CN113139768A - Goods shortage monitoring method based on unmanned vending machine - Google Patents

Goods shortage monitoring method based on unmanned vending machine Download PDF

Info

Publication number
CN113139768A
CN113139768A CN202110313625.3A CN202110313625A CN113139768A CN 113139768 A CN113139768 A CN 113139768A CN 202110313625 A CN202110313625 A CN 202110313625A CN 113139768 A CN113139768 A CN 113139768A
Authority
CN
China
Prior art keywords
commodity
stock
commodities
vending machine
unmanned vending
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110313625.3A
Other languages
Chinese (zh)
Other versions
CN113139768B (en
Inventor
陈云
周梓荣
龚庆祝
尹波
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Convenisun Technology Co ltd
Original Assignee
Guangdong Convenisun Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Convenisun Technology Co ltd filed Critical Guangdong Convenisun Technology Co ltd
Priority to CN202110313625.3A priority Critical patent/CN113139768B/en
Publication of CN113139768A publication Critical patent/CN113139768A/en
Application granted granted Critical
Publication of CN113139768B publication Critical patent/CN113139768B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F9/00—Details other than those peculiar to special kinds or types of apparatus
    • G07F9/02—Devices for alarm or indication, e.g. when empty; Advertising arrangements in coin-freed apparatus
    • G07F9/026—Devices for alarm or indication, e.g. when empty; Advertising arrangements in coin-freed apparatus for alarm, monitoring and auditing in vending machines or means for indication, e.g. when empty

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Finance (AREA)
  • Human Resources & Organizations (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Educational Administration (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Control Of Vending Devices And Auxiliary Devices For Vending Devices (AREA)

Abstract

The invention provides a goods shortage monitoring method based on an unmanned vending machine, which comprises the following steps: step 1: the method comprises the steps of obtaining the sales volume of each commodity of the unmanned vending machine in a specific time period, and grading each commodity in the unmanned vending machine based on the sales volume of each commodity; step 2: determining the stock shortage threshold value of each grade of commodity based on the grade division; and step 3: establishing a threshold label for the commodities in the unmanned vending machine according to the stock shortage threshold of each grade of commodities; and 4, step 4: scanning the commodities in the unmanned vending machine to obtain the quantity of the commodities, judging whether the commodities are out of stock or not based on the threshold value labels of the commodities, and sending out an out-of-stock alarm prompt if the commodities are out of stock; the accuracy of judging the out-of-stock is improved, intelligent statistics on commodities is realized, out-of-stock alarming reminding is sent, the condition that the unmanned vending machine of the staff is in short-stock is timely reminded, and shopping of customers is facilitated.

