# US 12,008,328 B1 · Intelligent automated order-based customer dialogue system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,008,328 B1
- Document ID: US12008328B1
- Status: Granted
- Kind: B1
- Application number: 18/135,049
- Filed: 2023-04-14
- Granted: 2024-06-11
- Earliest claimed: 2021-01-22
- Assignees: Walgreen Co.
- Applicants: Walgreen Co.
- Inventors: Oliver Derza
- Web page: https://patentgrep.com/patent/US12008328B1

## CPC

- G06F 40/35: Discourse or dialogue representation
- G06F 40/30: Semantic analysis
- G06Q 10/08: Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q 10/107: Computer-aided management of electronic mailing [e-mailing]
- G06Q 30/016: After-sales
- G06Q 30/0207: Discounts or incentives, e.g. coupons or rebates
- G06Q 30/0281: {Customer communication at a business location, e.g. providing product or service information, consulting}
- G06Q 30/0631: {Recommending goods or services}
- G06Q 30/0633: {Managing shopping lists, e.g. compiling or processing purchase lists (shipping orders G06Q10/083; order filling G06Q10/087)}
- G06Q 30/0639: {Locating goods or services, e.g. based on physical position of the goods or services within a shopping facility}
- G10L 15/1815: {Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G10L 2015/225: {Feedback of the input speech}
- G10L 2015/227: {of the speaker; Human-factor methodology}
- G10L 2015/228: {of application context}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Based on a detection that a customer has arrived at an enterprise location to pick up a previously-placed order, an intelligent automated customer dialogue system generates an interface via which an intelligent customer dialogue application dialogues with the customer. The application generates and initially offers, at the interface using natural language, content which is contextual to one or more items of the order, e.g., by using a specially trained intelligent dialogue machine learning model. The application may intelligently respond to the customer's natural language responses and/or requests to refine, augment, or redirect subsequently-offered content and/or dialogue, e.g., by using the model. Offered content (e.g., product information, services, coupons, suggestions, recommendations, etc.) generally provides value-add to the customer as well as maintains customer engagement. The system may be implemented at least partially by using a chatbot upon curbside pick-up, for example, as well as through other electronic customer facing channels.

## Claims

### Claim 1

A method, comprising:
applying, by a computing system of an enterprise, a machine learning model to an order of a customer of the enterprise to thereby generate an output,
the machine learning model trained based on a machine analysis of historical data indicative of orders placed by customers, items included in the orders, and subsequent customer activities related to the orders to determine one or more subsequent customer activities that have respective higher degrees of association to individual ordered items, combinations of ordered items, and/or to orders as a whole than respective degrees of association of other subsequent customer activities, and
the output being indicative of a particular item, from items included in the order, that has a respective higher degree of association with at least one subsequent customer activity than respective degrees of association of at least one other item included in the items included in the order with the at least one subsequent customer activity;
posing, by the computing system on a user interface associated with the customer, an initial question pertaining to a context of the particular item of the order indicated by the output of the machine learning model, the context corresponding to providing additional information related to the particular item, and the additional information excluding any information corresponding to a fulfillment of the order; and
responsive to receiving a response to the initial question, at least one of:
(i) obtaining, by the computing system, information corresponding to the response and presenting the obtained information at the user interface;
(ii) determining, by the computing system and based on a content of the response, a second question and presenting the question at the user interface; or
(iii) determining, by the computing system, an action to be performed in conjunction with a computing device of the enterprise and initiating the action.

### Claim 2 (depends on 1)

The method of claim 1, further comprising determining the initial question pertaining to the context of the particular item of the order based on information that is included in an account of the customer and that is stored at the computing system of the enterprise.

### Claim 3 (depends on 1)

The method of claim 1, further comprising receiving an electronic signal indicative of a presence of the customer at the enterprise, and wherein at least one of the applying of the machine learning model or the posing of the initial question is responsive to the receiving of the electronic signal.

### Claim 4 (depends on 1)

The method of claim 1, wherein the user interface is included in a mobile device operated by the customer, a stationary computing device of the enterprise fixedly disposed at an enterprise location, or a mobile computing device of the enterprise disposed at the enterprise location.

