Test and measurement system and method

Abstract

The artificial intelligence (AI) assistant will allow users to customize how data is represented and visualized. [Solution] The test measurement system 10 includes one or more test measurement devices 14, at least one of which is connected to a device under test (DUT), one or more memories, one or more generating AI models 18 connected to one or more test measurement devices 14, one or more processors, an AI assistant 14 is provided as an interface for the generating AI model, a user interface is displayed that allows the user to input prompts, the AI ​​assistant is used to convert the prompts into one or more queries for the generating AI model, commands are sent to the test measurement devices 14 connected to the DUT to perform one or more tests on the DUT, the results of one or more tests are obtained and converted into results that can be interpreted by the user, and the results of the prompts are provided to the user in the user interface.

Description

Technical Field

[0001] The present disclosure relates to a test measurement system, and more particularly to a test measurement system that uses artificial intelligence for customizable signal analysis, signal generation, and data visualization.

Background Art

[0002] Design engineers and test engineers use test measurement devices in fields such as aerospace, automotive, defense, and electronic devices to perform debugging, verification, quality control, etc. of the device under test. These tests confirm compliance with standards, error detection, performance measurement, and many other parameters and characteristics.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Non-Patent Documents

[0004]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in existing solutions, the user's ability to analyze and visualize the provided signals, which operate based on the data schema provided within the system, is limited. This provides the user with fixed and limited analysis, restricting the user's ability to analyze data according to individual needs.

[0006] Current testing tools handle specific forms of analysis, including signal measurement, protocol decoding, triggering, searching, plotting, annotation, signal generation, and code embedding / de-embedding. Users select tools based on the test scenario they are attempting to debug problems, verify devices, and so on. The traditional approach assumes that users understand how the tools work, how to use them, and their specifications, and that they can perform their tasks using them. Current systems can handle structured queries, but their structure is rigid and predefined, resulting in little flexibility. [Means for solving the problem]

[0007] Embodiments of the present invention enable users to customize how data is represented, visualized, and stored using an artificial intelligence (AI) assistant. These embodiments allow users to utilize prompts and test / measurement environments that guide them on how to annotate, draw, and save data. Actions generated by one or more prompts can be named, saved, and replayed. These actions can be templated and generalized so that the same actions can be applied to various inputs. These actions can be added to the user interface as "built-in" features, also known as "tools." These embodiments can incorporate the environment in which the user is working as context-specific capabilities. For example, if an instrument has an I2C protocol and there is a prompt to "divide multiple devices under test into multiple swim lanes," the AI ​​assistant knows that each device has a unique address and that the user wants to display these addresses in a "tiled" lane format, aligned in time with the addresses themselves. The AI ​​assistant provides an environment in which these capabilities can be combined, matched, and integrated in new ways. The addition of new capabilities is added to a palette of available actions.

[0008] This embodiment considers the operation of various devices and other resources within a test and measurement environment as "tools" and provides such operation (behavior). In this application, a tool refers to a set of operations and capabilities of processes, devices, or other resources that users access as needed to achieve the goal of testing and measuring the performance of all aspects of a complex system. Currently, tools are provided by vendors to users of the vendor's systems, enabling users to perform tasks or operate systems in specific ways. A fundamental assumption of these tools is that the user understands how the tools work, meaning that the user knows how to use the tools and has a sufficient understanding of the specifications and protocols of a particular test to determine whether the device is functioning correctly.

[0009] AI assistants and their underlying generative AI models (such as large-scale language models) can access specifications for training and create the necessary tools based on these specifications. In one example, a tool can name objects when used for signals being analyzed. The AI ​​assistant is aware of these tools and their capabilities, and as described above, can combine, integrate, and match tools as needed based on user queries and prompts. These tools can create one-point solutions to debug specific customer problems, provide analysis of data of specific types and sources, and render results and data in a way that the user can understand. Essentially, the user interacts with the AI ​​assistant, which collects the necessary data and communicates with the user using the tools it has developed. [Brief explanation of the drawing]

