Measurement application control unit, measurement application device, and method

Abstract

The present disclosure provides a measurement application control unit comprising: a text-based input interface configured to receive a text-based user request with respect to a measurement 5 application device; a pre-trained artificial intelligence algorithm coupled to the text-based input interface and configured to generate response data regarding a question related to the measurement application according to the text-based user request; and an output interface coupled to the pre-trained artificial intelligence algorithm and configured to output response data. In addition, the present disclosure provides a measurement application device and a corresponding method 10.

Description

Technical Field

[0001] The first aspect of this disclosure relates to a measurement application control unit, a measurement application device, and a corresponding method. Background Technology

[0002] Although applicable to any type of user controller measurement application, this disclosure will be described primarily in conjunction with laboratory-oriented measurement application equipment such as oscilloscopes.

[0003] Modern measurement application equipment includes a variety of functions to support specific tasks within the measurement application. To this end, measurement application equipment may include multiple options and configuration parameters that users can set for specific measurement applications.

[0004] Therefore, it is necessary to simplify the setup of measurement application equipment. Summary of the Invention

[0005] The aforementioned problems are resolved by the features of the independent claims of the first aspect of this disclosure. It should be understood that an independent claim of one claim class can be formed similarly to a dependent claim of another claim class.

[0006] Therefore, the following is provided: A measurement application control unit includes: a text-based input interface configured to receive a text-based user request regarding a measurement application, the measurement application including at least one measurement application device; a pre-trained artificial intelligence algorithm coupled to the text-based input interface and configured to generate response data regarding questions related to the measurement application device based on the text-based user request; and an output interface coupled to the pre-trained artificial intelligence algorithm and configured to output the response data.

[0007] In addition, the following are also provided: A measurement application device includes a measurement application control unit according to any embodiment disclosed herein, and a measurement application device controller coupled to the measurement application control unit.

[0008] In addition, the following are also provided: A method for controlling a measurement application device includes receiving a text-based user request regarding a measurement application including at least one measurement application device, generating response data based on the text-based user request using a pre-trained artificial intelligence algorithm, and outputting the response data.

[0009] This disclosure is based on the finding that modern measurement applications have the potential to provide the execution of a large number of user-configurable measurements or measurement tasks that may be difficult for users to remember and understand.

[0010] The most important measurements or measurement tasks can be prominently displayed on the main screen of the corresponding measurement application device within the measurement application. However, other measurements or measurement tasks, as well as options that may only be needed for very specific measurement tasks, may be hidden, for example, in submenus of the measurement application device's user interface.

[0011] In particular, inexperienced users may face difficulties when attempting to formulate questions about their specific measurement problems or tasks. These users may also encounter difficulties setting up and configuring measurement applications and devices. Inexperienced users may even lack knowledge of the specific functions of highlighted configuration options, especially those hidden within submenus of the measurement application's user interface.

[0012] Therefore, this disclosure provides a measurement application control unit, a method for controlling a measurement application device, and a corresponding measurement application device. Although not explicitly stated, this disclosure also provides a non-transitory computer-readable medium having instructions thereon that, when executed in a computer, cause the computer to perform the method according to any of the embodiments described herein.

[0013] The measurement application control unit includes a text-based input interface. This interface can receive text-based user requests from the user. These requests can include natural language text relating to the measurement application.

[0014] Text-based input interfaces can be implemented as data interfaces that receive text in binary form, such as ASCII-encoded text or text encoded in any other character encoding scheme. Such data interfaces can be provided as hardware interfaces (e.g., network interfaces) and program interfaces (e.g., APIs or callback functions), or a combination of both.

[0015] Text-based input interfaces can include any other type of interface, such as APIs, callback functions, shared memory, web-based UIs, REST APIs, classes, or interfaces, such as Python classes or Python interfaces, and are not limited to these examples.

[0016] The text-based user request is then fed into a pre-trained artificial intelligence algorithm, which generates corresponding response data based on the provided text-based user request.

[0017] Specifically, pre-trained artificial intelligence algorithms can be trained to receive text-based user requests presented in a natural language style, such as the style when a user makes a text-based user request to another user, or the style when a user expresses a text-based user request in, for example, an online forum.

[0018] Users might raise questions about the measurement application based on underlying electrical signals. For example, users might be provided with PWM signals or serial buses such as USB or SPI. In particular, inexperienced users may lack the knowledge needed to ask the right questions when faced with such a system. Therefore, response data can address questions that may be relevant to the specific measurement application. Inexperienced users might not know, for example, what options they have to measure the signal in such an application, or which characteristics of the signal they can measure. Response data can help users ask questions about this signal. It should be understood that these questions can be provided to another AI-based system that supports the user in performing the corresponding measurements.

[0019] As an example only, for PWM signals, response data could include or relate to questions such as, "How do I measure the duty cycle of a PWM signal?". Response data could also be presented in the form of, "Do you want to measure the duty cycle of a pulse width modulation signal?" Response data could also include explanations of technical terms such as "duty cycle." In the SPI bus example, response data could include or relate to questions such as, "How do I determine the bus frequency or the data rate on the bus?", or "How do I extract the digital data transmitted on the bus?". Response data could also be presented in the form of, "Do you want to determine the bus frequency or the data rate on the bus?", or "Do you want to extract the digital data transmitted on the bus?". Of course, the above examples are not limiting, and pre-trained AI algorithms can be trained to support users in asking any type of question related to a measurement application or the measurement application device within a measurement application. After the user confirms that the corresponding question is what they are trying to ask, the pre-trained AI algorithm can provide the user with an answer to the question, such as an explanation of how to perform the corresponding measurement task.

[0020] During operation, pre-trained artificial intelligence algorithms can help users discover any functions in the measurement application or the corresponding measurement application equipment that the user is not yet aware of.

[0021] Response data can be provided in different formats, which will be explained in more detail below. Generally, in embodiments, response data can be provided in text format. In the context of this disclosure, the term "text format" can refer to any type of text, including but not limited to natural language text and text written in a programming or scripting language.

[0022] Response data can be generated by a pre-trained artificial intelligence algorithm based solely on text-based user requests. In one embodiment, the pre-trained AI algorithm may also be provided with contextual data regarding the measurement application or at least one measurement application device within the measurement application. In such an embodiment, the pre-trained AI algorithm can also generate response data based on the contextual data (e.g., the current settings or configuration of the measurement application). The contextual data can be provided to the pre-trained AI algorithm by a preprocessor mentioned below. Therefore, the pre-trained AI algorithm may infer potential measurement problems or measurement environments. From such potential measurement problems or measurement environments, specific problems or measurement tasks can be derived, particularly automatically by the pre-trained AI algorithm.

