifying the commodity data, and the time is used as the basis for sorting the commodity data.
In some embodiments, the first unit of time is one day, i.e., a specific date; acquiring original sales data of the vending machine in a period of time before the target prediction date, cleaning, namely filtering, the original sales data, and removing invalid information and abnormal information to obtain commodity data in a period of time before the target prediction date; classifying the commodity data into a plurality of groups according to commodity names, respectively predicting each type of commodity, and respectively performing transverse prediction and longitudinal prediction on target prediction dates according to the commodity data of the corresponding group, so that each target prediction date has two prediction results of a transverse prediction value and a longitudinal prediction value; integrating the transverse predicted value and the longitudinal predicted value of each target predicted date according to the weight to obtain the predicted daily sales volume of each target predicted date; according to the steps, the predicted daily sales amount (namely, the predicted sales amount per first unit time) of each type of commodity in the vending machine in a target prediction date can be finally obtained. As shown in table 1, each column in table 1 is a product category, each row in table 1 is a specific date, i.e. the first unit time in this embodiment, and the blank space is filled into the predicted sales amount.
| Mineral water | Carbonated beverage | Functional beverage | Tea beverage | Milk beverage | |
| 1 month and 1 day | |||||
| 1 month and 2 days | |||||
| ..... | |||||
| 12 month and 30 days | |||||
| 12 month and 31 days |
TABLE 1
The vending machine manager can judge how each type of commodity should be loaded and how to replenish the commodity more accurately according to the predicted sales volume. In other embodiments of the application, the first unit time may be several consecutive days, a week, a month, etc. in addition to one day.
According to the method for predicting the commodity sales of the vending machine, the predicted sales are obtained through transverse prediction and longitudinal prediction according to bidirectional prediction, and the prediction result is more accurate and reliable; the manager of the vending machine can scientifically analyze and judge the replenishment quantity or the stocking quantity of each commodity by predicting the sales quantity.
In some embodiments of the present application, step S120: the transverse prediction and the longitudinal prediction are carried out on the commodity data to obtain a transverse prediction value and a longitudinal prediction value of a first unit time, and the method comprises the following steps:
s121: acquiring commodity data of each day in unit time period before first unit time to obtain a longitudinal data set;
s122: inputting the longitudinal data group into an autoregressive moving average model to obtain a longitudinal predicted value of a first unit time;
s123: acquiring commodity data of historical first unit data corresponding to a plurality of historical unit periods before a first unit time to obtain a transverse data group, wherein commodity data sales contained in the transverse data group and commodity data sales contained in the longitudinal data are the same;
s124: and inputting the transverse data group into an autoregressive moving average model to obtain a transverse predicted value of the first unit time.
In some embodiments, a specific day is taken as an example of the first unit time, for example, the first unit time is fifteen days a month, friday, and the unit time period is taken as thirty days; in the specific embodiment, commodity data of a first unit time, namely thirty days before fifteen days of a month, is obtained and is used as a longitudinal data group, and the longitudinal data group is input into an autoregressive moving average model to obtain a predicted sales volume of fifteen days of the month, namely a longitudinal predicted value; and acquiring commodity data (namely commodity data of corresponding historical first unit time in a plurality of historical unit periods) of thirty weeks and fifty weeks before the first unit time, namely fifteen days in one month, as a transverse data set, and inputting the transverse data set into an autoregressive moving average model to obtain the predicted sales volume, namely the transverse predicted value, of the fifteen days in one month. In other embodiments of the present application, besides thirty days, a period of consecutive days may also be twenty days, forty days, sixty days, etc., and the number of weeks taken in a number of consecutive weeks should be the same as the number of days of consecutive days, so as to ensure that the data sales in the vertical data set is the same as the data sales in the horizontal data set.
