Patent Application
20240257045
This application relates generally to space allocation and, more particularly, to systems and methods for automatically generating an optimal planogram for a retailer store.
Shelf space is a scarce and precious resource for a retailer. Shelf space allocation may involve a distribution of appropriate amount of shelf space among different products, together with their locations. The profitability of a store is in part dependent on an optimal placement of products for purchase by customers. If a customer cannot find a product, or a product does not catch his or her eye, or if there is insufficient stock on the shelf to meet demand, then a sale may be lost. Due to the limited shelf space, planogram may be one of the most important aspects that are used to improve financial performance. A planogram may be a visual representation of placement, organization, layout, or location of products within a retail store.
Previous attempts at generating planograms have deficiencies. Merchants or their representatives need to manually paint layouts to create planograms using personal judgement based on their experience and expertise. In addition, they often need to repeatedly revise the layouts after seeing unsatisfactory planograms based on random trials and tests. Unfortunately, planograms developed in this way can be time consuming, unreliable, and impact the sales performance negatively.
The embodiments described herein are directed to systems and methods for automatically generating an optimal planogram for a retailer store.
In various embodiments, a system including a non-transitory memory configured to store instructions thereon and at least one processor is disclosed. The at least one processor is operatively coupled to the non-transitory memory and configured to read the instructions to: obtain current product location information regarding current products being displayed in a retailer store; obtain recommended assortment information regarding future products to be displayed in the retailer store; based on the recommended assortment information, determine a plurality of candidate layouts each of which corresponds to a two-dimensional arrangement of the future product categories to be displayed in the retailer store; for each of the plurality of candidate layouts, compute an objective function based on the current product location information, a set of parameters and at least one of: a minimum area ratio, a first unprotected rank, a combined propensity score, or a contiguity score; generate, from the plurality of candidate layouts, an optimal layout that optimizes the objective function; generate a planogram based on the optimal layout for the retailer store; and transmit the planogram to a computing device associated with the retailer store for placing at least some of the future products in the retailer store according to the planogram.
In various embodiments, a computer-implemented method is disclosed. The computer-implemented method includes: obtaining current product location information regarding current products being displayed in a retailer store; obtaining recommended assortment information regarding future products to be displayed in the retailer store; based on the recommended assortment information, determining a plurality of candidate layouts each of which corresponds to a two-dimensional arrangement of the future product categories to be displayed in the retailer store; for each of the plurality of candidate layouts, computing an objective function based on the current product location information, a set of parameters and at least one of: a minimum area ratio, a first unprotected rank, a combined propensity score, or a contiguity score; generating, from the plurality of candidate layouts, an optimal layout that optimizes the objective function; generating a planogram based on the optimal layout for the retailer store; and transmitting the planogram to a computing device associated with the retailer store for placing at least some of the future products in the retailer store according to the planogram.
In various embodiments, a non-transitory computer readable medium having instructions stored thereon is disclosed. The instructions, when executed by at least one processor, cause at least one device to perform operations including: obtaining current product location information regarding current products being displayed in a retailer store; obtaining recommended assortment information regarding future products to be displayed in the retailer store; based on the recommended assortment information, determining a plurality of candidate layouts each of which corresponds to a two-dimensional arrangement of the future product categories to be displayed in the retailer store; for each of the plurality of candidate layouts, computing an objective function based on the current product location information, a set of parameters and at least one of: a minimum area ratio, a first unprotected rank, a combined propensity score, or a contiguity score; generating, from the plurality of candidate layouts, an optimal layout that optimizes the objective function; generating a planogram based on the optimal layout for the retailer store; and transmitting the planogram to a computing device associated with the retailer store for placing at least some of the future products in the retailer store according to the planogram.
The features and advantages of the present invention will be more fully disclosed in, or rendered obvious by the following detailed description of the preferred embodiments, which are to be considered together with the accompanying drawings wherein like numbers refer to like parts and further wherein:
This description of the exemplary embodiments is intended to be read in connection with the accompanying drawings, which are to be considered part of the entire written description. Terms concerning data connections, coupling and the like, such as “connected” and “interconnected,” and/or “in signal communication with” refer to a relationship wherein systems or elements are electrically and/or wirelessly connected to one another either directly or indirectly through intervening systems, as well as both moveable or rigid attachments or relationships, unless expressly described otherwise. The term “operatively coupled” is such a coupling or connection that allows the pertinent structures to operate as intended by virtue of that relationship.
