A self-contained, demand-adaptable warmer for storing, heating, and holding ready-to-drink beverages

Abstract

The beverage warmer includes multiple product shelves, each having multiple product lanes. Each product lane has a peripheral area, a heating area, and a service area. Product is loaded into the beverage warmer in the peripheral area of ​​the product lane and transported through each of the heating area and the service area in response to the product being removed from the beverage warmer. The product may be held in the heating area for a period of time and exposed to a first temperature. Upon expiration of the period, the product is transported from the heating area to the service area. The product is held in the service area at a second temperature, where the second temperature is lower than the first temperature.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Provisional Patent Application No. 63 / 024,188, filed May 13, 2020, the disclosure of which is expressly incorporated herein by reference. [Background technology]

[0002] background Ready-to-drink (RTD) beverages such as coffee or tea are often served at high temperatures (e.g., 40-70C). Currently, RTD beverage warmers heat all of the RTD beverages stored in the merchandising cabinet to the target consumption temperature. Accordingly, all of the RTD beverages stored in the merchandising cabinet are kept at high temperatures. The shelf life of RTD beverages is reduced when stored at high temperatures due to product spoilage and material deterioration, which causes the product quality to decrease over time. Current RTD beverage warmers therefore result in high spoilage rates due to holding large quantities of product at high temperatures for long periods of time. Product spoilage results in losses from retailers in the form of product buybacks. Additionally, when consumer demand is high, products can sell out quickly and it can take hours to have product available for sale. Summary of the Invention [Means for solving the problem]

[0003] summary In a first aspect of the disclosure, a beverage warmer includes a product shelf with a peripheral storage zone, a heating zone, and a service zone. The product shelf includes a first door between the storage zone and the heating zone, and a second door between the heating zone and the service zone. Each of the first and second doors is configurable between an open position and a closed position. The beverage warmer further includes a controller configured to operate the first door to transport product from the peripheral storage zone through the heating zone and to operate the second door to transport product from the heating zone to the service zone.

[0004] In some implementations of the first aspect of the present disclosure, the service zone includes a service area sized to receive a first number of items.

[0005] In some implementations of the first aspect of the present disclosure, the peripheral storage zone includes a loading area sized to receive the second number of items.

[0006] In some implementations of the first aspect of the present disclosure, the second number of items is greater than the first number of items.

[0007] In some implementations of the first aspect of the present disclosure, the heating zone includes a heating area sized to receive a single item.

[0008] In some implementations of the first aspect of the present disclosure, the service zone includes a proximity sensor configured to detect whether a product is present at a location within the service zone.

[0009] In some implementations of the first aspect of the present disclosure, the controller is configured to determine that the item has been removed from the service zone in response to the proximity sensor detecting that the item is not present at the location after detecting that the item is present at the location.

[0010] In some implementations of the first aspect of the present disclosure, the controller is further configured to, in response to determining that the product has been removed from the service zone, operate the first door to transport the product from the peripheral storage zone to the heating zone.

[0011] In some implementations of the first aspect of the present disclosure, the second door includes a wall with a door therethrough, the door being positioned at an upper portion of the wall.

[0012] In some implementations of the first aspect of the present disclosure, the product shelf further includes a plurality of product lanes, each of which extends through the peripheral storage zone, the heating zone, and the service zone.

[0013] In some implementations of the first aspect of the present disclosure, the beverage warmer further includes a plurality of product shelves.

[0014] In a second aspect of the disclosure, a method of operating a beverage warmer includes receiving a product into a loading area of ​​a product lane on a product shelf of the beverage warmer. The method includes transferring the product from the loading area through a first door to a heating area. The method includes heating the product in the heating area at a constant heating temperature for a constant heating time. The method includes transferring the product from the heating area through a second door to a service area after the heating time. The method includes maintaining the product at a service temperature in the service area.

[0015] In some implementations of the second aspect of the present disclosure, the method further includes detecting whether a second item is in a loading area of ​​the item lane. The method further includes detecting that the item is removed from the service area, and in response, transferring the second item from the loading area through the first door to the heating area.

[0016] In some implementations of the second aspect of the present disclosure, heating the commodity in the heating zone includes heating the commodity with one or more heating elements in the heating zone.

[0017] In some implementations of the second aspect of the present disclosure, the one or more heating elements include two heating elements positioned on either side of the heating region.

[0018] In some implementations of the second aspect of the present disclosure, the method further includes heating air in the service area to a service temperature with one or more heating elements in a service zone that includes the service area.

[0019] In some implementations of the second aspect of the present disclosure, the method further includes circulating the heated air in the service area with one or more fans positioned in the service zone.

[0020] In some implementations of the second aspect of the present disclosure, the method further includes detecting that no product is present in the service area. The method further includes displaying a time on a display adjacent to the service area. The time indicates a time remaining until the heated product is transported from the heating area through the second door to the service area.

[0021] In some implementations of the second aspect of the present disclosure, the method further includes detecting that the item is removed from the service area. The method further includes determining that a current time is within a low demand period and, in response, determining not to transfer the second item from the loading area through the first door to the heating area.

[0022] In some implementations of the second aspect of the present disclosure, transferring the goods through the first door includes rotating the first door, and transferring the goods through the second door includes rotating the second door.

[0023] A third aspect of the disclosure includes a method of activating a beverage warmer based on a machine learning model of a predicted demand pattern. The method includes training a machine learning model to predict a demand pattern for a future demand period. Training the machine learning model is based on a cost function that is a function of a ratio of cost of missed customers to cost of discarded goods. The method includes activating the beverage warmer based on the predicted demand pattern.

[0024] In some implementations of the third aspect of the present disclosure, the machine learning model is a random forest regression model.

[0025] In some implementations of the third aspect of the present disclosure, the cost of a lost customer is greater than the cost of a discarded item.

[0026] In some implementations of the third aspect of the present disclosure, a cost function for splitting decisions in a random forest regression model is: Regression:P+(CR*σ D ) where CR is the ratio and σ D is the standard deviation of past demand for the demand period, and P is the baseline demand forecast based on past demand data for the demand period.

[0027] In some implementations of the third aspect of the present disclosure, the cost of a lost customer is less than the cost of a discarded item.

[0028] In some implementations of the third aspect of the present disclosure, a cost function for splitting decisions in a random forest regression model is: Regression:P-(CR*σ D ) where CR is the ratio and σ D is the standard deviation of past demand for the demand period, and P is the baseline demand forecast based on past demand data for the demand period.

[0029] In some implementations of the third aspect of the present disclosure, operating the beverage warmer includes transporting the product from a peripheral storage zone to a heating zone to heat the product based on a demand pattern.

[0030] In some implementations of the third aspect of the present disclosure, operating the beverage warmer includes maintaining the product in a peripheral storage zone without heating the product based on a demand pattern that predicts a period of low demand.

[0031] These and other features will be more clearly understood from the following detailed description taken in conjunction with the accompanying drawings and claims.

[0032] BRIEF DESCRIPTION OF THE DRAWINGS For a more complete understanding of this disclosure, reference is now made to the following brief description taken in conjunction with the accompanying drawings and detailed description, in which like reference numerals represent like parts. [Brief description of the drawings]

[0033] [Figure 1A] 1 illustrates various views of a beverage warmer according to various embodiments of the present disclosure. [Figure 1B] 1 illustrates various views of a beverage warmer according to various embodiments of the present disclosure. [Figure 1C] 1 illustrates various views of a beverage warmer according to various embodiments of the present disclosure. [Figure 1D] 1 illustrates various views of a beverage warmer according to various embodiments of the present disclosure. [Figure 1E] 1 illustrates various views of a beverage warmer according to various embodiments of the present disclosure. [Diagram 2] 1 illustrates an exemplary display screen for a user interface of a beverage warmer suitable for implementing some embodiments of the present disclosure. [Figure 3A] 1A-1D illustrate various views of a shelf assembly of a beverage warmer suitable for implementing some embodiments of the present disclosure; [Figure 3B] 1A-1D illustrate various views of a shelf assembly of a beverage warmer suitable for implementing some embodiments of the present disclosure; [Figure 3C] 1A-1D illustrate various views of a shelf assembly of a beverage warmer suitable for implementing some embodiments of the present disclosure; [Figure 3D] 1A-1D illustrate various views of a shelf assembly of a beverage warmer suitable for implementing some embodiments of the present disclosure; [Figure 3E] 1A-1D illustrate various views of a shelf assembly of a beverage warmer suitable for implementing some embodiments of the present disclosure; [Figure 3F] 1A-1D illustrate various views of a shelf assembly of a beverage warmer suitable for implementing some embodiments of the present disclosure; [Figure 4A] 1 is a flow diagram of a machine learning process suitable for implementing certain embodiments of the present disclosure. [Figure 4B] 1 is a user interface for a dashboard for generating synthetic data for training machine learning models suitable for implementing some embodiments of the present disclosure. [Diagram 5] 1 is a diagram illustrating projected demand patterns for a number of different commodities suitable for implementing some embodiments of the present disclosure. [Figure 6A] 1 illustrates another beverage warmer according to various embodiments of the present disclosure. [Figure 6B] 1 illustrates another beverage warmer according to various embodiments of the present disclosure. [Figure 7] 1 illustrates an exemplary computer system suitable for implementing some embodiments of the present disclosure. [Figure 8] FIG. 1 is a perspective view of a first embodiment of a new beverage warmer design. [Figure 9] FIG. 1 is a front elevation view of a beverage warmer design. [Figure 10] FIG. 1 is a first side elevation view of a beverage warmer design. [Figure 11] FIG. 13 is a second side elevation view of the beverage warmer design. [Figure 12] FIG. 1 is a top view of a beverage warmer design. [Figure 13] FIG. 13 is a bottom view of the beverage warmer design. [Figure 14] FIG. 13 is a rear elevation view of the beverage warmer design. [Figure 15] FIG. 13 is a perspective view of a beverage warmer design with a transparent front surface. [Figure 16] FIG. 13 is a front elevation view of a beverage warmer design with a transparent front surface. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0034] Detailed Description Although exemplary implementations of one or more embodiments are illustrated below, it should be understood at the outset that the disclosed system and method may be implemented using any number of currently known or existing techniques. The present disclosure should in no way be limited to the exemplary implementations, drawings, and techniques illustrated below, but may be modified within the scope of the appended claims, together with the full scope of equivalents. The use of the phrase "and / or" indicates that any or any combination of the list of alternatives may be used. For example, "A", "B", and / or "C" means "A", or "B", or "C", or "A and B", or "A and C", or "A and B and C".