Description

Goods shortage monitoring method based on unmanned vending machine
Technical Field
The invention relates to the technical field of unmanned vending machines, in particular to a goods shortage monitoring method based on an unmanned vending machine.
Background
The vending machine is vending equipment commonly found in areas such as schools, restaurants and office building channels, shopping is facilitated for customers, and meanwhile the vending cost of merchants is reduced.
Goods suppliers of goods need to replenish goods to the vending machine regularly, special replenishment personnel who still need arrange regularly check the vending machine, discover and record the goods that need to be replenished, then periodically replenish the goods, this kind of mode not only can need the manpower to carry out loaded down with trivial details statistics, and can not real-time supervision unmanned vending machine's goods quantity, and then can not discover the condition that unmanned vending machine lacks the goods in time, can lead to the customer can't go out the goods after buying the lack of goods and paying, the shopping for the customer has brought inconvenience.
Secondly, the conventional method for judging the shortage of the vending machine cannot judge whether the vending machine is in shortage or not according to the respective characteristics of the vending machine, such as sales volume, application and the like, and the accuracy of judging the shortage needs to be improved.
Disclosure of Invention
The invention provides an out-of-stock monitoring method based on an unmanned vending machine, which is characterized in that commodities in the unmanned vending machine are graded according to the sales volume of each commodity sale in the unmanned vending machine, so that the accuracy of judging out-of-stock is improved, the intelligent counting of the commodities is realized, out-of-stock alarm reminding is sent, staff are reminded of the out-of-stock condition of the unmanned vending machine in time, and the shopping of customers is facilitated.
The invention provides a goods shortage monitoring method based on an unmanned vending machine, which comprises the following steps:
step 1: the method comprises the steps of obtaining the sales volume of each commodity of the unmanned vending machine in a specific time period, and grading each commodity in the unmanned vending machine based on the sales volume of each commodity;
step 2: determining the stock shortage threshold value of each grade of commodity based on the grade division;
and step 3: establishing a threshold label for the commodities in the unmanned vending machine according to the stock shortage threshold of each grade of commodities;
and 4, step 4: scanning the commodities in the unmanned vending machine to obtain the quantity of the commodities, judging whether the commodities are out of stock or not based on the threshold value labels of the commodities, and sending out an out-of-stock alarm prompt if the commodities are out of stock.
In one possible way of realisation,
in step 1, obtaining the sales volume of each commodity of the unmanned vending machine within the preset time comprises:
acquiring people flow data near the unmanned vending machine, and selecting a time period with people flow larger than a preset people flow as a specific time period based on the people flow data;
acquiring all order information of the unmanned vending machine in the specific time period;
acquiring order typesetting rules of all the order information, and setting an identification sequence based on the order typesetting rules;
identifying all the order information according to the identification sequence to obtain order types of all the order information, wherein the order types are divided into valid orders and invalid orders;
analyzing the effective order information based on a preset extraction target to acquire extraction rule information corresponding to the preset extraction target;
configuring an information extraction template for the effective order information based on the extraction rule information, and performing target extraction on the effective order information based on the information extraction template to obtain commodity purchase information;
determining the commodity name and the corresponding purchase quantity thereof based on the commodity purchase information to obtain the initial sales volume of each commodity;
analyzing the specific time period, acquiring the commodity types which are ordered from large to small according to the commodity sales in the specific time period, and establishing a serial number-commodity type comparison table;
and acquiring a corresponding relation between the commodity name and the serial number based on the commodity type-name comparison table and the serial number-commodity type comparison table, setting a weight value for the initial sales volume of each commodity based on the corresponding relation, and correcting the initial sales volume of each commodity to acquire the corrected sales volume of each commodity.
In one possible way of realisation,
in step 1, the grading each commodity in the unmanned vending machine based on the sales volume of each commodity includes:
acquiring commodity information of each commodity of the unmanned vending machine, and acquiring commodity price and average commodity use time of each commodity based on the commodity information;
inputting the commodity name of each commodity and the average commodity use time corresponding to the commodity name into a time prediction model to obtain the purchase time interval of each commodity;
setting a first numerical value for each commodity based on the sales volume of each commodity;
setting a second numerical value for each commodity based on the commodity price of each commodity;
setting a third numerical value for each commodity based on the purchase time interval of each commodity;
normalizing the first numerical value, the second numerical value and the third numerical value, and then performing addition operation to obtain the grade division value of each commodity;
and grading each commodity in the unmanned vending machine based on the grading value.
In one possible way of realisation,
in step 3, establishing a threshold label for the goods in the unmanned vending machine according to the out-of-stock threshold of the goods of each grade comprises:
acquiring a commodity image in the backorder threshold value of each grade of commodity;
scanning images of all commodities in the unmanned vending machine to obtain scanned images of all commodities;
comparing and matching the commodity image and the scanned image to obtain an image matching table;
determining the goods shortage threshold value corresponding to each commodity in the unmanned vending machine based on the image matching table;
acquiring a relation establishment request between each commodity and a backorder threshold value corresponding to each commodity;
setting a first resource for each commodity in the unmanned vending machine based on the relationship establishment request, and setting a second resource for a stock shortage threshold corresponding to each commodity;
and establishing a threshold label for the commodity in the unmanned vending machine based on the first resource and the second resource.
In one possible way of realisation,
in step 4, based on the threshold value label of the commodity, whether the commodity is out of stock is judged, and if the commodity is out of stock, sending out the out-of-stock alarm prompt comprises the following steps:
determining an out-of-stock threshold for the item based on the threshold label for the item;
judging whether the quantity of the commodities is larger than the stock shortage threshold value of the commodities;
if yes, indicating that the goods do not have the out-of-stock condition;
otherwise, indicating that the goods are out of stock and alarming and reminding.
In one possible way of realisation,