In the following, various embodiments are described with respect to the claimed systems as well as with respect to the claimed methods. Features, advantages or alternative embodiments herein can be assigned to the other claimed objects and vice versa. In other words, claims for the systems can be improved with features described or claimed in the context of the methods. In this case, the functional features of the method are embodied by objective units of the systems.
A planogram describes where product items are located/placed on shelves or other displays within a retail store. A planogram can also include information, such as, the number of each type of item on each shelf/display, schematics, visual representations of items in the store, diagram/model indicating assigned location(s) of items on shelves/displays, and/or store layout. A common goal for planogram generation is to maximize total profits and/or customer satisfaction for the store.
One critical step for planogram generation is to determine an optimal layout of product groups in a given two-dimensional space. For example, a rectangle, representing a space set aside on fixtures in a store, can be divided into multiple unit cells (e.g. multiple small rectangles) arranged contiguously to cover the entire rectangle without any gap. Based on some previously determined categories of products, a code (e.g. a color) representing a corresponding product category can be assigned to each unit cell to indicate that a location represented by the unit cell will be used to place the corresponding product category in the retailer store. After each unit cell is assigned a code (or determined not to store anything), a layout is determined for allocating space to the previously determined product categories. This process may be called layout paint, with a goal to find or paint an optimal layout in consideration of different concerns.
The present teaching discloses embodiments to automatically generate an optimal layout based on novel mathematical formulations incorporating all business concerns. For example, an optimal layout would indicate a space allocation that ensures: (1) each product category gets an appropriate amount of space; (2) all the highest priority (top ranked) items fit in the layout simultaneously; (3) changes relative to the existing layout are minimal; and (4) each coded portion (a layout portion including all unit cells having a same code or color) is as “blocky” as possible.
In some embodiments, with mathematical functions or scores defined for the above concerns, an integer programming, e.g. a mixed integer linear programming (MILP), is utilized to find guaranteed optimal solutions to the paint problem. For example, a concept of minimum area ratio is mathematically defined to ensure each product category gets an appropriate amount of space; and a concept of first unprotected rank is mathematically defined to ensure all the top ranked product items fit in the layout simultaneously. In addition, the system enforces minimal layout contiguity through block adjacency, and uses image processing to quantify a fuzzy concept of a deviation relative to the existing layout. In some embodiments, the MILP formulation simplifies the problem of modular flow allocation to one of block assignments. The optimal layout solution can be found in minutes or even seconds, enabling fast iteration and/or update if needed. A planogram may then be generated based on the optimal layout to indicate the areas allocated to each group of products on a set of two-dimensional fixtures.
Furthermore, in the following, various embodiments are described with respect to methods and systems for automatic planogram generation and optimization. In some embodiments, based on recommended assortment information regarding future products to be displayed in a retailer store, a plurality of candidate layouts are determined, where each candidate layout corresponds to a two-dimensional arrangement of the future product categories. For each candidate layout, an objective function is computed based on current product location information, a set of parameters and at least one of: a minimum area ratio, a first unprotected rank, a combined propensity score, or a contiguity score. From the plurality of candidate layouts, an optimal layout is generated to optimize the objective function. In some embodiments, an optimal layout that optimizes the objective function can be directly generated without generating the candidate layouts first. A planogram may be generated based on the optimal layout for the retailer store, and transmitted to a computing device associated with the retailer store for placing at least some of the future products in the retailer store according to the planogram.
Turning to the drawings,
In some examples, each of the planogram computing device 102 and processing device(s) 120 can be a computer, a workstation, a laptop, a server such as a cloud-based server, or any other suitable device. In some examples, each of the processing devices 120 is a server that includes one or more processing units, such as one or more graphical processing units (GPUs), one or more central processing units (CPUs), and/or one or more processing cores. Each processing device 120 may, in some examples, execute one or more virtual machines. In some examples, processing resources (e.g., capabilities) of one or more processing devices 120 are offered as a cloud-based service (e.g., cloud computing). For example, the cloud-based engine 121 may offer computing and storage resources of the one or more processing devices 120 to the planogram computing device 102.