In some embodiments of the present application, step S130: integrating the transverse predicted value and the longitudinal predicted value to obtain the predicted sales volume of the first unit time, wherein the method comprises the following steps:
s131: acquiring a transverse predicted value, a longitudinal predicted value and an actual value of corresponding historical first unit data in a plurality of historical unit periods before a first unit time to obtain a transverse predicted value group, a longitudinal predicted value group and an actual value group;
s132: calculating to obtain a transverse weight and a longitudinal weight according to the transverse predicted value set, the longitudinal predicted value set and the actual value set;
s133: and integrating the transverse predicted value and the longitudinal predicted value according to the transverse weight and the longitudinal weight to obtain the predicted sales volume of the first unit time.
In some embodiments, also taking the first unit time as fifteen days a month and friday as an example, the unit period is one week; in the specific embodiment, a transverse predicted value, a longitudinal predicted value and an actual value of friday thirty weeks before fifteen days of january are obtained to form thirty groups of sample data; here, the lateral predicted value and the vertical predicted value of friday thirty weeks before fifteen days of january are obtained by the same method as the above steps S121 to S124, and the actual value of friday thirty weeks before fifteen days of january, that is, the actual sales volume.
In some embodiments of the present application, step S132 includes:
establishing a relation among a transverse predicted value, a transverse weight, a longitudinal predicted value, a longitudinal weight and an actual value according to a least square method;
inputting the horizontal predictive value group, the vertical predictive value group and the actual value group into the relational expression to obtain the minimum value of the relational expression;
and obtaining a transverse weight and a longitudinal weight corresponding to the minimum value according to the minimum value of the relational expression.
In some embodiments, according to the least square method and the thirty sets of sample data, let the horizontal predicted value be x, the horizontal weight be a, the vertical predicted value be y, the vertical weight be b, and the actual value be z, obtain the following formula:
(ax+by-z)2
wherein, except the transverse weight a and the longitudinal weight b, the other values are known values; thirty groups of sample data are substituted into the formula to obtain the formulaLet (ax + by-z)2The minimum values a and b are the horizontal weight and the vertical weight. Obtaining the predicted sales amount of the first unit time according to the transverse weight, the transverse predicted value, the longitudinal weight and the longitudinal predicted value, wherein in some embodiments, the calculation formula is as follows: the horizontal weight value multiplied by the horizontal predicted value + the vertical weight value multiplied by the vertical predicted value is the predicted sales amount.
By the method, the transverse weight and the longitudinal weight of the week for seven days can be obtained, and the obtained transverse weight and longitudinal weight can be used for predicting other follow-up dates; as shown in table 2.
TABLE 2
In other embodiments, the sample data may be any sales volume of twenty, forty, fifty, etc. in addition to thirty. By solving the transverse weight and the longitudinal weight, the transverse predicted value and the longitudinal predicted value are organically combined according to the transverse weight and the longitudinal weight, and more accurate predicted daily sales are obtained.
In some embodiments of the application, step S110: acquiring commodity data, comprising:
s410: acquiring original sales data;
s420: and cleaning the original sales data to obtain commodity data.
Each original sales data comprises a transaction number, an order state, a cargo channel, a commodity name, a sales volume, a price, a cost, a real payment amount and time, wherein the order state comprises shipment and shipment abnormity; the commodity data obtained after the cleaning of the original sales data includes commodity names, sales amounts, and time, the commodity names are used as the basis for the classification of the commodity data, and the sales amounts are used as the basis for the sorting of the commodity data.
In some embodiments of the present application, step S420: cleaning the original sales data to obtain commodity data, comprising:
s421: classifying the original sales data according to the trade names and the sales volume in the original sales data;
s422: respectively screening the price, the cost and the real payment amount in the same type of original sales data by a max function and a min function to obtain the original sales data after one-time cleaning;
s423: obtaining the order state in the original sales data after one-time cleaning;
s424: filtering the original sales data with abnormal order states to obtain the original sales data after secondary cleaning;
s425: filtering data with information missing in the original sales data after the secondary cleaning to obtain original sales data after the tertiary cleaning;
s426: and obtaining commodity data according to the original sales data after the three times of cleaning.