[0023] Pre-trained artificial intelligence algorithms can also be trained to derive from contextual data, such as data about the past and current state of a measurement application device, where the measurement task has already been performed in the measurement application, and this information is taken into account when generating response data.

[0024] In one embodiment, a pre-trained artificial intelligence algorithm can be configured to engage in multiple rounds of question-and-answer iterations with the user to generate final response data. In such an embodiment, the pre-trained AI algorithm can be trained to first ask the user more general questions about the measurement application and then transition to more specific questions based on the user's answers. During these multiple rounds of question-and-answer iterations, the responses provided by the user to the measurement application control unit can be considered feedback to the control unit. In another embodiment, the user can restart the question-and-answer iteration process by indicating that the response data does not meet their requirements.

[0025] Pre-trained artificial intelligence algorithms can also be configured to categorize potential measurement problems or measurement environments into different measurement applications or measurement application tasks, and provide users with corresponding response data.

[0026] The measurement application control unit also includes an output interface for outputting response data. The explanation provided above for the input interface can be applied in analogous way to the output interface. In an embodiment, the input and output interfaces may be implemented as a single data interface.

[0027] In a measurement application device, response data can be provided, for example, to a measurement application device controller, which can further process the response data. The measurement application device controller can then output the response data to a user, for example, via a display.

[0028] In one embodiment, the measurement application device may include an audio output interface, such as a speaker, which can output the response data as audio to the user. To this end, a text-to-speech engine may be provided in the measurement application device to receive the response data from a pre-trained artificial intelligence algorithm and convert the response data into audio.

[0029] In this embodiment, the response data may also include or link to sections of user manuals, application data sheets, or tutorial videos, which include answers to the questions addressed by the response data. In such embodiments, the response data can directly guide the user to relevant content. Especially in long user manuals or tutorial videos, users can be directly guided to relevant sections without having to browse the entire manual or video.

[0030] To this end, the pre-trained AI algorithm can be trained using a single segment of the corresponding user manual or a single segment of the corresponding video. Alternatively, the pre-trained AI algorithm can also be trained using textual descriptions of video segments. The user manual or video can be manually segmented into individual segments. Furthermore, or alternatively, another AI system can be provided to segment the user manual or video into the corresponding segments. In other embodiments, the pre-trained AI algorithm can be trained using the complete user manual or video and can be configured to internally identify relevant segments.

[0031] It should be understood that the method for controlling a measurement application device according to this disclosure can be executed not only locally in a single measurement application device, but also remotely or in a distributed manner.

[0032] In this embodiment, the measurement application control unit may be provided, for example, remotely to the measurement application device. The measurement application control unit may be provided, for example, as a server, or a server-based or cloud-based application, which may be accessed by a user via a network interface. Any control data generated by the measurement application control unit for the measurement application device may be provided to the measurement application device via a suitable network or data connection. For this purpose, the measurement application device may include a corresponding communication interface.

[0033] In embodiments, the communication interface may include any kind of wired and wireless communication interface, such as network communication interface (especially Ethernet), wireless local area network (LAN) or WIFI interface, USB interface, Bluetooth interface, NFC interface, and visible or invisible light-based interface (especially infrared interface).

[0034] Furthermore, servers or cloud servers and measurement application devices can communicate with each other via an intermediary network, and such networks can include any type of network device, such as switches, hubs, routers, firewalls, and different types of network technologies.

[0035] Generally, such a server can be a dedicated server, implemented as a single hardware device. It can also be implemented as a distributed system comprising multiple servers, optionally with a load balancer to distribute the load among them. The server can also be provided as a so-called cloud or cloud server system, implemented through virtualization methods independent of the underlying hardware.

[0036] In one embodiment, the measurement application control unit can operate independently of the measurement application device and can even be coupled to the measurement application device without communication. In such an embodiment, the user can be the sole recipient of the generated response data, or the generated response data can be stored on a data carrier, such as a USB memory, which can be connected by the user to the measurement application device.

[0037] In embodiments, the measurement application control unit may include or be provided as part of at least one dedicated processing element, such as a processing unit, microcontroller, field-programmable gate array (FPGA), complex programmable logic device (CPLD), application-specific integrated circuit (ASIC), etc. Appropriate programs or configurations may be provided to implement the desired functions. The measurement application control unit may also be provided, at least in part, as a computer program product including computer-readable instructions executable by the processing element. In another embodiment, the measurement application control unit may be provided as additional or additional functions or methods to the firmware or operating system of the processing element, which already exists in the corresponding application (e.g., a measurement application device), implemented as corresponding computer-readable instructions. Such computer-readable instructions may be stored in memory coupled to or integrated into the processing element, which is analogous to a measurement application device controller of the measurement application device. The processing element may load the computer-readable instructions from memory and execute them. This also applies to any other elements, units, or functions disclosed herein that are part of the measurement application control unit, the measurement application device, and the methods for controlling the measurement application device.

[0038] Furthermore, it should be understood that any necessary support or additional hardware, such as power supply circuits and clock generation circuits, can be provided.

[0039] In the context of this disclosure, a measurement application device may include any device that can be used in a measurement application to acquire input signals or generate output signals, or to perform additional or supporting functions in the measurement application. A measurement application device may also include or be implemented as one or more program applications, also referred to as one or more measurement program applications, which can be executed on a computer device and can communicate with other measurement application devices to perform measurement tasks. A measurement application, also referred to as a measurement setup, may, for example, include at least one or more different measurement application devices for performing electrical, magnetic, or electromagnetic measurements, particularly on a single device under test. Such electrical, magnetic, or electromagnetic measurements may be performed, for example, in a measurement laboratory or on a production line of a corresponding production line. A measurement application or measurement setup may be used to identify individual devices under test, i.e., to determine the correct electrical operation of each device under test.

[0040] Therefore, measurement application equipment may include at least one signal acquisition section for acquiring the electrical, magnetic, or electromagnetic signal to be measured from the device under test, or at least one signal generation section for generating the electrical, magnetic, or electromagnetic signal that can be provided to the device under test. Such a signal acquisition section may include, but is not limited to, a front-end for acquiring, filtering, attenuating, or amplifying electrical signals. The signal generation section may include, but is not limited to, corresponding signal generators, amplifiers, and filters.

[0041] Furthermore, when acquiring signals, the measurement application device may include a signal processing section capable of processing the acquired signals. Processing may include converting the acquired signals from analog to digital signals, as well as any other type of digital signal processing, such as converting the signal from the time domain to the frequency domain.