In some examples, each of the multiple customer computing devices 110, 112, 114 can be a cellular phone, a smart phone, a tablet, a personal assistant device, a voice assistant device, a digital assistant, a laptop, a computer, or any other suitable device. In some examples, the web server 104 hosts one or more retailer websites. In some examples, the planogram computing device 102, the processing devices 120, and/or the web server 104 are operated by a retailer, and the multiple customer computing devices 110, 112, 114 are operated by customers of the retailer. In some examples, the processing devices 120 are operated by a third party (e.g., a cloud-computing provider).
The workstation(s) 106 are operably coupled to the communication network 118 via a router (or switch) 108. The workstation(s) 106 and/or the router 108 may be located at a store 109 of a retailer, for example. The workstation(s) 106 can communicate with the planogram computing device 102 over the communication network 118. The workstation(s) 106 may send data to, and receive data from, the planogram computing device 102. For example, the workstation(s) 106 may transmit data identifying items purchased by a customer at the store 109 to the planogram computing device 102.
Although
The communication network 118 can be a WiFi® network, a cellular network such as a 3GPP® network, a Bluetooth® network, a satellite network, a wireless local area network (LAN), a network utilizing radio-frequency (RF) communication protocols, a Near Field Communication (NFC) network, a wireless Metropolitan Area Network (MAN) connecting multiple wireless LANs, a wide area network (WAN), or any other suitable network. The communication network 118 can provide access to, for example, the Internet.
Each of the first customer computing device 110, the second customer computing device 112, and the Nth customer computing device 114 may communicate with the web server 104 over the communication network 118. For example, each of the multiple computing devices 110, 112, 114 may be operable to view, access, and interact with a website, such as a retailer's website, hosted by the web server 104. The web server 104 may transmit user session data related to a customer's activity (e.g., interactions) on the website. For example, a customer may operate one of customer computing devices 110, 112, 114 to initiate a web browser that is directed to the website hosted by the web server 104. The customer may, via the web browser, view item advertisements for items displayed on the website, and may click on item advertisements, for example. The website may capture these activities as user session data, and transmit the user session data to the planogram computing device 102 over the communication network 118. The website may also allow the operator to add one or more of the items to an online shopping cart, and allow the customer to perform a “checkout” of the shopping cart to purchase the items. In some examples, the web server 104 transmits purchase data identifying items the customer has purchased from the website to the planogram computing device 102.
In some examples, the store 109 may transmit a planogram request to the planogram computing device 102. The planogram request may be sent standalone or together with store related data of the store 109. In some examples, the planogram request may carry or indicate current product location information regarding current products being displayed in the store 109.
In some examples, the planogram computing device 102 may execute one or more models (e.g., programs or algorithms), such as a machine learning model, deep learning model, statistical model, etc., to determine an optimal layout for space allocation to different products to be displayed in the store 109. The planogram computing device 102 may generate and transmit a planogram based on the optimal layout to the store 109 over the communication network 118, and the store 109 may provide or update a display of products according to the planogram.
In some examples, the planogram computing device 102 may receive recommended assortment data regarding future products to be displayed in the store 109 from the web server 104. For example, the web server 104 may generate the recommended assortment data based on an item recommendation model and/or online activity data of different users, e.g. user session data or online purchase data, associated with the store 109. For example, if many orders placed online include a same product to be picked up from the store 109, the same product may be included in the recommended assortment for next product layout update at the store 109.
The planogram computing device 102 may determine a plurality of candidate layouts each of which corresponds to a two-dimensional arrangement of the future product categories to be displayed in the store 109, e.g. based on the recommended assortment information. For each of the plurality of candidate layouts, the planogram computing device 102 may compute an objective function based on the current product location information, a set of parameters and at least one of: a minimum area ratio, a first unprotected rank, a combined propensity score, or a contiguity score. In some embodiments, an optimal layout is generated, from the plurality of candidate layouts, by the planogram computing device 102 using one or more models stored in the database 116 to optimize the objective function. The planogram computing device 102 may then generate and transmit a planogram based on the optimal layout to the store 109, which may generate or update a product display in one or more aisles of the store 109 according to the planogram.
The planogram computing device 102 is further operable to communicate with the database 116 over the communication network 118. For example, the planogram computing device 102 can store data to, and read data from, the database 116. The database 116 can be a remote storage device, such as a cloud-based server, a disk (e.g., a hard disk), a memory device on another application server, a networked computer, or any other suitable remote storage. Although shown remote to the planogram computing device 102, in some examples, the database 116 can be a local storage device, such as a hard drive, a non-volatile memory, or a USB stick. The planogram computing device 102 may store purchase data received from the web server 104 in the database 116. The planogram computing device 102 may receive store related data from different stores 109 and store them as store data in the database 116. The planogram computing device 102 may also receive from the web server 104 user session data identifying events associated with browsing sessions, and may store the user session data in the database 116.