in step 4, after sending out the out-of-stock alarm prompt, the method further comprises the following steps:
determining the out-of-stock commodity based on the out-of-stock alarm prompt, and acquiring a state conversion instruction based on the out-of-stock commodity;
based on the conversion instruction, converting the state of the out-of-stock commodity from a quantity display state to an out-of-stock state; and closing the purchase link for the out-of-stock item.
In one possible way of realisation,
in step 4, scanning the commodities in the unmanned vending machine, and acquiring the quantity of the commodities comprises:
scanning all areas of commodities in the unmanned vending machine to obtain an overall image of all the areas, and preprocessing the overall image to obtain a standardized image;
the method comprises the steps that commodity information of commodities placed in the unmanned vending machine is obtained in advance, and an appearance characteristic set of the commodities is obtained on the basis of the commodity information;
determining a segmentation contour of the standardized image based on the appearance feature set, and performing image segmentation on the standardized image based on the segmentation contour to obtain a single commodity image;
judging whether the number of the single commodity images is consistent with the number of commodities placed in the unmanned vending machine or not;
if so, indicating that the segmentation contour of the standardized image is accurate;
otherwise, if the number of the single commodity images is larger than that of the commodities placed in the unmanned vending machine, performing similarity detection on the single commodity images, and combining two single commodity images meeting a first preset similarity requirement to obtain a new single commodity image;
otherwise, if the number of the single commodity images is smaller than that of commodities placed in the unmanned vending machine, re-determining the segmentation outline of the standardized image, and obtaining a new single commodity image;
identifying and segmenting the single commodity image based on commodity information corresponding to the single commodity image after judgment and re-segmentation to obtain a segmented area of the corresponding commodity, wherein the segmented area comprises an integral area and a local area;
determining the number of the whole areas as a first number;
determining a whole area adjacent to the local area, and intercepting a reference area close to the local area in the adjacent whole area;
judging the similarity between the local area and the reference area, counting the local area if the similarity meets a second preset similarity requirement, and finally obtaining a second quantity, or not counting the local area;
the number of the commodities is acquired based on the first number and the second number of the commodities.
In one possible way of realisation,
in step 4, scanning the commodities in the unmanned vending machine, and after acquiring the quantity of the commodities, further comprising:
determining the replenishment time of the commodities based on the quantity of the commodities and the stock shortage threshold corresponding to the commodities, wherein the process is as follows:
predicting the sale time of the commodities according to the following formula based on the quantity of the commodities and the backorder threshold value corresponding to the commodities;
Figure BDA0002990935290000051
wherein T represents the time of sale of the commodity, TSRepresenting an average time of sale of the goods at the number of the goods in the vending machine system, S representing the number of the goods, A representing an out-of-stock threshold of the goods, and S>A,
Figure BDA0002990935290000052
The sales volume of the commodity in the average sales time of the commodity is represented, e represents a natural number and takes a value of 2.72, delta represents the dependence value of the commodity on advertising, and takes a value of [0,0.6 ]]And tau represents the value of the advertisement putting strength of the commodity and takes a value of [0, 1%]；
Calculating replenishment time of the commodity according to the following formula based on the sale time of the commodity;
Figure BDA0002990935290000061
wherein, TBShowing the time for calculating the replenishment of the commodity, L showing the cost for replenishing the commodity once, C showing the total sales volume of the commodity after replenishing the commodity once and selling all the commodity, M showing the price of the commodity, D showing the cost of the commodity, and epsilon showing the replenishment compensation coefficient, wherein the value of epsilon is (0.2, 0.4);
and determining the replenishment reminding time based on the replenishment time, and carrying out replenishment reminding when the replenishment reminding time is reached.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart of a method for monitoring out-of-stock based on an unmanned vending machine according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Example 1
The embodiment of the invention provides a method for monitoring out-of-stock based on an unmanned vending machine, which comprises the following steps as shown in figure 1:
step 1: the method comprises the steps of obtaining the sales volume of each commodity of the unmanned vending machine in a specific time period, and grading each commodity in the unmanned vending machine based on the sales volume of each commodity;
step 2: determining the stock shortage threshold value of each grade of commodity based on the grade division;
and step 3: establishing a threshold label for the commodities in the unmanned vending machine according to the stock shortage threshold of each grade of commodities;
and 4, step 4: scanning the commodities in the unmanned vending machine to obtain the quantity of the commodities, judging whether the commodities are out of stock or not based on the threshold value labels of the commodities, and sending out an out-of-stock alarm prompt if the commodities are out of stock.
In this embodiment, the larger the sales volume, the higher the corresponding grade of the goods, and the larger the corresponding stock out threshold.
In this embodiment, the grade division of each article is related to the sales volume of the article, the price of the article, and the purchase time interval.
The working principle and the beneficial effects of the design scheme are as follows: the goods in the unmanned vending machine are graded according to the selling amount of each goods in the unmanned vending machine, the goods shortage threshold value of the graded goods is obtained, whether the goods are in shortage is judged, the accuracy of judging the shortage is improved, the goods in the unmanned vending machine are scanned, the quantity of the goods is obtained, intelligent statistics of the goods is achieved, the shortage alarm reminding is sent out, the condition that the unmanned vending machine of a worker is in shortage is timely reminded, and the shopping of customers is facilitated.
Example 2
Based on embodiment 1, an embodiment of the present invention provides a method for monitoring out-of-stock based on an unmanned vending machine, where in step 1, obtaining a sales volume of each commodity of the unmanned vending machine within a preset time includes:
acquiring people flow data near the unmanned vending machine, and selecting a time period with people flow larger than a preset people flow as a specific time period based on the people flow data;
acquiring all order information of the unmanned vending machine in the specific time period;
acquiring order typesetting rules of all the order information, and setting an identification sequence based on the order typesetting rules;
identifying all the order information according to the identification sequence to obtain order types of all the order information, wherein the order types are divided into valid orders and invalid orders;