[0035] The beverage warmer includes a plurality of product shelves, each of which has a plurality of product lanes. Each product lane has a peripheral area, a heating area, and a service area. A first number of ready-to-drink (RTD) beverage products are loaded into the beverage warmer in the peripheral area of ​​the product lane and are transported through each of the heating area and the service area as the products are removed from the beverage warmer. In response to, for example, detecting that the products are removed from the service area in the product lane, the products stored in the peripheral area may be transported to the heating area. The RTD beverage products may include PET or aluminum packaging. The products may be held in the heating area for a period of time and exposed to a first temperature, for example, 80°C. Other heating temperatures, such as 30-100°C, may be used for the heating area. The first temperature may be set to heat the RTD products quickly without causing deformation of the packaging. Upon expiration of the period, the products are transported from the heating area to the service area. The products are held at a second temperature in the service area, where the second temperature is lower than the first temperature, for example, 60°C. The second temperature may be set to a consumption temperature for the RTD products. Other product service temperatures, such as 30-100°C, may be used for the service area. A second number of RTD products may be held within the service area of ​​the product lane, where the second number of products is less than the first number of products. In one example, the first number of products held in the peripheral area of ​​the product lane is three products and the second number of products held in the service area of ​​the product lane is two products. A greater or lesser number of products may be held in each of the peripheral and / or service areas. Accordingly, fewer products are exposed to high temperatures within the beverage warmer, thereby reducing the rate of spoilage of the products and reducing losses from product repurchases.

[0036] 1A-1E illustrate various views of a beverage warmer 100 according to various embodiments of the present disclosure. The beverage warmer 100 includes a first product shelf 102a, a second product shelf 102b, and a third product shelf 102c, collectively the product shelves 102. The beverage warmer 100 may have more or fewer product shelves 102. The first product shelf 102a includes a first product lane 104a, a second product lane 104b, a third product lane 104c, and a fourth product lane 104d, collectively the product shelves 104. The beverage warmer 100 may have more or fewer product lanes 104 on each of the product shelves 102. In the illustrated example, each of the second and third product shelves 102b, 102c has the same number of product lanes 104 as the first product shelf 102a. In other examples, one or more of the second and third product shelves 102b, 102c may have a different number of product lanes 104 than the first product shelf 102a. For example, some product lanes 104 may be wider or narrower depending on product dimensions, resulting in a different number of product lanes 104.

[0037] The product shelves 102 are positioned within a housing 106. A front door 108 provides access through the housing 106 to products held within a service zone 110. Within the service zone 110, each of the product lanes 104 includes a service area 112. The service area 112 is sized to receive one or more products. In one example, the service area 112 is sized to receive two products. In the example shown, the front door 108 provides access to the service zone 110 for all of the product shelves 102 of the beverage warmer 100. The products may be ready-to-drink (RTD) beverage products in PET or aluminum packaging to provide a hot beverage option that is ready for immediate consumption. In some implementations, other products such as soups or other consumables for immediate consumption at a high temperature may be used with the beverage warmer 100.

[0038] In some implementations, one or more insulating barriers may be positioned on the product shelf 102 between one or more product lanes 104 so that products may be held at different temperatures in the different product lanes. Similarly, one or more insulating barriers may be positioned between one or more product shelves 102 so that products may be held at different temperatures on the different product shelves 102. In some implementations, one or more product barriers may be positioned between the product lane 104 and the product shelf 102 so that each of the product lanes may hold products at different temperatures. Each of the insulating barriers may be positioned in contact with or in close proximity (e.g., within 5 mm) of the front door 108 to maintain the different product temperature zones described above.

[0039] In some implementations, the product shelves 102 are tilted at an angle to facilitate a gravity feed to position products along the product lanes 104. Product barriers 114 are fitted at the ends of the service areas 112 to prevent products from falling as they proceed along the product lanes 104. In the example shown, the product barriers 114 span across each of the product shelves 102. In alternative implementations, products may be transported along the product shelves 102 by any other means, such as a vibrating table, rollers, conveyor belts, or any combination of gravity, vibrating tables, rollers, conveyor belts, and / or any other such known product transport mechanisms.

[0040] In some implementations, a product sanitizer (not shown) may be positioned around the service area 112. For example, ultraviolet light, disinfectant sprays, or other sanitizing mechanisms may be applied to products positioned within the service area 112. In some implementations, a product sanitizer may be positioned around the service area 112 for each of the product lanes 104. When a new product enters the service area 112, the product sanitizer may be activated for a predetermined period of time (e.g., ultraviolet light may be turned on for a predetermined period of time) to sanitize the packaging of the new product.

[0041] The service area 112 includes a proximity sensor 116 adapted to detect the presence of an item in the service area 112. The proximity sensor 116 may be an infrared emitter and an infrared sensor positioned on either side of the service area 112. The proximity sensor 116 may alternatively be an electromagnetic sensor, an acoustic sensor, or any other proximity sensor. The proximity sensor 116 is positioned at an end of the service area 112 opposite the item barrier 114. Accordingly, the proximity sensor 116 detects whether the service area 112 has reached a fixed quantity. In the illustrated example, the proximity sensor detects whether the service area 112 has two items positioned thereon.

[0042] In some implementations, the proximity sensor 116 is used to determine the number of items present in the service area 112. For example, each time the proximity sensor 116 detects an item, the item count may be incremented. The item count may be used to control the heating of additional items, as described in more detail below. Once the service area 112 reaches a fixed capacity, the proximity sensor 116 may be used to prevent heating additional items to hold in the service area 112. Once an item is removed from the service area 112, the proximity sensor 116 may be used to determine that additional capacity is available in the service area 112, and another item may be heated.

[0043] In some implementations, the product service area 112 includes a second proximity sensor 118 positioned between the proximity sensor 116 and the second proximity sensor 118. The second proximity sensor 118 is adapted to detect whether any product is positioned within the service area 112. For example, if the second proximity sensor 118 detects that no product is present, it is determined that no product is available within the service area 112. Otherwise, if the second proximity sensor 118 detects that a product is present, it is determined that at least one product is present within the service area 112. In various implementations, one or more of the proximity sensors 116 and / or the second proximity sensor 118 may be optionally present within the beverage warmer 100, or vice versa. In various implementations, the proximity sensor 116 and / or the proximity sensor 118 facilitate on-demand heating of the product as it is consumed, thereby ensuring availability of hot products while minimizing losses due to spoilage by limiting the number of heated products at a given time.

[0044] Each of the product lanes 104 has a corresponding display 120 positioned along a front 122 of each of the product shelves 102. In the example shown, there are four displays 120, each corresponding to one of the product lanes 104. The product displays 120 show status information for the corresponding one of the product lanes 104. For example, when a product is present in the service area 112, the display shows the temperature of the product. When a product is not present in the service area 112, the display shows the time remaining until the product is heated and positioned in the service area 112.