[0042] Measurement application equipment may also include a user interface to display the acquired signals to the user and allow the user to control the measurement application equipment. Of course, a housing can be provided to house the various components of the measurement application equipment. It should be understood that additional components, such as power supply circuits and communication interfaces, can be provided.

[0043] Measurement application equipment can be a standalone device that operates without any other components in the measurement application to perform tests on the device under test. Alternatively, it can be equipped with communication capabilities to interact with other measurement application equipment.

[0044] Measurement application equipment may include, for example, signal acquisition devices such as oscilloscopes (especially digital oscilloscopes), spectrum analyzers, or vector network analyzers. Such measurement application equipment may also include signal generation devices, such as signal generators (especially arbitrary signal generators, also known as arbitrary waveform generators) or vector signal generators. Other possible measurement application equipment includes devices similar to calibration standards or measurement probe tips.

[0045] Of course, at least some of the possible functions, such as signal acquisition and signal generation, can be combined in a single measurement application device.

[0046] In embodiments, the measurement application device may include a pure data acquisition device capable of acquiring input signals and providing the acquired input signals as digital input signals to a corresponding data storage or application server. Such a pure data acquisition device does not necessarily include a user interface or display. Instead, it can be remotely controlled, for example, via a suitable data interface such as a network interface or USB interface. The same applies to pure signal generation devices that generate output signals without including any user interface or configuration input elements. Instead, such signal generation devices can be operated remotely via a data connection.

[0047] Using the measurement application control unit, measurement application device, and method according to this disclosure, users can identify problems behind their measurement applications and interact with the measurement application device as described above in a natural manner similar to conversing with other users.

[0048] Other embodiments of this disclosure are the subject of other dependent claims and the following description with reference to the accompanying drawings.

[0049] The dependent claims that directly or indirectly reference claim 1 according to the first aspect of this disclosure are described in more detail below. To avoid doubt, features of the dependent claims relating to the measurement application control unit may be combined with each other in all variations, and the disclosure of the specification is not limited to the dependent relationships specified in the claim set. Furthermore, in all variations, features of other independent claims may be combined with any feature of the dependent claims relating to the measurement application control unit, wherein in the method, the respective method steps perform the functions of the respective elements.

[0050] In embodiments that can be combined with all other embodiments mentioned above or below, the measurement application control unit may further include an audio input interface configured to receive spoken requests, and a speech recognition unit coupled to the audio input interface and the text-based input interface. The speech recognition unit may be configured to convert the spoken request into a text-based request and provide the text-based request as a text-based user request to the text-based input interface.

[0051] Audio input interfaces can be provided as local or hardware audio input interfaces in the measurement application device controller or in a measurement application device that implements or includes the measurement application device controller.

[0052] In other embodiments, the audio input interface may be provided as a data interface for receiving audio data from another device. This data interface may be provided as a hardware interface, a software interface, or a combination of both. Generally, the hardware interface of the audio interface may include any kind of wired and wireless communication interface, such as a network communication interface (especially Ethernet), a wireless LAN or Wi-Fi interface, a USB interface, a Bluetooth interface, an NFC interface, or an interface based on visible or invisible light (especially an infrared interface).

[0053] An audio input interface is coupled to a speech recognition unit, which converts spoken requests (i.e., audio data) received via the audio input interface into text-based user requests. These text-based user requests can then be provided to the text-based input interface, just like any other text-based user request, for further processing by a pre-trained artificial intelligence algorithm.

[0054] The voice recognition unit can be provided as a hardware-based unit, a software-based unit, or a combination of both, as noted above for the control unit for measurement applications.

[0055] Using the audio input interface and voice recognition unit, users can communicate naturally with the measurement application control unit, just as if they were talking to other users.

[0056] In another embodiment, which may be combined with all other embodiments mentioned above or below, the pre-trained artificial intelligence algorithm may be pre-trained using at least one of the following: a user manual for at least one measurement application device, a datasheet for at least one measurement application device, an application note for at least one measurement application device, an application note for at least one measurement application, a user manual for an electronic device, a datasheet for an electronic device, an application note for an electronic device, an article about electronic circuits, an online forum discussion about electronic circuits, and a video about electronic circuits.

[0057] The pre-trained AI algorithm needs to be trained on data about the measurement application devices involved in the text-based user request. Of course, in this embodiment, the pre-trained AI algorithm can be trained on information about multiple different measurement application devices.

[0058] Generally, manufacturers of one or more measurement application devices already provide a wide selection of training data. This training data may be provided, for example, in the form of user manuals, datasheets, and application notes that the measurement application device manufacturer may publish.

[0059] An exemplary excerpt regarding the setting of the input voltage range from an oscilloscope user manual is provided below, which can be applied to all aspects of this disclosure: "The sensitivity of the analog input can be selected in 1-2-5 steps from 1mV / div to 10V / div using the knobs (VOLTS / DIV) in the vertical section. Each knob is associated with the active channel (press the corresponding channel key to activate the desired channel). Pressing a knob once switches to continuous sensitivity setting. The smaller knob (POSITION) in the vertical section can be used to determine the vertical setting of the active channel. Press the menu key to enter advanced options. On page 2|2 of this menu, a correction offset (DESKEW) can be added. Press the corresponding soft menu key to activate the offset. The offset value can be set using the general knob or the keyboard (KEYPAD) in the cursor / menu section. Each analog channel can be offset by ±32ns in time. This correction offset setting is used to compensate for different signal delays when using cables or probes of different lengths." This explanation may be accompanied by an oscilloscope image, or a partial image including vertical sections of buttons, switches, and knobs.

[0060] Application notes for at least one measurement application may include application notes that interpret the measurement application in a general scenario, such as the measurement of a PWM signal or measurements in an SPI communication system. In addition to general information, such application notes may also include information specific to one or more measurement application devices.

[0061] In this embodiment, the pre-trained artificial intelligence algorithm can be pre-trained based on general data that is not specific to any measurement application device.

[0062] Then, training data associated with one or more measurement application devices can be used to fine-tune the pre-trained artificial intelligence algorithm. This fine-tuning will allow the pre-trained AI algorithm to respond more appropriately to text-based user requests regarding the measurement application device.

[0063] In one embodiment, another pre-trained algorithm may be provided, trained to provide textual descriptions of images and charts. This pre-trained algorithm can be used to interpret the content of images or charts provided in training data, particularly those provided in manuals, datasheets, and application notes, in text form to a pre-trained artificial intelligence algorithm to perform training on the pre-trained AI algorithm. In embodiments, any other suitable type of preprocessing, such as optical character recognition, may be applied.

