Foundation model for industrial data analysis

Abstract

Supervised learning models, for instance models for anomaly detection, typically require large amounts of data to be trained. It is recognized herein, however, that acquiring and storing sensor data is often expensive or cost-prohibitive. Furthermore, although in some cases industrial data is abundant, labels for the industrial data are often scarce, and manual labeling is typically not scalable. Therefore, it is recognized herein there is a bottleneck in extracting actionable information from industrial data.

Description

FOUNDATION MODEL FOR INDUSTRIAL DATA ANALYSISBACKGROUND

[0001] An anomaly or faulty behavior can generally be defined as an event or occurrence that does not follow expected or normal behavior. In the context of neural networks or machine learning, an anomaly can be difficult to define, but the definition can be critical to the success and effectiveness of a given anomaly detector. Actionable decision support, for instance anomaly detections, based on analytics of time series data often requires supervised learning. For example, anomaly detection in general can require additional analysis for identification of the problem that is associated with the detected anomaly, and for determination of what action should be taken in response to the identified problem. Supervised learning models, for instance models for anomaly detection, typically require large amounts of data to be trained. It is recognized herein, however, that acquiring and storing sensor data is often expensive or cost-prohibitive. Furthermore, although in some cases industrial data is abundant, labels for the industrial data are often scarce, and manual labeling is typically not scalable. Therefore, it is recognized herein there is a bottleneck in extracting actionable information from industrial data.BRIEF SUMMARY

[0002] Embodiments of the invention address and overcome one or more of the described- herein shortcomings by providing methods, systems, and apparatuses that improve various analysis of time series industrial data, such that various industrial tasks (e.g., forecasting, anomaly detection, data imputation, etc.) are more accurate and efficient.

[0003] In an example aspect, analytics industrial computer system can include a sensor configured to capture real samples of data from a physical system. The computer system can further include a memory storing instructions that, when executed by the processor, cause the processor to perform various operations. The operations can include obtaining the real samples of data, wherein the data is associated with an industrial task. The operations can further include receiving a prompt from a user of the computer system, wherein the prompt is indicative of a pattern of interest. Based on the real samples of data and the prompt, the computer system can generate an output that identifies portions of the real samples of data that exhibit the pattern of interest, so as to define an identified pattern. Based on the identifiedpattern, the system can trigger a performance of the industrial task. For example, the identification of specific patterns can drive or trigger operations and maintenance decisions or actions.

[0004] In another example aspect, the computer system can generate a plurality of tokens from the prompt. The system can input the plurality of tokens into a time series foundation model (TSFM) defined by the system, such that the TSFM determines the identified pattern. The plurality of tokens can define one or more prompt tokens that indicate information associated with the industrial task. The plurality of tokens can also define one or more sequence tokens that indicate information associated with real samples of data. The plurality of tokens can also define a classify token that indicates a type of task corresponding to the industrial task. In various examples, the prompt includes text or an image that describes the pattern of interest, so as to define the prompt in a semi-structured format.BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0005] The foregoing and other aspects of the present invention are best understood from the following detailed description when read in connection with the accompanying drawings. For the purpose of illustrating the invention, there is shown in the drawings embodiments that are presently preferred, it being understood, however, that the invention is not limited to the specific instrumentalities disclosed. Included in the drawings are the following Figures:

[0006] FIG. 1 is a block diagram of an example system that includes an analytics computer system that defines a time series foundation model (TSFM) configured to identify patterns in data, in accordance with an example embodiment.

[0007] FIG. 2 is a block diagram that shows example inputs and outputs associated with the example TSFM, in accordance with an example.

[0008] FIG. 3 illustrates a computing environment within which embodiments of the disclosure may be implemented.

[0009] FIG. 4 illustrates an example of real data and a synthetic prompt being combined into a transformed sample, in accordance with an example embodiment.DETAILED DESCRIPTION

[0010] As an initial matter, it is recognized herein that current approaches to generating a machine learning (ML) model that distinguishes different specific types of patterns in timeseries data require training the ML model in a supervised learning manner. Supervised learning typically requires a large amount of data samples that are manually labeled. It is further recognized herein that for each specific problem addressed by a given ML model, the given ML model is typically required to be trained with specific (manually labeled) data samples associated with the respective problem. Thus, in current approaches to using ML models for analyzing time series industrial data and assisting in industrial tasks, labeled data samples are generally required for each category of interest.