[0045] Each of the product lanes 104 has a corresponding heated exit door 124. The heated exit door 124 separates the service area 112 from the heated area of ​​the product lane 104 (e.g., heated area 318, best shown in FIG. 3F). In the illustrated example, the heated exit door 124 includes a base 126 sized to receive the product, and a wall 125 extending from the base 126. Inside the wall is a door 128 extending through the wall 125 and providing a passageway between the heated area and the service area 112. As described in more detail below, the door 128 prevents excess heat from building up in the heated area that would otherwise distort the product. For example, plastic bottles tend to fill with products in such a way that there is a void in the neck of the bottle. Accordingly, heat may build up in the neck of the plastic bottle faster than the area of ​​the bottle in contact with the liquid product, thereby causing deformation of the bottle around the neck. The door 128 may remove excess heat from the heated area to prevent deformation of the neck of the plastic bottle. The door 128 is positioned at the top of the wall 125. In some implementations, the door 128 extends from the top of the wall 125 toward the bottom of the wall 125 a predetermined distance. For example, the predetermined distance may be 10%, 20%, 25%, 30%, 35%, 40%, 45%, or 50% of the total height of the wall 125. Other sizes of the door 128 are contemplated by the present disclosure. The bottom of the door 128 is positioned at a height close to (e.g., within 5 mm) the liquid fill level of the bottle along the wall. Although the door 128 is shown as a single through passage between the heating area and the service area 112, in various implementations the door 128 may take different shapes or be composed of multiple holes or slots through the wall 125.

[0046] As best shown in FIG. 1B , the service zone 110 includes a plurality of circulating fans 130a, 130b, 130c, 130d, collectively circulating fans 130. Generally, the circulating fans 130 are positioned around each of the product shelves 102 within the service zone 110. For example, the circulating fan 130a is positioned on the front 122 of the product shelf 102a. Although only the circulating fan 130a is positioned on the product shelf 102a, in various implementations, a circulating fan may be positioned on each side of the product shelf 102a. The circulating fans 130 operate to circulate air within the service zone 110 to maintain the products at a first temperature.

[0047] The service zone 110 also includes a number of heating elements 132a, 132b, collectively heating elements 132. The heating elements 132 may be any type of heating element, such as a resistive or induction heater. For example, the heating elements 132 may be strip heaters. Other types of heaters, such as silicon, infrared, induction, thin film resistive, thick film induction, resistive, forced hot air heaters, or convection heating and / or any combination thereof, are contemplated by the present disclosure. The heating elements 132 are activated to maintain the service zone 110 at a first temperature. Although the heating elements 132 are shown on one size of the product shelf 102c, more or fewer heating elements 132 may be used. For example, a single heating element 132 may be used. Alternatively, additional heating elements 132 may be positioned around multiple product shelves 102, such as product shelf 102a and / or product shelf 102b.

[0048] In the unlikely event that the front door 108 remains closed for a period of time, the temperature within the service zone 110 may become higher than the first temperature. For example, excess heat from the heating area may enter the service zone 110 through the door 128 on the heating exit door 124. In such a situation, the exhaust fan 134 may be operated to ventilate the excess heat through an upper surface 136 of the housing 106. As shown, the upper surface 136 has perforations to allow air circulated by the exhaust fan to be drawn from the service zone 110 and supplied through the upper surface 136 to the ambient environment. One or more temperature sensors (not shown) monitor the temperature of the service zone 110 to control the operation of the circulating fan 130, the heating element 132, and the exhaust fan 134 to maintain the service zone 110 at the first temperature.

[0049] 1C, heat shield 138a may be positioned between heating element 132a and circulating fan 130c. Similarly, heat shield 138b may be positioned between heating element 132b and circulating fan 130d. Heat shield 138 prevents consumers from directly contacting heating element 132 when retrieving goods from service zone 110.

[0050] 1C, the product shelves 102 extend at an angle across the depth of the beverage warmer 100 to facilitate a gravity feed to transport products from the heating zone 140 and the peripheral zone 142 to the service zone 110. For example, products may be loaded into the peripheral zone 142 of the beverage warmer 100, and gravity transports the products through the heating zone 140 to the service zone 110, as described in more detail below. A main controller 144, such as a programmable logic controller, controls various aspects of the beverage warmer 100, such as the temperatures maintained in each of the peripheral zone 142, the heating zone 140, and the service zone 110, as well as the operation of the circulating fan 130, the heating element 132, and the exhaust fan 134. Other components of the beverage warmer 100 are also controlled by the main controller 144, as described herein. As shown, the main controller 144 is positioned below the product shelf 102 c in a peripheral zone 142 of the beverage warmer 100 so as to limit exposure of the main controller 144 to heat generated by the beverage warmer 100 .

[0051] As shown in FIG. 1D , a rear door 146 provides access to the peripheral zone 142 through the housing 106 so that products can be loaded onto the shelves 102. Periphery fans 148a, 148b, and 148c, collectively the peripheral fans 148, are positioned on the rear door 146 and configured to remove heat from the peripheral zone 142. In the illustrated example, the peripheral fans 148 are positioned along the rear door 146 at the top of each of the shelves 102. In various implementations, the peripheral fans 148 are configured to blow hot air out of the peripheral zone 142 of the beverage warmer 100. In various implementations, one or more of the peripheral fans 148 may be configured to draw peripheral air into the peripheral zone 142 of the beverage warmer 100. For example, peripheral ventilation fan 148c may be configured to draw ambient air into peripheral zone 142, while peripheral ventilation fans 148a, 148b are configured to blow hot air out of peripheral zone 142. Periphery ventilation fan 148a is controlled by main controller 144 to maintain the temperature of peripheral zone 142 at or below a peripheral zone threshold temperature.

[0052] The user interface 150 is located under the rear door 146 and is connected to the main controller 144 to modify the configuration settings of the beverage warmer. In response, the operation of the beverage warmer 100 is modified based on the input received through the user interface 150. In various implementations, the user interface 150 is a touch screen user interface. In other implementations, the user interface 150 may include a display and one or more buttons or a keyboard for receiving user input. In other implementations, the user interface 150 may include a display and a port for communicating with an external terminal, such as an external keyboard for receiving user input. In other implementations, the user interface 150 may only include a communication terminal, such as a serial port, for connecting to an external device for displaying the configuration settings of the beverage warmer 100 and providing changed configuration settings of the main controller 144. Other types of user interfaces for receiving the current configuration status and modifying the configuration settings of the main controller 144 are also contemplated by this disclosure.

[0053] As shown in FIG. 1E, the beverage warmer 100 is shown with a rear door 146 removed to show details of the peripheral zone 142, also shown in FIG. 1C. Within the peripheral zone 142, each of the product lanes 104 includes a loading area 152. The loading area 152 is sized to receive one or more products. In one example, the loading area 152 is sized to receive three products. More or fewer products may be positioned within the loading area 152. In various implementations, more products may be positioned within the loading area 152 within the service area 112. In the illustrated example, the rear door 146 provides access to the peripheral zone 142 for all of the product shelves 102 of the beverage warmer 100. In some implementations, a separate rear door may provide access to the peripheral zone 142 for each of the product shelves 102.

[0054] In some implementations, the product shelves 102 are tilted at an angle to facilitate a gravity feed to position products along the product lane 104. At one end of the loading area 152 is a heated entry door 154 adapted to prevent products traveling along the product lane 104 from entering the heated zone 140 until desired. The heated entry door 154 is adapted to selectively allow products in the loading area 152 to enter the heated zone 140. The heated entry door 154 insulates the peripheral zone 142 from the heated zone 140, as described in more detail below. In alternative implementations, products may be transported along the product shelves 102 by any other means, such as a vibrating table, rollers, conveyor belts, or any combination of gravity, vibrating table, rollers, conveyor belts, and / or any other such known product transport mechanisms.

[0055] In the illustrated example, the heated exit door 124 and the heated entry door 154 are revolving doors adapted to move goods between the peripheral zone 142, the heated zone 140, and the service zone 110. In other implementations, the heated exit door 124 and the heated entry door 154 may be formed as vertical or horizontal shutters, bi-fold gates, or any other door structure.

[0056] The heating exit door 124 includes a semicircular wall 125 extending from a circular base 126. The heating exit door 124 is initially positioned such that the convex side of the semicircular wall 125 faces the heating zone 140. In this position, any items positioned within the heating zone 140 are prevented from passing through the door 124. When the door 124 is rotated 180 degrees so that the concave side of the semicircular wall 125 faces the heating zone 140, items positioned within the heating zone 140 can enter the door 124 and seat on the base 126. The door 124 rotates so that the concave side of the semicircular wall 125 faces the heating zone 140 in response to the items being placed within the heating zone 140 for a predetermined heating time. Once the items have been transferred to the base 126, the door 124 is rotated 180 degrees so that the convex side of the semicircular wall 125 again faces the heating zone 140. In response, the goods are transferred from the base 126 to the service area 112 .

