US-12619447-B2 - Message personalization for an electromechanical device

US12619447B2US 12619447 B2US12619447 B2US 12619447B2US-12619447-B2

Abstract

Message personalization for an electromechanical device is described. Data is received, the system information data associated with a change in state of one or more components of an electromechanical device. A message is generated by inputting the system information data as a prompt to generative artificial intelligence representative of one or more characteristics of the electromechanical device and trained to analyze the system information data. The message indicates feedback responsive to the change in state of the one or more components. The message is output, where one or more language characteristics of the message are associated with the one or more characteristics of the electromechanical device.

Inventors

Andrew CHALKLEY
Paul Telis Stathacopoulos

Assignees

EBAY INC.

Dates

Publication Date: 20260505
Application Date: 20231213

Claims (20)

1 . A computer-implemented method, comprising: receiving system information data associated with a change in state of one or more components of an electromechanical device; generating a message indicating feedback responsive to the change in state of the one or more components, the generating performed by inputting the system information data as a prompt to generative artificial intelligence representative of a plurality of characteristics of the electromechanical device, the generative artificial intelligence trained to analyze the system information data and to output the message that has one or more language characteristics based on the plurality of characteristics of the electromechanical device, wherein the one or more language characteristics are unique to the electromechanical device; and outputting the message indicating the feedback.
2 . The computer-implemented method of claim 1 , further comprising: transmitting, for display at a user interface, a request for the plurality of characteristics; and in response to the request, receiving user input indicating the plurality of characteristics.
3 . The computer-implemented method of claim 1 , further comprising determining the plurality of characteristics based on using object recognition techniques to analyze an image input associated with the electromechanical device.
4 . The computer-implemented method of claim 3 , wherein the image input indicates an identifier of the electromechanical device, the computer-implemented method further comprising accessing a database to obtain the plurality of characteristics, the database storing associations between the identifier of the electromechanical device and the plurality of characteristics of the electromechanical device.
5 . The computer-implemented method of claim 1 , further comprising: obtaining purchase history data associated with at least one component of the electromechanical device; and determining the plurality of characteristics based on the purchase history data.
6 . The computer-implemented method of claim 1 , wherein outputting the message comprises displaying, at a user interface, a text representation of the message.
7 . The computer-implemented method of claim 1 , wherein outputting the message comprises outputting, by an audio component, an audio representation of the message.
8 . The computer-implemented method of claim 1 , wherein the system information data includes a diagnostic code corresponding to the change in state of the one or more components of the electromechanical device.
9 . The computer-implemented method of claim 1 , wherein the system information data includes sensor data corresponding to the change in state of the one or more components of the electromechanical device.
10 . The computer-implemented method of claim 1 , wherein the message includes instructions to perform a maintenance procedure in response to the change in the one or more components of the electromechanical device.
11 . The computer-implemented method of claim 1 , wherein the message includes instructions to purchase at least one replacement component in response to the change in the one or more components of the electromechanical device.
12 . The computer-implemented method of claim 1 , further comprising: receiving, as output from the generative artificial intelligence, an indication of a modification to one or more system settings of the electromechanical device based on the change in the one or more components of the electromechanical device; and updating the one or more system settings based on the modification to the one or more system settings, wherein the message indicates the one or more system settings are updated.
13 . The computer-implemented method of claim 1 , further comprising: obtaining training data including the plurality of characteristics of the electromechanical device and instructions corresponding to operation of the electromechanical device; and updating one or more large language models using the training data, the generative artificial intelligence including the one or more large language models.
14 . The computer-implemented method of claim 1 , wherein the plurality of characteristics of the electromechanical device include at least one of a date of manufacture of the electromechanical device, a geographic location associated with the electromechanical device, a type of the electromechanical device, purchase history of components of the electromechanical device, or one or more physical characteristics of the electromechanical device, and wherein the one or more language characteristics are unique to the electromechanical device based on the generative artificial intelligence including a personalized messaging model trained to output the message that reflects the plurality of characteristics of the electromechanical device.
15 . The computer-implemented method of claim 1 , wherein the one or more components of the electromechanical device include at least one of hardware components or software components.
16 . The computer-implemented method of claim 1 , wherein the electromechanical device is a vehicle.
17 . A system, comprising: one or more processors; and a computer-readable storage medium storing instructions that are executable by the one or more processors to perform operations comprising: receiving system information data associated with a change in state of one or more components of an electromechanical device; generating a message indicating feedback responsive to the change in state of the one or more components, the generating performed by inputting the system information data as a prompt to generative artificial intelligence representative of a plurality of characteristics of the electromechanical device, the generative artificial intelligence trained to analyze the system information data and to output the message that has one or more language characteristics based on the plurality of characteristics of the electromechanical device, wherein the one or more language characteristics are unique to the electromechanical device; and outputting the message indicating the feedback.
18 . The system of claim 17 , wherein the operations further comprise: transmitting, for display at a user interface, a request for the plurality of characteristics; and in response to the request, receiving user input indicating the plurality of characteristics.
19 . The system of claim 17 , wherein the operations further comprise determining the plurality of characteristics based on using object recognition techniques to analyze an image input associated with the electromechanical device.
20 . One or more computer-readable storage media comprising computer-executable instructions stored thereon that, responsive to execution by one or more processors, perform operations comprising: obtaining training data including a plurality of characteristics of an electromechanical device and instructions corresponding to operation of the electromechanical device; updating one or more large language models using the training data, the updated one or more large language models representative of the plurality of characteristics of the electromechanical device, the one or more large language models trained to analyze system information data associated with a change in state of one or more components of the electromechanical device; receiving the system information data; generating, responsive to the change in state of the one or more components, a message indicating that has one or more language characteristics based on the plurality of characteristics of the electromechanical device, the generating performed by inputting the system information data as a prompt to the updated one or more large language models, wherein the one or more language characteristics are unique to the electromechanical device; and outputting the message indicating the feedback.