In some embodiments, the original sales data are classified according to trade names, and then the original sales data of each type of goods are classified according to sales volume, for example, the original sales data with sales volume of 1 are classified into one type, the original sales data with sales volume of 2 are classified into one type, and so on; in the present embodiment, the values of the price, the cost, and the real payment amount in the original sales data of the unified sales volume of the same type of product are all the same under normal conditions. Respectively screening a max function and a min function for the price, the cost and the actual payment amount in the original sales data of each type of sales volume of each type of commodities, wherein the max function and the min function are used for screening out the maximum value or the minimum value, if the maximum value or the minimum value can be screened out, indicating that the original sales data corresponding to the maximum value or the minimum value is not in accordance with the normal condition, and deleting the original sales data; and if any one of the price, the finished product or the actual payment amount can be screened out to obtain the maximum value or the minimum value, deleting the corresponding original sales data. Through the steps, the original sales data can be quickly and accurately cleaned once, and data with abnormal price, cost and payment amount are filtered out, so that the original sales data after once cleaning is obtained.
And carrying out secondary cleaning on the primary cleaned sales data, identifying the top order state in each piece of primary sales data, and filtering out data with order states of abnormal shipment to obtain the primary cleaned sales data. According to the original sales data after the secondary cleaning, data with missing information are filtered out, and original sales data after the tertiary cleaning are obtained; the data with information missing refers to data with any one or more items of information missing, such as a transaction number, an order status, a lane, a trade name, a sales amount, a price, a cost, a real payment amount, time, and the like, in the original sales data after the secondary cleaning. And finally, deleting data irrelevant to prediction in each original sales data according to the original sales data washed for three times to obtain commodity data. Through cleaning for many times, data with problems in the original sales data are filtered, so that the finally obtained commodity data are all effective data, and the accuracy and the reliability of prediction are improved.
In some embodiments of the present application, the commodity data includes a trade name, a sales amount, and a time.
In some embodiments, information other than the product name, sales amount, and time in each original sales data is deleted from the three-time cleaned original sales data obtained through the above-described steps 421 to 425 to obtain product data; the commodity names are used as a classification basis of commodity data, that is, the commodity data is classified according to commodity types, the sales amount is sample data required for prediction, and the time is used as a sorting and classification basis of the commodity data, for example, the commodity data are sequentially arranged according to a time sequence according to time information, and when the commodity data of a required certain period of time or a certain type of specific time is selected, the time information is used as a basis. By cleaning the original sales data, useless information and abnormal information are removed, only commodity names, sales volumes and time information needed for prediction are reserved, the processing amount of subsequent steps is reduced, and the prediction calculation efficiency is improved.
In some embodiments of the present application, the method for predicting sales of goods in a vending machine further comprises:
s710: inputting the commodity data into the long-term and short-term memory artificial neural network to obtain the predicted sales volume of the commodity in the second unit time; the second unit time comprises a plurality of first unit times;
s720: obtaining a total prediction amount according to the predicted sales amount of a plurality of first unit time;
s730: comparing the predicted total amount with a corresponding predicted sales amount per unit time; :
s740: and if the error between the total prediction amount and the predicted sales amount per second unit time is within the error range, judging that the predicted sales amount per first unit time is effective.
In some embodiments, in this particular embodiment, the first unit of time is taken as one day and the second unit of time is taken as one month; classifying the commodity data according to commodity names, then grouping the commodity data of each type of commodity according to months, inputting the commodity data of each type of commodity into the long-short term memory artificial neural network by taking the month as a unit, and obtaining the predicted monthly sales volume (namely the predicted sales volume of the second unit time) of each type of commodity; according to the predicted daily sales (namely, the predicted sales in the first unit time) of each type of goods obtained in the steps S110 to S130, adding the predicted daily sales belonging to the same month in the predicted daily sales of each type of goods to obtain the predicted total amount of each type of goods; and comparing the predicted total amount and the predicted monthly sales amount of the same type of commodity in the same month, and if the error between the predicted total amount and the predicted monthly sales amount is within the error range, judging that the predicted daily sales amount of the commodity is effective, namely the predicted sales amount of the commodity in the first unit time is effective. The predicted sales amount of the second unit time, namely the total predicted sales amount of a long time, such as the predicted sales amount of each month, obtained by the method can help managers to scientifically and accurately judge how to stock goods (stock type and stock quantity) in a long time in the future.