[0057] The heated entry door 154 includes a semicircular wall 155 extending from a circular base (shown below in FIG. 3F). The heated entry door 154 is initially positioned so that the convex side of the semicircular wall 155 faces the peripheral zone 142. In this position, any items positioned within the loading area 152 are prevented from passing through the door 154. When the door 154 is rotated 180° so that the concave side of the semicircular wall 155 faces the loading area 152, items positioned within the loading area 152 can enter the door 154 and seat on the base. The door 154 rotates so that the concave side of the semicircular wall 155 faces the loading area 152 in response to an item being removed from the service area 112. In various implementations, the door 154 rotates after a predetermined wait time to allow the item to be removed and replaced while the consumer decides which item to select. Once the goods have been transferred to the base, the door 154 is rotated 180° so that the convex side of the semicircular wall 155 again faces the loading area 152. The goods are transferred accordingly from the base to the heating zone 140.

[0058] The loading area 152 includes a proximity sensor 156 adapted to detect the presence of goods within the loading area 152. The proximity sensor 156 may be an infrared emitter and an infrared sensor positioned on either side of the loading area 152. The proximity sensor 156 may alternatively be an electromagnetic sensor, an acoustic sensor, or any other proximity sensor. The proximity sensor 156 is positioned at an end of the loading area 152 that includes the heated entry door 154. Accordingly, the proximity sensor 156 detects whether any goods are placed in the loading area 152.

[0059] In some implementations, the proximity sensor 156 may be located at one end of the loading area 152 that receives the goods. In this location, the proximity sensor 156 is used to determine the number of goods present in the loading area 152. For example, each time the proximity sensor 156 detects a product, the product count may be incremented. When a product is removed from the service area 112, the proximity sensor 156 may be used to determine that additional capacity is available to be heated in the loading area 152. In response, the proximity sensor 156 facilitates on-demand heating of the goods as they are consumed. In some implementations, the proximity sensor 156 is used only to maintain the number of goods within each of the loading area 152 and the service area 112. By using the algorithm-based data to adjust the proportion of total inventory held in the service zone 110 relative to the peripheral zone 142, customers are better able to maintain available hot goods with changes in demand. The beverage warmer 100 knows when to heat the goods to ensure they are available to consumers when they want them. The beverage warmer 100 may also physically move items from the perimeter zone 142 to the heating zone 140 to the service zone 110. The decision to determine what percentage of the total capacity of the beverage warmer 100 is divided into available zones based on a series of algorithmically driven decisions using data collected from local, ambient, and network sources such as past sales, weather, etc.

[0060] In some implementations, the product loading area 152 includes a second proximity sensor (not shown) positioned at an end of the loading area 152 that receives the product. The second proximity sensor is adapted to detect whether the loading area 152 has reached a fixed quantity. In various implementations, the proximity sensor 156 in the peripheral zone 142 and / or one or more of the second proximity sensors may optionally be present in the beverage warmer 100 or may alternatively not be present.

[0061] 2 illustrates an example display screen 200 for the user interface 150 of a beverage warmer 100 suitable for implementing some embodiments of the present disclosure. The display screen 200 includes a service zone status area 202, a service zone set point control area 204, an ambient zone status area 206, and a fan control area 208, and an ambient zone set point control area 210.

[0062] In the service zone status area 202, the hot side temperature 212 indicates the current temperature of the service zone 110. In the illustrated example, the hot side temperature is 45.53° C. The exhaust fan icon 214 indicates the current operating status of the exhaust fan 134. In the illustrated example, the exhaust fan 134 is off. In some implementations, the exhaust fan icon 214 is selectable to toggle the operating state of the exhaust fan 134 (e.g., turn the exhaust fan 134 on or off). The heater icon 216 indicates the current operating status of the heating element 132. In the illustrated example, the heating element 132 is turned on. In some implementations, the heater icon 216 is selectable to toggle the operating state of the heating element 132 (e.g., turn the heating element 132 on or off).

[0063] In the service zone set point control area 204, a set point icon 218 indicates the current set point temperature of the service zone 110. In the example shown, the current set point is 60° C. In response to selecting an up control icon 220 or a down control icon 222, the set point temperature of the service zone 110 increases or decreases, respectively.

[0064] In the surrounding zone status area 206, shelf temperatures 224a, 224b, 224c each indicate a measured temperature of each product shelf 102 within the surrounding zone 142. In the example shown, product shelf 102a has a surrounding zone 142 temperature of 33.87°C. product shelf 102b has a surrounding zone 142 temperature of 32.44°C. product shelf 102c has a surrounding zone 142 temperature of 28.10°C. Ambient temperature icon 226 indicates a temperature measurement of the ambient environment surrounding the beverage warmer 100.

[0065] In the fan control area 208, the circulation fan icon 228 indicates the current operating status of the circulation fan 130. In the illustrated example, the circulation fan icon 228 indicates that the circulation fan 130 is off. In some implementations, the circulation fan icon 228 is selectable to toggle the operating state of the circulation fan 130 (e.g., turn the circulation fan 130 on or off). The save fan icon 230 indicates the current operating status of the peripheral ventilation fan 148. In the illustrated example, the save fan icon 230 indicates that the peripheral ventilation fan 148 is off. In some implementations, the save fan icon 230 is selectable to toggle the operating state of the peripheral ventilation fan 148 (e.g., turn the peripheral ventilation fan 148 on or off).

[0066] In the peripheral zone set point control area 210, the peripheral set point icon 232 indicates the current set point temperature of the peripheral zone 142. In the example shown, the current peripheral set point is 35° C. In response to selection of the increase control icon 234 or the decrease control icon 236, the set point temperature of the peripheral zone 110 increases or decreases, respectively.

[0067] The display screen 200 above illustrates the selection of the enclosure icon 238. Upon selection of the lane icon 240, a different display screen (not shown) may display different control settings and measurements associated with each of the product lanes 104. For example, one or more temperature sensors may indicate the current temperature within the heating zone 140 for each of the product lanes 104. One or more icons may indicate the current operating status of one or more heating elements for each of the product lanes 104, and the operating status may be selectable to change. One or more icons may indicate the current heating set point temperature for each of the product lanes 104 within the heating zone 140, and the control icon may adjust the heating set point temperature. One or more icons may indicate the current status of the heated exit door 124 and heated entrance door 154, and the operating status of each may be toggled (e.g., rotate or open, respectively). One or more icons may indicate a wait time set point that indicates the amount of time to wait before a product is transferred from the peripheral zone 142 to the heated zone 140 to replace the removed product when the product is removed from the service area 112. The wait time allows the product to be removed and replaced while a consumer decides which product to select. The control icon may adjust the wait time set point.

[0068] Upon selection of the heat time icon 242, a different display screen (not shown) may display different control settings and measurements associated with each of the product lanes 104. For example, the heat time set point may indicate the time the product is held in the heating zone 142 before being transferred to the service zone 110. The control icon may adjust the heat time set point. In various implementations, the heat time set point may be adjusted individually within each of the product lanes 104. Accordingly, products in different product lanes may be heated for different times to account for differences in package size and package materials. Other control settings and measurements may be displayed and manipulated via the user interface 150.

[0069] 3A-3F illustrate various views of a shelf assembly 300 of a beverage warmer suitable for implementing some embodiments of the present disclosure. The shelf assembly 300 may be used for each of the product shelves 102 described above, with like numbers representing like parts. Each of the product lanes 104 of the shelf assembly 300 includes a door orientation sensor 302 and a door orientation disk 304. The door orientation disk 304 is configured to rotate in conjunction with the heated inlet door 154 and the heated outlet door 124. In some implementations, the door orientation disk 304 includes one or more magnets positioned on the door orientation disk 304 to match a predetermined orientation (e.g., open and / or closed orientation) of the door 124, 154. The door orientation sensor 302 may be a Hall effect sensor adapted to detect the presence of a magnet on the door orientation disk 304 to determine the current orientation of the door 124, 154. Other orientation sensors are contemplated by the present disclosure. The door orientation sensor 302 senses the orientation of the door 124, 154 relative to one or more orientations (eg, an open orientation, a partially open orientation, a closed orientation, etc.).

[0070] Each of the goods lanes 104 of the shelf assembly 300 also includes a lane controller 306 and a motor 308. The lane controller 306 is configured to communicate with the main controller 144 and to receive configuration settings provided through the user interface 150. The lane controller 306 then modifies the operation of one or more components of the goods lane 104. For example, the lane controller 306 may receive input from proximity sensors 116, 118, 156 in the goods lane 104 and control the operation of the doors 124, 154 accordingly. The lane controller 306 also controls the operation of the heating elements in the heating zone 140, as well as the operation of the motor 308, which will be described in more detail below. The lane controller 306 also provides operational status information for the goods lanes 104, such as the inventory status of the goods lanes (e.g., the number of goods in each of the service area 112 and the loading area 152), the set point temperature in the heating zone 140, the heating time that the goods remain in the heating zone 140, the time remaining before the goods placed in the heating zone 140 are transferred to the service area 112, and any other operational status of the goods lanes. By providing a separate lane controller 306 for each of the goods lanes 104, the goods lanes 104 may operate independently. In some implementations, one or more goods lanes may have different heating or service temperatures and / or different heating times.