[0011] Subject Matter Experts (SMEs) can manually label data samples. In some simple cases, the labels from the SMEs can be translated into rules, but in general it is not possible to extract such information in a form that is directly usable for monitoring real world data. The SME knowledge may be described as well in the form of simulation models, but it is again very challenging to directly use those models to monitor real world data.

[0012] In accordance with various embodiments, semi-structured information from a domain expert is interpreted in the form of a prompt. The prompt can include text, time series data, images, and the like. The prompt can indicate relevant patterns in any time series data in a zero-shot fashion, thereby bypassing the need for labels or even historical data for a specific application. Embodiments described herein can define a time series foundation model (TSFM) configured to add context, based on semi-structured inputs received from a domain expert, to various industrial tasks related to time series analytics. Those tasks can include, among others, forecasting, anomaly detection, and data imputation.

[0013] Referring initially to FIG. 1 , an example automation or industrial network or physical system 100 can include one or more plants or production networks 104 that contain control logic, host web servers, and the like. For example, the physical system 100 can include an enterprise or IT network 102 and multiple operational plant or production networks 104 communicatively coupled to the IT network 102. The production network 104 or enterprise network 102 can include one or more analytics computer systems or modules 106 connected within the production network 104. The computer system 106 can define a time series foundation model (TSFM) model 107, as further described herein. An example computer system 106 is connected to the IT network 102. The arrangement of the computer system 106 can vary as desired, and all such arrangements are contemplated as being within the scope of this disclosure. For example, in some cases, data augmentation and model training described herein can be performed on a different system than the system that monitors a physical system and collects the data from the physical system. In other cases, the system that collects the data can also augment the data and train the models.

[0014] Still referring to FIG. 1 , the production network 104 can include various production machines configured to work together to perform one or more manufacturing operations. Example production machines of the production network 104 can include, without limitation, robots 108 and other field devices that can be controlled by a respective PLC 114, such as sensors 110, actuators 112, or other machines, such as automatic guided vehicles (AGVs) 108. The PLC 114 can send instructions to respective field devices. In some cases, a given PLC 114 can be coupled to a human machine interfaces (HMIs) 116. It will be understood that the physical system 100 is simplified for purposes of example. That is, the physical system 100 may include additional or alternative nodes or systems, for instance other network devices, that define alternative configurations, and all such configurations are contemplated as being within the scope of this disclosure.

[0015] The network or system 100, in particular each production network 104, can define a field portion or level 118 and plant level or portion 120. For example, and without limitation, the plant level 120 can define one or more industrial plants or systems that can be geographically and functionally separate from or independent of each other. For example, the plant level 120 can include Brownfield plants and Greenfield plants that are each connected to respective field devices within the field level 118. The field level 118 can include various field devices such as the robots 108, PLC 114, sensors 110, actuators 112, HMIs 116, and AGVs. The sensors 110 can be configured to capture real samples of time series data from the physical system 100. The field portion 118 can define one or more production lines or control zones associated with a given plant in the plant level 120. The PLC 114, sensors 110, actuators 112, and HMI 116 within a given production line can communicate with each other via a respective field bus 122. Each control zone can be defined by a respective PLC 114, such that the PLC 114, and thus the corresponding control zone, can connect to the respective plant portion 120 via an Ethernet connection 124. In some cases, the robots 108 and AGVs can be configured to communicate with other devices within the fieldbus portion 118 via a WiFi connection 126. Similarly, the robots 108 and AGVs can communicate with the Ethernet portion 120, in particular a Supervisory Control and Data Acquisition (SCADA) server 128, via the Wi-Fi connection 126. In various examples, a respective computer system 106 is communicatively coupled between the PLC 114 and the respective plant in the plant level 120, for instance via the Ethernet connection 124 or the Wi-Fi connection 126. In some examples, the computer system 106 is defined by the PLC 114.

[0016] The plant level 120 of a given production network 104 can include various computing devices or subsystems communicatively coupled together via the Ethernet connection 124. Example computing devices or subsystems in the plant portion 120 include, without limitation,a mobile data collector 130, HMIs 132, the SCADA server 128, the computing system 106, a wireless router 134, a manufacturing execution system (MES) 136, an engineering system (ES) 138, and a log server 140. The ES 138 can include one or more engineering works stations. In an example, the MES 136, HMIs 132, ES 138, and log server 140 are connected to the production network 104 directly. The wireless router 134 can also connect to the production network 104 directly. Thus, in some cases, mobile users, for instance the mobile data collector 130 and robots 108 (e.g., AGVs), can connect to the production network 104 via the wireless router 134.

