Abstract: This specification relates to methods, and systems for stakeholder and impact discovery. One of the methods includes receiving a knowledge representation model indicating at least a first stakeholder and a first impact; determining an impact model based at least in part on the knowledge representation model; receiving distributed sensor data; and determining at least a second impact based at least in part on the impact model and the distributed sensor data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing an olfaction training program by an online service executing on a server. A first object and an aroma of the first object is transmitted to the client device of a user that presents the first object in a virtual reality environment and disperses the first aroma. In response, the user interacts with the vital reality environment. The user response is transmitted back to the online service. The user response is stored in a database along with the first data and the first aroma. The online service determines a second object and an aroma of the second obj ect based on the user response. The second object and the aroma of the second object is transmitted to the client device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing an olfaction training program by an online service executing on a server using an AR enabled headset. The objects in the vicinity of the users are identified and highlighted. If the objects have an aroma, the objects are used for olfaction tests. The user interacts with the AR environment to select an object in response to detecting an aroma. The user responses is transmitted back to the online service. The online service determines a subsequent object based on the user response. The subsequent object is then highlighted in the AR environment and the user is prompted to take a subsequent olfaction test.

Abstract: Implementations for receiving, by the design assistant, an initial set of requirements, each requirement in the initial set of requirements being manually provided by a user, providing, by the design assistant and using a knowledge graph, a first set of questions based on the initial set of requirements and content determined from at least one design document in a set of design documents, filtering, by the design assistant, one or more questions from the first set of questions to provide a second set of questions, providing, by the design assistant, at least a portion of the second set of questions as output to the user to elicit one or more responses from the user, and editing, by the design assistant, the initial set of requirements based on the one or more responses to provide a set of requirements, the set of requirements for the to-be-designed product.

Abstract: This document describes impact networks that enable stakeholders to measure and take actions to adjust the impact of changes to products and services. In one aspect, a method includes receiving a stakeholder impact graph defining stakeholders. Each stakeholder is a node that is connected to at least one other stakeholder by an impact relationship edge. Data defining a first design perturbation in one or more design properties for a product or service of a first stakeholder is received from the first stakeholder. A determination is made, for one or more second stakeholders of the stakeholders connected to the first stakeholder by a respective impact relationship edge, a respective impact on the second stakeholder caused by the first design perturbation. Data defining a remediation perturbation that adjusts the respective impact of the first deign perturbation on the one or more second stakeholders is received.

Abstract: Implementations for receiving, by the design assistant, an initial set of requirements, each requirement in the initial set of requirements being manually provided by a user, providing, by the design assistant and using a knowledge graph, a first set of questions based on the initial set of requirements and content determined from at least one design document in a set of design documents, filtering, by the design assistant, one or more questions from the first set of questions to provide a second set of questions, providing, by the design assistant, at least a portion of the second set of questions as output to the user to elicit one or more responses from the user, and editing, by the design assistant, the initial set of requirements based on the one or more responses to provide a set of requirements, the set of requirements for the to-be-designed product.

Abstract: Techniques are described for component design based on sensor data. Sensor data is collected by sensors in, or proximal to, a system under diagnosis (e.g., a vehicle), the sensor data describing use of one or more components of the system by one or more individuals. The sensor data from various instances of the component may be aggregated and analyzed to determine update(s) to the design of the component. For example, the aggregate sensor data may be analyzed to identify portions of the component frequently associated with movements by users (e.g., fidgeting, adjustments). The identified portion(s) can be presented graphically in a design view used to specify design modification(s) for the component. In some implementations, the aggregate sensor data is provided as input to a model that is trained, using machine learning, to output design modification(s) for the component based on the input aggregate sensor data.

Abstract: This specification relates to methods, and systems for stakeholder and impact discovery. One of the methods includes receiving a knowledge representation model indicating at least a first stakeholder and a first impact; determining an impact model based at least in part on the knowledge representation model; receiving distributed sensor data; and determining at least a second impact based at least in part on the impact model and the distributed sensor data.

Abstract: This document describes impact networks that enable stakeholders to measure and take actions to adjust the impact of changes to products and services. In one aspect, a method includes receiving a stakeholder impact graph defining stakeholders. Each stakeholder is a node that is connected to at least one other stakeholder by an impact relationship edge. Data defining a first design perturbation in one or more design properties for a product or service of a first stakeholder is received from the first stakeholder. A determination is made, for one or more second stakeholders of the stakeholders connected to the first stakeholder by a respective impact relationship edge, a respective impact on the second stakeholder caused by the first design perturbation. Data defining a remediation perturbation that adjusts the respective impact of the first deign perturbation on the one or more second stakeholders is received.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a predictive analytics system that provides a mechanism to change the design or implementations of a product manufactured in a supply chain are disclosed. In one aspect, a method includes the actions of receiving training data that includes private information for a node in a supply chain network and information regarding previous decisions related to product change requests for a product manufactured through the supply chain network; training, using the training data, a predictive model configured to render decisions for requests to change a part used in manufacturing the product; receiving a request to change a given part; applying the predictive model to the request to change the given part; determining a decision approving or denying the request; and transmitting the decision to the requesting node.

Abstract: Techniques are described for component design based on sensor data. Sensor data is collected by sensors in, or proximal to, a system under diagnosis (e.g., a vehicle), the sensor data describing use of one or more components of the system by one or more individuals. The sensor data from various instances of the component may be aggregated and analyzed to determine update(s) to the design of the component. For example, the aggregate sensor data may be analyzed to identify portions of the component frequently associated with movements by users (e.g., fidgeting, adjustments). The identified portion(s) can be presented graphically in a design view used to specify design modification(s) for the component. In some implementations, the aggregate sensor data is provided as input to a model that is trained, using machine learning, to output design modification(s) for the component based on the input aggregate sensor data.