[0071] In the illustrated example, the operation of the doors 124, 154 is controlled by a motor 308. When activated, the motor 308 rotates a main drive gear 310. An entry door gear 316 and a transfer gear 312 are in engagement with the main drive gear 310 such that rotation of the main drive gear 310 rotates the entry door gear 316 and the transfer gear 312, respectively. An exit door gear 314 is in engagement with the transfer gear 312 such that rotation of the transfer gear 312 rotates the exit door gear 314. The entry door gear 316 is coupled to rotate with the heated entry door 154, and the exit door gear 314 is coupled to rotate with the heated exit door 124. Accordingly, a single motor is configured to control the operation of both doors 124, 154 in the goods lane 104.

[0072] While the gear ratio in the illustrated example advances both doors 124, 154 the same angular distance for each revolution of the motor 308, in some implementations, different gear ratios may be used. For example, the ratio of size of the entry door gear 316 to the exit door gear 314 may be 1 to 2. Accordingly, one revolution of the entry door gear 316 results in two revolutions of the exit door gear. Such a gear ratio facilitates the transfer of goods from the heating zone 140 to the service area 112 without also receiving goods from the loading area 152 into the heating zone 140. In some implementations, separate motors may be directly coupled to each of the doors 124, 154 to facilitate independent actuation of the doors.

[0073] The product lane 104 may track consumer demand patterns by being able to transfer product from the heating zone 140 to the service area 112 without also receiving product from the loading area 152 into the heating zone 140. For example, if product is removed from the service area 112 and there is still product remaining in the service area and the lane controller 306 determines that the beverage warmer 100 is in a low demand period (e.g., after the lunch rush is over), product may not be loaded from the surrounding zone 142 to the heating zone 140 even though there is availability in the service area 112. In various implementations, a low demand period is a period during which the predicted demand for a future demand period is below a low demand threshold (e.g., one or less products in the next hour).

[0074] The demand pattern may be loaded and stored in the memory of the lane controller 306, such as via the main controller 144. The demand pattern indicates periods of low and high demand for controlling the operation of the doors 124, 154. In some implementations, the demand pattern may be dynamically determined based on predictive modeling performed by the lane controller 306 and / or the main controller 144, based on past consumption patterns and / or current conditions. For example, the past consumption pattern may be determined by past sales and spoilage rates of products at the beverage warmer 100 level, the shelf 102 level, or the product lane 104 level. Such past consumption patterns may also be coupled with a planogram indicating which products are stocked in each of the product lanes 104 of the beverage warmer 100. The current conditions may be based on current inventory levels within the beverage warmer 100, weather, holidays, local event schedules, etc. By controlling the operation of the doors 124, 154 based on the demand pattern, less products are exposed to high temperatures and even less spoilage. Product spoilage is minimized because only a selected portion (rather than all) of the inventory is heated. Automated transport of products within the beverage warmer 100 reduces the labor associated with frequently refilling the hot box with peripheral products. Heating algorithmically selected products based on demand data increases profit potential by reducing product spoilage and product repurchases.

[0075] FIG. 3F is a cross-sectional view of the shelf assembly 300 showing details of the heating zone 140. Each of the product lanes 104 in the heating zone 140 includes a heating area 318 for receiving the product to be heated from the loading area 152. A pair of heating elements 326, 328 are positioned in either size of the heating area 318. Positioning the heating elements on two sides of the product promotes more even and rapid heating of the product. The heating elements 326, 328 may be thick film radiant heating elements to effectively heat both PET bottles and aluminum cans without causing any packaging deformation. Other heating elements such as silicon, infrared, induction, thin film resistive, thick film induction, resistive, forced hot air heaters or convection heating, and / or any combination thereof may be used. In implementations where only PET bottles are used, infrared heaters may be particularly effective in heating the product without causing packaging deformation.

[0076] In various implementations, the lane controller 306 may control the operation of the heating elements 326, 328 such that they are activated only when a product is present within the heating zone 140. The heating elements 326, 328 thus consume energy only as required by the demand load of the beverage warmer. Accordingly, the amount of energy used to heat and maintain the product at a service temperature within the beverage warmer 110 is reduced compared to a beverage warmer that heats all of the product immediately.

[0077] The heating temperature of the heating elements may be controlled by the lane controller 306. For example, the heating temperature may be typically, for example, 80° C. Other heating temperatures, such as 30-100° C., may be used in the heating zone 318. In some implementations, the heating temperature is controlled based on the demand pattern. For example, the product may be started to be heated at a lower temperature (e.g., 5, 10, 15, or 20° C. below the typical heating temperature) for a longer period of time during a low demand period in anticipation of a high demand period. In some implementations, the product may be heated at a higher temperature (e.g., 5, 10, 15, or 20° C. above the typical heating temperature) for a shorter period of time. In some implementations, the product may be heated at different temperatures for different times (e.g., by vibrating or otherwise varying the heating temperature) to increase heat transfer while preventing deformation of the packaging. In some implementations, the product may be kept in the heating zone 318 with the heating elements 326, 328 turned off. For example, the desired temperature of the product may be changed throughout the day (e.g., warming the beverage in the morning and lowering or ambient temperature the beverage at lunchtime). More generally, the lane controller 306 can automatically select the optimal target temperature for the next package to be heated based on demand. By being able to dynamically heat or cool specific areas of inventory on a single countertop unit, product quality can be maintained regardless of consumer demand (wanting to purchase hotter products immediately) or ambient temperature (cooling inventory before heating to extend shelf life).

[0078] In some implementations, a single heating element may be used in each of the product lanes 104. In some implementations, the heating element may be placed on other surfaces, such as the heating area 318. In some implementations, a product agitator (not shown) may operate to rotate or vibrate the product in the heating area 318 to increase the rate of heat transfer to the product. In some implementations, the heated exit door 124 is used as a product agitator by vibrating back and forth without fully opening. For example, the heated exit door 124 may vibrate at a rotation of about 5° to 30°. In some implementations, different types of heating elements may be used in different product lanes 104. For example, one of the product lanes 104 may be designed for use with products packaged in PET, and infrared heaters may be used in the product lane designed. The other product lane 104 may have a different heating element that is particularly suited for heating aluminum packaging.

[0079] To limit excess heat from the heating zone 140 from entering the service zone 110, the wall 125 of the heating exit door 112 is formed with an insulating gap 320. Similarly, to limit excess heat from the heating zone 140 from entering the peripheral zone 142, the wall 155 of the heating entry door 152 is formed with an insulating gap 324. In some implementations, an insulating material such as polyurethane foam may fill the gap 320 and / or the gap 324. Additionally, between each of the product lanes 104 and on the ends of the product lanes 104, the heating zone 140 includes a gap 330. In some implementations, the gap 330 may be filled with an insulating material such as polyurethane foam or vacuum panels. Providing insulation between each of the product lanes 104 facilitates different heating and service temperatures between the different product lanes.

[0080] In various implementations, the demand patterns for the beverage warmer 100 are determined by a machine learning model. The machine learning model creates a forecast of demand ahead for a period of time (e.g., hour, day, week, next refill, etc.) based on historical demand and current state inputs to the machine learning algorithm. The historical demand and current state inputs used to train the machine learning model may include the date and / or time for the demand period (e.g., a given time on a given day of a week in a given month), the number of products purchased during the demand period (e.g., the number purchased / removed from each of the product lanes 104 and the type of product purchased / removed), the amount of customer demand during the demand period (e.g., the number of consumers in the store during the demand period), inventory levels (e.g., the number of each product type of product held within the beverage warmer 100), spoilage (e.g., spoilage or number of items removed from beverage warmer 100 due to noticed spoilage), inventory heating level (e.g., number of items currently being heated or being heated within beverage warmer 100), outlet hours (e.g., normal business hours of a retail point of sale that includes beverage warmer 100), weather and seasonality (e.g., current local weather forecast for the demand period, and information about the season, including any local holidays or special events), location (e.g., outlet identity, map location, geographic coordinates, geographic description), and customer profile (e.g., customer identity, customer preferences). Other training inputs may be provided to the machine learning model.

[0081] In some implementations, the machine learning model may be trained and executed on the beverage warmer 100 (e.g., on the main controller 144 or each lane controller 306). In some implementations, the machine learning model is trained remotely, such as on a server (not shown) that receives operational inputs (e.g., number of items stocked, number of sales, number of repurchases, etc.) for the operation of the beverage warmer 100. The server may periodically retrain the model based on updated operational inputs from the beverage warmer 100 and provide updated demand forecast models to the beverage warmer 100 for execution on the main controller 144 or each lane controller 306. In some implementations, the machine learning model may be trained and executed on the server to generate demand forecasts. The generated demand forecasts may be loaded into the beverage warmer 100, such as in the form of a demand profile, and the beverage warmer 100 may operate based on the received demand forecasts.