[0064] The training of pre-trained AI algorithms can be performed using unsupervised training methods. Alternatively, or additionally, pre-trained AI algorithms can be trained using supervised training methods, such as under the supervision of an experienced measurement engineer. Appropriate prompts can also be used to train the pre-trained AI algorithm.

[0065] In this embodiment, different pre-trained artificial intelligence algorithms with varying degrees of training and / or complexity, and therefore different capabilities, can be selected. The selection of a pre-trained AI algorithm can depend on any available hardware resources, such as memory, processing power, storage, and licensing costs. Of course, updated pre-trained AI algorithms can also be provided and installed in the measurement application control unit during operation.

[0066] In another embodiment, which may be combined with all other embodiments mentioned above or below, the pre-trained artificial intelligence algorithm may include a large language model based on at least one of a bidirectional encoded representation based on a Transformer model and a generative pre-trained Transformer model.

[0067] While two specific types of large language models have been explicitly disclosed above, it should be understood that pre-trained artificial intelligence algorithms can include any algorithm that can be trained on a set of training data, enabling it to generate response data based on text-based user requests.

[0068] Other possible types of algorithms or models include, but are not limited to, any type of language model, such as statistical models (e.g., N-grams), recurrent neural networks (e.g., the Long Short-Term Memory model LSTM), and transformer models.

[0069] In another embodiment, which may be combined with all other embodiments mentioned above or below, the measurement application control unit may further include a user input interface coupled to a pre-trained artificial intelligence algorithm, and the user input interface is configured to receive user input. The pre-trained artificial intelligence algorithm may be configured to generate response data about questions related to the measurement application based on text-based user requests and user input.

[0070] The user interface allows users to select keywords related to the measurement application. These keywords can be selected by the user as tags, words from a word cloud, or by freely typing or entering keywords. A pre-trained artificial intelligence algorithm can be trained to generate response data based on these keywords.

[0071] In another embodiment that may be combined with all other embodiments mentioned above or below, the user input interface may include at least one of buttons, switches, knobs, touchscreens, keyboards, mice, cameras, and gesture sensors.

[0072] The user input interface is a second interface that allows users to interact with the measurement application control unit, or a measurement application device that implements or includes the measurement application control unit.

[0073] The term "user input interface" refers to a user interface that provides users with any other interaction method based on non-text or natural language.

[0074] Therefore, the user input interface may include any other type of physical interface that allows users to physically interact with the measurement application control unit or measurement application device.

[0075] In addition to physical interaction elements such as buttons, knobs, and touchscreens, interaction can also be gesture-based. For this purpose, a camera or any other sensor for capturing gestures, such as LiDAR or ultrasonic sensors, can be provided.

[0076] Using this user input interface as a second input device for the user, the user can make text-based user requests that involve details of the user input or are further defined by the user input.

[0077] In the example embodiment, a user can initiate any element of the user input interface and provide a text-based user request about that element.

[0078] In one example, a user could activate a knob, switch, or button, or indicate a section on the display of the measurement application control unit or measurement application device, and provide a more general text-based user request, such as "What is this for?"

[0079] The pre-trained AI algorithm can then fuse information about user input and text-based user requests to generate response data.

[0080] The ability to perform this fusion can be provided to the pre-trained artificial intelligence algorithm during the fine-tuning phase of the training stage described above. Specifically, information provided in the user manual of the measurement application device can identify the input elements or areas of the device's display and explain their corresponding functions. When trained with this information, the pre-trained artificial intelligence algorithm can provide the user with response data explaining the corresponding functions.

[0081] The fusion of user input information and text-based user requests can also be performed by the preprocessor mentioned below.

[0082] In such embodiments, the preprocessor can provide pre-request sections that precede text-based user requests. These pre-request sections can, for example, indicate to the user which input element or display area to point to.

[0083] An exemplary pre-request section could be stated as: "The user touched the knob called 'Voltage Level' and asked:". The actual text-based user request can then be provided to a pre-trained artificial intelligence algorithm following this pre-request section.

[0084] Then, the complete request provided to the pre-trained artificial intelligence algorithm can be read as, for example, “The user touched a knob called ‘voltage level’ and asked: ‘In what type of measurement is this needed?’”.

[0085] Other examples could be pointing to a section of the screen where the user is instructing them, such as, "The user moves the mouse to the leftmost button in the lower display area and asks, 'What does this do?'", or "The user gestures toward the vertical axis of the chart shown on the screen and asks, 'What does this do?'"

[0086] Of course, this disclosure is not limited to the examples above, and can be applied to any other input element or user input type.

[0087] In another embodiment, which may be combined with all other embodiments mentioned above or below, the measurement application control unit may further include a translator coupled to a text-based input interface and a pre-trained artificial intelligence algorithm, wherein the translator may be configured to translate a text-based user request in a language not trained to operate using the pre-trained artificial intelligence algorithm into a translated text-based user request in a language trained to operate using the pre-trained artificial intelligence algorithm, and to provide the translated text-based user request to the pre-trained artificial intelligence algorithm.

[0088] Pre-trained AI algorithms can be trained to respond to text-based user requests delivered in a specific language. Therefore, a pre-trained AI algorithm may not be trained to respond to text-based user requests delivered in a language that the pre-trained AI algorithm is not trained to respond to.

[0089] To support collaboration among multiple users with different language skills, a translator can be provided in the measurement application control unit.

[0090] The translator can receive text-based user requests that operate in a language not trained by a pre-trained artificial intelligence algorithm. The translator can then translate the text-based user requests into the language that the pre-trained artificial intelligence algorithm is trained to operate in.

[0091] The translator enables multilingual teams with varying levels of language proficiency to collaborate easily, even when each team member speaks their native language instead of the language to which the pre-trained AI algorithm is trained.

[0092] In one embodiment, the translator may include a pre-trained artificial intelligence algorithm trained to translate natural language text from one language to another. In another embodiment, the translator includes a corresponding algorithm trained on general text data. In other embodiments, such an algorithm trained on general text data may be fine-tuned with text data specific to the technical field of the measurement application device.

[0093] In embodiments that can be combined with all other embodiments mentioned above or below, the measurement application control unit may further include a preprocessor coupled to a pre-trained artificial intelligence algorithm. The preprocessor may be configured to provide a pre-processed text-based request to the pre-trained artificial intelligence algorithm before the algorithm operates on the text-based user request.