### Claim 5 (depends on 4)

The method of claim 4, wherein the mobile computing device of the enterprise is a drone or a robot.

### Claim 6 (depends on 1)

The method of claim 1, wherein the presenting of the obtained information at the user interface comprises presenting a video, an article, or other information related to the particular item or to another item included in the order.

### Claim 7 (depends on 1)

The method of claim 1, wherein the response to the initial question is a natural language response, and the determining of the second question comprises determining a second question which redirects from, clarifies, or augments the natural language response.

### Claim 8 (depends on 1)

The method of claim 1, wherein the initiating of the action to be performed in conjunction with the computing device of the enterprise includes sending, to the computing device of the enterprise, at least one of an instruction corresponding to the order or information provided by the customer.

### Claim 9 (depends on 1)

The method of claim 1, wherein the initiating of the action to be performed in conjunction with the computing device of the enterprise includes establishing a communicative connection between the computing device of the enterprise and another computing device on which the user interface is included, thereby enabling the customer and an agent operating the computing device of the enterprise to communicate via the established communicative connection.

### Claim 10 (depends on 1)

The method of claim 1, wherein the output of the machine learning model is further indicative of the at least one subsequent customer activity, and the additional information is based on the at least one subsequent customer activity.

### Claim 11 (depends on 1)

The method of claim 1, further comprising:
updating the historical data to include data indicative of the order and a content presented on the user interface and corresponding to the order; and
re-training the machine learning model using the updated historical data.

### Claim 12 (depends on 1)

The method of claim 1, further comprising presenting a current status of the fulfillment of the order on the user interface, and dynamically updating the current status in accordance with the fulfillment of the order.

### Claim 13

A system of an enterprise, the system comprising:
one or more processors;
one or more memories storing an indication of an order placed by a customer of the enterprise;
a machine learning model stored on the one or more memories and trained based on a machine analysis of historical data indicative of orders placed by customers for pickup, items included in the orders, and subsequent customer activities related to the orders to determine one or more subsequent customer activities that have respective higher degrees of association to individual ordered items, combinations of ordered items, and/or to orders as a whole than respective degrees of association of other subsequent customer activities; and
an intelligent customer dialogue application stored on the one or more memories and executable by the one or more processors to:
apply the machine learning model to the order of the customer to thereby generate an output, the output being indicative of a particular item, from items included in the order, that has a respective higher degree of association with at least one subsequent customer activity than respective degrees of association of at least one other item included in the items included in the order with the at least one subsequent customer activity;
pose, on a user interface associated with the customer, an initial question pertaining to a context of the particular item of the order indicated by the output of the machine learning model, the context corresponding to providing additional information related to the particular item, and the additional information excluding any information corresponding to a fulfillment of the order; and
responsive to a reception of a response to the initial question, at least one of:
(i) obtain information corresponding to the response and present the obtained information at the user interface;
(ii) determine, based on a content of the response, a second question and present the question at the user interface; or
(iii) determine an action to be performed in conjunction with a computing device of the enterprise and initiate the action.

### Claim 14 (depends on 13)

The system of claim 13, wherein the intelligent customer dialogue application is further executable to determine the initial question based on the application of the machine learning model to the order.

### Claim 15 (depends on 13)

The system of claim 13, wherein the computing device of the enterprise is a first computing device operated by an agent of the enterprise, and the action includes an establishment of a communication channel between a second computing device on which the user interface is included and the first computing device, thereby enabling the customer and the agent to communicate via the established communication channel.

### Claim 16 (depends on 13)

The system of claim 13, wherein the computing device of the enterprise is operated by an agent of the enterprise, and the action includes a transmission, to the computing device of the enterprise, of at least one of: information provided by the customer, or an instruction for the agent and corresponding to the order.

### Claim 17 (depends on 13)

The system of claim 13, wherein the presentation of the obtained information includes a presentation of a video, article, or other information related to the particular item or another item included in the order.

### Claim 18 (depends on 13)

The system of claim 13, wherein the response to the initial question is a natural language response.

### Claim 19 (depends on 18)

The system of claim 18, wherein the natural language response is in at least one of a visual format or an auditory format.

### Claim 20 (depends on 18)

The system of claim 18, wherein the second question redirects, clarifies, or augments the natural language response.