[0082] In various implementations, the machine learning model is trained to predict demand patterns to minimize costs associated with spoilage and missed sales of the product. In some implementations, other success criteria may be modeled in the machine learning algorithm, such as maximizing revenue, not missing consumers, minimizing energy consumption, maximizing supply of selection, etc. Costs associated with spoilage of the product, such as the cost of lost product (e.g., cost per product in a product buyback program), the cost of taking up space in the beverage warmer 100 that could otherwise be used for usable inventory, and / or the incremental cost associated with a mechanism for removing the product after a given product spoilage time. Costs associated with missed sales include lost revenue or lost profits. For beverage products, typical costs associated with missed sales are greater than the costs associated with spoilage of the product.

[0083] Minimizing only the costs associated with product spoilage may result in a very conservative demand model (e.g., heating products only when there is consumer demand, such as when an input is received by the beverage warmer 100, results in long wait times and lost sales). Minimizing only the costs associated with missed sales may result in a very liberal demand model (e.g., heating all products, as is done today, results in increased product spoilage). The machine learning algorithm of the pending disclosure therefore seeks to minimize the cost ratio (CR) of the cost of a missed customer to the cost of product spoilage, as shown below:

number

[0084] In one example, the machine learning model is random forest regression, although other machine learning models such as gradient boosting or other ensemble methods may be used. Alternatively, deep learning methods may be used. Random forest regression generates a demand forecast for a future demand period using a cost function that minimizes a cost ratio. For example, the demand forecast may be the next demand hour, the next period until the beverage warmer 100 is scheduled to be refilled, or some other demand period. In one example, the demand period is a given time on a given day of the week (e.g., Monday at 1:00 p.m.).

[0085] Demand data for the demand period is obtained from a historical demand dataset and a standard deviation of the historical demand is determined (e.g., standard deviation from the demand level at 1:00 PM on Monday in the historical demand dataset). A demand buffer is determined based on the product of the standard deviation of the historical demand for the demand period and a cost ratio. In some implementations, a more complex demand buffer may be determined that considers additional parameters that affect demand, such as local weather, holidays, events, or other such dynamic demand events. The demand buffer models the natural fluctuations in demand over time while considering the cost of the demand fluctuations. A baseline demand forecast is determined based on historical demand data for the demand period (e.g., the average of the demand for the demand period). Other baseline demand forecasts may be used. Based on the above, the cost function for splitting decisions in random forest regression is: Regression:P+(CR*σ D ) Equation (2) where CR is the cost ratio and σ D is the standard deviation of past demand for the demand period, and P is the baseline demand forecast based on past demand data for the demand period.

[0086] For beverage products, the cost associated with a missed sale is typically greater than the cost associated with product spoilage, while for some products the cost associated with product spoilage may be greater than the cost associated with a missed sale. In such situations, the cost function for split decisions in random forest regression is modified as follows: Regression:P-(CR*σ D ) Equation (3) Other variations of cost functions based on cost ratios are contemplated by this disclosure.

[0087] 4A is a flow diagram of a machine learning process 400 suitable for implementing some embodiments of the present disclosure. A database 402 stores a set of historical demand data for various demand periods, such as the historical demand input described above. For example, the historical demand data may include the number of items purchased in a previous demand period, the amount of customer demand in a previous demand period, spoilage events in a previous demand period, etc. Using the data in the database 402, a machine learning model is generated at 404. For example, a server in communication with the beverage warmer 100 generates a random forest regression as described above. Alternatively, one or more of the main controller 144 and / or lane controllers 306 may generate the machine learning model.

[0088] The generated machine learning model is then applied to the beverage warmer 100 to generate a demand forecast. Current state data 406 is provided to the generated machine learning model, such as the current situation inputs described above. For example, the current state data may include current demand periods, stock levels, stock heating levels, business hours, weather and seasonality, and data for customer profiles and / or times. Using the current state data 406, the machine learning model generates a demand forecast for future demand periods at 408. The demand forecast may be provided to the beverage warmer 100 to control its operation. For example, one or more of the doors 124, 154 and / or heating elements 326, 328 may be operated according to the predicted demand patterns, as described above. Additional data 412 is provided to update the database 402 based on the operation of the beverage warmer 100 and actual purchase information.

[0089] FIG. 4B is a user interface for a dashboard 450 for generating synthetic data for training a machine learning model suitable for implementing some embodiments of the present disclosure. In various implementations, it is desirable to train a machine learning model using real-world data as opposed to the generated synthetic data. In such a situation, the dashboard 450 may be used to isolate the desired real-world data for training the machine learning model based on the control electronics of a particular beverage warmer. In some implementations, the machine learning model trained using the generated synthetic data may be used to compare and analyze between control schemes and hardware configurations of the beverage warmer. In some implementations, the machine learning model trained using the generated synthetic data may be used as an initial model for deployment to a beverage warmer, where real-world data collected from the beverage warmer may be used to generate an updated model for the beverage warmer.

[0090] The dashboard 450 may be used to set parameters for the behavior of the beverage warmer based on its hardware configuration. While the dashboard 450 may be used to generate synthetic data or filter real-world data to train machine learning models for the beverage warmer 100 described above, one or more parameters in the dashboard 450 may be changed to generate synthetic data or filter real-world data to train machine learning models for other devices as well.

[0091] As shown, the beverage warmer parameters include configuration settings 452. Configuration parameters 452 are a drop down menu of selectable configurations for the beverage warmer (e.g., an open cabinet configuration where all items are heated at the same time as is currently done, a split cabinet configuration with separate peripheral and heating zones such as beverage warmer 100 described above, or a vending configuration where the beverage warmer's control component takes the desired items for dispensing based on the received selections). An execute icon 454 indicates when to generate synthetic data or filter real world data based on the configured parameters described herein.

[0092] The scenario parameters 456 are a drop down menu of pre-configured beverage warmers that will activate the scenario (e.g., convenience store, gas station, train station, etc.). Other parameters include a peak demand parameter 458 (e.g., the peak amount of demand used to scale the generated demand profile), a time duration parameter 460 (e.g., the number of weeks of synthetic demand data to be generated or real world data to be filtered), and an expiration date 462 (e.g., the amount of time the product may remain hot before the expiration date expires). The replenishment method parameter 464 is a drop down menu of different replenishment methods (e.g., refilling on a predetermined schedule when a predetermined percentage of the beverage warmer inventory is depleted, or some other replenishment method).

[0093] Other parameters include replenishment time 466 (e.g., the amount of time between different stocking actions) and revenue per unit 468 (e.g., the amount of revenue generated when selling an item), which in some implementations are used as key performance indicators (KPIs) for the dashboard 450 and are not used to train the machine learning model. Cost of wasted units 470 and cost of lost customers 472 are used to train the machine learning model (e.g., to generate the cost ratios used in the cost function described above). Capacity parameter 474 (e.g., the amount of inventory the beverage warmer has), number of heating units parameter 476 (e.g., the amount of total inventory that can be heated by the beverage warmer at one time), minimum heated inventory parameter 478 (e.g., the minimum amount of inventory the beverage warmer must hold).

[0094] Heat time parameter 480, which is a drop down menu of different relative heating rates for the beverage warmer (e.g., slow, fast), and existing selection method parameter 482, which is a drop down menu of different selection methods (e.g., random selection, select the freshest product, force beverage warmer to select product, etc.). In various implementations, selection method parameter 482 may be used for comparative analysis between the control scheme and the beverage warmer hardware configuration, but is not used in the generation of the machine learning model. However, machine learning selection method parameter 484 is a drop down menu of different selection methods for the beverage warmer (e.g., random selection, select the freshest product, force beverage warmer to select product, etc.) that are modeled by the machine learning model.

[0095] The energy control parameters 486 indicate how much of the heating capacity of the beverage warmer can be turned on / off (e.g., variable amount of heating capacity, total heating capacity, etc.). In various implementations, the energy control parameters 486 are used as KPIs for the dashboard 450 and are not used to train the machine learning model. The energy to heat unit parameters 488 (e.g., the amount of energy used by the heating zone 140 in the beverage warmer 100 to heat the product) and the energy to keep the unit warm parameters 490 (e.g., the amount of energy used by the service zone 110 in the beverage warmer 100 to keep the product in the service zone 110 at a service temperature, i.e., the energy use by the circulating fan 130 and the heating element 132). In various implementations, the energy to heat unit parameters 488 and the energy to keep the unit warm parameters 490 are used as KPIs for the dashboard 450 and are not used to train the machine learning model. More or fewer parameters are contemplated by the present disclosure. For example, parameters relating to weather patterns, local events, etc. may also be included within dashboard 450.