analyzing the effective order information based on a preset extraction target to acquire extraction rule information corresponding to the preset extraction target;
configuring an information extraction template for the effective order information based on the extraction rule information, and performing target extraction on the effective order information based on the information extraction template to obtain commodity purchase information;
determining the commodity name and the corresponding purchase quantity thereof based on the commodity purchase information to obtain the initial sales volume of each commodity;
analyzing the specific time period, acquiring the commodity types which are ordered from large to small according to the commodity sales in the specific time period, and establishing a serial number-commodity type comparison table;
and acquiring a corresponding relation between the commodity name and the serial number based on the commodity type-name comparison table and the serial number-commodity type comparison table, setting a weight value for the initial sales volume of each commodity based on the corresponding relation, and correcting the initial sales volume of each commodity to acquire the corrected sales volume of each commodity.
In this embodiment, the order layout rule is a distribution of each piece of information of the order, such as user information, payment information, national vein commodity information, and the like on the order.
In this embodiment, the orders are identified according to the identification sequence, so that the identification can be performed orderly and efficiently, and the efficiency of setting the stock shortage threshold is improved.
In this embodiment. The valid order refers to an order which is successfully paid, and the invalid order refers to an order which is not completely paid.
In this embodiment, the preset extraction target is related to the purchase of the commodity in the order.
In this embodiment, the larger the serial number of the commodity name is, the larger the weight value is set for the initial sales volume of the commodity.
In this embodiment, the initial sales volume of the commodity is corrected based on the specific time period, so that the influence on the commodity type sales volume due to different selections in the specific time period can be avoided.
In this embodiment, for example, if the serial number corresponding to the drink is 3 from the serial number-product type comparison table, and if the product type corresponding to the product name called iced black tea is a drink from the product type-name comparison table, the correspondence between the product name and the serial number is 3 of the serial number of iced black tea.
The beneficial effect of above-mentioned design is: the sales volume of each commodity of the unmanned vending machine in a specific time period is obtained, a basis is provided for grading each commodity in the unmanned vending machine, and a basis is provided for improving the accuracy of judging the shortage of the commodities.
Example 3
Based on embodiment 1, an embodiment of the present invention provides a method for monitoring out-of-stock based on an unmanned vending machine, where in step 1, ranking each commodity in the unmanned vending machine based on a sales volume of each commodity includes:
acquiring commodity information of each commodity of the unmanned vending machine, and acquiring commodity price and average commodity use time of each commodity based on the commodity information;
inputting the commodity name of each commodity and the average commodity use time corresponding to the commodity name into a time prediction model to obtain the purchase time interval of each commodity;
setting a first numerical value for each commodity based on the sales volume of each commodity;
setting a second numerical value for each commodity based on the commodity price of each commodity;
setting a third numerical value for each commodity based on the purchase time interval of each commodity;
normalizing the first numerical value, the second numerical value and the third numerical value, and then calculating according to a preset method to obtain the grade division value of each commodity;
and grading each commodity in the unmanned vending machine according to a preset grading rule based on the grading value.
In this embodiment, the higher the sales of the article, the larger the first value, the lower the price of the article, the larger the second value, the shorter the purchase time interval, and the larger the third value.
In this embodiment, the preset grade division rule is that a grade numerical range is set according to an actual situation, and the higher the grade division value is, the higher the grade of the commodity is.
In this embodiment, the preset method is to add the second numerical value and the third numerical value, and then multiply the second numerical value and the third numerical value by the first numerical value to obtain the grade division value.
The beneficial effect of above-mentioned design is: the commodities in the unmanned vending machine are graded based on the sales volume of the commodities, the influence of commodity price and purchase time interval is considered when the commodities are graded, the precision of commodity grading is improved, and the improvement basis is determined for the commodity shortage threshold.
Example 4
Based on embodiment 1, an embodiment of the present invention provides an out-of-stock monitoring method based on an unmanned vending machine, where in step 3, establishing a threshold label for a commodity in the unmanned vending machine according to an out-of-stock threshold of each grade of commodity includes:
acquiring a commodity image in the backorder threshold value of each grade of commodity;
scanning images of all commodities in the unmanned vending machine to obtain scanned images of all commodities;
comparing and matching the commodity image and the scanned image to obtain an image matching table;
determining the goods shortage threshold value corresponding to each commodity in the unmanned vending machine based on the image matching table;
acquiring a relation establishment request between each commodity and a backorder threshold value corresponding to each commodity;
setting a first resource for each commodity in the unmanned vending machine based on the relationship establishment request, and setting a second resource for a stock shortage threshold corresponding to each commodity;
and establishing a threshold label for the commodity in the unmanned vending machine based on the first resource and the second resource.
In this embodiment, the first resource and the second resource are resource configurations, such as program configurations and memory configurations, required for establishing the out-of-stock thresholds corresponding to the commodities and the threshold tags, respectively.
The beneficial effect of above-mentioned design is: threshold value labels are established for commodities in the unmanned vending machine, the size of the threshold value of the commodities in the unmanned vending machine is confirmed, and a basis is provided for judging whether the commodities are out of stock or not based on the threshold value labels.
Example 5
Based on the embodiment 1, the embodiment of the invention provides a method for monitoring out-of-stock based on an unmanned vending machine, in the step 4, based on the threshold value label of the commodity, whether the commodity is out-of-stock is judged, and if the commodity is out-of-stock, sending out an out-of-stock alarm prompt includes:
determining an out-of-stock threshold for the item based on the threshold label for the item;
judging whether the quantity of the commodities is larger than the stock shortage threshold value of the commodities;
if yes, indicating that the goods do not have the out-of-stock condition;
otherwise, indicating that the goods are out of stock and alarming and reminding.