Abstract: Techniques are described for component configuration based on sensor data. Sensor data is collected by sensors in, or proximal to, a system under diagnosis (e.g., a vehicle), the sensor data describing the use of component(s) of the system by individual(s). The sensor data is analyzed (e.g., in real time) to determine an updated configuration for component(s) (e.g., an adjustment to the seat back, lumbar support of a car seat, etc.). The updated configuration may be communicated to the individual as a recommended configuration. In some implementations, the updated configuration may be communicated directly to the component which, on receiving and processing the configuration update, sends signals to various actuators to move the subcomponents of the component into the updated configuration. In some implementations, the sensor data is used to train, through machine learning, a model that provides configuration update(s) for component(s) based on the input sensor data.

Abstract: Techniques are described for component design based on sensor data. Sensor data is collected by sensors in, or proximal to, a system under diagnosis (e.g., a vehicle), the sensor data describing use of one or more components of the system by one or more individuals. The sensor data from various instances of the component may be aggregated and analyzed to determine update(s) to the design of the component. For example, the aggregate sensor data may be analyzed to identify portions of the component frequently associated with movements by users (e.g., fidgeting, adjustments). The identified portion(s) can be presented graphically in a design view used to specify design modification(s) for the component. In some implementations, the aggregate sensor data is provided as input to a model that is trained, using machine learning, to output design modification(s) for the component based on the input aggregate sensor data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a predictive analytics system that provides a mechanism to change the design or implementations of a product manufactured in a supply chain are disclosed. In one aspect, a method includes the actions of receiving training data that includes private information for a node in a supply chain network and information regarding previous decisions related to product change requests for a product manufactured through the supply chain network; training, using the training data, a predictive model configured to render decisions for requests to change a part used in manufacturing the product; receiving a request to change a given part; applying the predictive model to the request to change the given part; determining a decision approving or denying the request; and transmitting the decision to the requesting node.

Abstract: Techniques are described for component configuration based on sensor data. Sensor data is collected by sensors in, or proximal to, a system under diagnosis (e.g., a vehicle), the sensor data describing the use of component(s) of the system by individual(s). The sensor data is analyzed (e.g., in real time) to determine an updated configuration for component(s) (e.g., an adjustment to the seat back, lumbar support of a car seat, etc.). The updated configuration may be communicated to the individual as a recommended configuration. In some implementations, the updated configuration may be communicated directly to the component which, on receiving and processing the configuration update, sends signals to various actuators to move the subcomponents of the component into the updated configuration. In some implementations, the sensor data is used to train, through machine learning, a model that provides configuration update(s) for component(s) based on the input sensor data.

Abstract: Techniques are described for component design based on sensor data. Sensor data is collected by sensors in, or proximal to, a system under diagnosis (e.g., a vehicle), the sensor data describing use of one or more components of the system by one or more individuals. The sensor data from various instances of the component may be aggregated and analyzed to determine update(s) to the design of the component. For example, the aggregate sensor data may be analyzed to identify portions of the component frequently associated with movements by users (e.g., fidgeting, adjustments). The identified portion(s) can be presented graphically in a design view used to specify design modification(s) for the component. In some implementations, the aggregate sensor data is provided as input to a model that is trained, using machine learning, to output design modification(s) for the component based on the input aggregate sensor data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for promoting healthy behavior. The methods, systems, and apparatus include an action of receiving device capability information for multiple devices. The device capability information from each device describes capabilities of the device. Additional actions include receiving an indication of a health goal of a user and receiving health information of the user sensed by a first device of the multiple devices. Further actions include generating a health related instruction for a second device of the multiple devices based on the health information of the user sensed by the first device of the multiple devices, the health goal of the user, and the device capability information of the second device. An additional action includes providing the health related instruction to the second device.

Abstract: Techniques are described for presenting a hierarchical arrangement of node evaluation results to facilitate the review of a decision. Machine learning (ML) and/or artificial intelligence (AI) techniques are employed to automatically determine an individual result for each of multiple decision nodes that are hierarchically arranged to contribute to an overall result of a decision. A user interface may present the decision nodes and individual results, in their hierarchical arrangement, to enable a reviewer to provide feedback regarding one or more of the individual results and/or the overall result. The reviewer feedback may be employed to further refine the model used to determine the individual results for the decision nodes.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for promoting healthy behavior. The methods, systems, and apparatus include an action of receiving device capability information for multiple devices. The device capability information from each device describes capabilities of the device. Additional actions include receiving an indication of a health goal of a user and receiving health information of the user sensed by a first device of the multiple devices. Further actions include generating a health related instruction for a second device of the multiple devices based on the health information of the user sensed by the first device of the multiple devices, the health goal of the user, and the device capability information of the second device. An additional action includes providing the health related instruction to the second device.

Abstract: Methods, systems, and apparatus, including computer program products, for generating feedback. In one aspect, a method includes receiving sensor data from a plurality of sensors, wherein at least one of the plurality of sensors is associated with a mobile device of a user; aggregating the received sensor data to generate aggregated sensor data; processing the aggregated sensor data to determine an aggregated metric; comparing the aggregated metric to a target associated with the user to determine a measure of performance; and generating feedback based on the determined measure of performance. Further, the mobile device can comprise a mobile personal services device that includes one or more of an audio sensor, a video sensor, an environmental sensor, a biometric sensor, a location sensor, an activity detector, and a health monitor. The feedback can be displayed on the mobile personal services device. The feedback also can be displayed in near real-time.