Description

BACKGROUND Conventional techniques used to perform maintenance on an electromechanical device (e.g., an automobile or vehicle) typically include running diagnostics on one or more components of the electromechanical device. In one or more implementations, a diagnostics tool or system may be utilized to access and interpret diagnostics information. The diagnostics tool or system may be an on-board diagnostics (OBD) tool communicatively coupled with and/or integrated with a system of the electromechanical device. For example, the electromechanical device may include a port that couples the system of the electromechanical device with the diagnostics tool or system. The diagnostics tool or system may provide real-time data and/or diagnostics codes to identify issues with the electromechanical device and/or to determine a recommended maintenance procedure for the electromechanical device. A computer system may implement machine learning techniques, or artificial intelligence, to generate an output given a prompt as input. For example, a computer system may utilize a generative artificial intelligence model to generate content, data, or outputs that were not explicitly programmed or provided to the generative artificial intelligence model in training data. The generative artificial intelligence model is trained utilizing deep learning techniques (e.g., neural networks) to detect patterns and structures within the training data. In some examples, the generative artificial intelligence model may include one or more large language models for generating text in response to prompts or queries. A large language model may capture patterns and relationships in language, enabling the model to understand context, generate coherent text, and perform various natural language processing tasks. SUMMARY A personalized messaging system detects, analyzes, and presents information to a user of an electromechanical device. In one or more implementations, the personalized messaging system implements generative artificial intelligence (e.g., one or more large language models) to generate messages for presentation to a user. For example, the personalized messaging system obtains training data, including characteristics of the electromechanical device, environmental information of an environment of the electromechanical device, and/or electromechanical device data (e.g., maintenance and repair information). The personalized messaging system utilizes the training data to update large language models to generate messages that are representative of the characteristics of the electromechanical device and to train the large language models to analyze data collected from the electromechanical device. The personalized messaging system generates the messages by inputting data that indicates a change in state of a component of an electromechanical device (e.g., an automobile or vehicle) as a prompt to the large language models. The large language models output messages that include feedback responsive to the change in state of the components. For example, the messages include one or more of instructions for repair or maintenance of the component, an indication that one or more system settings of the components are updated, or the like. The messages have language characteristics representative of the characteristics of the electromechanical device. This Summary introduces a selection of concepts in a simplified form that are further described below in the Detailed Description. As such, this Summary is not intended to identify essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS The detailed description is described with reference to the accompanying figures. FIG. 1 is an illustration of an environment in an example implementation that is operable to employ techniques described herein. FIG. 2 depicts an example of model training logic for message personalization for an electromechanical device. FIG. 3 depicts an example of a personalized message generator for message personalization for an electromechanical device. FIG. 4 depicts an example system for message personalization for an electromechanical device. FIG. 5 depicts an example of another system for message personalization for an electromechanical device. FIG. 6 depicts an example of a user interface for message personalization for an electromechanical device. FIG. 7 depicts an example of another system for message personalization for an electromechanical device. FIG. 8 depicts a procedure in an example implementation of message personalization for an electromechanical device. FIG. 9 illustrates an example of a system that includes an example computing device that is representative of one or more computing systems and/or devices that may implement the various techniques described herein. DETAILED DESCRIPTION Overview Message personalization techniques for an electrom