[0010] [Figure 1] Figure 1 shows a diagram of an embodiment of the test measurement system. [Figure 2] Figure 2 shows an example of a complex system. [Figure 3] Figure 3 shows an embodiment of the process flow of an AI-assisted test and measurement system. [Figure 4] Figure 4 shows a diagram of the signal analysis layers. [Figure 5] Figure 5 shows a diagram of the signal with points of interest marked. [Figure 6] Figure 6 shows a diagram illustrating the definition of the physical layer. [Figure 7] Figure 7 shows a diagram of the decoding layer. [Figure 8] Figure 8 shows an example of an image of a prompt response in an AI-assisted test measurement system. [Figure 9] Figure 9 shows an example of an image of a prompt response in an AI-assisted test measurement system. [Figure 10] Figure 10 shows an example of an image of a prompt response in an AI-assisted test measurement system. [Figure 11] Figure 11 shows an example of an image of a prompt response in an AI-assisted test measurement system. [Figure 12] Figure 12 shows an example of an image of a prompt response in an AI-assisted test measurement system. [Figure 13] Figure 13 shows an example of an image of a prompt response in an AI-assisted test measurement system. [Modes for carrying out the invention]

[0011] The terms used in this application each have their own specific definitions. "User prompt" or "prompt" refers to what the user inputs into the user interface of the AI assistant. The term "query" is a structured request that includes the exact specification of how to handle the available measurement data and is sent to an analysis engine or a rendering engine. A query operates on a pool of information from information sources including, but not limited to, the channels of an oscilloscope that receives data, mathematical functions, protocol decoding, the population of measurement values, search results, spectral data, saved files, data from multiple connected devices, etc.

[0012] "Analysis engine" refers to a software component that processes input data, applies specific rules or algorithms, and outputs results. The analysis engine often converts data from one form, structure, or representation to another, enabling further utilization and insights. The analysis engine selects a data source such as which channel of which device, performs operations such as calculations, statistical analysis, filtering, and, if necessary, compares the results with the specifications regarding compliance. "Rendering engine" refers to a software component that obtains the processed output from the analysis engine and converts it into a visual form such as charts, graphs, images, or interactive displays to make it easy for humans to interpret the data. The rendering engine displays the results of the analysis engine. This includes plots, swim lanes (forms like multiple lanes in a swimming pool), annotated / non-annotated waveforms, color-coding, layout, and display parameters, etc.

[0013] As described above, the current query needs to follow a very detailed format and specify each component and parameter. The functions processed by AI assistants and generative AI are quite different. An AI assistant analyzes the user's prompt and identifies data sources, analysis needs, and display requirements. The AI assistant uses knowledge of the current device, protocol, available data, and data sources as the context of the prompt. Then, the AI assistant creates the analysis results and the rendered query in a format and content suitable for the parameters derived from the user prompt. In addition to using saved query patterns and available tools, the AI assistant can also save new query patterns as templates for later use.

[0014] Regarding tools, the AI assistant can, for example, use existing tools or create "created" tools from the available functions of the system rather than fixed pre-programmed measurement functions. The AI assistant can create and use multiple modular tools that can be connected to each other as needed, with each of these tools performing a specific task and passing the result of that task to the next tool. Examples include, but are not limited to, cycle detectors, root mean square (RMS) measurements, various error measurements and detectors, and swim lane rendering such as creating visual displays using separate lanes for data streams. The AI assistant automatically selects appropriate measurement tools, connects these measurement tools in a customized sequence as needed, sets appropriate parameters, generates a structured query, and executes the measurement chain.

[0015] For example, if a user enters the prompt "Measure power consumption during each clock cycle," the AI ​​assistant breaks it down into "Calculate clock period → Measure RMS power → Display results." A more complex prompt might be "Organize by device address and display communication errors," which the AI ​​assistant breaks down into "Decode protocol data → Detect errors → Group by address → Create a visual display." These are just a few examples, and many more are shown below.

[0016] Figure 1 shows a system diagram of a test measurement system 10 having an AI assistant 16. A user 12 interacts with the AI ​​assistant 16 through a test measurement device 14, such as an oscilloscope. Alternatively, the user 12 can interact with the test measurement device 14 through the AI ​​assistant 16 on a separate computing device. The user 12 accesses the AI ​​assistant 16 on a computing device 15, which then connects to the test measurement device 14, representing multiple devices to which the AI ​​assistant 16 can connect. The AI ​​assistant has an application programming interface (API) for accessing generative AI models 18, such as large-scale language models (LLMs), large-scale multimodal models (LMMs), and other generative AI models. The test measurement device 14 has one or more processors and may run on an operating system also used by the computing device, such as Microsoft Windows®.