In some examples, the planogram computing device 102 generates and/or updates different models for automatic planogram generation and optimization. The models, when executed by the planogram computing device 102, allow the planogram computing device 102 to determine optimal product layouts and generate planograms for each store or for each concerned space (e.g. one or more shelves, one or more aisles) for product arrangement and allocation in a store.
In some examples, the planogram computing device 102 assigns the models (or parts thereof) for execution to one or more processing devices 120. For example, each model may be assigned to a virtual machine hosted by a processing device 120. The virtual machine may cause the models or parts thereof to execute on one or more processing units such as GPUs. In some examples, the virtual machines assign each model (or part thereof) among a plurality of processing units. Based on the output of the models, the planogram computing device 102 may generate a planogram.
As shown in
The processors 201 can include one or more distinct processors, each having one or more cores. Each of the distinct processors can have the same or different structure. The processors 201 can include one or more central processing units (CPUs), one or more graphics processing units (GPUs), application specific integrated circuits (ASICs), digital signal processors (DSPs), and the like.
The instruction memory 207 can store instructions that can be accessed (e.g., read) and executed by the processors 201. For example, the instruction memory 207 can be a non-transitory, computer-readable storage medium such as a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory, a removable disk, CD-ROM, any non-volatile memory, or any other suitable memory. The processors 201 can be configured to perform a certain function or operation by executing code, stored on the instruction memory 207, embodying the function or operation. For example, the processors 201 can be configured to execute code stored in the instruction memory 207 to perform one or more of any function, method, or operation disclosed herein.
Additionally, the processors 201 can store data to, and read data from, the working memory 202. For example, the processors 201 can store a working set of instructions to the working memory 202, such as instructions loaded from the instruction memory 207. The processors 201 can also use the working memory 202 to store dynamic data created during the operation of the planogram computing device 102. The working memory 202 can be a random access memory (RAM) such as a static random access memory (SRAM) or dynamic random access memory (DRAM), or any other suitable memory.
The input-output devices 203 can include any suitable device that allows for data input or output. For example, the input-output devices 203 can include one or more of a keyboard, a touchpad, a mouse, a stylus, a touchscreen, a physical button, a speaker, a microphone, or any other suitable input or output device.
The communication port(s) 209 can include, for example, a serial port such as a universal asynchronous receiver/transmitter (UART) connection, a Universal Serial Bus (USB) connection, or any other suitable communication port or connection. In some examples, the communication port(s) 209 allows for the programming of executable instructions in the instruction memory 207. In some examples, the communication port(s) 209 allow for the transfer (e.g., uploading or downloading) of data, such as machine learning model training data.
The display 206 can be any suitable display, and may display the user interface 205. The user interfaces 205 can enable user interaction with the planogram computing device 102. For example, the user interface 205 can be a user interface for an application of a retailer that allows a customer to view and interact with a retailer's website. In some examples, a user can interact with the user interface 205 by engaging the input-output devices 203. In some examples, the display 206 can be a touchscreen, where the user interface 205 is displayed on the touchscreen.
The transceiver 204 allows for communication with a network, such as the communication network 118 of
The optional GPS device 211 may be communicatively coupled to the GPS and operable to receive position data from the GPS. For example, the GPS device 211 may receive position data identifying a latitude, and longitude, from a satellite of the GPS. Based on the position data, the planogram computing device 102 may determine a local geographical area (e.g., town, city, state, etc.) of its position. Based on the geographical area, the planogram computing device 102 may determine relevant trend data (e.g., trend data identifying events in the geographical area) and cluster different stores into different regions.
In some examples, the user session data 350 may include item engagement data, search query data, and user ID (e.g., a customer ID, retailer website login ID, a cookie ID, etc.). The item engagement data may include one or more of a session ID (i.e., a website browsing session identifier), item clicks identifying items which a user clicked (e.g., images of items for purchase, keywords to filter reviews for an item), items added-to-cart identifying items added to the user's online shopping cart, advertisements viewed identifying advertisements the user viewed during the browsing session, and advertisements clicked identifying advertisements the user clicked on. The search query data may identify one or more searches conducted by a user during a browsing session (e.g., a current browsing session).
