KR20220165126A - System for unmaned goods inspection - Google Patents

Abstract

In a system for inspecting an unmanned product installed in a store and capable of an unmanned payment, the system for inspecting the unmanned product according to one embodiment of the present invention comprises: a barcode recognition part that recognizes at least one or more purchase target products through a barcode; a weight detection part that measures a weight of the recognized purchase target product; and a control part that enables the product information corresponding to the relevant barcode to be retrieved, when the barcode of the purchase target product is scanned, extracts the standard weight information of the purchase target product, and determines whether or not to register the purchase target product by comparing the extracted standard weight information and the inspection weight information measured from the weight detection part. Therefore, the present invention is capable of having an effect of minimizing product loss.

Description

Unmanned product inspection system {SYSTEM FOR UNMANED GOODS INSPECTION}

The present invention relates to an unmanned product inspection system.

Recently, social issues and phenomena such as a minimum wage increase and a reduction in weekly working hours are accelerating the unmanned stores in the retail market in earnest, and the convenience and cost reduction effect due to non-face-to-face are added, further invigorating the market.

Specifically, domestic hypermarkets are already operating both manned and unmanned checkout counters, and the number of unmanned checkout counters is increasing as time goes on.

In other words, in the long term, the proportion of the manned calculation method using cashiers in the offline distribution field is gradually decreasing, and even research on unmanned stores without clerks in the store is underway.

However, the unmanned checkout counter has the following problems.

Conventional unmanned checkout counters have the advantage of being installed in convenience stores, marts, etc. to protect the privacy of customers and providing an untact payment method that does not require a cashier to be present for the checkout, but there is a limit to loss in the unmanned checkout process there is

Specifically, there are cases where customers do not intentionally or mistakenly scan products at the conventional unmanned checkout counter, and customers can easily leave the store with unscanned products as they are in an environment where there are no employees. loss occurs

In order to overcome these problems, Korean Registered Patent No. 10-1424706 proposes a method of determining whether an item is abnormal by considering the detection time when an item not read by the barcode reader passes through the detection sensor. The patent is a cart-based product inspection system, and has a limitation that it is difficult to have expensive smart carts in convenience stores and small marts.

Embodiments of the present invention have been proposed to solve the above problems, and are intended to provide an unmanned product inspection system capable of minimizing product loss by performing weight inspection on products recognized at an unmanned checkout counter.

An unmanned product inspection system according to embodiments of the present invention is an unmanned product inspection system installed in a store and capable of unattended payment, comprising: a barcode recognition unit that recognizes at least one product to be purchased through a barcode; a weight sensor for measuring the weight of the recognized product to be purchased; And when the barcode of the product to be purchased is scanned, product information corresponding to the barcode is retrieved, standard weight information of the product to be purchased is extracted, and the extracted standard weight information is compared with the inspection weight information measured by the weight sensor. and a control unit that determines whether the product to be purchased is registered.

In addition, if the inspection weight information is within the allowable error range of the standard weight information, the control unit generates weight matching information and registers the product to be purchased, and the inspection weight information determines the allowable error range of the standard weight information. If out of range, weight discrepancy information may be generated to stop the registration process of the product to be purchased.

Also, the control unit generates manager call information when the weight sensor does not receive the inspection weight information of the product to be purchased from the weight sensor for a predetermined time after the standard weight information is extracted.

In addition, if the reference weight information is out of a predetermined allowable range, the control unit may register the product to be purchased by setting the inspection weight information of the product to be purchased corresponding to the corresponding barcode to “0”.

In addition, the control unit generates cumulative inspection weight information by adding up the inspection weight information for at least one product to be purchased received from the weight sensor, and detects the generated cumulative inspection weight information in real time to provide event information when a change occurs. It further includes an event generating unit that generates.

The event generation unit may generate initialization event information so that all products to be purchased stored on the weight sensor may be removed before the barcode recognition unit recognizes the barcode of the product to be purchased.

In addition, the event generating unit, when the cumulative inspection weight information is changed in a state in which the barcode of the product to be purchased is not scanned by the barcode recognition unit, generates first mismatch event information to perform a registration procedure for the product to be purchased. Stop.

