Abstract: Systems and processes for efficient word encoding are provided. In accordance with one example, a method includes, at an electronic device with one or more processors and memory, receiving a user input including a word sequence, and providing a representation of a current word of the word sequence. The representation of the current word may be indicative of a class of a plurality of classes and a word associated with the class. The method further includes determining a current word context based on the representation of the current word and a previous word context, and providing a representation of a next word of the word sequence. The representation of the next word of the word sequence may be based on the current word context. The method further includes displaying, proximate to the user input, the next word of the word sequence.

Abstract: A system for identifying address components includes an interface and a processor. The interface is to receive an address for parsing. The processor is to determine a matching model of a set of models based at least in part on a matching probability for each model for a tokenized address, which is based on the address for parsing, and associate each component of the tokenized address with an identifier based at least in part on the matching model, wherein each component of the set of components is associated with an identifier, and wherein probabilities of each component of the set of components are determined using training addresses.

Abstract: A method and system are provided for assisting users in a conversation. The method includes identifying concepts in the conversation. The method further includes linking identified concepts in the conversation by matching the identified concepts in the conversation to concepts in a knowledge base. The method also includes generating and displaying on the display device, one or more context dependent suggestions for the conversation based on attributes and values associated with the linked concepts in the knowledge base.

Abstract: The program directs a computer processor to resolve an anaphor in electronic natural language text. The program detects a plurality of entities and an anaphor in a span of parsed natural language text comprising one or more sentences, and extracts pairs of related entities based on domain knowledge. The program constructs a set of tuples, wherein each tuple is a data type comprising an anaphor, an antecedent entity (AE) appearing before the anaphor in the span of parsed natural language text, and an entity (E) appearing after the anaphor in the span of parsed natural language text, wherein the anaphor refers to the AE and relates the AE to the E. The program resolves the anaphor by determining which entity in the plurality of entities the anaphor references, using the constructed set of tuples, and selecting an AE among one or more candidate AEs.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: monitoring one or more message of the conversation between multiple users for an entity reference; detecting the entity reference in a message in the conversation. An entity reference list stores previously established alternate name referring to a user in the conversation. By analyzing the message and following messages in the conversation for relevance of and sentiment to the entity reference, the entity reference is evaluated and if acceptable, the entity reference list is updated with the entity reference as a new alternate name to identify the user in subsequent messages.

Abstract: Systems and methods for determining knowledge-guided information for a recurrent neural networks (RNN) to guide the RNN in semantic tagging of an input phrase are presented. A knowledge encoding module of a Knowledge-Guided Structural Attention Process (K-SAP) receives an input phrase and, in conjunction with additional sub-components or cooperative components generates a knowledge-guided vector that is provided with the input phrase to the RNN for linguistic semantic tagging. Generating the knowledge-guided vector comprises at least parsing the input phrase and generating a corresponding hierarchical linguistic structure comprising one or more discrete sub-structures. The sub-structures may be encoded into vectors along with attention weighting identifying those sub-structures that have greater importance in determining the semantic meaning of the input phrase.

Abstract: Determining whether a proposed message contextually fits a messaging session. A method obtains a proposed message to be sent in a messaging session between users of a messaging service. The method identifies a context of the proposed message. The method determines whether the proposed message contextually fits the messaging session based on characteristics of an expected response to the proposed message, the characteristics of the expected response being based on patterns of communication between the users. The method also performs processing based on whether the proposed message contextually fits the messaging session.

Abstract: An apparatus and method for printing steganography is disclosed. The apparatus comprises a wearable unit and a controlling unit that are programmatically controlled by a processor. The controlling unit converts content to be published into a phoneme transcription for a target language, processes the content and further arranges the processed content as per a specified page layout. Further, the phoneme transcribed content is embedded into a QR code that is again extracted by a wearable unit to read the content, the content layout, and reading sequence. The wearable unit also converts the phoneme transcribed content into a voice output. Further, the wearable unit comprises motor sensors to sense a readers' body and neck movements to guide a reader to read content in a correct manner such that voice output is programmatically paused, stopped, repeated at intervals so determined.