[0017] Model 18 performs learning, which includes all or part of the knowledge set 20. This allows the model to interact with the user through a language recognition interface such as natural language processing (NLP), recognizing the words the user uses when making requests to the AI ​​system. The AI ​​assistant 16 provides the user interface for Model 18 and may also have its own language recognition interface, in addition to having access to some or all of the knowledge in the knowledge set 20.

[0018] When user 12 inputs a request in the form of a prompt, the AI ​​assistant 16 sends these prompts to the model as queries, if necessary. The AI ​​assistant 16 may, depending on the situation, be able to operate independently of the model, which will be explained in more detail below. As will be explained in more detail later, the user's interactive interactions, such as prompts that are converted into commands and queries, and the results, may be stored in the data store 28.

[0019] In some embodiments, the AI ​​assistant or model may use various tools from the toolset 22. The system may already have these tools, referred to hereby as “existing tools,” such as the rendering engine 24 and the analysis engine 26. Others may be created and saved by the AI ​​assistant, including those added to existing tools, and referred to hereby as “created tools.” For example, the rendering engine may generate specific data displays for the user to view results, and the AI ​​assistant may create other tools for these displays, such as annotations and plots. By utilizing the AI ​​assistant 16 and model 18, the system performs conversions between signals and data received from the device under test (DUT), providing context and human-interpretable results and analyses, enabling the user 12 to perform measurement, analysis, debugging, and other tasks on complex systems. The AI ​​assistant can leverage existing tools in new and unique ways, connect these tools, create and leverage new tools in new and unique ways, and combine and match existing and new tools to create new workflows as needed.

[0020] For example, and not limited to, Figure 2 shows a part 30 of a complex system that requires testing, measurement, or debugging. In this example, the system is made up of an automobile. In addition to the various components shown, the system includes three different buses. The central body controller 36, additional drivetrain systems 34, and simpler devices such as the door locks 38 communicate via the CAN (controller area network) 32, shown by a solid line. Components such as the door panel operating device 42 and the motor 44 for the passenger-side door mirror 46 communicate via the LIN (local interconnect network) 40, shown by a dashed line. LIN is also often used as a subnetwork for CAN. Components such as the digital radio 50, speakers 52, and CD player 54 communicate via the MOST (media-oriented system transport) system 48, shown by a dotted line. This diagram, while showing only a portion of the components, systems, and buses, highlights the complexity of the test measurement environment and illustrates how the use of artificial intelligence assistants can be helpful in running tests, collecting and analyzing data, and presenting results in the user interface by rendering graphics, measurements, and numerical data.

[0021] Figure 3 illustrates an embodiment of the process by which the AI ​​assistant processes user prompts and analyzes and renders information from one or more test measurement devices. As mentioned above, the AI ​​assistant may be loaded with knowledge before interacting with the user. This knowledge may include, but is not limited to, instrument knowledge about instruments in the test measurement system, analytical knowledge about various analysis formats and calculations and processes involved in the analysis, knowledge about how to render the results, and knowledge of instrument environment settings regarding how to set up and operate the instruments. This may include SCPI (standard commands for programmable instruments) commands and instrument IP addresses.

[0022] The user specifies the environment settings to be set up and provides prompts (or requests) for analysis. The AI ​​assistant then analyzes the prompts and constructs analytical queries and rendering queries. The AI ​​assistant retrieves data from instruments through requests and instrument access. The data is then stored in a data store. The AI ​​assistant sends the analytical query to the analysis engine. The analysis engine may consist of tasks performed by the AI ​​model, or it may consist of existing software programs that perform the analysis indicated by the query.

[0023] In response to a query, the analytics engine accesses input data from data stores and other locations where the AI ​​assistant may have stored data. The analytics engine then processes the analytical query and stores the analytical data in the data store.

[0024] The AI ​​assistant then sends a rendering query (or request) to the rendering engine. The rendering engine then accesses the analysis data and renders it on the user interface so that the user can view the analysis results. The user can then send the analysis data to a data serializer tool for storage.