Further, the event generation unit generates second mismatch event information to stop the registration process of the product to be purchased when the cumulative inspection weight information is reduced in a state in which the barcode of the product to be purchased is scanned by the barcode recognition unit. can do.

In addition, the event generation unit generates product removal event information when the cumulative inspection weight information is out of a permissible range measurable by the weight sensor, and stops the registration process of the product to be purchased.

In addition, the control unit may further include an artificial intelligence learning unit that sets inspection weight information of the product to be purchased that satisfies a preset condition through artificial intelligence learning as learning data and calculates an average weight value based on the set learning data. can

In addition, the artificial intelligence learning unit updates pre-stored inspection weight information of a product to be purchased based on the weight average value.

The unmanned product inspection system according to embodiments of the present invention has an effect of minimizing product loss by performing weight inspection on products recognized at an unmanned checkout counter.

1 is a diagram showing an unmanned product inspection system according to an embodiment of the present invention.
2 is a block diagram of an unmanned product inspection system according to an embodiment of the present invention.
3 is a flowchart of an unmanned product inspection system according to an embodiment of the present invention.

Other advantages and features of the present invention, and methods for achieving them, will become clear with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms, but only the present embodiments make the disclosure of the present invention complete, and the common knowledge in the art to which the present invention belongs It is provided to fully inform the holder of the scope of the invention, and the present invention is only defined by the scope of the claims.

Even if not defined, all terms (including technical or scientific terms) used herein have the same meaning as generally accepted by common technology in the prior art to which this invention belongs. Terms defined by general dictionaries may be interpreted to have the same meaning as they have in the related art and/or the text of the present application, and are not conceptualized or overly formalized, even if not expressly defined herein. won't

Terms used in this specification are for describing embodiments and are not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used in the specification, 'comprise' and/or various conjugations of this verb, such as 'comprise', 'comprising', 'comprising', 'comprising', etc., refer to a mentioned composition, ingredient, component, Steps, acts and/or elements do not preclude the presence or addition of one or more other compositions, ingredients, components, steps, acts and/or elements. In this specification, the term 'and/or' refers to each of the listed elements or various combinations thereof.

Meanwhile, terms such as '~unit', '~group', '~block', and '~module' used throughout this specification may mean a unit that processes at least one function or operation. For example, it can mean software, hardware components such as FPGAs or ASICs. However, '~ unit', '~ group', '~ block', '~ module', etc. are not meant to be limited to software or hardware. '~unit', '~group', '~block', '~module' may be configured to be in an addressable storage medium or configured to reproduce one or more processors.

Therefore, as an example, '~unit', '~group', '~block', and '~module' are components such as software components, object-oriented software components, class components, and task components. fields, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays and Include variables. Components and functions provided within '~units', '~groups', '~blocks', and '~modules' can be found in smaller numbers of components and '~units', '~groups', '~blocks'. ', '~ modules', or may be further separated into additional components and '~ parts', '~ groups', '~ blocks', and '~ modules'.

Hereinafter, specific embodiments of the present invention will be described in detail with reference to the drawings.

In addition, in describing the present invention, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present invention, the detailed description will be omitted.

1 is a diagram showing an unmanned product inspection system according to an embodiment of the present invention, and FIG. 2 is a block diagram of the unmanned product inspection system according to an embodiment of the present invention.

1 and 2, the unmanned product inspection system 10 according to an embodiment of the present invention includes a barcode recognition unit 100, a weight detection unit 200, a control unit 300 and a display unit 400. can do.

The unmanned product inspection system 10 is installed in a store and enables unmanned payment, and can be applied to a mart, convenience store, etc. where a consumer selects a desired purchase target product in a store and pays for it through a checkout counter located on the exit side.

First, the barcode recognition unit 100 may recognize at least one product to be purchased through a barcode.

Specifically, the product to be purchased is identified by recognizing the barcode printed on the wrapping paper or the product. Here, the barcode is a combination of bars and spaces in a specific form to express characters, numbers, and symbols, and can be implemented as, for example, a one-dimensional barcode, a two-dimensional barcode, a QR code, a data matrix, and the like.