In a second aspect of the embodiments of the present invention, an operation control device is provided, and the operation control device 600 may be any type of intelligent terminal, such as a mobile phone, a tablet computer, a personal computer, and the like.
As shown in fig. 6, according to some embodiments of the present invention, the operation control apparatus 600 includes: one or more control processors 601 and a memory 602, one control processor 601 being exemplified in fig. 6.
The control processor 601 and the memory 602 may be connected by a bus or other means, and fig. 6 exemplifies a connection by a bus.
The memory 602 is a non-transitory computer readable storage medium, and can be used for storing non-transitory software programs, non-transitory computer executable programs, and units, such as program instructions/units corresponding to the operation control apparatus 600 in the embodiment of the present invention. The control processor 601 executes various functional applications and data processing by executing non-transitory software programs, instructions and units stored in the memory 602, namely, implements the method for predicting the commodity sales of the vending machine according to the above-mentioned method embodiment.
The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to program instructions/units, and the like. Further, the memory 602 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 602 may optionally include memory located remotely from the control processor 601, which may be connected to the operation control device 600 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more units are stored in the memory 602 and, when executed by the one or more control processors 601, perform the method of predicting vending machine item sales in any of the method embodiments described above. For example, the above-described method steps S110 to S130 in fig. 1, method steps S121 to S124 in fig. 2, method steps S131 to S133 in fig. 3, method steps S410 to S420 in fig. 4, method steps S421 to S426 in fig. 5, and method steps S710 to S740 in fig. 7 are performed.
In a third aspect of the embodiments of the present invention, a computer-readable storage medium is further provided, where the computer-readable storage medium stores computer-executable instructions, which are executed by one or more control processors 601, for example, by one of the control processors 601 in fig. 6, and may enable the one or more control processors 601 to perform the method for predicting commodity sales of a vending machine in the above method embodiment, for example, to perform the above-described method steps S110 to S130 in fig. 1, method steps S121 to S124 in fig. 2, method steps S131 to S133 in fig. 3, method steps S410 to S420 in fig. 4, method steps S421 to S426 in fig. 5, and method steps S710 to S740 in fig. 7. .
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a general hardware platform, and certainly can also be implemented by hardware. 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, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
In the description herein, reference to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and alterations to these embodiments may be made without departing from the principles and spirit of this application, and are intended to be included within the scope of this application.
Claims (10)
1. A method for predicting sales of goods in a vending machine, comprising:
acquiring commodity data;
performing transverse prediction and longitudinal prediction on the commodity data to obtain a transverse prediction value and a longitudinal prediction value of a first unit time; the transverse prediction is carried out according to the commodity data of a corresponding historical first unit time in a plurality of historical unit periods, and the longitudinal prediction is carried out according to the commodity data of a unit time period before the first unit time;
and obtaining the predicted sales volume of the first unit time according to the transverse predicted value and the longitudinal predicted value.
2. The method for predicting the commodity sales of a vending machine according to claim 1, wherein the performing of the horizontal prediction and the vertical prediction on the commodity data to obtain the horizontal prediction value and the vertical prediction value of the first unit time comprises:
acquiring the commodity data of each day in unit time period before the first unit time to obtain a longitudinal data group;
inputting the longitudinal data group into an autoregressive moving average model to obtain a longitudinal predicted value of the first unit time;
acquiring commodity data of a plurality of historical first unit times corresponding to the historical unit periods to obtain a transverse data group, wherein commodity data sales contained in the transverse data group and the commodity data sales contained in the longitudinal data are the same;
and inputting the transverse data group into an autoregressive moving average model to obtain a transverse predicted value of the first unit time.
