ARTIFICIAL INTELLIGENCE IN TESTING AND MEASURING ENVIRONMENTS

Abstract

A test and measurement system comprises one or more test and measurement devices, at least one of which is connected to a device under test (DUT), one or more memories, a generative artificial intelligence model (generative AI model) connected to the one or more test and measurement devices and the one or more memories, and one or more processors to provide an artificial intelligence assistant (AI assistant) as an interface to the generative AI model, to provide a user interface that allows a user to enter a prompt, to use the AI ​​assistant to translate the prompt into one or more queries for the generative AI model, and to send commands to the test and measurement device connected to the DUT to perform one or more tests on the DUT.To take the results from one or more tests and convert them into user-interpretable results, and to provide the user with the results from the input prompt in the user interface.

Description

CROSS-REFERENCE TO RELATED REGISTRATIONS

[0001] This disclosure claims priority under 35 USC § 119 of Indian Provisional Patent Application No. 202421072357 entitled “AI ASSISTANT FOR CUSTOM VISUALIZATION, ANALYTICS, AND DATA TRANSFORMATION”, filed on September 25, 2024, and is a non-provisional application of and claims the benefits of US Provisional Patent Application No. 63 / 709,375, entitled “SIGNAL ANALYSIS AND SIGNAL GENERATION USING ARTIFICIAL INTELLIGENCE AND LARGE LANGUAGE MODELS”, filed on October 18, 2024, the disclosures of which are incorporated herein by reference in full. AREA OF TECHNOLOGY

[0002] This disclosure relates to test and measurement systems, in particular test and measurement systems that use artificial intelligence for adaptable signal analysis, signal generation and data visualization. BACKGROUND

[0003] Designers and test engineers use test and measurement equipment in fields such as aerospace, automotive, defense, and electronics to debug, validate, and perform quality control on devices under test. These tests verify compliance with standards, detect defects, measure performance, and many other parameters and characteristics.

[0004] However, existing solutions limit the user's ability to analyze and visualize the provided signals based on the data schema provided by the system. This results in a fixed and limited analysis for the user, restricting their ability to analyze the data according to their specific needs.

[0005] Current testing tools can perform specific types of analysis, such as signal measurements, protocol decoding, triggering, searching, graphing, annotating, signal generation, and code embedding / de-embedding. The user selects the tools based on a test scenario to troubleshoot a problem, validate a device, and so on. The traditional approach assumes the user understands how the tools work, how to use them, and is familiar with the specification they are working with. While current systems can handle structured queries, they have rigid structures, are predefined, and lack flexibility. BRIEF DESCRIPTION OF THE DRAWINGS Fig. Figure 1 shows a schematic representation of an embodiment of a test and measurement system. Fig. Figure 2 shows an example of a complex system. Fig. Figure 3 shows a training example of a process flow for an AI-supported test and measurement system. Fig. Figure 4 shows a diagram of layers of signal analysis. Fig. Figure 5 shows a diagram of a signal with reference points. Fig. Figure 6 shows a diagram with definitions of the physical layer. Fig. Figure 7 shows a diagram of a decoding layer. Fig. Figures 8-13 show images of a response to a prompt in an AI-supported testing and measurement system. DESCRIPTION

[0006] The present embodiments employ an AI assistant to allow the user to customize the presentation, visualization, and storage of data. These embodiments enable the user to utilize prompts and a test and measurement environment that describe how data should be annotated, drawn, or stored. The behavior generated by the prompt or a series of prompts can be named, saved, and replayed. Behavioral patterns can be created and generalized as templates so that the same actions can be applied to different inputs. These behaviors can be added to the user interface as "built-in" capabilities, also referred to as "tools." The embodiments can take into account the user's environment as context-specific capabilities.For example, if the device uses an I2C protocol and the prompt is "Divide the devices to be tested into task areas," the AI ​​assistant knows that each device has a unique address and that the user wants to display the addresses in their own time-controlled, "shielded" track area. The AI ​​assistant provides an environment where functions can be mixed, matched, and combined in new ways. Adding new capabilities expands the range of available behaviors.