[0096] 5 is a predicted demand pattern 500 for a number of different products suitable for implementing some embodiments of the present disclosure. The predicted demand pattern is shown as the amount of demand (e.g., number of products expected to be sold) for each of a number of time intervals (e.g., hours) for a prediction period (e.g., a day). A first demand pattern 502 shows the predicted demand pattern for a first product. A second demand pattern 504 shows the predicted demand pattern for a second product. A third demand pattern 506 shows the predicted demand pattern for a third product. A fourth demand pattern 508 shows the predicted demand pattern for a fourth product. In the illustrated example, the demand for the first product is predicted only between 5:00 a.m. and 5:00 p.m., when a shift in demand occurs and additional demand is predicted for other products. Accordingly, not only can operation of the beverage warmer 100 be modified based on the predicted demand pattern (e.g., not starting heating of any of the second, third, or fourth items until 5:00 p.m.), but machine inventory decisions may also be made using the predicted demand pattern (e.g., most or all of the machines will stock the first item between 5:00 a.m. and 5:00 p.m.).

[0097] 6A-4B illustrate another beverage warmer 600 according to various implementations of the present disclosure. The beverage warmer 600 is substantially similar to the beverage warmer 100, except that each of the product shelves 102 has a separate door. For example, a first door 602a provides access to the first product shelf 102a, a second door 602b provides access to the second product shelf 102b, and a third door 602c provides access to the third product shelf 102c. Each of the doors 602 may open downward, similar to an oven, as shown in FIG. 6B. In some implementations, the doors 602 may open outward. Providing separate doors 602 for each of the product shelves 102 facilitates setting different service temperatures within the service zone 110. In some implementations, one or more insulating barriers may be positioned between the product shelves 102.

[0098] Figures 8-16 show various views of the beverage warmer design. Figure 8 is a perspective view of a first embodiment of a new beverage warmer design. Figure 9 is a front elevation view of the beverage warmer design. Figure 10 is a first side elevation view of the beverage warmer design. Figure 11 is a second side elevation view of the beverage warmer design. Figure 12 is a top view of the beverage warmer design. Figure 13 is a bottom view of the beverage warmer design. Figure 14 is a back elevation view of the beverage warmer design. Figure 15 is a perspective view of the beverage warmer design with a transparent front surface. Figure 16 is a front elevation view of the beverage warmer design with a transparent front surface.

[0099] 7 illustrates an example computer system 700 suitable for implementing some embodiments of the present disclosure. For example, one or more components or controller components of the beverage dispenser 504 may be implemented as a computer system 700. In some implementations, one or both of the HMI 1004 and the CDM 1006 may be implemented as a computer system 700.

[0100] It should be appreciated that the logical operations described herein with respect to the various figures may be implemented (1) as a series of computer-implemented operations or program modules (i.e., software) executing on a computing device (e.g., the computing device depicted in FIG. 7); (2) as interconnected mechanical logic circuits or circuit modules (i.e., hardware) within a computing device; and / or (3) a combination of software and hardware in a computing device. Thus, the logical operations discussed herein are not limited to any particular combination of hardware and software. The implementation is a matter of choice depending on the performance and other requirements of the computing device. Accordingly, the logical operations described herein are referred to variously as operations, structural devices, acts, or modules. These operations, structural devices, acts, and modules may be implemented in software, firmware, special purpose digital logic, and any combination thereof. It should also be appreciated that more or fewer operations may be performed than illustrated in the figures and described herein. These operations may also be performed in orders different from those described herein.

[0101] Referring to FIG. 7, an exemplary computing device 700 is illustrated in which an embodiment of the present invention may be implemented. For example, each of the main controller 144 and the lane controller 306 may be implemented as a computing device such as the computing device 700. It should be understood that the exemplary computing device 700 is only one example of a suitable computing environment in which an embodiment of the present invention may be implemented. Optionally, the computing device 700 may be any well-known computing system, including, but not limited to, personal computers, servers, portable or laptop devices, multiprocessor systems, microprocessor-based systems, networked personal computers (PCs), minicomputers, mainframe computers, embedded systems, and / or distributed computing environments including a plurality of any of the above systems or devices. A distributed computing environment enables remote computing devices coupled to a communication network or other data transmission medium to perform various tasks. In a distributed computing environment, program modules, applications, and other data may be stored in local and / or remote computer storage media.

[0102] In some implementations, the computing device 700 may include two or more computers that communicate with each other to cooperate to perform a task. For example, but not by way of limitation, an application may be partitioned in a manner that allows for concurrent and / or parallel processing of the application's instructions. Alternatively, data processed by an application may be partitioned in a manner that allows for concurrent and / or parallel processing of different portions of the data set by two or more computers. In some implementations, virtualization software may be utilized by the computing device 700 to provide the functionality of multiple servers that are not directly tied to the number of computers in the computing device 700. For example, the virtualization software may provide 20 virtual servers on 4 physical computers. In some implementations, the functionality disclosed above may be provided by running one and / or more applications in a cloud computing environment. Cloud computing may include providing computing services over a network connection using dynamically scalable computing resources. Cloud computing may be at least partially assisted by virtualization software. The cloud computing environment may be established by an enterprise and / or rented as needed from a third party provider. Some cloud computing environments may include cloud computing resources owned and operated by an enterprise, as well as cloud computing resources rented and / or leased from third party providers.

[0103] In its most basic configuration, a computing device 700 typically includes at least one processing unit 720 and a system memory 730. Depending on the exact configuration and type of computing device, the system memory 730 may be volatile (such as random access memory (RAM)), non-volatile (such as read only memory (ROM), flash memory, etc.), or some combination of the two. This most basic configuration is illustrated in FIG. 7 by dashed line 710. The processing unit 720 may be a standard programmable processor that performs the mathematical and logical operations necessary for the operation of the computing device 700. Although only one processing unit 720 is shown, there may be multiple processors. Although instructions may be discussed as being executed by a processor in this manner, the instructions may be executed simultaneously, serially, or alternatively by one or more processors. The computing device 700 may also include a bus or other communication mechanism for communicating information between the various components of the computing device 700.

[0104] Computing device 700 may have additional features / functionality. For example, computing device 700 may include additional storage such as removable storage 740 and non-removable storage 750, including, but not limited to, a magnet or optical disk or tape. Computing device 700 may also contain a network connection 780 that allows the device to communicate with other devices, such as over the communication paths described herein. Network connection 780 may take the form of a modem, modem bank, Ethernet card, Universal Serial Bus (USB) interface card, serial interface, token ring card, Fiber Distributed Data Interface (FDDI) card, Wireless Local Area Network (WLAN) card, wireless transceiver card such as Code Division Multiple Access (CDMA), Global System for Mobile Communications (GSM), Long Term Evolution (LTE), Worldwide Interoperable Microwave Access (WiMAX), and / or other air interface protocol wireless transceiver cards, and other well-known network devices. Computing device 700 may also have input devices 770, such as a keyboard, keypad, switches, dials, a mouse, a trackball, a touch screen, a voice recognition device, a card reader, a paper tape reader, or other well-known input devices. Output devices 760, such as a printer, a video monitor, a liquid crystal display (LCD), a touch screen display, a display, speakers, etc., may also be included. Additional devices may be connected to the bus to facilitate communication of data between components of computing device 700. All these devices are well known in the art and need not be discussed at length here.

[0105] The processing unit 720 may be configured to execute program code encoded on a tangible computer-readable medium. Tangible computer-readable medium refers to any medium that can provide data that causes the computing device 700 (i.e., a machine) to operate in a specific manner. A variety of computer-readable media may be utilized to provide instructions to the processing unit 720 for execution. Exemplary tangible computer-readable media may include, but are not limited to, volatile, non-volatile, removable, and non-removable media implemented in any method or technology for storage of information, such as computer-readable instructions, data instructions, program modules, or other data. The system memory 730, the removable storage 740, and the non-removable storage 750 are all examples of tangible computer storage media. Exemplary tangible computer readable recording media include, but are not limited to, integrated circuits (e.g., field programmable gate arrays or application specific ICs), hard disks, optical disks, magneto-optical disks, floppy disks, magnetic tape, holographic storage media, solid state devices, RAM, ROM, Electrically Erasable Programmable Read Only Memory (EEPROM), Flash memory or other storage technologies, CD-ROMs, Digital Versatile Disks (DVDs) or other optical storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices, or other magnetic storage devices.

[0106] It is essential in electrical and software engineering that functionality that can be implemented by loading executable software into a computer can be transformed into a hardware implementation by known design rules. The decision to implement a concept in software or hardware is typically driven by considerations of design stability and number of units produced, rather than any issues involved in transferring from the software domain to the hardware domain. Designs that are generally subject to frequent changes may be preferred to be implemented in software, since revolving a hardware implementation is more expensive than revolving a software design. Stable designs that are generally produced in large quantities may be preferred to be implemented in hardware, for example, in an application specific integrated circuit (ASIC), since a hardware implementation may be less expensive than a software implementation to achieve high volume production. A design may be developed and tested in software form, and later transformed by known design rules into an equivalent hardware implementation in an application specific integrated circuit that wires up the software's instructions. A computer that has been programmed and / or loaded with executable instructions may be considered a specific machine or device, just as a machine controlled by a new ASIC is a specific machine or device.