Abstract: Described herein are systems and methods for human-like language acquisition in a compositional framework to implement object recognition or navigation tasks. Embodiments include a method for a model to learn the input language in a grounded and compositional manner, such that after training the model is able to correctly execute zero-shot commands, which have either combination of words in the command never appeared before, and/or new object concepts learned from another task but never learned from navigation settings. In embodiments, a framework is trained end-to-end to learn simultaneously the visual representations of the environment, the syntax and semantics of the language, and outputs actions via an action module. In embodiments, the zero-shot learning capability of a framework results from its compositionality and modularity with parameter tying.

Abstract: Disclosed subject matter relates to data analytics including a method and system for generating a contextual summary of one or more charts. A summary generating system extracts chart data associated with each chart received from one or more sources and determines context of the chart data. The summary generating system computes statistical data of each chart by analyzing chart data based on predefined rules corresponding to the context. The form of analysis to be performed depends on the context of the chart data. Furthermore, insights of each chart are generated by mapping the statistical data with predefined narratives corresponding to the context. Finally, the summary generating system, automatically generates the contextual summary of the charts corresponding to the context of the chart data in a predefined template format using the generated insights of each of the one or more charts. The contextual summary provides holistic information of the interpreted charts.

Abstract: Systems and methods for multiple topic automated chatting are provided. The systems and method provide multiple topic automated (or artificial intelligence) chatting by analyzing user inputs in a conversation to determine a plurality topics, to determine and score features related to the determined topics and different users, and to create a knowledge graph of the determined topics. Based on these determinations, the systems and methods may determine if a reply should be provided and then predict a reply.

Abstract: Systems and methods for identifying and locating related content using natural language processing are generally disclosed herein. One embodiment includes an HTML5/JavaScript user interface configured to execute scripting commands to perform natural language processing and related content searches, and to provide a dynamic interface that enables both user-interactive and automatic methods of obtaining and displaying related content. The natural language processing may extract one or more context-sensitive key terms of text associated with a set of content. Related content may be located and identified using keyword searches that include the context-sensitive key terms. For example, text associated with video of a first content, such as text originating from subtitles or closed captioning, may be used to perform searches and locate related content such as a video of a second content, or text of a third content.

Abstract: Various embodiments described herein facilitate multi-lingual communications. The systems and methods of some embodiments enable multi-lingual communications through different modes of communication including, for example, Internet-based chat, e-mail, text-based mobile phone communications, postings to online forums, postings to online social media services, and the like. Certain embodiments implement communication systems and methods that translate text between two or more languages. Users of the systems and methods may be incentivized to submit corrections for inaccurate or erroneous translations, and may receive a reward for these submissions. Systems and methods for assessing the accuracy of translations are described.

Abstract: Exemplary embodiments relate to techniques for improving a machine translation system. The machine translation system may include one or more models for generating a translation. The system may generate multiple candidate translations, and may present the candidate translations to different groups of users, such as users of a social network. User engagement with the different candidate translations may be measured, and the system may determine which of the candidate translations was most favored by the users. For example, in the context of a social network, the number of times that the translation is liked or shared, or the number of comments associated with the translation, may be used to determine user engagement with the translation. The models of the machine translation system may be modified to favor the most-favored candidate translation. The translation system may repeat this process to continue to tune the models in a feedback loop.

Abstract: Adaptive pseudo translation provides dynamic adjustment of a generated pseudo translation based on one or more rules and one or more dynamically detected parameters. A pseudo translation of data is requested and an adaptive pseudo translation is initiated. String is extracted from the data and an encoding and language of the string is dynamically detected. A target language is proactively selected based on a parameter. A buffer size is dynamically determined based on the detected encoding, detected languages and target language. The extracted string is dynamically transformed into pseudo translated text based on the buffer size. The dynamically generated pseudo translation provides a highly accurate mock translation to one or more target languages.

Abstract: The present invention relates to a device of simultaneous interpretation based on real-time extraction of an interpretation unit, the device including a voice recognition module configured to recognize voice units as sentence units or translation units from vocalized speech that is input in real time, a real-time interpretation unit extraction module configured to form one or more of the voice units into an interpretation unit, and a real-time interpretation module configured to perform an interpretation task for each interpretation unit formed by the real-time interpretation unit extraction module.

Abstract: Example embodiments of the present disclosure include a system comprising a computer-readable storage medium storing at least one program and a computer-implemented method for providing an interactive and social fitting room experience. Consistent with some embodiments, the method may include selecting a target audience to poll for feedback on an image of an individual wearing a garment in a fitting room. The method may further include transmitting the image to a computing device of each member of the target audience, and compiling feedback regarding the image from members of the target audience. The method may further include causing the compiled feedback to be displayed to the individual on an interactive mirror display in the fitting room.