[0094] Preprocessors can be used to instruct pre-trained artificial intelligence algorithms on general information that users may, for example, skip or forget in text-based user requests.

[0095] Preprocessed text-based requests can be provided to pre-trained artificial intelligence algorithms before the actual text-based user request, as illustrated above for the user input interface.

[0096] In an embodiment, the preprocessor may provide the pre-trained artificial intelligence algorithm with information about at least one of the following, but not limited to: the measurement application device that the user may be involved with, the measurement application settings that the user is using, the measurement application devices present in the measurement application settings, the specifications of one or more measurement application devices, and the type or format required for the response data.

[0097] The example preprocessed text-based requests proposed by the preprocessor may include, but are not limited to, the following requests: "The two measurement inputs of the OSCI1 oscilloscope are coupled to the device under test (DUT) via PROBE measurement probes. The DUT is a microcontroller, and the measurement probes are coupled to the microcontroller's I2C signal line." "In the measurement setup, the signal generator is coupled to the input of the device under test, which acts as an amplifier. In addition, the oscilloscope is coupled to the output of the amplifier." In an embodiment, the preprocessor may include another pre-trained artificial intelligence algorithm trained to generate pre-processed text-based requests, as exemplified above. This pre-trained AI algorithm may be trained, for example, based on a set of example descriptions of measurement application settings and corresponding pre-processed text-based requests. This other pre-trained AI algorithm may include a large language model or any other type of algorithm, as explained herein with respect to pre-trained AI algorithms.

[0098] In other embodiments, the preprocessor may not be implemented as a pre-trained artificial intelligence algorithm. These embodiments of the preprocessor may include, for example, a state machine, which may be configured to append relevant information about the measurement application settings to a corresponding pre-processed text-based request. The information about the measurement application settings may be provided, for example, in tabular form, where each row includes information about a component of the measurement application settings. Generally, this information may be provided in any suitable, particularly structured, format.

[0099] This information can indicate, for example, the type of component, such as a signal generating device, a signal acquiring device, a device under test, a probe, an adapter, etc. It can also indicate the number of outputs or inputs of the corresponding component, and how the inputs and outputs are coupled to other components.

[0100] In such an embodiment, the preprocessor may, for example, simply insert information into a template string and concatenate the template strings of all elements in the measurement application settings to generate a corresponding preprocessed text-based request.

[0101] In another embodiment, which may be combined with all other embodiments mentioned above or below, a pre-trained artificial intelligence algorithm may be configured to receive text-based user requests regarding the use of a measurement application device and generate usage response data including a corresponding explanation of how to use the measurement application device.

[0102] As mentioned above, users can provide questions about the use of the measurement application's devices. Such requests can be answered by a pre-trained artificial intelligence algorithm using response data that includes a textual description of the answer to the user's question.

[0103] Therefore, the measurement application control unit allows inexperienced users to immediately learn how to use a particular feature of the measurement application equipment without consulting a training manual or other more experienced users.

[0104] In another embodiment, which may be combined with all other embodiments mentioned above or below, a pre-trained artificial intelligence algorithm may be configured to receive text-based user requests regarding control of the measurement application device and generate usage response data including corresponding control commands regarding control of the measurement application device.

[0105] Unlike explaining the different features of measurement application devices to users, control response data can directly provide control commands that users can implement in the measurement application device or multiple measurement application devices within the measurement setup.

[0106] These control commands can be provided to the user in the form of natural text commands. Example control commands may include, but are not limited to, "Set the voltage range to 0V-100V", "Set the magnification factor to 10x", "Set the scaling of the graph's X-axis to 0.5", "Start measurement", "Stop measurement", "Start signal generation", "Stop signal generation", etc.

[0107] Generally, these control commands can include any options, parameters, or user input commands that the measurement application device may include or allow.

[0108] In this embodiment, a text-based user request may also refer to a previous measurement or measurement protocol or the measurement result of a previous measurement. For example, a user may instruct "repeat the last measurement" or "repeat the measurement performed yesterday".

[0109] In embodiments that can be combined with all other embodiments mentioned above or below, the measurement application control unit may further include a code generator coupled to or integrated with a pre-trained artificial intelligence algorithm. The code generator may be configured to generate configuration and control commands for the measurement application device in a predetermined control or programming language, and to provide the generated configuration and control commands to the controller of the measurement application device.

[0110] While the control commands described above are easy for users to understand, measurement application devices may not be directly controlled by such commands.

[0111] However, modern measurement applications include more than just user interfaces for controlling the equipment. Instead, these applications are often programmable and controllable.

[0112] Such control programs can be provided, for example, in a domain-specific scripting or programming language, such as the SCPI language (Standard Commands for Programmable Instruments). In other embodiments, the control programs can be provided in more general programming languages, such as Python or JavaScript, and these control programs can be interpreted in the measurement application device or as a compiled program executed in the measurement application device.

[0113] Therefore, a code generator, or a pre-trained artificial intelligence algorithm with an integrated code generator, can be trained or configured to generate control commands from response data. These control commands can be provided in any suitable format, such as the control program described above, but are not limited to such a program.

[0114] In such an embodiment, a pre-trained artificial intelligence algorithm can receive text-based user requests, as described above. These user requests may include, as described above, general information about the measurement application, such as the type of bus or serial communication used. A code generator or the pre-trained artificial intelligence algorithm can then generate control commands required to measure specific characteristics in this measurement setup. In an embodiment, the pre-trained artificial intelligence algorithm may generate such control commands only at a later stage after multiple rounds of question-and-answer iterations with the user. Such user requests may also directly request the measurement application device or multiple measurement application devices to configure the measurement application setup in a specific manner.

[0115] In one embodiment, the code generator or pre-trained artificial intelligence algorithm may also generate multiple sets of control commands and may ask the user to select one set for further processing.

[0116] The code generator or pre-trained artificial intelligence algorithm can then generate corresponding control commands in the form of direct control commands or control program commands. These control commands can be provided to the measurement application device for execution. In this embodiment, the generated control commands can be presented to the user before being provided to the measurement application device for execution.

[0117] The measurement application control unit may also include a code verification unit or code verifier. The code verification unit can be configured to analyze the generated code and detect inappropriate commands or configurations within it. Such a code verification unit may include, but is not limited to, any of artificial intelligence-based code analyzers and rule-based code analyzers. If the code verification unit detects inappropriate commands or configurations, it can present its findings to the user, for example, via a user interface, and ask the user whether the generated code is acceptable.

[0118] The term "inappropriate" in relation to generated code can refer to commands or configurations that may damage the device under test or the measurement application, or commands or configurations that impose costs on the user, for example, because they involve installing additional applications on the measurement device.