In addition, the barcode recognition unit 100 may be a one-dimensional imager using a laser or a linear imager or a two-dimensional imager, and a handheld type that a consumer can hold in his hand and use an imager function, or a countertop used It has a form such as presentation type or multi-plane type.

That is, the barcode recognition unit 100 is a scanner, which is a known barcode recognition module, and the barcode recognition unit 100 scans the barcode of a product to be purchased with light passing through a mirror and a filter, and transmits light corresponding to the barcode stripe. A barcode is received by receiving an intensity change signal.

Next, the weight detection unit 200 may measure the weight of the product to be purchased recognized by the barcode recognition unit 100 .

Specifically, the weight sensor 200 provides a space for placing products, and the consumer transfers the recognized product to be purchased to the weight sensor 200 and places it there.

Accordingly, the weight sensor 200 may measure the weight of the stacked products and transmit the measured weight information to the control unit 300 using wired or wireless communication.

At this time, the weight sensor 200 includes a weight sensor, which is a known weight measurement module, and the weight sensor may have a measurable weight range.

When the barcode of the product to be purchased is scanned by the barcode recognition unit 100, the control unit 300 retrieves product information corresponding to the corresponding barcode, extracts standard weight information of the product to be purchased, and It is determined whether the product to be purchased is registered by comparing the inspection weight information measured by the weight sensor 200 .

In addition, the controller 300 has a separate communication unit (not shown) to receive scan information of the product from the barcode recognition unit 100 and weight information of the product from the weight sensor 200 through wired/wireless communication. do. In addition, the controller 300 may further include a product DB for pre-stored information on types, standard weights, and prices of all products displayed in the store.

Specifically, if the inspection weight information is within the allowable error range of the reference weight information, the control unit 300 generates weight matching information and registers the product to be purchased, and the inspection weight information allows the reference weight information to be accepted. If it is out of the error range, weight mismatch information may be generated to stop the registration process of the product to be purchased.

Here, stopping the registration process of the product to be purchased does not simply stop the product registration process, and provides the consumer with a reason to stop the registration process through the display unit 400 and provides a notification to perform the registration process again. it means.

In addition, the allowable error range may be an error range of ±3% or ±5% based on the reference weight information, and is preferably ±3% in the present invention. In addition, the product information includes the type, standard weight, and price of the product to be purchased.

For example, when a consumer intends to purchase banana milk in a store, the controller 300 receives type, standard weight, and price information corresponding to the banana milk when the barcode recognition unit 100 scans the banana milk. Import and extract the standard weight of the banana milk. Thereafter, the reference weight of the extracted banana milk is compared with the inspection weight information of the banana milk measured by the weight sensor 200 .

More specifically, when the standard weight information of the banana milk is 200 g and the measured weight information of the banana milk is 202 g, the control unit 300 sets the standard weight information to a tolerance range (±3 %) of 194 to 206 g, so the banana milk is registered.

In addition, the control unit 300 may generate manager call information if the weight sensor 200 does not receive the inspection weight information of the product to be purchased for a predetermined time after the standard weight information of the product to be purchased is extracted. can

For example, when the control unit 300 scans banana milk and extracts the standard weight of the banana milk, if the weight detection unit 200 does not receive the banana milk inspection weight information for 1 to 2 minutes, It is judged that inspection of banana milk is impossible, so that a manager can be called.

In addition, if the standard weight information of the product to be purchased is out of the preset allowable range, the control unit 300 sets the inspection weight information of the product to be purchased corresponding to the corresponding barcode to “0” and registers the product to be purchased. can do.

For example, when a consumer wants to purchase 1.5 liter water in a store, the controller 300 calls the type, standard weight, and price information corresponding to the water when the water is scanned by the barcode recognition unit 100. And extract the reference weight of the water.

Thereafter, if the predetermined allowable range is 0.1 to 1 kg and the standard weight of the extracted water is 1.5 kg, the control unit 300 sets and registers the water inspection weight information as 0 kg.

Accordingly, in the present invention, damage to the weight sensor 200 can be prevented by excluding the weight inspection of a product having a weight exceeding a predetermined allowable range.