The beneficial effect of above-mentioned design is: whether goods are out of stock is judged by comparing the quantity of the goods with the out-of-stock threshold value, and warning is carried out when goods are out of stock, so that the goods out of stock monitoring is completed without manual help, and the condition that goods are out of stock of the unmanned vending machine is convenient to find in time.
Example 6
Based on embodiment 1, the embodiment of the present invention provides a method for monitoring out-of-stock based on an unmanned vending machine, and in step 4, after sending out an out-of-stock alarm prompt, the method further includes:
determining the out-of-stock commodity based on the out-of-stock alarm prompt, and acquiring a state conversion instruction based on the out-of-stock commodity;
based on the conversion instruction, converting the state of the out-of-stock commodity from a quantity display state to an out-of-stock state; and closing the purchase link for the out-of-stock item.
The beneficial effect of above-mentioned design is: the state of the out-of-stock commodity is converted into the out-of-stock state, the purchase link of the out-of-stock commodity is closed, the condition that the customer cannot take out the commodity after purchasing the out-of-stock commodity and paying is avoided, and inconvenience is avoided for the customer.
Example 7
Based on embodiment 1, an embodiment of the present invention provides a method for monitoring out-of-stock based on an unmanned vending machine, where in step 4, scanning the commodities in the unmanned vending machine, and acquiring the quantity of the commodities includes:
scanning all areas of commodities in the unmanned vending machine to obtain an overall image of all the areas, and preprocessing the overall image to obtain a standardized image;
the method comprises the steps that commodity information of commodities placed in the unmanned vending machine is obtained in advance, and an appearance characteristic set of the commodities is obtained on the basis of the commodity information;
determining a segmentation contour of the standardized image based on the appearance feature set, and performing image segmentation on the standardized image based on the segmentation contour to obtain a single commodity image;
judging whether the number of the single commodity images is consistent with the number of commodities placed in the unmanned vending machine or not;
if so, indicating that the segmentation contour of the standardized image is accurate;
otherwise, if the number of the single commodity images is larger than that of the commodities placed in the unmanned vending machine, performing similarity detection on the single commodity images, and combining two single commodity images meeting a first preset similarity requirement to obtain a new single commodity image;
otherwise, if the number of the single commodity images is smaller than that of commodities placed in the unmanned vending machine, re-determining the segmentation outline of the standardized image, and obtaining a new single commodity image;
identifying and segmenting the single commodity image based on commodity information corresponding to the single commodity image after judgment and re-segmentation to obtain a segmented area of the corresponding commodity, wherein the segmented area comprises an integral area and a local area;
determining the number of the whole areas as a first number;
determining a whole area adjacent to the local area, and intercepting a reference area close to the local area in the adjacent whole area;
judging the similarity between the local area and the reference area, counting the local area if the similarity meets a second preset similarity requirement, and finally obtaining a second quantity, or not counting the local area;
the number of the commodities is acquired based on the first number and the second number of the commodities.
In this embodiment, the whole area is an area where a front image of the corresponding product can be obtained.
In this embodiment, the local area is an area where only a local front image of the corresponding product can be obtained.
In this embodiment, the similarity determination is performed on the reference areas close to the local areas in the local area, so that the accuracy of commodity identification can be improved, and the misdetermination of the local area due to incomplete local areas can be avoided.
The beneficial effect of above-mentioned design is: through right commodity in the unmanned aerial vehicle vending machine scans, acquires the quantity of commodity, has realized the monitoring to commodity quantity in the unmanned aerial vehicle vending machine, judges to provide the data basis for the out-of-stock.
Example 8
Based on embodiment 1, an embodiment of the present invention provides a method for monitoring out-of-stock based on an unmanned vending machine, where in step 4, after scanning commodities in the unmanned vending machine and obtaining the quantity of the commodities, the method further includes:
determining the replenishment time of the commodities based on the quantity of the commodities and the stock shortage threshold corresponding to the commodities, wherein the process is as follows:
predicting the sale time of the commodities according to the following formula based on the quantity of the commodities and the backorder threshold value corresponding to the commodities;
Figure BDA0002990935290000131
wherein T represents the time of sale of the commodity, TSRepresenting an average time of sale of the goods at the number of the goods in the vending machine system, S representing the number of the goods, A representing an out-of-stock threshold of the goods, and S>A,
Figure BDA0002990935290000132
The sales volume of the commodity in the average sales time of the commodity is represented, e represents a natural number and takes a value of 2.72, delta represents the dependence value of the commodity on advertising, and takes a value of [0,0.6 ]]And tau represents the value of the advertisement putting strength of the commodity and takes a value of [0, 1%]；
Calculating replenishment time of the commodity according to the following formula based on the sale time of the commodity;
Figure BDA0002990935290000133
wherein, TBShowing the time for calculating the replenishment of the commodity, L showing the cost for replenishing the commodity once, C showing the total sales volume of the commodity after replenishing the commodity once and selling all the commodity, M showing the price of the commodity, D showing the cost of the commodity, and epsilon showing the replenishment compensation coefficient, wherein the value of epsilon is (0.2, 0.4);
and determining the replenishment reminding time based on the replenishment time, and carrying out replenishment reminding when the replenishment reminding time is reached.
In this embodiment, the sale time of the commodity is the time from the number of the commodity to the stock out threshold corresponding to the commodity.
In this embodiment, the influence of the sales volume of the product on the advertisement is taken into account when calculating the sales time of the product, so that the predicted sales time is more accurate.
In the embodiment, the replenishment time is determined according to the replenishment cost of the commodity and the total sales volume of the commodity after replenishment, so that the cost performance of the replenishment time is improved under the condition of meeting the requirements of customers.
The beneficial effect of above-mentioned design is: the replenishment time of the commodities is determined based on the quantity of the commodities and the stock shortage threshold value corresponding to the commodities, so that replenishment is timely performed, the requirements of customers are met, and convenience is brought to shopping of the customers.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (8)