Abstract: A centralized command and control network system for the automated manufacture of a personalized custom-fit garment comprises a centralized control system; automated programmable manufacturing equipment configured for assembling and stitching the personalized custom-fit garment from a digital pattern; and automated programmable material handling equipment configured for transporting the personalized custom-fit garment or its components through each step of the manufacturing equipment. After the customer has had his or her body scanned, and selected and personalized a garment design, the inventive manufacturing system will then manufacture the garment upon receipt of the order in an automated manner without requiring further substantive manual intervention or touch labor. The resultant personalized custom-fit garment is based on the customer's three-dimensional body shape and style and fit preferences. The system can be used to prepare any kind of garments.

Abstract: Quantifying power usage for a service. An example method may include identifying a dependency model for the service, the dependency model based in part on infrastructure providing the service. The method may also include determining power usage for the service using the dependency model.

Abstract: A method of designing a cutting drum for earth moving equipment is disclosed. The cutting drum has two or more ring segments, each ring segment comprising a plurality of cutting tools, and the rotational position of at least one ring segment is adjustable relative to one or more other ring segment and fixable in the new rotational position. The method involves inputting a plurality of design parameters of a cutting drum into a computer program, performing a computer simulated analysis of the cutting drum using the computer program to determine at least one operational value associated with at least one design objective, using the computer simulated analysis to determine the relative locations of the ring segments that correspond to the at least one design objective, and rotating the or each adjustable ring segment relative to at least one other ring segment so that the relative locations of the ring segments correspond to the at least one design objective.

Abstract: A computer-implemented method for multi-user CAx editing of a model of a design object may include (1) identifying one or more geometric elements referenced in response to creating a feature within the model of the design object, (2) receiving a feature operation that references the geometric elements referenced in response to creating the feature, (3) in response to receiving the feature operation, identifying a geometric element referenced by the feature operation, and (4) generating a unique persistent label for the geometric element. Various other methods and systems are also disclosed herein.

Abstract: A computer readable storage medium stores a facetization processing program that causes a computer to execute a process. The process includes: voxelizing a three-dimensional shape; generating first voxels corresponding to the three-dimensional shape; specifying an area surrounded by the generated first voxels; setting the specified area as voxels to generate second voxels; and facetizing third voxels at a boundary between at least one of the first voxels and a non-voxel area, and the second voxels and the non-voxel area.

Abstract: A computer-implemented land planning system is designed to generate at least one conceptual fit solution to a user-defined land development problem. The system employs a computer readable medium and a computer program encoded on the medium. The computer program is operable, when executed on a computer, for electronically creating at least one candidate solution to the land development problem. The candidate solution incorporates engineering measurements applicable in development of an undeveloped land site, the land site including a conceptually designed vehicle parking area. A fitness function quantitatively evaluates the candidate solution based on its cost. A heuristic problem-solving strategy manipulates the engineering measurements of the candidate solution to achieve a more quantitatively fit solution to the land development problem. Documentation illustrating the fit solution to the land development problem is delivered to the user.

Abstract: A technique for simplifying structure data for representing an environment. Polyhedrons can make up structure data used in an application such as modeling, visualization, and navigation. Consequently, the operations that are performed on the data often involve determining, for each polyhedron that defines a structure such as a building, whether the polyhedron obstructs a line-of-sight line between a first point in space being considered in the application and a second point. In order to determine whether a polyhedron obstructs a line-of-sight line, a data-processing system operating on the structure data must determine whether any walls of the polyhedron intersect the line. Thus, the more polyhedrons there are or the more vertices that are in each polyhedron, the more walls there are, and the more intersection checks are required, thereby adding to the computations. The disclosed technique reduces the number of walls by simplifying objects that make up the structure data.

Abstract: Methods and apparatus to model thermal mixing for prediction of multi-stream flows are described. An example method includes determining characteristics of a nozzle of an aircraft; estimating momentum diffusion due to turbulence associated with the nozzle based on the determined characteristics; and estimating thermal diffusion due to the turbulence associated with the nozzle based on the estimated momentum diffusion, wherein the estimating of the thermal diffusion due to the turbulence is based on a spatially varying turbulent Prandtl number.