[0025] A key aspect of the process in the above embodiment lies in the nature of the instrument data and the role of the AI ​​assistant in transforming the meaning of the signals and data collected from the instrument into a form that is easy for humans to interpret and understand. Figure 4 shows the process from the signal received by the instrument to the final numerical value that the user can understand. The first layer is the signal layer. For example, a signal may consist of changes in voltage or current over a certain period of time, indicated by the length of the signal. The PHY (i.e., physical) layer converts the signal into a digital representation of the analog signal. The decoding layer then converts the signal from the PHY layer into a bit sequence based on a specific protocol (e.g., a communication protocol). The original signal is generated according to this protocol, and in the process of signal transformation, the process adapts the signal to a format suitable for that protocol. This allows the signal to be compared to a test specification and verified to ensure compliance requirements are met.

[0026] Figure 5 shows an example of an analog signal and various characteristics important for analyzing that signal. These characteristics and landmarks may be important for the performance of the DUT that generated the signal. The performance of the DUT is usually measured based on test specifications.

[0027] Figure 6 shows the results of the physical layer transformation of key landmarks from the signal in Figure 5. The items shown in the figure represent landmarks that describe the characteristics of the signal. For example, T LPX This refers to the timing parameters related to the transition from low power (LP) to high-speed mode. The observable characteristics here are T LPX However, it may also be required that it be greater than a certain value.

[0028] Figure 7 shows the decoding process for obtaining physical definitions in the PHY layer and converting these physical definitions into bit sequences based on protocol definitions. Various fields and bits of the protocol definitions are used to convert bus signals, as described in Figure 2, into important bit sequences. These bit sequences require conversion into something human-readable and are illustrated as content in Figure 4.

[0029] The process of achieving this result becomes much simpler for the user by using an AI assistant, as shown in the message flow embodiment in Figure 2. Figures 8-13 show the results of responding to prompts similar to those in the content layer of Figure 4.

[0030] Users may want to monitor vehicle sensors such as temperature, pressure, and oxygen. In this example, since these sensors are connected to the vehicle's CAN bus, the user wants to analyze, visualize, and debug the data communication on the CAN bus.

[0031] Figure 8 shows the response to the following user prompt. "Display the device's frame data (temperature, pressure, oxygen) in a swim lane format. Display the data frame in white and the remote frame in gray." As shown in Figure 8, the temperature, pressure, and oxygen readings are decoded from the bus and provided to the user in an easy-to-understand diagram. The 22°C data 60 in the temperature lane is a remote frame and is shown as a pattern in the diagram instead of gray.

[0032] Figure 9 shows the results obtained from the following prompt. "Please display the device data in a <readable format> along with the <input signal> and <decoded data>." Readable data is shown on the top line, the decoded result is in the center, and the input signal is at the bottom.

[0033] Figure 10 shows the result of the following prompts. "Display the frames for <Temperature> and <Oxygen> that are malfunctioning, and depict them in <Red>." In Figure 10, areas with patterns are shown in red, while frames that fulfill the request are shown as patterns rather than in red (e.g., 62).

[0034] Figure 11 shows the result of the following prompts. "Annotate faulty frames where the <rise time> is outside the <limit range>. The <limit range> is between <10 nanoseconds> and <20 nanoseconds>." The two frames with dashed borders, such as 64 shown in Figure 11, are frames outside the restricted range.

[0035] Figure 12 shows the results obtained from the following follow-on prompt. "Add the waveform of the frame with the <rise time> error." As shown in Figure 12, the two waveforms show a slight difference in line thickness at 66 and 68, which indicates an error in the rise time.

[0036] Figure 13 shows a scatter plot in response to the following prompt. "Use a scatter plot to display the data between <temperature> and <pressure>."

[0037] As another example, you could ask an AI assistant to monitor something for a certain period of time. For instance, "Show me the statistics for <temperature>. Continue monitoring for the next hour and save the data as <filename>." This may result in the following table. [Table 1]

[0038] In this way, users can communicate with the device in natural language and request data in various formats, enabling faster understanding, problem solving, and debugging. The AI ​​assistant highlights errors and presents data clearly. Users can analyze the data in the context of their setup. This approach detects anomalies at the basic level and presents errors in high-level language and visual representations. Prompts are translated into queries and commands, such as those for the one-hour monitoring mentioned above, and can be saved and used as templates. The AI ​​assistant can also create "monitoring" tools, whether the user sees them or not, which further speeds up the AI ​​assistant's processing. 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.