[0017] It will be appreciated that the program modules, applications, computer-executable instructions, code, or the like depicted herein are merely illustrative and not exhaustive, and that processing described as being supported by any particular module may alternatively be distributed across multiple modules or performed by a different module. In addition, various program module(s), script(s), plug-in(s), Application Programming Interface(s) (API(s)), or any other suitable computer-executable code may be provided to support functionality provided by the program modules, applications, or computer-executable code depicted herein and / or additional or alternate functionality. Further, functionality may be modularized differently such that processing described as being supported collectively by the collection of program modules depicted herein may be performed by a fewer or greater number of modules, or functionality described as being supported by any particular module may be supported, at least in part, by another module. In addition, program modules that support the functionality described herein may form part of one or more applications executable across any number of systems or devices in accordance with any suitable computing model such as, for example, a client-server model, a peer-to-peer model, and so forth. In addition, any of the functionality described as being supported by any of the program modules depicted herein may be implemented, at least partially, in hardware and / or firmware across any number of devices, for instance computer system 106.

[0018] Referring also to FIG. 2, the analytics computing system 106 can define one or more ML models, in particular the TSFM model 107, configured to be trained with training data and then used in more general tasks as compared to the training data. In an example, the TSFM model 107 defines an encoder 202 communicatively coupled to a foundation module or model 204 that is communicatively coupled to a patch module 206. The encoder 202 can be configured to receive an input 201. The input 201 can include time-series data and a prompt associated with the time-series data. In an example, the time-series data is obtained from sensors 110, though it will be understood that time-series data can be obtained from other system or modules, and all such mechanisms for obtaining time series data are contemplatedas being within the scope of this disclosure. In various examples, the prompt can define a pattern description associated with the time series data that the TSFM 107 can classify in accordance with the pattern description or pattern of interest. For example, an expert can describe a pattern that is defined by given time-series data in a semi-structured format (prompt), such as in text or a graph.

[0019] In various examples, the prompt can combine text and time series information (e.g., in the form of data or images). Time series information might come from manual sketches, outputs of simulation models, or data from other processes, by way of example and without limitation. The encoder 202 can learn to process the information in the prompt based on pretraining of the encoder 202. In an example, data augmentation is performed to create synthetic samples for pre-training / testing of the model based on real data, so that the data is transformed and associated with synthetically created labels. Large language models can help in creating the text prompts and variations of them.

[0020] Unlike traditional time series foundation models, the TSFM 107 can add context based on prompts from a user. To the extent such traditional models use prompts or prompt tokens, those prompt tokens are obtained in a data-driven fashion, such that labeled data is required that corresponds to a task of interest. In contrast, the TSFM 107 can perform zero-shot classification for time series data, based on prompt inputs. In particular, for example, the TSFM 107 can output a time series with indications of when time patterns occurred in the time series data, and with an identification of the specific patterns involved and the signals that are affected by the time patterns. A signal can correspond to a univariate time series measurement (e.g., corresponding to one sensor). The time series data can correspond to multiple signals (e.g., multiple sensors).

[0021] Referring in particular to FIG. 2, the encoder 202 can receive the input 201 , which can include a prompt in the form of a semi-structured description of patterns of interest. In some examples, the description of the patterns of interest may include text and time series data. The time series data might define real world data, or might be represented, for example and without limitation, in the form of drawings or sketches, or in the form of simulation data. For example, sketches or drawings that represent the time series data can included pre-defined markings that indicate ranges or multiple options. For example, drawings of a given time series pattern might include one or more specific graphical symbols that make the drawing more expressive. By way of example, and without limitation, a vertical arrow might indicate that the range may vary, a solid line might indicate the average behavior, dotted lines might indicate min and max, horizontal arrows might indicate variations on the time axis (e.g., it could happen slower or faster), etc.