[0007] The implementations provide these behaviors—that is, the way the various devices and other resources in the test and measurement environment behave—in the form of "tools." A tool, as used here, refers to a set of operations, devices, or other resource behaviors and / or capabilities that the user can access as needed to achieve the goals of testing and measuring the performance of all aspects of a complex system. Currently, vendors provide users of their systems with tools that allow the user to perform tasks or cause the system to behave in specific ways.These tools assume that the user knows how the tools work, that they know how to use the tool, and that they understand the respective test specification or protocol well enough to know whether the device(s) are working correctly.

[0008] The AI ​​assistant and its underlying generative AI model, such as a rich language model, access the specification(s) for training and can then create the necessary tools based on the specification. In one embodiment, the tools can name objects when applied to a signal being analyzed. The AI ​​assistant knows the tools and their capabilities and, as mentioned above, can combine, mix, and adapt the tools as needed, based on the user query / input prompt. The tools can create a point solution to resolve a customer-specific problem, provide an analysis of data of a specific type or from a specific source, and present the results and / or data in a user-friendly manner.Essentially, the user interacts with the AI ​​assistant, and the AI ​​assistant collects the necessary data and communicates with the user using the tools developed by the AI ​​assistant.

[0009] The following terms are used here with specific definitions. The term "user prompt" refers to the user's input into the AI ​​assistant's user interface. The term "query" is a structured request sent to analysis and rendering engines with precise instructions on what to do with the available measurement data. Queries work with a pool of information from sources that include, but are not limited to, oscilloscope channels receiving data, mathematical functions, protocol decoding, collections of measurements, search results, spectral data, stored files, and data from multiple connected devices.

[0010] The term "analysis engine" refers to a software component that processes input data, applies specific rules or algorithms, and outputs the results. Often, the data is transformed from one format, structure, or representation to another to enable further use or insight. The analysis engine selects the data source, such as which channels on which devices, processes operations like calculations, statistical analyses, and filtering, and, if necessary, compares the results against specifications for compliance. The term "rendering engine" refers to a software component that transforms the processed output of an analysis engine into a visual form, such as charts, graphs, illustrations, or interactive displays, so that humans can easily interpret the data. It displays or presents the results of the analysis engine.This can include diagrams, task fields, waveforms with and without annotations, color coding, as well as layout and display parameters.

[0011] As mentioned previously, current queries must adhere to very specific formats and name the various components and parameters. The AI ​​Assistant and the generative AI process function quite differently. The AI ​​Assistant analyzes the user's input to determine the data sources, analysis needs, and display requirements. It uses knowledge of current devices, protocols, available data, and data sources as context for the user's input. The AI ​​Assistant then generates the analysis and display queries in the correct format and with the correct content for the specified parameters derived from the user's input. The AI ​​Assistant can also use saved query patterns and available tools, as well as save new query patterns as templates for later use.

[0012] Regarding tools, the AI ​​assistant can use existing tools and / or create "generated" tools from the system's available capabilities, rather than relying on fixed, pre-programmed measurement functions. The AI ​​assistant can create and use modular tools that can be linked together as needed, with each tool performing a specific task and passing the results of that task to the next tool. Examples include period detectors, RMS measurements (RMS = Root Mean Square), various error measurements and detectors, and swim-lane rendering, which is the creation of visual displays with separate areas for data streams.The AI ​​assistant automatically selects the correct measurement tools, connects them as needed in user-defined sequences, sets the appropriate parameters, generates the structured query(s), and then executes the measurement chain.

[0013] For example, the user could enter the prompt "Measure power consumption during each clock cycle," and the AI ​​assistant would break this down into "Find clock periods → Measure RMS power → Display results." A more complex prompt might be "Display communication errors sorted by device address," which the AI ​​assistant would break down as follows: "Decode protocol data → Find errors → Group by address → Create visual display." These are just a few examples; more are listed below.

[0014] Fig. Figure 1 shows a system diagram of a test and measurement system with an AI assistant 16. The user 12 interacts with the AI ​​assistant 16 via a test and measurement device 14, such as an oscilloscope. Alternatively, the user 12 can interact with the device 14 via the AI ​​assistant 16 on a separate computing device. The user 12 would access the AI ​​assistant 16 on a computer device 15, which is then connected to the device 14, representing multiple devices with which the AI ​​assistant 16 can be connected. The AI ​​assistant has a programming interface (API) for accessing a generative AI model 18, such as a large language model (LLM), a large multimodal model (LMM), or another generative AI model.