[0039] In this way, combining AI assistants and generative AI models can make the test and measurement environment far more user-friendly, allowing for a better understanding of problems that arise during the testing, analysis, and debugging of DUTs, whether they are simple DUTs or DUTs in complex environments involving multiple protocols and standards.

[0040] Embodiments of the disclosed technology can operate on a specially programmed general-purpose computer, including specially created hardware, firmware, digital signal processors, or processors that operate according to programmed instructions. The terms “controller” or “processor” in this application mean microprocessors, microcomputers, ASICs, and dedicated hardware controllers, etc. Embodiments of the disclosed technology can be implemented by one or more computers (including monitoring modules) or other devices, using computer-readable data such as program modules and computer-executable instructions. Generally, program modules include routines, programs, objects, components, data structures, etc., which, when executed by a processor in a computer or other device, perform specific tasks or implement specific abstract data type expressions. Computer-executable instructions may be stored on computer-readable storage media such as hard disks, optical disks, removable storage media, solid-state memory, and RAM. As will be understood by those skilled in the art, the functions of the program modules may be combined or distributed as needed in various embodiments. Furthermore, these functions can be embodied in whole or in part in firmware or hardware equivalents such as integrated circuits or field-programmable gate arrays (FPGAs). One or more aspects of the disclosed technology can be more effectively implemented using specific data structures, such data structures are considered to be within the scope of computer-executable instructions and computer-usable data described herein.

[0041] The disclosed embodiments may, in some cases, be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried or stored in one or more computer-readable media that can be read and executed by one or more processors. Such instructions may be referred to as computer program products. The computer-readable media described herein means any medium accessible by a computing device. For example, but not limited to, computer-readable media may include computer storage media and communication media.

[0042] Computer storage media means any medium that can be used to store computer-readable information. Examples of computer storage media include, but are not limited to, random-access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory and other memory technologies, compact disc read-only memory (CD-ROM), DVD (Digital Video Disc) and other optical disc storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices and other magnetic storage devices, and any other volatile or non-volatile removable or non-removable media implemented by any technology. Computer storage media exclude signals themselves and temporary forms of signal transmission.

[0043] A communication medium means any medium that can be used to transmit computer-readable information. Examples of communication mediums, though not limited to them, include coaxial cables, fiber optic cables, air, or any other medium suitable for transmitting electrical, optical, radio frequency (RF), infrared, sound, or other types of signals. Examples

[0044] The following examples are provided that are useful for understanding the technology disclosed herein. These embodiments may include one or more of the examples described below, or any combination thereof.

[0045] Example 1 is a test measurement system, One or more test measurement devices comprising at least one test measurement device having one or more ports for connecting to a device under test (DUT), One or more memories containing knowledge of test measurements, The above-mentioned test measurement device and the above-mentioned generative artificial intelligence (AI) model connected to the above-mentioned memory, One or more processors and Equipped with, The one or more processors The process of providing an artificial intelligence (AI) assistant as an interface to the above-mentioned generated AI model, The process involves presenting a user interface that allows the user to input prompts interpreted by the AI ​​assistant, and Using the above AI assistant, the process involves converting the above prompt into one or more queries for the above generating AI model, In response to the above prompt, the process involves sending a command to at least one test measuring device to perform one or more tests on the above DUT, The process involves obtaining the results of one or more of the above tests and converting them into results that can be interpreted by the user. The above user interface includes a process for providing the user with the results based on the above prompts. It is configured to execute a program that causes one or more of the above processors to perform the task.

[0046] Embodiment 2 is the test measurement system of Embodiment 1, wherein one or more processors are further configured to execute a program that causes one or more processors to perform a process of providing the AI ​​assistant with information about the environment of the test measurement system.

[0047] Example 3 is the test measurement system of Example 2, wherein a program that causes one or more processors to perform the process of providing the AI ​​assistant with information about the environment of the test measurement system includes a program that causes the AI ​​assistant to perform the process of accessing one or more of the following: test specifications, general test measurement knowledge, knowledge about specific equipment in the environment, analytical knowledge, rendering knowledge, and knowledge of one or more devices and systems to be tested in the environment.