1. A goods shortage monitoring method based on an unmanned vending machine is characterized by comprising the following steps:
step 1: the method comprises the steps of obtaining the sales volume of each commodity of the unmanned vending machine in a specific time period, and grading each commodity in the unmanned vending machine based on the sales volume of each commodity;
step 2: determining the stock shortage threshold value of each grade of commodity based on the grade division;
and step 3: establishing a threshold label for the commodities in the unmanned vending machine according to the stock shortage threshold of each grade of commodities;
and 4, step 4: scanning the commodities in the unmanned vending machine to obtain the quantity of the commodities, judging whether the commodities are out of stock or not based on the threshold value labels of the commodities, and sending out an out-of-stock alarm prompt if the commodities are out of stock.
2. The method for monitoring the out-of-stock based on the unmanned aerial vehicle as claimed in claim 1, wherein the step 1, obtaining the sales volume of each commodity of the unmanned aerial vehicle within a preset time comprises:
acquiring people flow data near the unmanned vending machine, and selecting a time period with people flow larger than a preset people flow as a specific time period based on the people flow data;
acquiring all order information of the unmanned vending machine in the specific time period;
acquiring order typesetting rules of all the order information, and setting an identification sequence based on the order typesetting rules;
identifying all the order information according to the identification sequence to obtain order types of all the order information, wherein the order types are divided into valid orders and invalid orders;
analyzing the effective order information based on a preset extraction target to acquire extraction rule information corresponding to the preset extraction target;
configuring an information extraction template for the effective order information based on the extraction rule information, and performing target extraction on the effective order information based on the information extraction template to obtain commodity purchase information;
determining the commodity name and the corresponding purchase quantity thereof based on the commodity purchase information to obtain the initial sales volume of each commodity;
analyzing the specific time period, acquiring the commodity types which are ordered from large to small according to the commodity sales in the specific time period, and establishing a serial number-commodity type comparison table;
and acquiring a corresponding relation between the commodity name and the serial number based on the commodity type-name comparison table and the serial number-commodity type comparison table, setting a weight value for the initial sales volume of each commodity based on the corresponding relation, and correcting the initial sales volume of each commodity to acquire the corrected sales volume of each commodity.
3. The method as claimed in claim 1, wherein the step 1 of ranking the commodities in the vending machine based on the sales volume of the commodities comprises:
acquiring commodity information of each commodity of the unmanned vending machine, and acquiring commodity price and average commodity use time of each commodity based on the commodity information;
inputting the commodity name of each commodity and the average commodity use time corresponding to the commodity name into a time prediction model to obtain the purchase time interval of each commodity;
setting a first numerical value for each commodity based on the sales volume of each commodity;
setting a second numerical value for each commodity based on the commodity price of each commodity;
setting a third numerical value for each commodity based on the purchase time interval of each commodity;
normalizing the first numerical value, the second numerical value and the third numerical value, and then performing addition operation to obtain the grade division value of each commodity;
and grading each commodity in the unmanned vending machine based on the grading value.
4. The method as claimed in claim 1, wherein the step 3 of establishing the threshold label for the goods in the vending machine according to the out-of-stock threshold of the goods of each grade comprises:
acquiring a commodity image in the backorder threshold value of each grade of commodity;
scanning images of all commodities in the unmanned vending machine to obtain scanned images of all commodities;
comparing and matching the commodity image and the scanned image to obtain an image matching table;
determining the goods shortage threshold value corresponding to each commodity in the unmanned vending machine based on the image matching table;
acquiring a relation establishment request between each commodity and a backorder threshold value corresponding to each commodity;
setting a first resource for each commodity in the unmanned vending machine based on the relationship establishment request, and setting a second resource for a stock shortage threshold corresponding to each commodity;
and establishing a threshold label for the commodity in the unmanned vending machine based on the first resource and the second resource.
5. The method for monitoring the out-of-stock based on the unmanned vending machine as claimed in claim 1, wherein in the step 4, based on the threshold label of the goods, whether the goods are out-of-stock is judged, and if the goods are out-of-stock, sending out an out-of-stock alarm prompt comprises:
determining an out-of-stock threshold for the item based on the threshold label for the item;
judging whether the quantity of the commodities is larger than the stock shortage threshold value of the commodities;