The planogram computing device 102 may also receive online purchase data 304 from the web server 104, which identifies and characterizes one or more online purchases, such as purchases made by the user and other users via a retailer's website hosted by the web server 104. The planogram computing device 102 may also receive store related data 302 from the store 109, which identifies and characterizes one or more in-store purchases. In some embodiments, the store related data 302 may also indicate other information about the store 109.
The planogram computing device 102 may parse the store related data 302 and the online purchase data 304 to generate store data 330 and user transaction data 340, respectively. In this example, the store data 330 may include, for each store, one or more of: a store ID 332 of the store, a store location 333 of the store, a space allocation data 334 including current product location information in the store, a current product data 336 identifying and charactering current products being displayed in the store. In this example, the user transaction data 340 may include, for each purchase, one or more of: an order number 342 identifying a purchase order, item IDs 343 identifying one or more items purchased in the purchase order, item brands 344 identifying a brand for each item purchased, item prices 346 identifying the price of each item purchased, item categories 348 identifying a product type (e.g., category) of each item purchased, a purchase date 345 identifying the purchase date of the purchase order, a user ID 349 for the user making the corresponding purchase, and store ID 332 for the pickup store or shipping-from store associated with the corresponding online purchase.
In some embodiments, the database 116 may further store catalog data, which may identify one or more attributes of a plurality of items, such as a portion of or all items a retailer carries. The catalog data may identify, for each of the plurality of items, an item ID (e.g., an SKU number), item brand, item type (e.g., grocery item such as milk, clothing item), item description (e.g., a description of the product including product features, such as ingredients, benefits, use or consumption instructions, or any other suitable description), and item options (e.g., item colors, sizes, flavors, etc.).
The database 116 may also store product layout data 320 identifying and characterizing product layouts for stores. In this example, the product layout data 320 may include, for each store and in response to each planogram request, one or more of: future product data 322 identifying future products to be displayed in the store corresponding to the planogram request; candidate layout data 324 identifying candidate product layouts each corresponding to a two-dimensional arrangement of the future product categories to be displayed in the store; and optimal layout data 326 identifying an optimal layout that can maximize or minimize an objective function based on one or more of the following factors for layout optimization: a maximization of a minimum area ratio, a maximization of the first unprotected rank, a maximization of a combined propensity score, and a maximization of a contiguity score. In some embodiments, the planogram computing device 102 may receive recommended assortment data 308 from the web server 104, and extract the future product data 322 from the received recommended assortment data 308 to store in the database 116. In other embodiments, the planogram computing device 102 may receive the future product data 322 together with a planogram request 310 from the store 109 to store in the database 116.
In some embodiments, the database 116 may also store product classification rules 370 and coding rules 380. In some embodiments, the future products to be displayed in a store are classified into a plurality of product groups, based on one or more of the product classification rules 370. For example, the future products may be classified based on at least one of: product type, product brand, product price, and/or product packet size. In some embodiments, each candidate layout may include a plurality of coded layout portions each being coded based on one or more of the coding rules 380. For example, each of the plurality of coded layout portions is coded in the candidate layout based on at least one of: color, grayscale, filled pattern, filled texture, filled gradient, and/or filled picture.
The database 116 may also store layout optimization model data 390 identifying and characterizing one or more layout optimization models and related data. For example, the layout optimization model data 390 may include an area ratio model 392, a ranking model 394, a propensity model 396, a contiguity model 398, and an integer programming model 399. The models 392-398 can be used to compute functions and/or scores for each candidate layout. The area ratio model 392 may be used to generate a minimum area ratio representing a level of equitability of space allocation for the plurality of product groups, while the ranking model 394 may be used to generate a first unprotected rank representing a level of protection of top products in each of the plurality of product groups. The propensity model 396 may be used to generate a combined propensity score representing a deviation of the candidate layout from a current layout of current products. The contiguity model 398 may be used to generate a contiguity score representing a level of blockiness of the plurality of coded layout portions in the candidate layout. Based on these functions and/or scores, the integer programming model 399 can be used to compute an objective function and optimize the objective function to determine an optimal layout from the candidate layouts.