[0015] Model 18 undergoes training that may encompass all or some of the topics in the knowledge set 20. This enables the model to interact with the user via a speech recognition interface, such as natural language processing (NLP), and to recognize the words used by the user 12 when the user makes a request to the AI ​​system. The AI ​​assistant 16 can provide the user interface for Model 18 and may have its own speech recognition interface, as well as access to some or all of the knowledge from the knowledge set 20.

[0016] When the user enters 12 requests in the form of prompts, the AI ​​assistant 16 sends these prompts to the model as queries, if necessary. The AI ​​assistant 16 can also operate independently of the model, depending on the situation, as explained in more detail below. As explained in more detail below, user interactions, such as prompts that are converted into commands and queries, results, etc., can be stored in data storage 28.

[0017] In some embodiments, the AI ​​assistant and / or the model can use various tools from the toolset 22. The system may already possess these tools, referred to here as "pre-existing tools," such as the rendering engine 24 and the analysis engine 26. Others may be generated and stored by the AI ​​assistant, referred to here as "generated tools," including additions to pre-existing tools. For example, the rendering engine may generate certain data displays so that the user can see the results, and the AI ​​assistant may create other tools for these displays, such as annotations, charts, etc.The use of the AI ​​Assistant 16 and Model 18 enables the system to translate between signals and data received from devices under test (DUTs) and deliver contextual and human-interpretable results and analyses, allowing the user to measure, analyze, debug, and perform other tasks on complex systems. The AI ​​Assistant can utilize existing tools in new and unique ways, combine them, create and utilize generated tools in new and unique ways, and blend and match existing and generated tools to create new workflows as needed.

[0018] As an example, without limitation, shows Fig. 2 a part 30 of a complex system that requires at least one of the functions of testing, measuring, and troubleshooting. In this example, the system comprises a motor vehicle. In addition to the various components shown, the system includes three different types of buses. The solid lines indicate components that communicate via a Controller Area Network (CAN) 32, such as the central body control 36 and additional powertrain systems 34, as well as simpler devices such as the door lock 38. The dashed lines indicate components that communicate via a Local Interconnect Network (LIN) 40, such as the door panel controls 42 and the associated motor 44 on the passenger-side mirror 46. The dashed lines indicate components that communicate via a Media-Oriented System Transport System (MOST system) 48, such as the digital radio 50 and the loudspeaker 52.Although this diagram only shows a portion of the components, systems, and buses, it highlights the complexity of the test and measurement environment and illustrates how the use of an AI-powered assistant would help with conducting tests, acquiring data, analyzing data, and subsequently presenting the results on a user interface, for example, by displaying graphs, measurements, values, etc.

[0019] Fig. Figure 3 shows an embodiment of a process in which the AI ​​assistant processes a user prompt to analyze and display information from one or more test and measurement devices. As mentioned earlier, the AI ​​assistant can load knowledge prior to each user interaction. This knowledge can include, but is not limited to, device knowledge for the device(s) in the test and measurement system, analytical knowledge about the various forms of analysis and any calculations or operations performed as part of the analysis, rendering knowledge about how to render the results, and device configuration knowledge about how to train and operate the devices as needed. This can include SCPI commands (standard commands for programmable devices), IP addresses for the devices, and so on.

[0020] The user specifies the configuration and submits a prompt for analysis. The AI ​​assistant then analyzes the prompt to generate an analysis query and a rendering query. The AI ​​assistant then retrieves the data from the measuring device, either on request or by accessing the device. The data can then be stored in the data store. The AI ​​assistant then submits the analysis query to the analysis engine. The analysis engine can be a task performed by the AI ​​model or an existing software program that performs the analysis specified in the query.

[0021] In response to the query, the analysis engine accesses the input, either from the data store or from another location where the AI ​​assistant has stored the data. The analysis engine then processes the analysis query and stores the analysis data in the data store.

[0022] The AI ​​assistant then sends the rendering request to the rendering engine. The rendering engine accesses the analysis data and renders it on a user interface so the user can see the results. The user can then save the data by sending it to a data serialization tool.

[0023] An important aspect of the process described above lies in the nature of the device data and the role of the AI ​​assistant, which transforms the meaning of the signals or data captured by the device and puts them into a form that is interpretable and understandable for humans.