Abstract: The present system for modeling intelligent sensor selection and placement takes signal and sensor information and calculates a statistical inference. As signal data passes through a series of processors, it is transformed by functions to account for signal emission, sensor reception, environmental factors, and noise. This produces a simulation of what the emitted signal would appear to be at a given sensor. The system may be used to select the most effective sensors for a given area or to determine the best sensor coverage for a given area.

Abstract: Systems, methods and articles of manufacture for rendering images depicting materials are disclosed. A stable Neo-Hookean energy model is disclosed which does not include terms that can produce singularities, or require the use of arbitrarily selected clamping parameters. The stable Neo-Hookean energy may include a length-preserving term and volume-preserving term(s), and the volume-preserving terms themselves may include term(s) from a Taylor expansion of a logarithm of a measurement of volume. The stable Neo-Hookean energy may further include an origin barrier term that increases the difficulty of reaching the origin and expands a mesh in response to a perturbation when the mesh is at the origin. Closed-form expressions of eigenvalues and eigenvectors of a Hessian of the stable Neo-Hookean energy are disclosed, which may be used in a simulation of a material to, e.g., project the Hessian to semi-positive-definiteness in Newton iterations used to determine a substantially minimal energy configuration.

Abstract: In some aspects, locations for nodes are computed for a one-dimensional flow model that models well system fluid flow in a subterranean region. Truncation error threshold data indicate a truncation threshold value for each of the nodes. Discretization data indicate a lowest-order term truncated from a discretized governing flow equation for each of the nodes. The locations for the nodes can be computed based on a scalar cost function, such that each of the lowest order terms is less than or equal to the truncation error threshold value for the respective node.

Abstract: According to one aspect, embodiments of the invention provide a CDC simulation system comprising a timing analysis module configured to receive a circuit design, analyze the circuit design to identify at least one CDC, and generate a report including information related to the at least one CDC, a CDC simulation module configured to communicate with the timing analysis module and to receive the report from the timing analysis module, and a test bench module configured to communicate with the CDC simulation module, to receive the circuit design, and to operate a test bench code to simulate the operation of the circuit design, wherein the CDC simulation module is further configured to edit a top level of the test bench code, based on the received report, such that the test bench module is configured to identify timing violations in the circuit design due to the at least one CDC.

Abstract: Methods and systems for verifying a derived clock using assertion-based verification. The method comprises counting the number of full or half cycles of a fast clock that occur between the rising edge and the falling edge of a slow clock (i.e. during the ON phase of the slow clock); counting the number of full or half cycles of the fast clock that occur between the falling edge and the rising edge of the slow clock (i.e. during the OFF phase of the slow clock); and verifying the counts using assertion-based verification.

Abstract: An apparatus includes a processor and a memory configured to store design data used for disposition and wiring of a logic circuit on a programmable logic device, and store a table indicating a relationship between a power supply voltage value and a delay amount for each type of element in the logic circuit, the relationship having a nature to set the delay amount so as to increase in value as the power supply voltage value is smaller. The processor determines, as an optimum voltage value, a power supply voltage value at which the delay margin of a critical path indicates a desired value that is in the positive and is a minimum value. The processor outputs configuration information including the optimum voltage value and the design data so as to form the logic circuit on the programmable logic device supplied with a voltage determined by the optimum voltage value.

Abstract: A method of preparing a programmable integrated circuit device for configuration using a high-level language includes compiling a plurality of virtual programmable devices from descriptions in said high-level language. That compiling includes compiling configurations of configurable routing resources from programmable resources of said programmable integrated circuit device, and compiling configurations of a plurality of complex function blocks from programmable resources of said programmable integrated circuit device. A machine-readable data storage medium may be encoded with a library of such compiled configurations. A virtual programmable device may include a stall signal network and routing switches of the virtual programmable device may include stall signal inputs and outputs.

Abstract: This disclosure relates generally to electronic design automation using high level synthesis techniques to generate circuit designs that include safety features. The algorithmic description representation can be specified in a first language and include at least one programming language construct associated with a first safety data type. Compiling the algorithmic description may involve identifying the at least one construct, accessing a first safety data type definition associated with the first safety data type, and generating a second representation of the circuit design based on the algorithmic description representation and the first safety data type definition. The second representation can be provided in a second language and include at least one safety feature for a portion of the circuit design associated with the at least one construct.