3. The method for predicting the commodity sales of vending machines according to claim 1 or 2, wherein the step of integrating the lateral predicted value and the longitudinal predicted value to obtain the predicted sales of the first unit time comprises the steps of:
acquiring transverse predicted values, longitudinal predicted values and actual values of a plurality of corresponding historical first unit times in the historical unit periods to obtain transverse predicted value groups, longitudinal predicted value groups and actual value groups;
calculating to obtain a transverse weight and a longitudinal weight according to the transverse predicted value set, the longitudinal predicted value set and the actual value set;
and integrating the transverse predicted value and the longitudinal predicted value according to the transverse weight and the longitudinal weight to obtain the predicted sales volume of the first unit time.
4. The method for predicting commodity sales of vending machines according to claim 3, wherein said calculating lateral weights and vertical weights according to said set of lateral predictive values, said set of vertical predictive values, and said set of actual values comprises:
establishing a relational expression of the transverse predicted value, the transverse weight, the longitudinal predicted value, the longitudinal weight and the actual value according to a least square method;
inputting the horizontal prediction value set, the vertical prediction value set and the actual value set into a relational expression to obtain a minimum value of the relational expression;
and obtaining the transverse weight and the longitudinal weight corresponding to the minimum value according to the minimum value of the relational expression.
5. The method for predicting the commodity sales of vending machines according to claim 1 or 2, wherein said obtaining commodity data comprises:
acquiring original sales data;
and cleaning the original sales data to obtain the commodity data.
6. The method of predicting vending machine commodity sales of claim 5, wherein said cleaning the raw sales data to obtain the commodity data comprises:
classifying the original sales data according to the trade names and sales volumes in the original sales data;
respectively carrying out max and min function screening on the price, the cost and the actual payment amount in the original sales data of the same type to obtain the original sales data after one-time cleaning;
obtaining the order state in the primary cleaned sales data;
filtering the original sales data with abnormal order states to obtain original sales data after secondary cleaning;
filtering data with information missing in the original sales data after the secondary cleaning to obtain original sales data after the tertiary cleaning;
and obtaining the commodity data according to the original sales data after the three times of cleaning.
7. The method of predicting the sales of goods from vending machine according to claim 1 or 2, wherein said goods data comprises the goods name, the sales and the time.
8. The method of predicting vending machine commodity sales of claim 1 or claim 2, further comprising:
inputting the commodity data into a long-term and short-term memory artificial neural network to obtain the predicted sales volume of the commodity in the second unit time; wherein the second unit time comprises a plurality of the first unit times;
obtaining a total prediction amount according to the predicted sales amount of a plurality of first unit time;
comparing the predicted total amount with a corresponding predicted sales amount for the second unit of time;
and if the error between the total prediction amount and the predicted sales amount of the second unit time is within an error range, judging that the predicted sales amount of the first unit time is effective.
9. An operation control device characterized by comprising:
at least one control processor, and a memory communicatively coupled to the at least one control processor;
wherein the memory stores instructions executable by the at least one control processor to enable the at least one control processor to perform the method of predicting vending machine item sales as claimed in any one of claims 1 to 8.