[0024] Fig. Figure 4 shows the path of a signal received by a measuring instrument to a final measurement that a user can understand. The first layer is the signal layer. The signal could be, for example, a change in voltage or current over a specific period, represented by the length of the signal. The PHY, or physical layer, converts the signal into a digital representation of the analog signal. The decoding layer then converts the signal on the PHY layer into bit sequences based on a specific protocol, such as a communication protocol. The original signal was generated in accordance with this protocol, and during the conversion, the signal is brought into the correct format for the protocol. In this way, the signal can be compared with the test procedure to determine whether the signal meets the compliance requirements.

[0025] Fig. Figure 5 shows an example of an analog signal and the various characteristics of the signal that are important for its analysis. These characteristics and reference points can be important for the performance of the device under test (DUT) that generated it. The performance of the DUT is generally measured according to the test procedure.

[0026] Fig. Figure 6 shows the resulting conversion of the physical layer of the main reference points from the signal of Fig. 5. The elements shown in the diagram represent the reference points that define the characteristics of the signal. For example, T refers to LPX on a timing parameter that relates to a transition from low-power mode (LP) to high-speed mode. The observable feature may require that T LPX is greater than a certain value.

[0027] Fig. Figure 7 shows the decoding process that is performed to convert the physical definitions in the PHY layer into bit sequences based on a protocol definition. The various fields and bits of the protocol definition are used to represent the signals of a bus, as described in Fig. The information described in section 2 must be translated into meaningful bit sequences. These bit sequences must then be translated into something that humans can understand, such as the content in... Fig. 4 is shown.

[0028] The process of achieving this result becomes much easier for the user when they use the AI ​​assistant, as in Fig. Figure 2 shows the embodiment of the message flow. Fig. Figures 8-13 show similar results to the content level of Fig. 4 in response to various prompts.

[0029] The user can interact with the vehicle's sensors, such as those measuring temperature, pressure, and oxygen. In this example, these sensors are connected to the vehicle's CAN bus, should the user wish to analyze, visualize, and debug the data communication on the CAN bus.

[0030] Fig. 8 shows the response to a user query, "Show me the frames for the devices." <temperatur> , <druck>and <sauerstoff>in Areas of responsibility. Show <datenrahmen>in<Weiß> and telescopic frames in <grau>"

[0031] As in Fig. As shown in Figure 8, the temperature, pressure, and oxygen readings from the bus have been decoded and are displayed to the user in an easy-to-understand diagram. The data for Figure 60, within a temperature range of 22°C, are shown as a sample in the figure.

[0032] Fig. Figure 9 shows the results of a query that read, "Show me the data for the devices in<lesbarem Format> together with <eingangssignal>and<dekodierten Daten> "

[0033] The readable data is displayed in the top line, the decoding in the middle, and the input signals at the bottom.

[0034] Fig. Figure 10 shows the results of a command prompt that read, "Show me the <temperatur>- and <sauerstoff>-Frame with errors and draw them in <rot>"

[0035] In Fig. The grey represents red, and the frames corresponding to the prompt are not red, but patterned, e.g. 62.

[0036] Fig. 11 shows the results of a command prompt that read, "Comment on the images with errors whose <anstiegsszeit><außerhalb der Boundaries> lies.<inneren Grenzen> are <10ns> to <20ns>."

[0037] The two in Fig. The 11 frames shown with the dashed boxes (e.g. 64) are outside the limits.

[0038] Fig. Figure 12 shows the results of the following command prompt, which read: "Add the wave shapes for the frames with <anstiegs>-errors."

[0039] As in Fig. As can be seen in 12, the two waveforms with the slightly more pronounced lines at 66 and 68 can be seen, which indicate the rise time errors.

[0040] Fig. Figure 13 shows a scatter plot in response to the prompt: "Show me the data between <temperatur>and <druck>based on a scatter plot."

[0041] Another example: The AI ​​assistant could be asked to monitor something over a specific period. For example: "Show me the statistics of <temperatur>Continue monitoring for the next 1 hour and save the data under <dateiname>".

[0042] The result could be the following table: Address 101 Mittelwert (Grad C) 30 Grad C Median (Grad C) 43 Grad C Maximum (Grad C) 45 Grad C Minimum (Grad C) 10 Grad C

[0043] In this way, users can communicate with the device in natural language and query data in various formats, enabling faster understanding, problem-solving, and troubleshooting. The AI ​​assistant highlights errors and presents data clearly. Users can analyze the data in the context of its structure. The approach detects anomalies in the underlying layers and presents errors in a higher-level language and visual representations. The prompts are transformed into queries and commands, such as the prompt above to monitor for one hour, which can be saved for use as a template. The AI ​​assistant can also create a monitoring tool, which the user does not see, but which further accelerates the AI ​​assistant's processes.The AI ​​assistant dynamically generates new combinations of measurement tools based on natural language input, enabling customized measurement and analysis workflows that are not possible with current fixed user interfaces.