[0119] In another embodiment, which may be combined with all other embodiments of the measurement application control unit mentioned above or below, the pre-trained artificial intelligence algorithm may include an algorithm that is executed locally on the measurement application device.

[0120] Depending on the measurement application used by the measurement application control unit, the measurement data and the specific configuration of the measurement settings may be confidential.

[0121] In such an embodiment, details of the measurement setup or measurement application should not be transmitted to a public service that can host pre-trained artificial intelligence algorithms.

[0122] In such an embodiment, the pre-trained artificial intelligence algorithm can be executed locally in the measurement application device.

[0123] In an embodiment, the pre-trained artificial intelligence algorithm executed locally in the measurement application device may include an algorithm adapted to the processing and storage resources locally available in the measurement application device.

[0124] In this embodiment, the locally executed, pre-trained artificial intelligence algorithm can be run on a server or dedicated computer that is communicatively coupled to the measurement application device via a secure connection. A secure connection can be provided by deploying both devices in the same network within the user's premises of the measurement application device, or by establishing a VPN or any other encrypted communication between the measurement application device and the corresponding server.

[0125] In another embodiment, which may be combined with all other embodiments mentioned above or below, the measurement application control unit may further include a complexity estimator coupled to the text-based input interface. The complexity estimator may be configured to estimate the complexity of the text-based user request and, if the estimated complexity is higher than a predetermined threshold, forward the text-based user request to an external pre-trained artificial intelligence algorithm.

[0126] As mentioned above, locally executed, pre-trained artificial intelligence algorithms can be adapted to the local processing and storage resources available in the corresponding measurement application device.

[0127] Therefore, such pre-trained artificial intelligence algorithms may not include the ability to answer all possible text-based user requests, and may be limited to answering simple text-based user requests.

[0128] To allow users to make complex text-based user requests, the measurement application control unit can be equipped with a complexity estimator.

[0129] The complexity estimator can analyze received text-based user requests and determine or estimate their complexity. If the determined or estimated complexity exceeds a predetermined threshold, the corresponding text-based user request can be provided to an external, more powerful, pre-trained artificial intelligence algorithm. As mentioned above, the external pre-trained artificial intelligence algorithm can be provided, for example, as a network-attached server or a cloud server.

[0130] Of course, the predetermined threshold can be adapted to the capabilities of a pre-trained artificial intelligence algorithm executed locally. Example complexity measures could include, for example, the number of letters, or the number of words, or the number of sentences, or any combination thereof.

[0131] In embodiments that can be combined with all other embodiments mentioned above or below, the complexity estimator can be configured to request user consent via the user interface of the measurement application device before providing one of the text-based user requests to an external pre-trained artificial intelligence algorithm.

[0132] As mentioned above, data regarding measurement settings or applications may be confidential. Therefore, the complexity estimator may request the user's consent or permission before providing or transmitting text-based user requests to an external, pre-trained artificial intelligence algorithm.

[0133] If the user refuses, the complexity estimator can notify the user that the locally executed, pre-trained AI algorithm may ultimately be unable to correctly answer the text-based user request, and provide the text-based user request to the locally executed, pre-trained AI algorithm.

[0134] In another embodiment, which may be combined with all other embodiments mentioned above or below, the complexity estimator may be configured to indirectly provide text-based user requests to an external pre-trained artificial intelligence algorithm via a request anonymizer.

[0135] The request anonymizer can act as an intermediary device through which the complexity estimator can communicate, rather than directly providing text-based user requests to an external, pre-trained artificial intelligence algorithm.

[0136] Although not explicitly stated, the request anonymizer is disclosed herein as a separate entity that can be used independently of any measurement application device or measurement application control unit. Externally trained artificial intelligence algorithms and request anonymizers can be used in conjunction with any aspect of this disclosure.

[0137] The request anonymizer may include, for example, a server that aggregates text-based user requests from multiple measurement application control units and forwards these requests to an externally operated, pre-trained artificial intelligence algorithm, without including any information that could identify the measurement application control unit or measurement application device. The request anonymizer may, for example, remove such information from the text-based user requests or replace it with other predetermined information.

[0138] In another embodiment, which may be combined with all other embodiments mentioned above or below, the measurement application control unit may further include a text-based user request generator configured to receive at least one of an image, video, or non-text description of at least one of the measurement application device, the device under test, and the measurement application settings, wherein the text-based user request generator may also be configured to generate a text-based user request based on at least one of the images or videos, and to provide the generated text-based user request to a pre-trained artificial intelligence algorithm.

[0139] By utilizing a text-based user request generator, users are provided with an alternative means of submitting their requests to the measurement application processing device.

[0140] Users can simply provide one or more images or videos relevant to the measurement application without submitting specific text-based user requests to a pre-trained artificial intelligence algorithm. Other non-textual descriptions may include, for example, log files from the measurement application's device, such as those from a cellular tester.

[0141] The text-based user request generator can then analyze the corresponding image or video and generate a corresponding text-based user request that resembles the measurement application settings shown in the image or video.

[0142] In another embodiment, which may be combined with all other embodiments mentioned above or below, the measurement application control unit may further include a confidence estimator configured to calculate and output confidence values ​​of the response data generated by a pre-trained artificial intelligence algorithm.

[0143] A confidence estimator can be a dedicated unit or component within a measurement application control unit. Alternatively, the confidence estimator can be integrated into a pre-trained artificial intelligence algorithm. The pre-trained AI algorithm can, for example, automatically output a confidence value along with the output response data. The confidence value can refer to a measure of how accurate the response data is for the corresponding user request. Therefore, the user can determine whether the response data is accurate enough for their task based on the confidence value.

[0144] In one embodiment, if the confidence value falls below a predetermined threshold, the user may be prompted to contact the technical support of the manufacturer of the corresponding measurement application equipment and request assistance from a human technical support engineer. Of course, this support can be provided by the manufacturer as a paid service.

[0145] The second aspect: The second aspect of this disclosure relates to a measurement application processing device, a corresponding measurement application, and a corresponding computer-implemented method.

[0146] The features of independent claims address the aforementioned problems. It should be understood that an independent claim of one claim class can be formed similarly to a dependent claim of another claim class.

[0147] Therefore, the following is provided: A measurement application processing device includes: a text-based input interface configured to receive a text-based user request regarding a measurement application; a pre-trained artificial intelligence algorithm coupled to the text-based input interface and configured to generate response data regarding the measurement application based on the text-based user request; and an output interface coupled to the pre-trained artificial intelligence algorithm and configured to output the response data.