As another example, when one plastic bag is scanned by the barcode recognition unit 100, the control unit 300 retrieves the type, standard weight, and price information corresponding to the plastic bag and extracts the standard weight of the plastic bag. do.

Thereafter, if the predetermined allowable range is 0.1 to 1 kg and the standard weight of the extracted plastic bag is 10 g, the control unit 300 sets and registers the inspection weight information of the plastic bag as 0 kg.

Also, referring to FIG. 2 , the control unit 300 further includes an event generation unit 310, an artificial intelligence learning unit 320, and a payment unit 330.

First, the control unit 300 generates cumulative inspection weight information by summing the inspection weight information for at least one product to be purchased received from the weight sensor 200, and detects and changes the generated cumulative inspection weight information in real time. It may further include an event generation unit that generates event information when it occurs.

Specifically, the event generation unit 310, when the inspection weight information of cookies, milk, and ramen, which are products to be purchased by the consumer, is 100g, 200g, and 150g, respectively, sums up the weights of the products to be purchased and cumulative inspection of 450g It generates weight information, and detects the generated cumulative inspection weight information in real time until the registration of each product to be purchased is completed.

In addition, the event generation unit 310 performs an initialization event so that all products to be purchased placed on the weight sensor 200 can be removed before the barcode recognition unit 100 recognizes the barcodes of the products to be purchased. generate information

Thereafter, the display unit 400 may receive the initialization event information and provide a voice notification to the consumer along with the phrase "Remove all products from the scale."

In addition, if the cumulative inspection weight information is changed in a state in which the barcode of the product to be purchased is not scanned by the barcode recognition unit 100, the event generation unit 310 generates first inconsistency event information to determine the purchase The registration process of the target product may be suspended.

Specifically, the event generation unit 310, when the consumer proceeds to register sweets, milk, and ramen, when the cumulative inspection weight information is changed in a state in which the registration of the snack and milk is completed and the barcode of the ramen is not scanned , It is determined that an unrecognized product exists, and the first discrepancy event information is generated to stop the product registration process.

Thereafter, the display unit 400 receives the first discrepancy event information and provides a voice notification to the consumer along with the phrase "an item that has not been scanned is placed on a scale."

In addition, when the cumulative inspection weight information is reduced in a state in which the barcode of the product to be purchased is scanned by the barcode recognition unit 100, the event generating unit 310 generates second inconsistency event information to determine the target product to be purchased. Suspend the product registration process.

Specifically, when the consumer proceeds to register cookies, milk, and ramen, the event generating unit 310 detects the weight of the snack or milk in a state in which the barcode of the ramen is scanned as soon as the registration of the snack and milk is completed. ) and the cumulative inspection weight information is reduced, it is determined that the product is intentionally removed by the consumer, and second inconsistent event information is generated to stop the product registration process.

Thereafter, the display unit 400 receives the second discrepancy event information and provides a voice notification to the consumer along with the phrase "the item scanned first has been removed from the scale."

In addition, the event generation unit 310 generates product removal event information to register the product to be purchased when the cumulative inspection weight information of at least one product to be purchased is out of the allowable range measurable by the weight sensor 200. stop the procedure

Specifically, the event generation unit 310 provides product removal event information when the measurable range of the weight sensor 200 is 0 to 10 kg and the cumulative inspection weight information of products to be purchased by the consumer exceeds 10 kg. generate

Thereafter, the display unit 400 receives the product removal event information and provides a voice notification to the consumer along with the phrase "Weight exceeded. Please register the product multiple times."

Next, the control unit 300 sets the inspection weight information of the product to be purchased that satisfies a preset condition through artificial intelligence learning as learning data, and artificial intelligence that generates optimized standard weight information based on the set learning data. A learning unit 330 is further included.

In this case, the predetermined condition may be weight information continuously measured n or more times while falling within the tolerance range.

As Example 1, when the standard weight information of the first product to be purchased is 100g and five different consumers purchase the first product to be purchased one by one, the inspection weight information of the first product to be purchased is 103g for each consumer, It may appear as 101g, 99g, 102g, or 98g.