[0044] In this way, an AI assistant in conjunction with a generative AI model can make the test and measurement environment far more user-friendly and enable a better understanding of problems that arise when testing, analyzing and debugging DUTs, whether they are simple DUTs or DUTs in complex environments with multiple protocols and standards involved.

[0045] Aspects of the disclosure may operate on specially designed hardware, firmware, digital signal processors, or on a specially programmed general-purpose computer with a processor that operates according to programmed instructions. The terms "controller" or "processor" as used here are intended to include microprocessors, microcomputers, application-specific integrated circuits (ASICs), and specialized hardware controllers. One or more aspects of the disclosure may be embodied in computer-usable data and computer-executable instructions, such as in one or more program modules executed by one or more computers (including monitoring modules) or other devices. In general, program modules include routines, programs, objects, components, data structures, and so on.These are instructions that perform specific tasks or implement certain abstract data types when executed by a processor in a computer or other device. The computer-executable instructions can be stored on a non-transient, computer-readable medium such as a hard disk, optical disk, removable storage medium, solid-state memory, random access memory (RAM), etc. As will be clear to those skilled in the art, the functionality of the program modules can be arbitrarily combined or distributed in various aspects. Furthermore, the functionality can be embodied wholly or partially in firmware or hardware equivalents such as integrated circuits, FPGAs, and the like.Certain data structures can be used to implement one or more aspects of the disclosure more effectively, and such data structures are considered within the context of the computer-executable instructions and computer-usable data described here.

[0046] The disclosed aspects may, in some cases, be implemented in hardware, firmware, software, or a combination thereof. The disclosed aspects may also be implemented in the form of instructions stored on one or more non-transitory, computer-readable media that can be read and executed by one or more processors. Such instructions may be referred to as a computer program product. Computer-readable media, as described here, are any media accessible to a computing device. Computer-readable media may include, but are not limited to, computer storage media and communication media.

[0047] Computer storage media are all media that can be used to store computer-readable information. Examples of computer storage media include RAM, ROM, EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory or other storage technologies, CD-ROM (Compact Disc Read Only Memory), DVD (Digital Video Disc) or other optical disc storage, magnetic cartridges, magnetic tapes, magnetic disk storage or other magnetic storage media, as well as any other volatile or non-volatile, removable or non-removable media used in any technology. Computer storage media exclude signals as such and temporary forms of signal transmission.

[0048] Communication media are all media that can be used to transmit computer-readable information. Examples of communication media include coaxial cables, fiber optic cables, air, or any other medium suitable for transmitting electrical, optical, radio frequency (RF), infrared, acoustic, or other signals. EXAMPLES

[0049] Examples of the disclosed technologies are listed below. An embodiment of the technologies may include one or more, and any combination of, the examples described below.

[0050] Example list a test and measurement system comprising the following: one or more test and measurement devices, including at least one test and measurement device with one or more ports for connecting the at least one test and measurement device to a device under test (DUT); one or more memories containing test and measurement knowledge; a generative artificial intelligence model (generative AI model) connected to the one or more test and measurement devices and the one or more memories; one or more processors trained to execute code that causes the one or more processors to provide an artificial intelligence assistant (AI assistant) as an interface to the generative AI model; and a user interface that allows a user to input a prompt for interpretation by the AI ​​assistant.to use the AI ​​assistant to translate the input prompt into one or more queries for the generative AI model; to send commands to at least one of the test and measurement devices to perform one or more tests on the DUT in response to the input prompt; to take results from the one or more tests and convert them into user-interpretable results; and to provide the user with results from the input prompt in the user interface.

[0051] Example 2 is the test and measurement system from Example 1, wherein the one or more processors are further configured to execute code to cause the one or more processors to provide information about an environment of the test and measurement system to the AI ​​assistant.