Abstract: Generating a layout of an integrated circuit chip area from a description of an integrated circuit (IC). The description includes a register-transfer-level (RTL) design. The RTL design is partitioned in large blocks for synthesis of large block synthesis (LBS) blocks. The description of the IC further includes a floorplan for the IC, wherein each LBS block to be synthesized is assigned to a respective rectilinear shape in the floorplan and the rectilinear shapes do not overlap each other.

Abstract: Non-transitory computer-readable media to perform a method for designing a multiband filter. The method includes generating an initial circuit structure comprising a desired number and type of circuit elements; generating an initial circuit design by mapping the frequency response requirements of the initial circuit structure into normalized space; generating an acoustic filter circuit design by transferring the initial filter circuit design; generating a pre-optimized circuit design by unmapping one or more circuit elements of the acoustic filter circuit design into real space and introducing parasitic effects; and communicating the pre-optimized circuit design to a filter optimizer that generates a final circuit design comprising a plurality of resonators, wherein a first resonator exhibits a high resonant frequency, a second resonator demonstrates a low resonant frequency and the difference between the low resonant frequency and the high resonant frequency is at least 1.

Abstract: According to exemplary embodiments, a system and method for automated system power supply design is provided. The system and method enables circuit designers to quickly and independently design complicated single or multi rail power supply systems including multiple loads and sequencing requirements. The power solutions offered to designers may include all required power supplies to power up the loads including sequencers and load switches. The power supply design system may be implemented on a standalone processing unit, a distributed computing network, internet based web application, or among various other network applications.

Abstract: A method of designing a microwave filter using a computerized filter optimizer, comprises generating a filter circuit design in process (DIP) comprising a plurality of circuit elements having a plurality of resonant elements and one or more non-resonant elements, optimizing the DIP by inputting the DIP into the computerized filter optimizer, determining that one of the plurality of circuit elements in the DIP is insignificant, removing the one insignificant circuit element from the DIP, deriving a final filter circuit design from the DIP, and manufacturing the microwave filter based on the final filter circuit design.

Abstract: Any primitive cells or blocks can be represented physically by a Barycenter compact model (or Barycenter model), and any black box model can also be physically represented by a Barycenter compact model physically. A hierarchical boundary condition between blocks is formulated by the Barycenter compact model. Hierarchical boundary condition problems between blocks can be limited within two levels only if using the Barycenter compact model.

Abstract: Disclosed systems and methods pertain to finfet based integrated circuits designed with logic cell architectures which support multiple diffusion regions for n-type and p-type diffusions. Different diffusion regions of each logic cell can have different widths or fin counts. Abutting two logic cells is enabled based on like fin counts for corresponding p-diffusion regions and n-diffusion regions of the two logic cells. Diffusion fills are used at common edges between the two logic cells for extending lengths of diffusion, based on the like fin counts. The logic cell architectures support via redundancy and the ability to selectively control threshold voltages of different logic cells with implant tailoring. Half-row height cells can be interleaved with standard full-row height cells.

Abstract: A computer implemented method for calculating a ground capacitance adjust for a wire segment going through a given routing tile. The method includes providing the routing tile having a plurality of wires wherein the wire segment being a victim wire and neighboring wires being aggressor wires; computing ground capacitance adjusts for a victim wire averaged across all aggressor slew values and across possible spacing values between the victim wire and the neighboring aggressor wires to take into account a potential coupling effect by the neighboring aggressor wires, assuming a distribution of signal slews of wires belonging to the routing tile and assuming the victim wire's neighbors have signal slews from the distribution of slews for this tile for possible spacing values responsible for the coupling effect, to guide placement of the wire segment in the routing tile to avoid coupling noise.

Abstract: A method for generating a three-dimensional (3D) computer model of an assembly that includes wiring routing, which includes creating a part data structure that defines a part in a virtual product management system. The part data structure includes a plurality of nodes that define at least 3D part design data, 3D wiring routing design data and wiring routing annotation data of the part. The method includes importing at least the 3D part design data, the 3D wiring routing design data and the wiring routing annotation data to the part data structure from a computer-aided design (CAD) model system and generating a 3D computer model of the assembly. The method also includes transmitting the 3D computer model of the assembly to an electronic end user device.