[0048] Example 4 is a test measurement system according to any of Examples 1 to 3, wherein one or more processors are further configured to execute a program that causes the AI ​​assistant to perform a process of accessing one or more existing tools in response to the prompt.

[0049] Example 5 is the test measurement system of Example 4, wherein one or more processors are further configured to execute a program that causes the AI ​​assistant to perform the process of connecting two or more of the existing tools to each other in response to the prompt.

[0050] Example 6 is the test measurement system of Example 4, wherein one or more of the existing tools described above include one or more of the following processes: search, trigger, analysis, rendering, data serialization, measurement, and decoding.

[0051] Example 7 is a test measurement system according to any of Examples 1 to 6, wherein one or more processors are further configured to execute a program that causes the AI ​​assistant to perform the process of creating one or more new tools in response to the prompt.

[0052] Example 8 is a test measurement system of Example 7, wherein one or more processors are further configured to execute a program that causes the AI ​​assistant to perform the process of connecting one or more new tools to create a workflow.

[0053] Example 9 is a test measurement system according to any of Examples 1 to 8, wherein one or more processors are further configured to perform a process of saving the prompts and commands as templates.

[0054] Example 10 is a method, The process of providing an artificial intelligence (AI) assistant as an interface to a generated AI model, The process involves presenting a user interface that allows the user to input prompts interpreted by the AI ​​assistant, and Using the above AI assistant, the process involves converting the above prompt into one or more queries, In response to the above prompt, the process involves sending commands to one or more test measurement devices in the test measurement system to perform one or more tests on the device under test (DUT), The process involves obtaining the results of one or more of the above tests and converting them into results that can be interpreted by the user. The above user interface includes a process for providing the user with the results based on the above prompts. It is equipped with.

[0055] Example 11 is the method of Example 10, further comprising the process of providing the AI ​​assistant with information regarding the environment of the test measurement system.

[0056] Example 12 is the method of Example 11, wherein the process of providing the AI ​​assistant with information about the environment of the test measurement system includes the process of using the AI ​​assistant to access one or more of the following: test specifications, general test measurement knowledge, knowledge of specific equipment in the environment, analytical knowledge, rendering knowledge, and knowledge of one or more devices and systems being tested in the environment.

[0057] Example 13 is a method of any of Examples 10 to 12, further comprising the process of accessing one or more existing tools using the AI ​​assistant in response to the above prompt.

[0058] Example 14 is the method of Example 13, wherein the process of accessing one or more existing tools using the AI ​​assistant includes the process of connecting the existing tools using the AI ​​assistant to create a new workflow.

[0059] Example 15 is the method of Example 13, wherein one or more of the existing tools described above include one or more of the following processes: searching, triggering, analyzing, rendering, data serialization, measurement, and decoding.

[0060] Example 16 is one of the methods of Examples 10 to 15, further comprising the process of causing the AI ​​assistant to create one or more new tools in response to the above prompt.

[0061] Example 17 is the method of Example 16, wherein the process of causing the AI ​​assistant to create one or more of the new tools includes the process of causing the AI ​​assistant to connect two or more of the new tools to each other to create a new workflow.

[0062] Example 18 is the method of Example 10, further comprising the process of saving the above prompt and the above command as a template.

[0063] The aforementioned versions of the subject matter of this disclosure have many effects that have been described or will be apparent to those skilled in the art. Nevertheless, not all of these effects or features are required in all versions of the disclosed apparatus, system, or method.

[0064] In addition, the description of this application refers to certain features. It should be understood that the disclosures herein include all possible combinations of these particular features. Where a particular feature is disclosed in relation to a particular aspect or example, that feature may, to the extent possible, also be used in relation to other aspects and examples.

[0065] Furthermore, when this application refers to a method having two or more defined steps or processes, these defined steps or processes may be performed in any order or simultaneously, as long as the circumstances do not rule out such possibilities.