Here, if the predetermined condition is a case where the weight information belonging to the tolerance ±5% is continuously measured 5 or more times, the artificial intelligence learning unit 330 checks the weight information of the first purchase target product 103g, Since 101g, 99g, 102g, and 98g all belong to ±5% of 100g, which is the standard weight information of the first purchase target product, and are measured 5 times consecutively, they can be set as learning data and learned.

In addition, the artificial intelligence learning unit 300 calculates an average weight value of inspection weight information that satisfies the corresponding condition, and updates pre-stored inspection weight information of a product to be purchased based on the calculated average weight value.

That is, 100g, which is the standard weight information of the first purchase target product, may be updated to 100.6g, which is the calculated average weight value.

As Example 2, when the standard weight information of the first purchase target product is 100g and five different consumers purchase the first purchase target product one by one, the inspection weight information of the first purchase target product is 100g for each consumer, It may appear as 107g, 93g, 102g, or 98g.

Here, if the predetermined condition is a case where the weight information belonging to the tolerance ±5% is continuously measured 5 or more times, the artificial intelligence learning unit 330 checks the weight information of the first purchase target product 100g, Among 107g, 93g, 102g, and 98g, 107g and 93g do not belong to ±5% of 100g, which is the standard weight information of the first purchase target product, and are not values measured 5 times in a row, so they can be set as learning data and learned. none.

Next, the payment unit 330 may calculate a purchase product list, price information, and a total amount of payment when the registration process of the product to be purchased is completed. In addition, the payment unit 330 may output the calculated purchase product list, price information, and total payment to the display unit 400 to make the consumer aware of the registered product and induce payment.

In addition, the payment unit 330 may support both a coupon registration service and a point registration service when paying for a registered product.

The display unit 400 may include a display module and a speaker module that emit light based on information received from the controller 300, and may be connected to the controller 300 through wired or wireless communication.

In addition, the display unit 400 is provided to enable inquiries about using convenience stores or marts, supports services such as product inquiries and product payment method inquiries, and enables communication between consumers and managers by being connected to a manager and a network.

That is, the display unit 400 may output information received from the control unit 300 as a message, image, video or audio.

3 is a flowchart of an unmanned product inspection system according to an embodiment of the present invention.

Referring to FIG. 3 , the execution of the unmanned product inspection system 10 according to an embodiment of the present invention recognizes at least one product to be purchased through a barcode (S100), and measures the weight of the recognized product to be purchased (S100). S200) can be done.

Specifically, the consumer recognizes the product to be purchased one by one with the barcode recognition unit 100, places the recognized product to be purchased on the weight sensor 200, and measures the weight of the product to be purchased.

Then, when the barcode of the product to be purchased is scanned, the control unit 300 retrieves product information corresponding to the barcode and extracts standard weight information of the product to be purchased, and the extracted standard weight information and the weight sensor 200 ), it is determined whether to register the product to be purchased by comparing the inspection weight information measured from (S300).

More specifically, in step S300, if the inspection weight information of the product to be purchased is within the tolerance range of the standard weight information of the product to be purchased, the control unit 300 generates weight matching information and registers the product to be purchased, If the inspection weight information of the product to be purchased is out of the allowable error range of the standard weight information of the product to be purchased, weight mismatch information is generated and the registration process of the product to be purchased is stopped.

In addition, in step S300, the control unit 300 generates cumulative inspection weight information by summing the inspection weight information for at least one product to be purchased received from the weight sensor 200, and generates the cumulative inspection weight information. Event information can be generated when a change occurs by detecting it in real time.

Specifically, when the cumulative inspection weight information is changed in a state in which the barcode of the product to be purchased is not scanned by the barcode recognition unit 100, the control unit 300 generates first discrepancy event information to determine the target product to be purchased. The product registration process may be suspended.

In addition, when the cumulative inspection weight information is reduced in a state in which the barcode of the product to be purchased is scanned by the barcode recognition unit 100, the control unit 300 generates second inconsistency event information to determine the value of the product to be purchased. The registration process may be suspended.