In some examples, the planogram computing device 102 receives a planogram request 310 from the store 109. The planogram request 310 may be associated with a request to allocate area from a concerned space (e.g. one or more aisles) in the store 109 to predetermined product groups of future products to be displayed in the store 109. For example, the future products are pre-classified based on their brands into different product groups each associated with a different brand, and the planogram request 310 is to seek an optimal layout to allocate each unit cell, in a two-dimensional space corresponding to an aisle in the store 109, to a different brand. In response, the planogram computing device 102 may first obtain current product location information regarding current products being displayed in the store 109, and obtain recommended assortment information regarding the future products to be displayed in the store 109, from the store 109, the web server 104 and/or the database 116. The planogram computing device 102 may then generate multiple candidate layouts based on the recommended assortment information. The planogram computing device 102 can compute, for each candidate layout, an objective function based on the current product location information, a set of parameters and at least one of: a minimum area ratio, a first unprotected rank, a combined propensity score, or a contiguity score, based on respective models in the layout optimization model data 390. The optimal layout is generated by the planogram computing device 102 to optimize (e.g. minimize or maximize) the objective function among all of the candidate layouts based on at least one of: a maximization of the minimum area ratio, a maximization of the first unprotected rank, a maximization of the combined propensity score, or a maximization of the contiguity score. In some embodiments, each candidate layout is determined subject to at least the following two conditions: (1) each unit cell is assigned to one and only one of the plurality of coded layout portions in the candidate layout; and (2) each unit cell is assigned to a same coded layout portion as at least two other unit cells contiguous to the unit cell in the candidate layout.
In some embodiments, the planogram computing device 102 may assign one or more of the above described operations to a different processing unit or virtual machine hosted by one or more processing devices 120. Further, the planogram computing device 102 may obtain the outputs of the these assigned operations from the processing units, and generate the planogram 312 the based on the outputs. The planogram computing device 102 may transmit the planogram 312 to the store 109 in response to the planogram request 310.
In some embodiments, the pre-determined two-dimensional space may be empty, and a request is sent to generate a planogram for placing products in the pre-determined two-dimensional space. In other embodiments, the pre-determined two-dimensional space may have some products displayed therein, and a request is sent to generate a planogram to update the products and/or their space allocation in the pre-determined two-dimensional space.
Based on the planogram request, both current product location information and recommended assortment information are obtained. The current product location information may be used to determine a current layout of current products being displayed in the retailer store. The recommended assortment information may indicate future products to be displayed in the retailer store according to a planogram to be generated in response to the planogram request.
A classification may be performed, before or after the planogram request is received, to divide the future products into different groups, based on some product attributes. For example, the products are classified based on at least one of: product type, product brand, product price, or product packet size. In the example shown in
Each product group may be assigned a respective code. That is, different product groups are represented by different codes in a layout. The different codes may be generated based on e.g. color, grayscale, filled pattern, filled texture, filled gradient, or filled picture. In the example shown in
As shown in
In some embodiments, the layout 400 is a current layout that needs to be updated or optimized. In some embodiments, the layout 400 is one of a plurality of candidate layouts. An optimal layout may be generated or selected from the plurality of candidate layouts based on one or more models. An optimal planogram may then be generated based on the optimal layout, for the store to place the future products accordingly.
In some embodiments, there are different concerns when generating the optimal layout. In some examples, the spaces allocated to different coded layout portions in the optimal layout should not overlap. The layout 400 addresses and satisfies this concern because there is no overlap between any two of the coded layout portions in the layout 400.
In some examples, the space allocated to each coded layout portion in the optimal layout must be “blocky,” with no isolated cells, where exclaves are discouraged but not prohibited. In the layout 400, there is no single isolated cell, but there is an exclave 434 for the coded layout portion 430 corresponding to the product group “Multivitamins.” As shown in
In some examples, an optimal layout to update a current layout should include coded layout portions being in roughly the same locations as they are in the current layout. A slight movement of the border between two coded layout portions is not as problematic as larger changes. Sometimes, a large change may be required, e.g., when new coded layout portions are introduced to place new product groups. Mathematical explanations, e.g. a combined propensity score, can be used to represent a deviation of the optimal layout (or any candidate layout) from the current layout of current products.
In some examples, an optimal layout should allocate space based on product dimensions. For example, the amount of space allocated to each coded layout portion in the optimal layout should be roughly proportional to the space taken up by all products in the coded layout portion, to address fairness or equitability of space allocation for different products having different dimensions. In addition, an optimal layout should also ensure that the best products in each coded layout portion will have enough space to be displayed in the store. The best products are the top ranked products in each coded layout portion, where the ranking can be predetermined by business experts and/or based on a ranking algorithm. Mathematical explanations can be used to measure and ensure these concerns. For example, a minimum area ratio can be used to represent a level of equitability of space allocation for the plurality of product groups. For example, a first unprotected rank can be used to represent a level of protection of top products in each product group corresponding to each coded layout portion.
Based on the planogram request, current product location information and recommended assortment information are obtained at operation 510. The current product location information indicates locations of current products being displayed in the retailer store. The current product location information may be obtained from parsing the planogram request or from a database, e.g. the database 116 in
The process 500 may then go to two different branches in parallel. In one branch, the process 500 goes to operation 520 to determine a plurality of candidate layouts based on the recommended assortment information. Each of the plurality of candidate layouts corresponds to a two-dimensional arrangement of the future product categories to be displayed in the retailer store. The branch then goes to a module 530 for optimal layout generation. In some embodiments, each candidate layout of the plurality of candidate layouts comprises a same number of unit cells arranged in a same manner, e.g. as shown in
In another branch, the process 500 goes to operation 512 to determine a current layout of current products being displayed in the retailer store. In some examples, the current layout may be determined based on the current product location information. In some examples, the current layout may be directly received together with the planogram request. In some examples, the current layout may be retrieved from a database e.g. the database 116 in
To avoid being so strict on the propensity scores, an image smoothing may be performed on the original placement 610 to obtain a smoothed matrix form 620 as shown in
Referring back to
As shown in
Referring back to
In some embodiments, N may be initiated with a number different from one. For example, N may be initiated to be 3 or 4, or a number close or equal to the first unprotected rank of another candidate layout, or a number close or equal to an average of all known or computed first unprotected ranks of other candidate layouts. If an initial N value already enables the first area to be smaller than the second area for any one of the plurality of coded layout portions in a candidate layout, the N value is decreased by one to repeat the above steps of (a) and (b), until a second value of N is found to enable the first area to be not smaller than the second area for all of the plurality of coded layout portions in the candidate layout. In that case, the first unprotected rank is determined for the candidate layout based on the second value of N plus one.
In some embodiments, N value can be changed by two or more for each iteration, and the change step may become smaller after the N value is found to be too small or too big. For example, N value can be initialized to be 3, and increased and decreased by 2 depending on a comparison result between the first area and the second area. If N=3 enables the first area to be not smaller than the second area for all of the plurality of coded layout portions in the candidate layout, N is increased by 2 to be 5. If N=5 enables the first area to be smaller than the second area for any of the plurality of coded layout portions in the candidate layout, N is decreased by 1 to be 4. If N=4 enables the first area to be smaller than the second area for any of the plurality of coded layout portions in the candidate layout, N=4 is the first unprotected rank for the candidate layout. Otherwise, if N=4 enables the first area to be not smaller than the second area for all of the plurality of coded layout portions in the candidate layout, N=5 is the first unprotected rank for the candidate layout.
The determined first unprotected rank may be sent to operation 536 to compute and optimize the objective function. In some embodiments, the method for computing the first unprotected rank can be stored as a first unprotected rank model in the database 116, where the first unprotected rank model can be retrieved or updated from time to time.
As shown in
Referring back to
At operation 534, a contiguity score is computed to represent a level of blockiness of the plurality of coded layout portions in each candidate layout. In some embodiments, a total quantity of contiguity cell pairs in each candidate layout is computed, where each contiguity cell pair includes two unit cells that are contiguous to each other and belonging to a same coded layout portion in the candidate layout. Then the contiguity score for the candidate layout can be computed based on the total quantity. In some embodiments, the method for computing the contiguity score can be stored as the contiguity model 398 in the database 116, where the contiguity model 398 can be retrieved or updated from time to time. The contiguity score may also be sent to operation 536 to compute and optimize the objective function.
At operation 536, an objective function is computed for each candidate layout based on a set of parameters and at least one of: the minimum area ratio computed from operation 531, the first unprotected rank computed from operation 532, the combined propensity score computed from operation 533, and the contiguity score computed from operation 534.