[0066] For the sake of explanation, specific embodiments of the present invention have been illustrated and described, but it should be understood that various modifications are possible without deviating from the gist and scope of the invention. Therefore, the present invention should not be limited to anything other than the appended claims. [Explanation of Symbols]

[0067] 10 Test and Measurement Systems 12 users 14 Test and measurement equipment 15 Computing Devices 16 AI Assistants 18 Generative AI Models 20 Knowledge Sets 22 Tool Set 24 Rendering Engines 26 Analysis Engines 28 Data Store 30. Part of a complex system (automobile) 32 CAN(controller area network) 34 Additional Systems 36 Central Body Controller 38 Door Locks 40 LIN(local interconnect network) 42 Door Panel Operating Device 44 motors 46. ​​Passenger-side door mirror 48 MOST (media-oriented system transport) system 50 Digital Radio 52 speakers 54 CD (Compact Disc) Player

Claims

1. A test and measurement system, One or more test measurement devices, including at least one test measurement device having one or more ports for connecting to a device under test (DUT), One or more memories containing knowledge of test measurements, The above-mentioned one or more test measurement devices and one or more generative artificial intelligence (AI) models connected to the above-mentioned memory, One or more processors and Equipped with, The one or more processors The process of providing an artificial intelligence (AI) assistant as an interface to the above-mentioned generated AI model, The process involves presenting a user interface that allows the user to input prompts interpreted by the AI ​​assistant, and The process involves using the above AI assistant to convert the above prompt into one or more queries for the above-mentioned AI model, The process involves sending a command to at least one test measuring device to perform one or more tests on the DUT in response to the above prompt, The process involves obtaining the results of one or more of the above tests and converting them into results that can be interpreted by the user. The process of providing the user with the results based on the above prompt in the above user interface and A test and measurement system configured to execute a program that causes one or more of the above-mentioned processors to perform the above task.

2. The test measurement system according to claim 1, wherein one or more processors are further configured to execute a program that causes one or more processors to perform a process of providing the AI ​​assistant with information about the environment of the test measurement system by accessing one or more of the following: test specifications, general test measurement knowledge, knowledge of specific equipment in the environment of the test measurement system, analytical knowledge, rendering knowledge, and knowledge of one or more devices and systems to be tested in the environment.

3. The test measurement system according to claim 1, wherein one or more processors are further configured to execute a program that causes the AI ​​assistant to perform a process of accessing one or more existing tools in response to the prompt, and the one or more existing tools include one or more of the following processes: search, trigger, analyze, render, data serialization, measurement, and decoding.

4. The test measurement system according to claim 3, wherein one or more processors are further configured to execute a program that causes the AI ​​assistant to perform the process of connecting two or more of the existing tools to each other in response to the prompt.

5. The test measurement system according to claim 1, wherein one or more processors are further configured to execute a program that causes the AI ​​assistant to create and connect one or more new tools and combine them into a workflow in response to the prompt.

6. The process of providing an artificial intelligence (AI) assistant as an interface to a generated AI model, The process involves presenting a user interface that allows the user to input prompts interpreted by the AI ​​assistant, and Using the above AI assistant, the process involves converting the above prompt into one or more queries, In response to the above prompt, the process involves sending a command to one or more test measurement devices in the test measurement system to perform one or more tests on the device under test (DUT), The process involves obtaining the results of one or more of the above tests and converting them into results that can be interpreted by the user. The process of providing the user with the results based on the above prompt in the above user interface and A test and measurement method that includes [the following].

7. The test measurement method according to claim 6, further comprising the process of providing the AI ​​assistant with information about the environment of the test measurement system by using the AI ​​assistant to access one or more of the following: test specifications, general test measurement knowledge, knowledge of specific devices in the environment of the test measurement system, analytical knowledge, rendering knowledge, and knowledge of one or more devices and systems to be tested in the environment.

8. The test measurement method according to claim 6, further comprising the process of accessing one or more existing tools using the AI ​​assistant in response to the above prompt, wherein the one or more existing tools include one or more of the following processes: search, trigger, analyze, render, data serialization, measurement, and decoding.

9. The test measurement method according to claim 8, wherein the process of accessing one or more existing tools using the above-mentioned AI assistant includes the process of connecting the above-mentioned existing tools using the above-mentioned AI assistant to create a new workflow.

10. The test measurement method according to claim 6, further comprising the process of saving the above prompt and the above command as a template.

Images