[0148] In addition, the following are also provided: A measurement application includes a measurement application processing device according to a second aspect of this disclosure and at least one measurement application device.

[0149] In addition, the following are also provided: A computer-implemented method includes receiving a text-based user request about a measurement application, generating response data about the measurement application based on the text-based user request using a pre-trained artificial intelligence algorithm, and outputting the response data.

[0150] This disclosure is based on the finding that modern measurement application equipment may include a large number of user-configurable parameters that may be difficult for users to remember and understand.

[0151] The most important options are prominently displayed on the main screen of the corresponding measurement application device. However, other options that may be needed only for very specific measurement tasks may be hidden, for example, in submenus of the measurement application device's user interface.

[0152] This measurement application equipment can be used to set up and execute a large number of different measurement applications.

[0153] In particular, inexperienced users may face difficulties setting up measurement applications and configuring measurement application devices within such applications. Inexperienced users may even lack knowledge about the specific functions of highlighted configuration options, especially those hidden in submenus within the user interface of the measurement application device. Furthermore, inexperienced users may lack knowledge about how to interconnect different measurement application devices and devices under test.

[0154] Therefore, this disclosure provides a measurement application processing device, a corresponding measurement application device, and a computer-implemented method.

[0155] The measurement application processing device includes a text-based input interface. This text-based input interface can receive text-based user requests from a user. Such user requests can include natural language text relating to the measurement application.

[0156] Text-based input interfaces can be implemented as data interfaces that receive text in binary form, such as ASCII-encoded text or text encoded using any other character encoding scheme. Such data interfaces can be provided as hardware interfaces (e.g., network interfaces) and program interfaces (e.g., APIs or callback functions), or a combination of both.

[0157] Text-based input interfaces can include any other type of interface, such as APIs, callback functions, shared memory, web-based UIs, and REST. APIs, classes, or interfaces, such as Python classes or interfaces, but not limited to these examples.

[0158] The text-based user request is then fed into a pre-trained artificial intelligence algorithm, which generates corresponding response data based on the provided text-based user request.

[0159] Specifically, pre-trained artificial intelligence algorithms can be trained to receive text-based user requests presented in a natural language style, such as the style when a user makes a text-based user request to another user, or the style when a user expresses a text-based user request in, for example, an online forum.

[0160] Response data can be provided in different formats, which will be explained in more detail below. Generally, in embodiments, response data can be provided in text format. In the context of this disclosure, the term "text format" can refer to any type of text, including but not limited to natural language text, text written in a programming or scripting language, or a combination of both.

[0161] When natural language text is provided as response data, the natural language text can be structured as guidance or instructions to inform the user how to configure the corresponding measurement application device and how to find the corresponding settings or configuration options in the menu structure of the measurement application device.

[0162] The measurement application processing device also includes an output interface for outputting response data. The explanation provided above for the input interface can be applied in analogous way to the output interface. In an embodiment, the input interface and the output interface may be implemented as a single data interface.

[0163] In measurement applications, response data can be provided, for example, to a measurement application device controller, which can further process the response data. The measurement application device controller can output the response data to a user, for example, via a display, or perform internal configuration based on the response data. In such embodiments, the response data can be provided in a form used only by the measurement application device controller. In embodiments, the response data can be provided in multiple forms or styles simultaneously. For example, the response data can be provided in a form usable by the measurement application device controller while also being provided to the user in natural language text format.

[0164] In one embodiment, such a measurement application device may include an audio output interface, such as a speaker, which can output response data as audio to a user. To this end, a text-to-speech engine can be provided in the measurement application device to receive response data from a pre-trained artificial intelligence algorithm and convert the response data into audio.

[0165] In other embodiments, the methods according to this disclosure can also be executed remotely or in a distributed manner. In embodiments, the measurement application processing device can, for example, be provided remotely to one or more measurement application devices. The measurement application processing device can be provided, for example, as a server, or a server-based or cloud-based application, which can be accessed by a user via a network interface. Any control data generated by the measurement application processing device for one or more measurement application devices can be provided to one or more measurement application devices via a corresponding network or data connection. For this purpose, the measurement application devices may include corresponding communication interfaces.

[0166] In embodiments, the communication interface may include any kind of wired and wireless communication interface, such as network communication interface (especially Ethernet), wireless local area network (LAN) or WIFI interface, USB interface, Bluetooth interface, NFC interface, and visible or invisible light-based interface (especially infrared interface).

[0167] Furthermore, servers or cloud servers and one or more measurement application devices can communicate with each other via an intermediary network, and such a network can include any type of network device, such as switches, hubs, routers, firewalls, and different types of network technologies.

[0168] Generally, such a server can be a dedicated server, implemented as a single hardware device. It can also be implemented as a distributed system comprising multiple servers, optionally with a load balancer to distribute the load among them. The server can also be provided as a so-called cloud or cloud server system, implemented through virtualization methods independent of the underlying hardware.

[0169] In this embodiment, the measurement application processing device can operate independently of one or more measurement application devices, and can even be coupled to one or more measurement application devices without communication. In such an embodiment, the user can be the sole recipient of the generated response data, or response data that can be directly interpreted by one or more measurement application devices can be stored on a corresponding data carrier.

[0170] In embodiments, the measurement application processing device may include or be provided as part of at least one dedicated processing element, such as a processing unit, microcontroller, field-programmable gate array (FPGA), complex programmable logic device (CPLD), application-specific integrated circuit (ASIC), etc. Appropriate programs or configurations may be provided to implement the desired functionality. The measurement application processing device may also be provided at least in part as a computer program product including computer-readable instructions executable by the processing element. In another embodiment, the measurement application processing device may be provided as additional or additional functions or methods of firmware or operating system of a processing element already present in the corresponding application (e.g., a measurement application device), implemented as corresponding computer-readable instructions. Such computer-readable instructions may be stored in memory coupled to or integrated into the processing element, which is analogous to a measurement application device controller of the measurement application device. The processing element may load the computer-readable instructions from memory and execute them. This also applies to any other elements, units, or functions disclosed herein that are part of the measurement application processing device, the measurement application device, and the methods for controlling the measurement application device.

[0171] Furthermore, it should be understood that any necessary support or additional hardware, such as power supply circuits and clock generation circuits, can be provided.