[0022] Text in the input 201 can refer to the time series data in the input 201 so as to describe the patterns of interest. Based on the input 201 , the encoder 202 can generate a plurality of tokens 203, for instance one or more prompt tokens 203a, one or more sequence tokens 203b, and a classify (CLS) token 203c. The CLS token 203c can provide an indication to the foundation module 204 of the type of task being performed using the time series data from the input 201 . The sequence tokens 203b can contain information extracted from the multivariate time series data or information from the input 201 . The prompt tokens 203a can provide information about the specific task being performed. In an example embodiment, no training of the foundation model 204 using the data associated with the specific task is required, thereby defining a zero-shot learning solution. In this example, the prompt tokens 203a can be obtained by encoding the prompt that is in the input 201 , which can be obtained from a domain expert. By way of further example, the domain expert might identify one or more patterns, and might identify (e.g., via text or images) conditions for the one or more identified patterns. For example, an expert might indicate that if a given dataset includes one or more given variables that change at one or more respective rates over time, then one or respective patterns can be identified. By way of a specific power system example in which there are multiple measurements of current and voltage in various locations, specific patterns can be drawn to illustrate what a short circuit looks like, or a broken cable, loss of generation, loss of load, etc. Those patterns may happen differently in each measurement depending on where the event happens, but the system does not need all of the possible combinations. Using text, the matching voltages and currents can be indicated. For example, if the voltage changes in a given manner, and corresponding currents change in a given manner, a pattern of interest can be identified. Using text or graphical indications in the drawings can also indicate that the amplitude of pattern may change.

[0023] Still referring to FIG. 2, based on the plurality of tokens 203, the foundation module 204 can generate an output 205 that indicates one or more patterns of interest in the time series data from the input 201. By way of example, if a first and second pattern are identified in the prompt of the input 201 , and thus in the prompt token 203a, the output 205 can indicate where the first and second patterns occur in the time series data of the input 201 , and thus in the sequence tokens 203b. Thus, the foundation module 204 can identify, via the output 205, specific points or locations within the time series data that patterns exist. In various examples, the identification of specific types of patterns in an industrial application can drive operation and maintenance decisions and actions. For instance, a controller can operate differently following the detection of a pattern that indicates a different operating condition of the system, making the operation more efficient or safer. Identification of a specific failure mode can,based on identification of the corresponding pattern, enable proper automatic mitigation of the issue and can indicate the proper means for fixing the problem, minimizing downtime and other negative consequences of the failure. The output 205 can also indicate which signals are involved (e.g., which currents and voltages in the power system example) I mentioned above. In some examples, this can be performed using a multivariate output, with one time series of pattern indications provided for each signal, instead of a single one.

[0024] In another example, text information can also be included in the output 205. Such text information can correspond to notes about the results or related explanations. By way of example, a note might indicate the presences of both the first and second patterns in the time series data, but the note might further indicate that the first pattern was a better match as compared to the second pattern. The textual output can also provide additional information based on requests coming from the prompt in the input 201 . For example, the input prompt might indicate that it may be required to scale the reference time series data provided as input to match the data, or that there may be some varying time delay among different signals. In such cases, the prompt might also include a request that the information about the scaling factor or delay value used for matching the patterns is provided as textual output.

[0025] Continuing with the example, the TSFM 107 can also perform reinforcement learning from human feedback (RLHF) to improve the textual outputs in terms of the usefulness and clarity of the information for the end user. For example, the TSFM 107 can include the result of a large language models (LLM) where the user can establish dialogs with the model to obtain additional information or correct mistakes. In the case of an example embodiment, such dialogs can be a means for iteratively guiding the model for refining the results of the time series task.

[0026] Context can be added in a similar fashion to other time series related analytics tasks, such as forecasting, anomaly detection, and data imputation. For instance, context can be added to forecasting by augmenting the TSFM 107 to include another prompt input 201 . In both cases this is a zero-shot task, but prompts can provide a context that can potentially help in achieving superior performance in the results. Prompts can be in the form of text (e.g., “the equipment will operate at higher loads”, or “provide an optimistic view”) or other modalities (e.g., other reference time-series), including multi-modal.

[0027] Regardless of the types of tasks which are the focus of the TSFM 107 at a given time, the TSFM 107 can be pre-trained in accordance with various embodiments. In some cases, for zero-shot classification of patterns, data augmentation is performed during pre-training so that sufficient data is available to train the TSFM 107. Data augmentation can be performed by creating data samples from the transformation of real-world time series data. For example, alibrary of parameterized time series transformations can automatically generate matching prompts and time series data. By way of example, the computer system 106 can include a random transformation module that takes real-world time series data as input, and based on the real-world time series data, transforms and augments the real-world time series data so as to define transformed time series data. The TSFM 107 can further define an LLM that takes as input the original prompt (e.g., input 201 ) The LLM can generate variations of the original prompt. In some cases, the TSFM 107 can generate prompts based on the transformed time series data, such that the data augmentation library might only include the generation of transformations and not the matching prompts.