In addition, in step S300, the control unit 300 sets the inspection weight information of the product to be purchased that satisfies a preset condition through artificial intelligence learning as learning data, and calculates an average weight based on the set learning data. Thereafter, based on the weight average value, pre-stored inspection weight information of a product to be purchased may be updated.

Next, when registration of the product to be purchased is completed, the payment unit 330 may perform payment for the registered product to be purchased (S400).

Accordingly, the unmanned product inspection system of the present invention has an effect of minimizing product loss by performing weight inspection on products recognized at an unmanned checkout counter.

The above detailed description is illustrative of the present invention.

In addition, the foregoing is intended to illustrate and describe preferred embodiments of the present invention, and the present invention can be used in various other combinations, modifications and environments. That is, changes or modifications are possible within the scope of the concept of the invention disclosed in this specification, within the scope equivalent to the written disclosure and / or within the scope of skill or knowledge in the art. The written embodiment describes the best state for implementing the technical idea of the present invention, and various changes required in the specific application field and use of the present invention are also possible. Therefore, the above detailed description of the invention is not intended to limit the invention to the disclosed embodiments. Also, the appended claims should be construed to cover other embodiments as well.

10: Unmanned product inspection system
100: barcode recognition unit
200: weight sensor
300: control unit
400: display unit

Claims (11)

In the unmanned product inspection system installed in the store and capable of unmanned payment,
a barcode recognition unit for recognizing at least one product to be purchased through a barcode;
a weight sensor for measuring the weight of the recognized product to be purchased; and
When the barcode of the product to be purchased is scanned, product information corresponding to the barcode is retrieved, standard weight information of the product to be purchased is extracted, and the extracted standard weight information is compared with the inspection weight information measured by the weight sensor. An unmanned product inspection system including a control unit for determining whether a product to be purchased is registered.
According to claim 1,
The control unit,
If the inspection weight information is within the allowable error range of the reference weight information, weight matching information is generated and the product to be purchased is registered;
If the inspection weight information is out of the allowable error range of the standard weight information, the unmanned product inspection system generates weight mismatch information and stops the registration process of the product to be purchased.
According to claim 2,
The control unit,
The unmanned product inspection system for generating manager call information when the inspection weight information of the product to be purchased is not received from the weight sensor for a predetermined time after the standard weight information is extracted.
According to claim 3,
The control unit,
The unmanned product inspection system registering the product to be purchased by setting the inspection weight information of the product to be purchased corresponding to the corresponding barcode to “0” when the standard weight information is out of a predetermined allowable range.

According to claim 4,
The control unit,
An event generating unit that generates cumulative inspection weight information by adding up the inspection weight information for at least one product to be purchased received from the weight sensor, detects the generated cumulative inspection weight information in real time, and generates event information when a change occurs. An unmanned product inspection system that includes more.
According to claim 5,
The event generator,
An unmanned product inspection system that generates initialization event information so that all products to be purchased stored on the weight sensor can be removed before the barcode recognition unit recognizes the barcode of the product to be purchased.
According to claim 6,
The event generator,
When the cumulative inspection weight information is changed in a state in which the barcode of the product to be purchased is not scanned by the barcode recognition unit, first inconsistency event information is generated to stop the registration procedure of the product to be purchased.
According to claim 7,
The event generator,
When the cumulative inspection weight information is reduced in a state in which the barcode of the product to be purchased is scanned by the barcode recognition unit, second inconsistency event information is generated and the unmanned product inspection system stops the registration procedure of the product to be purchased.
According to claim 8,
The event generator,
The unmanned product inspection system for generating product removal event information and stopping the registration process of the product to be purchased when the cumulative inspection weight information is out of the allowable range measurable by the weight sensor.
According to claim 9,
The control unit,
An unmanned product inspection system further comprising an artificial intelligence learning unit that sets inspection weight information of the product to be purchased that satisfies a predetermined condition through artificial intelligence learning as learning data and calculates an average weight value based on the set learning data.
According to claim 10,
The artificial intelligence learning unit,
An unmanned product inspection system for updating pre-stored inspection weight information of a product to be purchased based on the weight average value.

Images