[0052] Example 3 is the test and measurement system from Example 2, wherein the code that causes the one or more processors to provide information about the environment to the AI ​​assistant includes code that causes the AI ​​assistant to access one or more of the following information: test specifications, general test and measurement knowledge, knowledge of specific devices in the environment, analysis knowledge, rendering knowledge, and knowledge of one or more devices and systems being tested in the environment.

[0053] Example 4 is the test and measurement system from one of Examples 1 to 3, wherein the one or more processors are further configured to execute code to induce the AI ​​assistant to access one or more pre-existing tools in response to the input prompt.

[0054] Example 5 is the test and measurement system from Example 4, wherein the one or more processors are further configured to execute code to induce the AI ​​assistant to connect one or more of the existing tools in response to the input prompt.

[0055] An example is the test and measurement system from Example 4, where one or more of the existing tools include search, trigger, analysis, rendering, data serialization, measurement, and decoding.

[0056] Example 7 is the test and measurement system from one of Examples 1 to 6, wherein the one or more processors are further configured to execute code to cause the AI ​​assistant to create one or more generated tools in response to the input prompt.

[0057] Example 8 is the test and measurement system from Example 7, wherein the one or more processors are further configured to execute code that causes the AI ​​assistant to integrate the one or more generated tools into a workflow.

[0058] Example 9 is the test and measurement system from one of Examples 1 to 8, wherein the one or more processors are further configured to store the input prompt and the instructions as a template.

[0059] Example 10 is a procedure comprising: providing an AI assistant as an interface to a generative AI model; presenting a user interface that allows a user to input a prompt for interpretation by the AI ​​assistant; using the AI ​​assistant to translate the prompt into one or more queries; sending commands to one or more test and measurement devices in a test and measurement system to perform one or more tests on a device under test (DUT) in response to the prompt; taking results from the one or more tests and converting them into user-interpretable results; and providing results from the prompt to the user interface.

[0060] Example 11 is the procedure of Example 10, which further includes providing the AI ​​assistant with information about the environment of the test and measurement system.

[0061] Example 12 is the procedure from Example 11, wherein providing information about the environment to the AI ​​assistant includes using the AI ​​assistant to access one or more of the following information: test specifications, general testing and measurement knowledge, knowledge of specific devices in the environment, analysis knowledge, rendering knowledge, and knowledge of one or more of the devices and systems being tested in the environment.

[0062] Example 13 is the method claimed in one of Examples 10 to 12, which further comprises using the AI ​​assistant to access one or more pre-existing tools in response to the input prompt.

[0063] Example 14 is the procedure from Example 13, wherein the use of the AI ​​assistant to access one or more existing tools includes using the AI ​​assistant to integrate the existing tools with a new workflow.

[0064] Example 15 is the procedure from Example 13, wherein the one or more existing tools include search, trigger, analysis, rendering, data serialization, measurement, and decoding.

[0065] Example 16 is the procedure according to one of Examples 10 to 15, wherein the AI ​​assistant creates one or more generated tools in response to the input prompt.

[0066] Example 17 is the procedure from Example 16, wherein the creation of the one or more generated tools by the AI ​​assistant includes the integration of the one or more generated tools into a new workflow.

[0067] Example 18 is the procedure from Example 10, which further includes saving the command prompt and the commands as a template.

[0068] The previously described versions of the disclosed item have many advantages, which have either been described or would be obvious to a person with normal knowledge. However, these advantages or features are not necessary in all versions of the disclosed devices, systems, or processes.

[0069] Furthermore, this written description refers to certain features. It is to be assumed that the disclosure in this specification includes all possible combinations of these particular features. If a particular feature is disclosed in connection with a specific aspect or example, this feature may, to the extent possible, also be used in connection with other aspects and examples.

[0070] Where this application refers to a procedure with two or more defined steps or operations, the defined steps or operations may be carried out in any order or simultaneously, provided that the context does not preclude such possibilities.