10. A computer-readable storage medium having stored thereon computer-executable instructions for causing a computer to perform the method of predicting vending machine item sales as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110170458.1A CN112819540A (en) | 2021-02-08 | 2021-02-08 | Method and device for predicting commodity sales of vending machine and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110170458.1A CN112819540A (en) | 2021-02-08 | 2021-02-08 | Method and device for predicting commodity sales of vending machine and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112819540A true CN112819540A (en) | 2021-05-18 |
Family
ID=75863720
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110170458.1A Pending CN112819540A (en) | 2021-02-08 | 2021-02-08 | Method and device for predicting commodity sales of vending machine and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112819540A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116778635A (en) * | 2023-05-26 | 2023-09-19 | 东莞嘉丰机电设备有限公司 | Fruit juice vending machine and control system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003178356A (en) * | 2001-12-11 | 2003-06-27 | Japan Tobacco Inc | Sales prediction method |
| CN105184975A (en) * | 2015-10-14 | 2015-12-23 | 微点（北京）文化传媒有限公司 | Management system and management method for vending machine |
| CN110135876A (en) * | 2018-02-09 | 2019-08-16 | 北京京东尚科信息技术有限公司 | The method and device of Method for Sales Forecast |
| CN111091241A (en) * | 2019-12-11 | 2020-05-01 | 亿达信息技术有限公司 | BP neural network-based drug sales prediction and decision method and system |
| CN111538955A (en) * | 2020-04-17 | 2020-08-14 | 北京小米松果电子有限公司 | Goods sales prediction method, device and storage medium |
| CN111582912A (en) * | 2020-04-20 | 2020-08-25 | 佛山科学技术学院 | Portrait modeling method based on deep embedding clustering algorithm |
-
2021
- 2021-02-08 CN CN202110170458.1A patent/CN112819540A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003178356A (en) * | 2001-12-11 | 2003-06-27 | Japan Tobacco Inc | Sales prediction method |
| CN105184975A (en) * | 2015-10-14 | 2015-12-23 | 微点（北京）文化传媒有限公司 | Management system and management method for vending machine |
| CN110135876A (en) * | 2018-02-09 | 2019-08-16 | 北京京东尚科信息技术有限公司 | The method and device of Method for Sales Forecast |
| CN111091241A (en) * | 2019-12-11 | 2020-05-01 | 亿达信息技术有限公司 | BP neural network-based drug sales prediction and decision method and system |
| CN111538955A (en) * | 2020-04-17 | 2020-08-14 | 北京小米松果电子有限公司 | Goods sales prediction method, device and storage medium |
| CN111582912A (en) * | 2020-04-20 | 2020-08-25 | 佛山科学技术学院 | Portrait modeling method based on deep embedding clustering algorithm |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116778635A (en) * | 2023-05-26 | 2023-09-19 | 东莞嘉丰机电设备有限公司 | Fruit juice vending machine and control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108922026B (en) | Replenishment management method and device for vending machine and user terminal | |
| CN108549851B (en) | Method and device for identifying goods in intelligent container and intelligent container | |
| CN107016810B (en) | Self-service decrement weighing charging system and self-service decrement weighing charging method | |
| CN110335426A (en) | Commodity pricing method, intelligent electronic-scale and cash register system | |
| CN113850651A (en) | Off-line store distribution method and related equipment | |
| CN110264236A (en) | Vending machine sales data analysis method, device and storage medium | |
| CN110348902A (en) | A kind of acquisition device and method of tobacco retail terminal sales information | |
| CN112070423A (en) | Stock pre-occupation method and device, electronic equipment and storage medium | |
| US20230419323A1 (en) | Systems and methods for routing electronic transactions using network simulation and forecasting | |
| CN113888254A (en) | Shelf commodity management method and electronic equipment | |
| CN113762701A (en) | Article replenishment method, article replenishment device and storage medium | |
| CN110503456B (en) | Fresh product production guiding method and system | |
| CN112819540A (en) | Method and device for predicting commodity sales of vending machine and computer-readable storage medium | |
| CN110826481A (en) | Data processing method, commodity identification method, server and storage medium | |
| CN110675021A (en) | Kitchen waste treatment method and device | |
| CN114219397A (en) | Inventory management method, device, equipment and storage medium | |
| KR102466396B1 (en) | Method and apparatus for managing commodity information | |
| CN116957471B (en) | Intelligent retail service method, system, electronic equipment and storage medium | |
| CN111507779A (en) | Method and device for grading commodities | |
| CN113139768B (en) | Goods shortage monitoring method based on unmanned vending machine | |
| CN113095914B (en) | Order management method, system, equipment and computer storage medium for electronic commerce platform | |
| CN111126893B (en) | Vending machine stock management method, equipment and computer readable storage medium | |
| CN110782135B (en) | Tableware circulation control method and device | |
| CN110956761B (en) | Object processing method and system, computer system and computer readable medium | |
| DE102019106057A1 (en) | Method, device for data processing and holding device for classifying food |
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 |