[0107] In an example implementation, processing unit 720 may execute program code stored in system memory 730. For example, a bus may carry data to system memory 730, and processing unit 720 receives and executes instructions from system memory 730. Data received from system memory 730 may optionally be stored on removable storage 740 or non-removable storage 750 before or after execution by processing unit 720.

[0108] It should be understood that the various techniques described herein may be implemented in conjunction with hardware or software, or a combination thereof, as appropriate. Thus, the methods and apparatus of the disclosed subject matter, or certain aspects or portions thereof, may take the form of program code (i.e., instructions) embodied in a volatile medium, such as a floppy disk, a CD-ROM, a hard drive, or any other machine-readable storage medium, which when loaded and executed by a machine, such as a computing device, causes the machine to become an apparatus for practicing the disclosed subject matter. When executing program code on a programmable computer, the computing device generally includes a processor, a processor-readable storage medium (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device. One or more programs may implement or utilize the steps described in connection with the disclosed subject matter, for example, through the use of an application programming interface (API), a reusable controller, or the like. Such programs may be implemented in a high-level process-based or object-oriented programming language to communicate with a computer system. However, the programs may be implemented in assembly or machine language, if desired. In either case, the language may be an edited or interpreted language, and the language may be combined with hardware implementations.

[0109] Embodiments of the methods and systems may be described herein with reference to block diagrams and flow diagrams of methods, systems, apparatus, and computer program products. It will be understood that each block of the block diagrams and flow diagrams, and combinations of blocks in the block diagrams and flow diagrams, respectively, can be implemented by computer program instructions. These computer program instructions may be loaded onto a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute on the computer or other programmable data processing apparatus, generate means for implementing the functions specified in one or more blocks of the flow diagrams.

[0110] These computer program instructions may also be stored in a computer readable memory such that the instructions stored in the computer readable memory can direct a computer or other programmable data processing apparatus to function in a particular manner to produce an article of manufacture including computer readable instructions for implementing the functions set forth in one or more of the blocks of the flowcharts. The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus such that the instructions executing on the computer or other programmable apparatus cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process providing steps for implementing the functions set forth in one or more of the blocks of the flowcharts.

[0111] Accordingly, the blocks of the block diagrams and flow diagrams support combinations of means for performing the specified functions, combinations of steps for performing the specified functions, and program instruction means for performing the specified functions. It will also be understood that each block of the block diagrams and flow diagrams, and combinations of blocks of the block diagrams and flow diagrams, can be implemented by a dedicated hardware-based computer system that performs the specified functions or steps, or a combination of dedicated hardware and computer instructions.

[0112] Although several embodiments have been provided in this disclosure, it should be understood that the disclosed systems and methods may be embodied in many other specific forms without departing from the spirit and scope of the disclosure. The examples should be considered illustrative and not limiting, and the intention should not be limited to the details given herein. For example, various elements or components may be combined or integrated in another system, or certain features may be omitted or not implemented.

[0113] Additionally, the techniques, systems, subsystems, and methods described and illustrated in various embodiments individually or separately may also be combined or integrated with other systems, modules, techniques, or methods without departing from the scope of the present disclosure. Other items shown or discussed as directly coupled or in communication with each other may be indirectly coupled or in communication, electrically, mechanically, or otherwise, through some interface, device, or intermediate component. Other examples of modifications, substitutions, and alterations can be ascertained by one of ordinary skill in the art and can be made without departing from the spirit and scope disclosed herein. EXAMPLES

[0114] Additional Examples 1. A method of operating a beverage warmer based on a machine learning model of predicted demand patterns, comprising: training a machine learning model to predict demand patterns for a future demand period, where training the machine learning model is based on a cost function that is a function of a ratio of cost of lost customers to cost of discarded goods; and activating the beverage warmer based on the predicted demand pattern.

[0115] 2. The method of example 1, wherein the machine learning model is a random forest regression model.

[0116] 3. The method according to example 2, wherein the cost of a lost customer is greater than the cost of a discarded product.

[0117] 4. The cost function for splitting decisions in a random forest regression model is Regression: P+(CR*σ_D) where CR is a ratio, σ_D is the standard deviation of past demand for the demand period, and P is a baseline demand forecast based on past demand data for the demand period.

[0118] 5. The method according to example 2, wherein the cost of a lost customer is less than the cost of a discarded good.

[0119] 6. The cost function for splitting decisions in a random forest regression model is Regression: P-(CR*σ_D) where CR is a ratio, σ_D is the standard deviation of past demand for the demand period, and P is a baseline demand forecast based on past demand data for the demand period.

[0120] 7. The method of example 1, wherein operating the beverage warmer includes transporting the product from a peripheral storage zone to a heating zone to heat the product based on demand patterns.

[0121] 8. The method of example 1, wherein operating the beverage warmer includes holding the product in a peripheral storage zone without heating the product based on a demand pattern predicting a period of low receipt.

Claims

1. A beverage warmer, comprising: a merchandise shelf having a peripheral storage zone, a heating zone, and a service zone, the merchandise shelf including a first door between the peripheral storage zone and the heating zone, and a second door between the heating zone and the service zone, each of the first and second doors being configurable between an open position and a closed position; inputting current state data, including at least (1) the time of the store having the beverage warmer, and (2) the spoilage of the product in the beverage warmer, into the generative machine learning model; Using the generative machine learning model to generate a demand forecast; a controller configured to operate the first door to transport the product from the peripheral storage zone through the heating zone based on the demand forecast, and to operate the second door to transport the product from the heating zone to the service zone based on the demand forecast.

2. The beverage warmer of claim 1 , wherein the service zone includes a service area sized to receive a first number of items.

3. The beverage warmer of claim 2 , wherein the peripheral storage zone includes a loading area sized to receive a second number of items.

4. The beverage warmer of claim 3 , wherein the second number of items is greater than the first number of items.

5. The beverage warmer of claim 3 , wherein the heating zone comprises a heating area sized to receive a single item.

6. The beverage warmer of claim 1 , wherein the service zone includes a proximity sensor configured to detect whether a product is present at a location within the service zone.

7. 7. The beverage warmer of claim 6, wherein the controller is configured to determine that a product has been removed from the service zone in response to the proximity sensor detecting that a product is not present at the location after detecting that a product is present at the location.

8. 8. The beverage warmer of claim 7, wherein the controller is further configured to, in response to determining that a product has been removed from the service zone, operate the first door to transport a product from the peripheral storage zone to the heating zone.

9. The beverage warmer of claim 1 , wherein the second door comprises a wall with a door, the door being positioned at an upper portion of the wall.

10. 2. The beverage warmer of claim 1, wherein the product shelf further comprises a plurality of product lanes, each of the product lanes extending through the peripheral storage zone, the heating zone, and the service zone.

11. 11. The beverage warmer of claim 10, further comprising a plurality of merchandise shelves.

12. 1. A method of operating a beverage warmer, comprising: inputting current state data, including at least (1) the time of the store having the beverage warmer installed, and (2) spoilage of the product in the beverage warmer, into a generating machine learning model of the controller; Using the generative machine learning model to generate a demand forecast; receiving the product into a loading area of ​​a product lane on a product shelf of the beverage warmer; transferring the items from the loading area through a first door to a heating area based on the demand forecast; heating the products in the heating region at a constant heating temperature for a constant heating time based on the demand forecast; transporting the product from the heating area through a second door to a service area after the heating time based on the demand forecast; and maintaining said product at a constant serving temperature in said service area.

13. detecting whether a second item is in the loading area of ​​the item lane; 13. The method of claim 12, further comprising: detecting when the item is removed from the service area; and in response, transferring the second item from the loading area through the first door to the heating area.

14. The method of claim 12 , wherein heating the commodity in the heating zone comprises heating the commodity with one or more heating elements in the heating zone.

15. The method of claim 14 , wherein the one or more heating elements include two heating elements positioned on opposite sides of the heating region.

16. The method of claim 14 , further comprising heating air in the service area to the service temperature with one or more heating elements in a service zone that includes the service area.

17. The method of claim 16 , further comprising circulating the heated air within the service area with one or more fans positioned within the service zone.

18. Detecting the absence of merchandise present within the service area; 13. The method of claim 12, further comprising displaying a time on a display adjacent to the service area, the time indicating the time remaining until heated goods are transported from the heating area through the second door to the service area.

19. detecting when the item is removed from the service area; 13. The method of claim 12, further comprising: determining that a current time is during a low demand period; and responsively determining based on the demand forecast not to transport a second item from the loading area through the first door to the heating area.

20. 13. The method of claim 12, wherein transferring the goods through the first door includes rotating the first door and transferring the goods through the second door includes rotating the second door.

Images