Abstract: Aspects of the disclosure are directed to a metal only cell-based power grid (PG) architecture. In accordance with one aspect, the power gird (PG) architecture includes a cell building block structure with a N×M grid configuration including N cell building blocks arranged in a first direction and M cell building blocks arranged in a second direction, wherein the first direction and the second direction are orthogonal to one another; and a plurality of power grid (PG) cells, wherein each of the N cell building blocks and each of the M cell building blocks are occupied by a PG cell of the plurality of PG cells.

Abstract: A method of forming a layout design for fabricating an integrated circuit is disclosed. The method includes generating a first layout of the integrated circuit based on design criteria, generating a standard cell layout of the integrated circuit, generating a via color layout of the integrated circuit based on the first layout and the standard cell layout and performing a color check on the via color layout based on design rules. The first layout having a first set of vias arranged in first rows and first columns. The standard cell layout having standard cells and a second set of vias arranged in the standard cells. The via color layout having a third set of vias. The third set of vias including a portion of the second set of vias and corresponding locations, and color of corresponding sub-set of vias.

Abstract: Closing timing for a circuit design can include displaying, using a display device, a first region having a plurality of controls corresponding to a plurality of data sets generated at different times during a phase of a design flow for a circuit design, wherein each control selects a data set associated with the control, and displaying, using the display device, a second region configured to display a list of critical paths for data sets selected from the first region using one of the plurality of controls. Closing timing further can include displaying, using the display device, a third region configured to display a representation of a target integrated circuit including layouts for the critical paths of the list for implementations of the circuit design specified by the selected data sets.

Abstract: A dynamic media object management system that communicates media objects such as imagery with source media modalities including medical imaging systems and media archival, review, and analysis workstations, among other types of systems. The system includes a management console with a user interactive subsystems controller that may include one or more parameter databases populated via the user interactive subsystems controller with media tag transfer syntaxes, media format mapping protocols, compatibility matrices, and media processing rules that may include technologist reviewer routing rules, \communication schedules, and other types of predetermined and, or predefined parameters. The system may also include, among other components, a modality services subsystem that can communicate media objects within and outside the system.

Abstract: A method includes identifying a medical service for a user based on a request signal received from a mobile device associated with the user, the mobile device and identifying a plurality of medical service providers based on at least the medical service type. The method includes determining a plurality of travel times, wherein each of the plurality of travel times is indicative of a time to travel between the location and a provider location of a respective one of the plurality of service providers. The plurality of travel times are based on traffic information. The method also includes determining a ranking of the plurality of medical service providers based on the plurality of travel times and causing the mobile device to display at least a portion of the ranking.

Abstract: A system and method for a decentralized autonomous healthcare economy platform are provided. The system and method aggregates all of the healthcare data into a global graph-theoretic topology and processes the data via a hybrid federated and peer to peer distributed processing architectures.

Abstract: A tele-health services cabin includes a plurality of vital signs monitoring devices, a cabin management unit, and videoconferencing hardware via which a remote practitioner in a remote medical call center videoconferences with a patient in the cabin to diagnose symptoms of the patient. The cabin management unit includes a processor that controls the cabin, a data input at which patient data is provided from the vital signs monitoring devices, and a transmitter connectable to a communication link for bi-directional communication between the cabin management unit and the medical call center, where the transmitter transmits the patient data to the medical call center. The tele-health services cabin may include a patient chair including a motorized seat back and at least one sensor encapsulated in the seat back. The tele-health services cabin may include a hands-free medical device station. The tele-health services cabin may include an automatic cleaning system.

Abstract: A computer-implemented method or system is provided for providing connecting relationships between wearable devices. The method includes measuring a first health parameter of a user via one or more sensors of a first wearable device; measuring a second health parameter of the user via one or more sensors of a second wearable device; determining an alert action based on a combination of the measurements of first health parameter and the second health parameter; and generating a notification to the user based on the alert action.

Abstract: A method and apparatus for monitoring and/or managing adherence to a medication regimen that involves use of a sensor. Dispensing medicine from a container commonly involves motion of the container, which can be a distinctive motion. In some embodiments, a processor monitors motion sensor data from a motion sensor that is physically coupled to the container, such that the motion sensor and the container move in unison. A processor analyzes the sensor data to determine physical movement of the container. When the determined movement matches the distinctive motion of medicine being dispensed, the processor can determine that medicine has been dispensed. A computer system can compare the dispensed medication to a planned medication regimen to determine a state of compliance to the medication regimen. The computer system can take an action based on the compliance state, such as sending a message indicating the compliance state to a medical professional.