if yes, indicating that the goods do not have the out-of-stock condition;
otherwise, indicating that the goods are out of stock and alarming and reminding.
6. The method for monitoring out-of-stock based on the unmanned vending machine as claimed in claim 1, wherein in the step 4, after the alarm prompt for out-of-stock is issued, the method further comprises:
determining the out-of-stock commodity based on the out-of-stock alarm prompt, and acquiring a state conversion instruction based on the out-of-stock commodity;
based on the conversion instruction, converting the state of the out-of-stock commodity from a quantity display state to an out-of-stock state; and closing the purchase link for the out-of-stock item.
7. The method for monitoring the out-of-stock based on the unmanned aerial vehicle as claimed in claim 1, wherein in the step 4, scanning the goods in the unmanned aerial vehicle and obtaining the quantity of the goods comprises:
scanning all areas of commodities in the unmanned vending machine to obtain an overall image of all the areas, and preprocessing the overall image to obtain a standardized image;
the method comprises the steps that commodity information of commodities placed in the unmanned vending machine is obtained in advance, and an appearance characteristic set of the commodities is obtained on the basis of the commodity information;
determining a segmentation contour of the standardized image based on the appearance feature set, and performing image segmentation on the standardized image based on the segmentation contour to obtain a single commodity image;
judging whether the number of the single commodity images is consistent with the number of commodities placed in the unmanned vending machine or not;
if so, indicating that the segmentation contour of the standardized image is accurate;
otherwise, if the number of the single commodity images is larger than that of the commodities placed in the unmanned vending machine, performing similarity detection on the single commodity images, and combining two single commodity images meeting a first preset similarity requirement to obtain a new single commodity image;
otherwise, if the number of the single commodity images is smaller than that of commodities placed in the unmanned vending machine, re-determining the segmentation outline of the standardized image, and obtaining a new single commodity image;
identifying and segmenting the single commodity image based on commodity information corresponding to the single commodity image after judgment and re-segmentation to obtain a segmented area of the corresponding commodity, wherein the segmented area comprises an integral area and a local area;
determining the number of the whole areas as a first number;
determining a whole area adjacent to the local area, and intercepting a reference area close to the local area in the adjacent whole area;
judging the similarity between the local area and the reference area, counting the local area if the similarity meets a second preset similarity requirement, and finally obtaining a second quantity, or not counting the local area;
the number of the commodities is acquired based on the first number and the second number of the commodities.
8. The method for monitoring the out-of-stock based on the unmanned aerial vehicle as claimed in claim 1, wherein in step 4, after scanning the goods in the unmanned aerial vehicle and obtaining the quantity of the goods, the method further comprises:
determining the replenishment time of the commodities based on the quantity of the commodities and the stock shortage threshold corresponding to the commodities, wherein the process is as follows:
predicting the sale time of the commodities according to the following formula based on the quantity of the commodities and the backorder threshold value corresponding to the commodities;
Figure FDA0002990935280000041
wherein T represents the time of sale of the commodity, TSRepresenting an average time of sale of the goods at the number of the goods in the vending machine system, S representing the number of the goods, A representing an out-of-stock threshold of the goods, and S>A,
Figure FDA0002990935280000052
The sales volume of the commodity in the average sales time of the commodity is represented, e represents a natural number and takes a value of 2.72, delta represents the dependence value of the commodity on advertising, and takes a value of [0,0.6 ]]And tau represents the value of the advertisement putting strength of the commodity and takes a value of [0, 1%]；
Calculating replenishment time of the commodity according to the following formula based on the sale time of the commodity;
Figure FDA0002990935280000051
wherein, TBShowing the time for calculating the replenishment of the commodity, L showing the cost for replenishing the commodity once, C showing the total sales volume of the commodity after replenishing the commodity once and selling all the commodity, M showing the price of the commodity, D showing the cost of the commodity, and epsilon showing the replenishment compensation coefficient, wherein the value of epsilon is (0.2, 0.4);
and determining the replenishment reminding time based on the replenishment time, and carrying out replenishment reminding when the replenishment reminding time is reached.
CN202110313625.3A 2021-03-24 2021-03-24 Goods shortage monitoring method based on unmanned vending machine Active CN113139768B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110313625.3A CN113139768B (en) 2021-03-24 2021-03-24 Goods shortage monitoring method based on unmanned vending machine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110313625.3A CN113139768B (en) 2021-03-24 2021-03-24 Goods shortage monitoring method based on unmanned vending machine