[0028] Referring now to FIG. 4, an example shows real data 400 that comes from an example industrial process. Example synthetic prompts 402 can be generated (e.g., via random walk, inverse Fourier or wavelet transforms, etc.) from the real data 400. The real data 400 and synthetic prompt 402 can be pre-processed (e.g., filtered, scaled, etc.) and combined (e.g., summed) to create a transformed sample 404 that matches the prompt 402.

[0029] Without being bound by theory, existing solutions for classification of patterns are based on supervised learning, requiring a potentially large amount of labeled samples for the patterns of interest. Even using strategies such as fine-tuning or meta-learning some amount of labeled samples are typically required. In contrast, embodiments described herein can perform zero-shot classification based on a prompt that describes the patterns of interest. Therefore, industrial tasks may be performed even when no labels or no historical data is available. This can represent a significant benefit in terms of data requirements and efficiency of solutions. Furthermore, embodiments can enable the implementation of time series analytics in situations where a solution would otherwise not be possible due to the lack historical of data. Further still, existing TSFMs might obtain the context of the task directly from the time series data provided as input. In accordance with various embodiments, however, additional context is provided via multi-modal prompting from the user to the TSFM 107, thereby incorporating domain knowledge to improve inference results.

[0030] Thus, as described herein, an analytics industrial computer system can include a sensor configured to capture real samples of data from a physical system. The computer system can further include a memory storing instructions that, when executed by the processor, cause the processor to perform various operations. The operations can include obtaining the real samples of data, wherein the data is associated with an industrial task. The operations can further include receiving a prompt from a user of the computer system, wherein the prompt is indicative of a pattern of interest. Based on the real samples of data and the prompt, the computer system can generate an output that identifies portions of the realsamples of data that exhibit the pattern of interest, so as to define an identified pattern. Based on the identified pattern, the system can trigger a performance of the industrial task. For example, the identification of specific patterns can drive or trigger operations and maintenance decisions or actions.

[0031] In another example aspect, the computer system can generate a plurality of tokens from the prompt. The system can input the plurality of tokens into a time series foundation model (TSFM) defined by the system, such that the TSFM determines the identified pattern. The plurality of tokens can define one or more prompt tokens that indicate information associated with the industrial task. The plurality of tokens can also define one or more sequence tokens that indicate information associated with real samples of data. The plurality of tokens can also define a classify token that indicates a type of task corresponding to the industrial task. In various examples, the prompt includes text or an image that describes the pattern of interest, so as to define the prompt in a semi-structured format.

[0032] FIG. 3 illustrates an example of a computing environment within which embodiments of the present disclosure may be implemented. A computing environment 500 includes a computer system 510 that may include a communication mechanism such as a system bus 521 or other communication mechanism for communicating information within the computer system 510. The computer system 510 further includes one or more processors 520 coupled with the system bus 521 for processing the information. The analytics computer system 106 may include, or be coupled to, the one or more processors 520.

[0033] The processors 520 may include one or more central processing units (CPUs), graphical processing units (GPUs), or any other processor known in the art. More generally, a processor as described herein is a device for executing machine-readable instructions stored on a computer readable medium, for performing tasks and may comprise any one or combination of, hardware and firmware. A processor may also comprise memory storing machine-readable instructions executable for performing tasks. A processor acts upon information by manipulating, analyzing, modifying, converting or transmitting information for use by an executable procedure or an information device, and / or by routing the information to an output device. A processor may use or comprise the capabilities of a computer, controller or microprocessor, for example, and be conditioned using executable instructions to perform special purpose functions not performed by a general purpose computer. A processor may include any type of suitable processing unit including, but not limited to, a central processing unit, a microprocessor, a Reduced Instruction Set Computer (RISC) microprocessor, a Complex Instruction Set Computer (CISC) microprocessor, a microcontroller, an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), a System-on-a-Chip (SoC), a digital signal processor (DSP), and so forth. Further, the processor(s) 520 may have any suitable microarchitecture design that includes any number of constituent components such as, for example, registers, multiplexers, arithmetic logic units, cache controllers for controlling read / write operations to cache memory, branch predictors, or the like. The microarchitecture design of the processor may be capable of supporting any of a variety of instruction sets. A processor may be coupled (electrically and / or as comprising executable components) with any other processor enabling interaction and / or communication therebetween. A user interface processor or generator is a known element comprising electronic circuitry or software or a combination of both for generating display images or portions thereof. A user interface comprises one or more display images enabling user interaction with a processor or other device.

[0034] The system bus 521 may include at least one of a system bus, a memory bus, an address bus, or a message bus, and may permit exchange of information (e.g., data (including computer-executable code), signaling, etc.) between various components of the computer system 510. The system bus 521 may include, without limitation, a memory bus or a memory controller, a peripheral bus, an accelerated graphics port, and so forth. The system bus 821 may be associated with any suitable bus architecture including, without limitation, an Industry Standard Architecture (ISA), a Micro Channel Architecture (MCA), an Enhanced ISA (EISA), a Video Electronics Standards Association (VESA) architecture, an Accelerated Graphics Port (AGP) architecture, a Peripheral Component Interconnects (PCI) architecture, a PCI-Express architecture, a Personal Computer Memory Card International Association (PCMCIA) architecture, a Universal Serial Bus (USB) architecture, and so forth.

[0035] Continuing with reference to FIG. 3, the computer system 510 may also include a system memory 530 coupled to the system bus 521 for storing information and instructions to be executed by processors 520. The system memory 530 may include computer readable storage media in the form of volatile and / or nonvolatile memory, such as read only memory (ROM) 531 and / or random access memory (RAM) 532. The RAM 532 may include other dynamic storage device(s) (e.g., dynamic RAM, static RAM, and synchronous DRAM). The ROM 531 may include other static storage device(s) (e.g., programmable ROM, erasable PROM, and electrically erasable PROM). In addition, the system memory 530 may be used for storing temporary variables or other intermediate information during the execution of instructions by the processors 520. A basic input / output system 533 (BIOS) containing the basic routines that help to transfer information between elements within computer system 510, such as during start-up, may be stored in the ROM 531. RAM 532 may contain data and / or program modules that are immediately accessible to and / or presently being operated on by theprocessors 520. System memory 530 may additionally include, for example, operating system 534, application programs 535, and other program modules 536. Application programs 535 may also include a user portal for development of the application program, allowing input parameters to be entered and modified as necessary.

[0036] The operating system 534 may be loaded into the memory 530 and may provide an interface between other application software executing on the computer system 510 and hardware resources of the computer system 510. More specifically, the operating system 534 may include a set of computer-executable instructions for managing hardware resources of the computer system 510 and for providing common services to other application programs (e.g., managing memory allocation among various application programs). In certain example embodiments, the operating system 534 may control execution of one or more of the program modules depicted as being stored in the data storage 540. The operating system 534 may include any operating system now known or which may be developed in the future including, but not limited to, any server operating system, any mainframe operating system, or any other proprietary or non-proprietary operating system.

[0037] The computer system 510 may also include a disk / media controller 543 coupled to the system bus 521 to control one or more storage devices for storing information and instructions, such as a magnetic hard disk 541 and / or a removable media drive 542 (e.g., floppy disk drive, compact disc drive, tape drive, flash drive, and / or solid state drive). Storage devices 540 may be added to the computer system 510 using an appropriate device interface (e.g., a small computer system interface (SCSI), integrated device electronics (IDE), Universal Serial Bus (USB), or FireWire). Storage devices 541 , 542 may be external to the computer system 510.

[0038] The computer system 510 may also include a field device interface 565 coupled to the system bus 521 to control a field device 566, such as a device used in a production line. The computer system 510 may include a user input interface or GUI 561 , which may comprise one or more input devices, such as a keyboard, touchscreen, tablet and / or a pointing device, for interacting with a computer user and providing information to the processors 520.

[0039] The computer system 510 may perform a portion or all of the processing steps of embodiments of the invention in response to the processors 520 executing one or more sequences of one or more instructions contained in a memory, such as the system memory 530. Such instructions may be read into the system memory 530 from another computer readable medium of storage 540, such as the magnetic hard disk 541 or the removable media drive 542. The magnetic hard disk 541 (or solid state drive) and / or removable media drive 542 may contain one or more data stores and data files used by embodiments of the presentdisclosure. The data store 540 may include, but are not limited to, databases (e.g., relational, object-oriented, etc.), file systems, flat files, distributed data stores in which data is stored on more than one node of a computer network, peer-to-peer network data stores, or the like. The data stores may store various types of data such as, for example, skill data, sensor data, or any other data generated in accordance with the embodiments of the disclosure. Data store contents and data files may be encrypted to improve security. The processors 520 may also be employed in a multi-processing arrangement to execute the one or more sequences of instructions contained in system memory 530. In alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions. Thus, embodiments are not limited to any specific combination of hardware circuitry and software.

[0040] As stated above, the computer system 510 may include at least one computer readable medium or memory for holding instructions programmed according to embodiments of the invention and for containing data structures, tables, records, or other data described herein. The term “computer readable medium” as used herein refers to any medium that participates in providing instructions to the processors 520 for execution. A computer readable medium may take many forms including, but not limited to, non-transitory, non-volatile media, volatile media, and transmission media. Non-limiting examples of non-volatile media include optical disks, solid state drives, magnetic disks, and magneto-optical disks, such as magnetic hard disk 541 or removable media drive 542. Non-limiting examples of volatile media include dynamic memory, such as system memory 530. Non-limiting examples of transmission media include coaxial cables, copper wire, and fiber optics, including the wires that make up the system bus 521. Transmission media may also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications.

[0041] Computer readable medium instructions for carrying out operations of the present disclosure may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, statesetting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may bemade to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0042] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, may be implemented by computer readable medium instructions.

[0043] The computing environment 500 may further include the computer system 510 operating in a networked environment using logical connections to one or more remote computers, such as remote computing device 580. The network interface 570 may enable communication, for example, with other remote devices 580 or systems and / or the storage devices 541 , 542 via the network 571 . Remote computing device 580 may be a personal computer (laptop or desktop), a mobile device, a server, a router, a network PC, a peer device or other common network node, and typically includes many or all of the elements described above relative to computer system 510. When used in a networking environment, computer system 510 may include modem 572 for establishing communications over a network 571 , such as the Internet. Modem 572 may be connected to system bus 521 via user network interface 570, or via another appropriate mechanism.

[0044] Network 571 may be any network or system generally known in the art, including the Internet, an intranet, a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a direct connection or series of connections, a cellular telephone network, or any other network or medium capable of facilitating communication between computer system 510 and other computers (e.g., remote computing device 580). The network 571 may be wired, wireless or a combination thereof. Wired connections may be implemented using Ethernet, Universal Serial Bus (USB), RJ-6, or any other wired connection generally known in the art. Wireless connections may be implemented using Wi-Fi, WiMAX, and Bluetooth, infrared, cellular networks, satellite or any other wireless connection methodology generally known in the art. Additionally, several networks may work alone or in communication with each other to facilitate communication in the network 571.

[0045] It should be appreciated that the program modules, applications, computerexecutable instructions, code, or the like depicted in FIG. 3 as being stored in the system memory 530 are merely illustrative and not exhaustive and that processing described as being supported by any particular module may alternatively be distributed across multiple modules or performed by a different module. In addition, various program module(s), script(s), plug-in(s), Application Programming Interface(s) (API(s)), or any other suitable computer-executable code hosted locally on the computer system 510, the remote device 580, and / or hosted on other computing device(s) accessible via one or more of the network(s) 571 , may be provided to support functionality provided by the program modules, applications, or computer-executable code depicted in FIG. 3 and / or additional or alternate functionality. Further, functionality may be modularized differently such that processing described as being supported collectively by the collection of program modules depicted in FIG. 3 may be performed by a fewer or greater number of modules, or functionality described as being supported by any particular module may be supported, at least in part, by another module. In addition, program modules that support the functionality described herein may form part of one or more applications executable across any number of systems or devices in accordance with any suitable computing model such as, for example, a client-server model, a peer-to-peer model, and so forth. In addition, any of the functionality described as being supported by any of the program modules depicted in FIG. 3 may be implemented, at least partially, in hardware and / or firmware across any number of devices.

[0046] It should further be appreciated that the computer system 510 may include alternate and / or additional hardware, software, or firmware components beyond those described or depicted without departing from the scope of the disclosure. More particularly, it should be appreciated that software, firmware, or hardware components depicted as forming part of the computer system 510 are merely illustrative and that some components may not be present or additional components may be provided in various embodiments. While various illustrative program modules have been depicted and described as software modules stored in system memory 530, it should be appreciated that functionality described as being supported by the program modules may be enabled by any combination of hardware, software, and / or firmware. It should further be appreciated that each of the above-mentioned modules may, in various embodiments, represent a logical partitioning of supported functionality. This logical partitioning is depicted for ease of explanation of the functionality and may not be representative of the structure of software, hardware, and / or firmware for implementing the functionality. Accordingly, it should be appreciated that functionality described as being provided by a particular module may, in various embodiments, be provided at least in part byone or more other modules. Further, one or more depicted modules may not be present in certain embodiments, while in other embodiments, additional modules not depicted may be present and may support at least a portion of the described functionality and / or additional functionality. Moreover, while certain modules may be depicted and described as sub-modules of another module, in certain embodiments, such modules may be provided as independent modules or as sub-modules of other modules.

[0047] Although specific embodiments of the disclosure have been described, one of ordinary skill in the art will recognize that numerous other modifications and alternative embodiments are within the scope of the disclosure. For example, any of the functionality and / or processing capabilities described with respect to a particular device or component may be performed by any other device or component. Further, while various illustrative implementations and architectures have been described in accordance with embodiments of the disclosure, one of ordinary skill in the art will appreciate that numerous other modifications to the illustrative implementations and architectures described herein are also within the scope of this disclosure. In addition, it should be appreciated that any operation, element, component, data, or the like described herein as being based on another operation, element, component, data, or the like can be additionally based on one or more other operations, elements, components, data, or the like. Accordingly, the phrase “based on,” or variants thereof, should be interpreted as “based at least in part on.”

[0048] Although embodiments have been described in language specific to structural features and / or methodological acts, it is to be understood that the disclosure is not necessarily limited to the specific features or acts described. Rather, the specific features and acts are disclosed as illustrative forms of implementing the embodiments. Conditional language, such as, among others, “can,” “could,” “might,” or “may,” unless specifically stated otherwise, or otherwise understood within the context as used, is generally intended to convey that certain embodiments could include, while other embodiments do not include, certain features, elements, and / or steps. Thus, such conditional language is not generally intended to imply that features, elements, and / or steps are in any way required for one or more embodiments or that one or more embodiments necessarily include logic for deciding, with or without user input or prompting, whether these features, elements, and / or steps are included or are to be performed in any particular embodiment.

[0049] The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion ofinstructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustration, and combinations of blocks in the block diagrams and / or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

Claims

CLAIMSWhat is claimed is:1 . An analytics computer system, comprising: a sensor configured to capture real samples of data from a physical system; a memory storing instructions that, when executed by the processor, cause the processor to: obtain the real samples of data, the data associated with an industrial task; receive a prompt from a user of the computer system, the prompt indicative of a pattern of interest; based on the real samples of data and the prompt, generate an output that identifies portions of the real samples of data that exhibit the pattern of interest, so as to define an identified pattern; and based on the identified pattern, trigger a performance of the industrial task.

2. The system as recited in claim 1 , the memory further storing instructions that, when executed by the processor, cause the processor to: generate a plurality of tokens from the prompt; and input the plurality of tokens into a time series foundation model (TSFM) defined by the system, such that the TSFM determines the identified pattern.

3. The system as recited in claim 2, wherein the plurality of tokens define one or more prompt tokens that indicate information associated with the industrial task.

4. The system as recited in claim 2, wherein the plurality of tokens define one or more sequence tokens that indicate information associated with real samples of data.

5. The system as recited in claim 2, wherein the plurality of tokens define a classify token that indicates a type of task corresponding to the industrial task.

6. The system as recited in any one of the preceding claims, wherein the prompt includes text or an image that describes the pattern of interest, so as to define the prompt in a semistructured format.

7. A method performed by an analytics computer system, the method comprising: obtaining real samples of data from a physical system, the data associated with an industrial task; receiving a prompt from a user of the computer system, the prompt indicative of a pattern of interest; based on the real samples of data and the prompt, generate an output that identifies portions of the real samples of data that exhibit the pattern of interest, so as to define an identified pattern; and based on the identified pattern, trigger a performance of the industrial task.

8. The method as recited in claim 7, the method further comprising: generating a plurality of tokens from the prompt; and inputting the plurality of tokens into a time series foundation model (TSFM), such that the TSFM determines the identified pattern.

9. The method as recited in claim 8, wherein the plurality of tokens define one or more prompt tokens that indicate information associated with the industrial task.

10. The method as recited in claim 8, wherein the plurality of tokens define one or more sequence tokens that indicate information associated with real samples of data.11 . The method as recited in claim 8, wherein the plurality of tokens define a classify token that indicates a type of task corresponding to the industrial task.

12. The method as recited in any one of claims 7 to 11 , wherein the prompt includes text or an image that describes the pattern of interest, so as to define the prompt in a semi-structured format.

13. A non-transitory computer-readable medium encoded with executable instructions that, when executed, cause one or more computer systems to perform a process as in any one of claims 7 to 11 .

Images