[0071] Although specific examples of the invention have been presented and described for illustrative purposes, various modifications may be made without affecting the spirit and scope of the invention. Accordingly, the invention should not be limited except by the accompanying claims. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] IN 202421072357

[0001] US 63 / 709,375

[0001] Cited non-patent literature

[0000] AI ASSISTANT FOR CUSTOM VISUALIZATION, ANALYTICS, AND DATA TRANSFORMATION" on September 25, 2024

[0001] < / dateiname> < / temperatur> < / druck> < / temperatur> < / anstiegs> < / anstiegsszeit> < / rot> < / sauerstoff> < / temperatur> < / eingangssignal> < / grau> < / datenrahmen> < / sauerstoff> < / druck> < / temperatur>

Claims

[1] A test and measurement system comprising the following: one or more test and measuring devices, comprising at least one test and measuring device with one or more connections for connecting the at least one test and measuring device to a device under test (DUT); one or more storage devices with testing and measurement capabilities; a generative model for artificial intelligence (generative AI model) that is connected to one or more test and measurement devices and one or more storage devices; one or more processors trained to execute code that causes the one or more processors to do the following: to provide an artificial intelligence assistant (AI assistant) as an interface to the generative AI model; to represent a user interface that allows a user to enter a prompt for interpretation by the AI ​​assistant; to use the AI ​​assistant to translate the input prompt into one or more queries for the generative AI model; Sending commands to at least one of the test and measurement devices to perform one or more tests on the DUT in response to the prompt; to take the results from one or more tests and convert them into user-interpretable results; and to provide the user with the results of the command prompt on the user interface. [2] The test and measurement system according to claim 1, wherein the one or more processors are further configured to execute code to cause the one or more processors to provide information about an environment of the test and measurement system to the AI ​​assistant. [3] The test and measurement system according to claim 2, wherein the code that causes the one or more processors to provide information about the environment to the AI ​​assistant comprises code that causes the AI ​​assistant to access one or more of the following information: test specifications, general test and measurement knowledge, knowledge of specific devices in the environment, analysis knowledge, rendering knowledge, and knowledge of one or more of the devices and systems being tested in the environment. [4] The test and measurement system according to any one of claims 1 to 3, wherein the one or more processors are further configured to execute code to cause the AI ​​assistant to access one or more existing tools in response to the input prompt. [5] The test and measurement system according to claim 4, wherein the one or more processors are further configured to execute code to cause the AI ​​assistant to connect one or more of the existing tools in response to the input prompt. [6] The test and measurement system according to claim 4 or 5, wherein the one or more existing tools comprise search, trigger, analysis, rendering, data serialization, measurement and decoding. [7] The test and measurement system according to any one of claims 1 to 6, wherein the one or more processors are further configured to execute code to cause the AI ​​assistant to generate one or more generated tools in response to the input prompt. [8] The test and measurement system according to claim 7, wherein the one or more processors are further configured to execute code that causes the AI ​​assistant to integrate the one or more generated tools into a workflow. [9] The test and measurement system according to any one of claims 1 to 8, wherein the one or more processors are further configured to store the input prompt and the instructions as a template. [10] A procedure comprising the following: Providing an artificial intelligence assistant (AI assistant) as an interface to a generative AI model; Representing a user interface that allows a user to enter a prompt for interpretation by the AI ​​assistant; Use the AI ​​assistant to translate the prompt into one or more queries; Sending commands to one or more test and measurement devices in a test and measurement system to perform one or more tests on a device under test (DUT) in response to the input prompt; Taking results from one or more tests and converting these results into user-interpretable results; and Providing results from the command prompt to the user interface for the user. [11] The method according to claim 10, further comprising providing the AI ​​assistant with information about an environment of the test and measurement system. [12] The method according to claim 11, wherein providing the AI ​​assistant with information about the environment comprises using the AI ​​assistant to access one or more of the following information: test specifications, general testing and measurement knowledge, knowledge of specific devices in the environment, analysis knowledge, rendering knowledge, and knowledge of one or more of the devices and systems being tested in the environment. [13] The method according to any one of claims 10 to 12, further comprising a use of the AI ​​assistant to access one or more existing tools in response to the input prompt. [14] The method according to claim 13, wherein the use of the AI ​​assistant for accessing one or more tools comprises using the AI ​​assistant to integrate the existing tools into a new workflow. [15] The method according to claim 13 or 14, wherein the one or more existing tools comprise search, trigger, analysis, rendering, data serialization, measurement and decoding. [16] The method according to any one of claims 11 to 15, wherein the AI ​​assistant creates one or more generated tools in response to the input prompt. [17] The method according to claim 16, wherein the creation of the one or more generated tools by the AI ​​assistant comprises the connection of the one or more generated tools in a new workflow by the AI ​​assistant. [18] The method according to any one of claims 11 to 17, further comprising storing the input prompt and the commands as a template.

Images