# US 2021/0241330 A1 · Pricing Operation Using Artificial Intelligence for Dynamic Price Adjustment > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0241330 A1 - Document ID: US20210241330A1 - Status: Published application - Kind: A1 - Application number: 16/779,383 - Filed: 2020-01-31 - Published: 2021-08-05 - Earliest claimed: 2020-01-31 - Assignees: salesforce.com, inc. - Applicants: salesforce.com, inc. - Inventors: Parth Vijay Vaishnav; Mitchell Christensen - Web page: https://patentgrep.com/patent/US20210241330A1 ## CPC - G06Q 30/0283: Price estimation or determination - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - G06N 3/084: Backpropagation, e.g. using gradient descent - G06N 3/09: Supervised learning - G06Q 30/0206: {Price or cost determination based on market factors} - G06N 3/045: Combinations of networks - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Embodiments regard pricing operation using artificial intelligence for price adjustment. An embodiment of one or more mediums include instructions for receiving a request at a pricing platform for pricing of sales items in a sales transaction, including a first sales item; generating a price for the first sales item; and determining whether a dynamic price adjustment function is enabled for the first sales item, and, if so, performing the dynamic adjustment price function for the first sales item, including accessing a trained neural network trained for price adjustments based at least in part on training data including news data from one or more sources and data regarding pricing, receiving a dynamic price adjustment for the first sales item from the trained neural network, and applying the dynamic price adjustment to the generated price to produce an adjusted price for the first sales item. ## Claims ### Claim 1 One or more non-transitory computer-readable storage mediums having stored thereon executable computer program instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising: receiving a request at a pricing platform for pricing of one or more sales items in a sales transaction, including a first sales item; generating a price for the first sales item; and determining whether a dynamic price adjustment function is enabled for the first sales item, and, if so, performing the dynamic adjustment price function for the first sales item, including: accessing a trained neural network, wherein the neural network is trained for price adjustments based at least in part on training data including news data from one or more sources and data regarding pricing, receiving a dynamic price adjustment for the first sales item from the trained neural network, and applying the dynamic price adjustment to the generated price to produce an adjusted price for the first sales item. ### Claim 2 (depends on 1) The mediums of claim 1, wherein the instructions include instructions to perform operations comprising: obtaining or receiving current news data as input data for the trained neural network, the dynamic price adjustment being based at least in part on the current news data. ### Claim 3 (depends on 1) The mediums of claim 1, wherein the trained neural network is a part of the pricing platform. ### Claim 4 (depends on 1) The mediums of claim 1, wherein the trained neural network is a part of an external system, and wherein the instructions include instructions to perform operations comprising: providing a request to the external system to infer a price adjustment for the first sales item; and receiving the inferred price adjustment from the external system. ### Claim 5 (depends on 1) The mediums of claim 1, wherein the news data includes one or more of: financial news data streams; general news data streams; social media streams; and social media influencer streams. ### Claim 6 (depends on 1) The mediums of claim 1, wherein the sales transaction includes a plurality of sales items, and wherein the instructions include instructions to perform operations comprising: determining whether the dynamic price adjustment function is enabled for each sales item of the plurality of sales items, and, if so, performing the dynamic adjustment price function for the sales item. ### Claim 7 (depends on 6) The mediums of claim 6, wherein determining whether the dynamic price adjustment function is enabled for each sales item of the plurality of sales items includes accessing one or more settings for the dynamic price adjustment function and determining whether the dynamic price adjustment is enabled based on the one or more settings. ### Claim 8 (depends on 6) The mediums of claim 6, wherein the instructions include instructions to perform operations comprising: aggregating pricing for the plurality of sales items, including aggregating any prices that are modified by the dynamic price adjustment function. ### Claim 9 (depends on 1) The mediums of claim 1, wherein the dynamic price adjustment is any of a price increase, a price decrease, or application of a substitute price for the first sales item. ### Claim 10 A system comprising: one or more processors; a memory to store data; and a pricing service to server a plurality of clients, the pricing service including a price function and a dynamic price adjustment function, wherein the pricing service is to: receive a request for pricing of a plurality of sales items in a sales transaction, the plurality of sales items including a first sales item; generate a price for the first sales item; and determine whether the dynamic price adjustment function is enabled for the first sales item, and, if so, perform the dynamic adjustment price function for the first sales item, including: access a trained neural network, wherein the neural network is trained for price adjustments based at least in part on training data including news data from one or more sources and data regarding pricing, receive a dynamic price adjustment for the first sales item from the trained neural network, and apply the dynamic price adjustment to the generated price to produce an adjusted price for the first sales item. ### Claim 11 (depends on 10) The system of claim 10, wherein performing the dynamic price adjustment function includes the pricing service to: obtain or receive current news data as input data for the trained neural network, the dynamic price adjustment being based at least in part on the current news data. ### Claim 12 (depends on 10) The system of claim 10, wherein system includes the trained neural network. ### Claim 13 (depends on 10) The system of claim 10, wherein the trained neural network is a part of an external system, and wherein the pricing service is to: provide a request to the external system to infer a price adjustment for the first sales item; and receive the inferred price adjustment from the external system. ### Claim 14 (depends on 10) The system of claim 10, wherein the news data includes one or more of: financial news data streams; general news data streams; social media streams; and social media influencer streams. ### Claim 15 (depends on 10) The system of claim 10, wherein the pricing service is to: determine whether the dynamic price adjustment function is enabled for each sales item of the plurality of sales items, and, if so, perform the dynamic adjustment price function for the sales item. ### Claim 16 (depends on 15) The system of claim 15, further comprising one or more settings for the dynamic price function, and wherein determining whether the dynamic price adjustment function is enabled for each sales item of the plurality of sales items includes accessing the one or more settings for the dynamic price adjustment function and determining whether the dynamic price adjustment is enabled based on the one or more settings. ### Claim 17 A method comprising: receiving a request at a pricing platform for pricing of a plurality of sales items in a sales transaction; generating a price for each sales item of the plurality of sales items; and determining whether a dynamic price adjustment function is enabled for each sales item, and, if so, performing the dynamic adjustment price function for the sales item, including: accessing a trained neural network, wherein the neural network is trained for price adjustments based at least in part on training data including news data from one or more sources and data regarding pricing, receiving a dynamic price adjustment for the sales item from the trained neural network, and applying the dynamic price adjustment to the generated price to produce an adjusted price for the sales item. ### Claim 18 (depends on 17) The method of claim 17, further comprising: obtaining or receiving current news data as input data for the trained neural network, the dynamic price adjustment being based at least in part on the current news data. ### Claim 19 (depends on 17) The method of claim 17, further comprising receiving one or more settings for the dynamic price adjustment function, wherein determining whether the dynamic price adjustment function is enabled for each sales item of the plurality of sales items includes accessing the one or more settings for the dynamic price adjustment function and determining whether the dynamic price adjustment is enabled based on the one or more settings. ### Claim 20 (depends on 17) The method of claim 17, further comprising: obtaining news data and pricing data for neural network training; performing training of a untrained neural network, including applying the news data and pricing data to the untrained neural network, and training the neural network until a threshold accuracy is reached to generate the trained neural network.