Publications (2)

Publication Number Publication Date
CN113139768A true CN113139768A (en) 2021-07-20
CN113139768B CN113139768B (en) 2023-01-13

Family

ID=76809998

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110313625.3A Active CN113139768B (en) 2021-03-24 2021-03-24 Goods shortage monitoring method based on unmanned vending machine

Country Status (1)

Country Link
CN (1) CN113139768B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113850657A (en) * 2021-11-29 2021-12-28 新石器慧通（北京）科技有限公司 Unmanned vehicle-based commodity selling method and device, electronic equipment and storage medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103295067A (en) * 2013-04-10 2013-09-11 南京邮电大学 Vending machine managing system based on Internet of Things
CN107463945A (en) * 2017-07-12 2017-12-12 浙江大学 A kind of type of merchandize recognition methods based on depth matching network
CN107730168A (en) * 2017-09-28 2018-02-23 中南大学 A kind of automatic vending machine automated stock control system and method based on image recognition
CN108629894A (en) * 2018-04-17 2018-10-09 合肥美的智能科技有限公司 Automatic replenishment method, system, sales counter and computer equipment
CN108710921A (en) * 2018-03-27 2018-10-26 佛山市欢腾电子有限公司 A kind of long-range control method of unmanned supermarket, system
CN108922026A (en) * 2018-07-09 2018-11-30 深圳码隆科技有限公司 A kind of management method that replenishes, device and the user terminal of automatic vending machine
CN109305505A (en) * 2018-08-30 2019-02-05 苏宁易购集团股份有限公司 A kind of replenish based reminding method and system based on gravity sensing shelf
CN109543527A (en) * 2018-10-19 2019-03-29 北京陌上花科技有限公司 For the commodity detection method of unmanned shelf, device and retail terminal

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103295067A (en) * 2013-04-10 2013-09-11 南京邮电大学 Vending machine managing system based on Internet of Things
CN107463945A (en) * 2017-07-12 2017-12-12 浙江大学 A kind of type of merchandize recognition methods based on depth matching network
CN107730168A (en) * 2017-09-28 2018-02-23 中南大学 A kind of automatic vending machine automated stock control system and method based on image recognition
CN108710921A (en) * 2018-03-27 2018-10-26 佛山市欢腾电子有限公司 A kind of long-range control method of unmanned supermarket, system
CN108629894A (en) * 2018-04-17 2018-10-09 合肥美的智能科技有限公司 Automatic replenishment method, system, sales counter and computer equipment
CN108922026A (en) * 2018-07-09 2018-11-30 深圳码隆科技有限公司 A kind of management method that replenishes, device and the user terminal of automatic vending machine
CN109305505A (en) * 2018-08-30 2019-02-05 苏宁易购集团股份有限公司 A kind of replenish based reminding method and system based on gravity sensing shelf
CN109543527A (en) * 2018-10-19 2019-03-29 北京陌上花科技有限公司 For the commodity detection method of unmanned shelf, device and retail terminal

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113850657A (en) * 2021-11-29 2021-12-28 新石器慧通（北京）科技有限公司 Unmanned vehicle-based commodity selling method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN113139768B (en) 2023-01-13

Similar Documents

Publication Publication Date Title
CN109214806A (en) Self-help settlement method, apparatus and storage medium
CN112785354B (en) Commodity recommendation system for retail management platform
CN114119001B (en) Intelligent management and analysis platform for cash collection of commodity sales based on artificial intelligence
CN110533130B (en) Price management system of terminal is sold to intelligence
CN113538012A (en) Buyer user intelligent management method based on internet e-commerce platform data analysis
CN113139768B (en) Goods shortage monitoring method based on unmanned vending machine
CN111724114A (en) E-commerce commodity distribution logistics intelligent management system based on big data
CN110738441B (en) Commodity reservation distribution method and system based on Internet
CN110826481A (en) Data processing method, commodity identification method, server and storage medium
CN116611796A (en) Exception detection method and device for store transaction data
CN108921482B (en) Fast-moving consumer goods delivery method and system
CN115510329B (en) Brand marketing software management method based on cloud computing big data
CN111415208A (en) New product pricing system and method based on reverse thrust method and dynamic pricing model
US20230005001A1 (en) System for automated and dynamic pricing and donation
CN114971083A (en) Method for purchasing, predicting and selling goods
CN112785374B (en) Information recommendation system and method based on unmanned retail terminal
CN114282818A (en) Bright area electronic tag control method for maximizing sales
CN114358870A (en) Chain store and store passenger flow volume acquisition and analysis system
CN111768139B (en) Stock processing method, apparatus, device and storage medium
CN112819540A (en) Method and device for predicting commodity sales of vending machine and computer-readable storage medium
CN113205400B (en) Financial accounting method, system and computer readable storage medium based on Amazon platform
CN116645375B (en) Cigarette retail merchant inventory checking method based on three-dimensional reconstruction algorithm
US20230289629A1 (en) Data-driven predictive recommendations
CN109741119A (en) Accounting method, device, system and computer readable storage medium
CN116205555B (en) Logistics information visual management system and method based on big data

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant