SHOPIFY INC.

Systems and methods are disclosed for positioning of a device of interest within a merchant environment. In this regard, embodiments of a computer implemented method for positioning of a device of interest within a merchant environment are disclosed. In one embodiment, the computer implemented method comprises obtaining positions of a plurality of mobile merchant devices within a merchant environment, obtaining data indicative of a relative position of a device of interest relative to one or more of the plurality of mobile merchant devices, and computing a position of the device of interest within the merchant environment based on the data indicative of the relative position of the device of interest relative to the one or more of the plurality of mobile merchant devices and positions of the one or more of the plurality of mobile merchant devices.

Methods and systems for prompting a large language model (LLM) to process inputs from multiple user elements to generate a revised block of text are described. One or more text-editing instructions related to respective one or more selected text portions in a block of text are received. A prompt is generated for a LLM to generate a revised block of text, the prompt including at least a portion of an annotated block of text, the annotated block of text including each text-editing instruction inserted into the block of text relative to each respective selected text portion. The prompt is provided to the LLM and a revised block of text is received and outputted.

A method for categorizing a product, the method including receiving information for the product; inputting the information into a trained machine learning model for a taxonomy tree; receiving a plurality of arrays, each array representing a level in the taxonomy tree and consisting of probabilities for each category represented in the level that the product is categorized in that category; choosing, from a highest level tier array, a category having a highest probability, thereby designating a tier prediction; collecting, from a second level tier array, all children of the tier prediction; determining whether a highest probability from the children of the tier prediction exceeds a threshold, and if yes, choosing the category with the highest probably as a new tier prediction; and repeating the determining; when the threshold is not exceeded or if the tier prediction has no children, and selecting the tier prediction as a predicted category.

According to one aspect of the concepts and technologies disclosed herein, a cloud computing system can include a load adaptation architecture framework that performs operations for orchestrating and managing one or more services that may operate within at least one of layers 4 through 7 of the Open Systems Interconnection (“OSP”) communication model. The cloud computing system also can include a virtual resource layer. The virtual resource layer can include a virtual network function that provides, at least in part, a service. The cloud computing system also can include a hardware resource layer. The hardware resource layer can include a hardware resource that is controlled by a virtualization layer. The virtualization layer can cause the virtual network function to be instantiated on the hardware resource so that the virtual network function can be used to support the service.

Systems and methods are provided for the generation of augmented reality (AR) scenery for a physical item. The AR scenery allows a customer to interact with the physical item in the real-world, while also allowing the customer to view the physical item in a virtual setting that may be tailored to the customer and/or to the physical item. According to an embodiment, an AR scene is generated for a physical item. The AR scene includes computer-generated scenery and at least a portion of an image of the physical item, where the computer-generated scenery is based on information associated with the user and/or the physical item. The AR scene is then displayed on a device.

Methods and systems for indicating a resource usage parameter for prompting a large language model (LLM) are described. A user input is received, from an electronic device, for generating a prompt to a LLM. A prompt resource usage parameter is computed based on the user input. A trained resource prediction model is used to generate a predicted response resource usage parameter for a response from the LLM, based on the user input. A total resource usage parameter is computed, based on the prompt resource usage parameter and the predicted response resource usage parameter. A representation of the total resource usage parameter is communicated to the electronic device, to cause the electronic device to provide an output of the representation of the total resource usage parameter.

A computer-implemented method is provided. The computer-implemented method may include automatically aggregating a subset of reviews from a plurality of reviews into an input prompt, the subset of reviews selected based on relevancy values assigned to reviews in the plurality of reviews. The computer-implemented method may further include inputting the input prompt into a generative language model yielding a summary review of the subset of reviews generated by the generative language model by: inputting the input prompt into the generative language model yielding attribute data associated with the subset of reviews and generated by the generative language model; and inputting the attribute data into the generative language model yielding the summary review generated by the generative language model.

During computer operation, it is sometimes necessary for the computer to retrieve data by performing a query. There may be situations in which multiple queries may need to be executed. In some embodiments, when multiple individual queries need to be executed, instead of executing each individual query to obtain data requested by each individual query, a single query may be generated from the individual queries. The single query encompasses all the data requests in each individual query and may therefore be referred to as a “merged query”. The merged query is then executed, and the data returned is mapped to responses for the individual queries. Technical benefits may include the reduction or elimination of duplicate data fetching, e.g. fewer query operations/data fetches, while still fetching all data requested by all of the individual queries.

A generative machine-learning model may be used for data encryption/decryption. In one example, a model may be configured based on at least one configuration setting. The model at an encoder may be prompted. The model may generate an array of values, each corresponding to a possible next symbol. A code word representing the index of the array at which there is a value corresponding to the next symbol of the information may be selected as an encrypted version of the symbol. The model at the decoder may be configured like the model at the encoder. The model at the decoder may be prompted. The model may generate an array of values, each corresponding to a possible next symbol. A decrypted symbol corresponding to a value at an index of the array represented by the code word may be selected.

A computer system and computer-implemented method are described. The method may include obtaining user data and a set of defined queries; generating a set of answers to the set of defined queries, the generation including causing a model to create, based on the user data and the set of defined queries, the set of answers; using an embedding model to generate a vector based on the set of answers; and uploading, by a browser application, the vector to a server during a browsing session.