In some embodiments, the set of parameters comprises: a first weight associated with the minimum area ratio, a second weight associated with the first unprotected rank, a third weight associated with the combined propensity score, and a fourth weight associated with the contiguity score. Then the objective function can be computed based on a weighted sum of the minimum area ratio, the first unprotected rank, the combined propensity score and the contiguity score, with their respective associated weights. In some embodiments, the weights can be predetermined or pre-trained and stored in a database, e.g. the database 116 in
The objective function is optimized at operation 536 to generate an optimal layout 540 from the plurality of candidate layouts. In some embodiments, the optimal layout 540 can minimize or maximize the objective function among all of the plurality of candidate layouts based on at least one of: a maximization of the minimum area ratio, a maximization of the first unprotected rank, a maximization of the combined propensity score, or a maximization of the contiguity score. The maximization of the minimum area ratio ensures to allocate space equitably across all product groups. The maximization of the first unprotected rank ensures to protect top ranked products in each product group as much as possible. The maximization of the combined propensity score minimizes a deviation of the concerned layout from the current layout. The maximization of the contiguity score maximizes a level of blockiness of the plurality of coded layout portions in the concerned layout. While the optimal layout 540 optimizes the objective function, it takes into consideration the above four goals together based on predetermined weights.
In some embodiments, the method for computing and optimizing the objective function can be stored as the integer programming model 399 in the database 116, where the integer programming model 399 can be retrieved or updated from time to time. For example, the integer programming model 399 may be based on a mixed integer linear programming (MILP) to be performed automatically at the module 530. The optimal layout 540 may be sent to operation 550 to generate a planogram based on the optimal layout 540, and transmit the planogram to a computing device associated with the retailer store for placing at least some of the future products in the retailer store according to the planogram, in response to the planogram request. In some embodiments, the operation 550 also includes some post-processing of the optimal layout 540, e.g. preparing the optimal layout 540 in proper format, performing automated validation checks for the optimal layout 540, and publishing the optimal layout 540 in the proper format, e.g. a generated planogram.
In some embodiments, the optimal layout 540 is determined subject to at least the following two conditions: (A) each unit cell is assigned to one and only one of the plurality of coded layout portions in the candidate layout, and (B) each unit cell is assigned to a same coded layout portion as at least two other unit cells contiguous to the unit cell in the candidate layout. In some embodiments, each of the plurality of candidate layouts is generated to meet the above two conditions at the first place.
In some embodiments, other constraints or conditions may be applied, and/or other objective functions may be computed when applying a MILP model for optimal layout generation and optimization. In some embodiments, additional concerns for generating an optimal layout include a signed contract with some vendors, which may require their products to be allocated to a specific location or portion in the final layout.
At operation 1010, an optimal layout is generated from the plurality of candidate layouts to optimize the objective function. A planogram is then generated at operation 1012 based on the optimal layout for the retailer store. The planogram may be transmitted at operation 1014 to a computing device associated with the retailer store for placing at least some of the future products in the retailer store according to the planogram.
Although the methods described above are with reference to the illustrated flowcharts, it will be appreciated that many other ways of performing the acts associated with the methods can be used. For example, the order of some operations may be changed, and some of the operations described may be optional.
In addition, the methods and system described herein can be at least partially embodied in the form of computer-implemented processes and apparatus for practicing those processes. The disclosed methods may also be at least partially embodied in the form of tangible, non-transitory machine-readable storage media encoded with computer program code. For example, the steps of the methods can be embodied in hardware, in executable instructions executed by a processor (e.g., software), or a combination of the two. The media may include, for example, RAMs, ROMs, CD-ROMs, DVD-ROMs, BD-ROMs, hard disk drives, flash memories, or any other non-transitory machine-readable storage medium. When the computer program code is loaded into and executed by a computer, the computer becomes an apparatus for practicing the method. The methods may also be at least partially embodied in the form of a computer into which computer program code is loaded or executed, such that, the computer becomes a special purpose computer for practicing the methods. When implemented on a general-purpose processor, the computer program code segments configure the processor to create specific logic circuits. The methods may alternatively be at least partially embodied in application specific integrated circuits for performing the methods.
Each functional component described herein can be implemented in computer hardware, in program code, and/or in one or more computing systems executing such program code as is known in the art. As discussed above with respect to
The foregoing is provided for purposes of illustrating, explaining, and describing embodiments of these disclosures. Modifications and adaptations to these embodiments will be apparent to those skilled in the art and may be made without departing from the scope or spirit of these disclosures. Although the subject matter has been described in terms of exemplary embodiments, it is not limited thereto. Rather, the appended claims should be construed broadly, to include other variants and embodiments, which can be made by those skilled in the art.