[0172] In the context of this disclosure, a measurement application device may include any device that can be used in a measurement application to acquire input signals or generate output signals, or to perform additional or supporting functions in the measurement application. A measurement application device may also include or be implemented as one or more applications, also referred to as one or more measurement applications, which may be executed on a computer device and may communicate with other measurement application devices to perform measurement tasks. A measurement application, also referred to as a measurement setup, may, for example, include at least one or more different measurement application devices for performing electrical, magnetic, or electromagnetic measurements, particularly on a single device under test. Such electrical, magnetic, or electromagnetic measurements may be performed in a measurement laboratory or on a production line of a corresponding production line. A measurement application or measurement setup may be used to identify a single device under test, i.e., to determine the correct electrical operation of each device under test.

[0173] Therefore, measurement application equipment may include at least one signal acquisition section for acquiring the electrical, magnetic, or electromagnetic signal to be measured from the device under test, or at least one signal generation section for generating the electrical, magnetic, or electromagnetic signal that can be provided to the device under test. Such a signal acquisition section may include, but is not limited to, a front-end for acquiring, filtering, attenuating, or amplifying electrical signals. The signal generation section may include, but is not limited to, corresponding signal generators, amplifiers, and filters.

[0174] Furthermore, when acquiring signals, the measurement application device may include a signal processing section capable of processing the acquired signals. Processing may include converting the acquired signals from analog to digital signals, as well as any other type of digital signal processing, such as converting the signal from the time domain to the frequency domain.

[0175] Measurement application equipment may also include a user interface to display the acquired signals to the user and allow the user to control the measurement application equipment. Of course, a housing can be provided to house the various components of the measurement application equipment. It should be understood that additional components, such as power supply circuits and communication interfaces, can be provided.

[0176] Measurement application equipment can be a standalone device that operates without any other components in the measurement application to perform tests on the device under test. Alternatively, it can be equipped with communication capabilities to interact with other measurement application equipment.

[0177] Measurement application equipment may include, for example, signal acquisition devices such as oscilloscopes (especially digital oscilloscopes), spectrum analyzers, or vector network analyzers. Such measurement application equipment may also include signal generation devices, such as signal generators (especially arbitrary signal generators, also known as arbitrary waveform generators) or vector signal generators. Other possible measurement application equipment includes devices similar to calibration standards or measurement probe tips.

[0178] Of course, at least some of the possible functions, such as signal acquisition and signal generation, can be combined in a single measurement application device.

[0179] In embodiments, the measurement application device may include a pure data acquisition device capable of acquiring input signals and providing the acquired input signals as digital input signals to a corresponding data storage or application server. Such a pure data acquisition device does not necessarily include a user interface or display. Instead, it can be remotely controlled, for example, via a suitable data interface such as a network interface or USB interface. The same applies to pure signal generation devices that generate output signals without including any user interface or configuration input elements. Instead, such signal generation devices can be operated remotely via a data connection.

[0180] Using the measurement application processing device, measurement application, and method according to this disclosure, users can describe measurement applications and receive suggestions about various measurement applications as if they were communicating with other users.

[0181] For example, a text-based user request could refer to a general description of a measurement application. The response data, then provided by a pre-trained artificial intelligence algorithm, could include information about how to implement such a measurement application and which measurement application devices are used for it.

[0182] In an embodiment, the measurement application processing device can adapt the style of the response data to the user's level of knowledge. This can be done, for example, by using a preprocessor described below. The preprocessor can, for example, generate a corresponding preprocessed text-based request that indicates the response should include a specific level of detail.

[0183] Other embodiments of this disclosure are the subject of other dependent claims and the following description with reference to the accompanying drawings.

[0184] The dependent claims that directly or indirectly reference claim 37 according to the second aspect of this disclosure are described in more detail below. To avoid doubt, features of the dependent claims relating to the measurement application processing apparatus can be combined with each other in all variations, and the disclosure of the specification is not limited to the claim dependencies specified in the claim set. Furthermore, in all variations, features of other independent claims can be combined with any feature of the dependent claims relating to the measurement application processing apparatus, wherein in the method, the respective method steps perform the functions of the respective measurement application processing apparatus elements.

[0185] In embodiments that can be combined with all other embodiments of the measurement application processing device mentioned above or below, the measurement application processing device may further include an audio input interface configured to receive spoken requests, and a speech recognition unit coupled to the audio input interface and the text-based input interface. The speech recognition unit may be configured to convert the spoken request into a text-based request and provide the text-based request as a text-based user request to the text-based input interface.

[0186] The audio input interface can be provided as a local or hardware audio input interface in a measurement application processing device, or in a measurement application device that implements or includes a measurement application processing device.

[0187] In other embodiments, the audio input interface may be provided as a data interface for receiving audio data from another device. This data interface may be provided as a hardware interface, a software interface, or a combination of both. Generally, the hardware interface of such a data interface serving as an audio interface may include any type of wired and wireless communication interface, such as network communication interfaces (especially Ethernet), wireless LAN or Wi-Fi interfaces, USB interfaces, Bluetooth interfaces, NFC interfaces, and interfaces based on visible or invisible light (especially infrared interfaces).

[0188] An audio input interface is coupled to a speech recognition unit, which converts spoken requests (i.e., audio data) received via the audio input interface into text-based user requests. These text-based user requests can then be provided to the text-based input interface, just like any other text-based user request, for further processing by a pre-trained artificial intelligence algorithm.

[0189] The speech recognition unit can be provided as a hardware-based unit, a software-based unit, or a combination of both, as noted above for measurement application processing devices.

[0190] Using the audio input interface and voice recognition unit, users can communicate naturally with the measurement application processing device, just as if they were talking to other users.

[0191] In another embodiment, which can be combined with all other embodiments of the measurement application processing device mentioned above or below, the pre-trained artificial intelligence algorithm may be pre-trained using at least one of the following: user manuals for one or more measurement application devices or measurement applications, data sheets for one or more measurement application devices or measurement applications, application notes for one or more measurement application devices or measurement applications, data sheets for electronic devices, application notes for electronic devices, articles about electronic circuits, online forum discussions about electronic circuits, and videos about electronic circuits.

[0192] Pre-trained artificial intelligence algorithms need to be trained on data about one or more measurement application devices and measurement applications that can be performed using one or more measurement application devices, which may involve text-based user requests.

[0193] Generally, manufacturers of one or more measurement application devices already provide a wide selection of training data. This training data may be provided, for example, in the form of user manuals, datasheets, and application notes that the measurement application device manufacturer may publish.

[0194] In one embodiment, the pre-trained artificial intelligence algorithm can be pre-trained based on general data (such as freely available text) that is not specific to any measurement application device.

[0195] Then, training data associated with one or more measurement application devices and potential measurement applications can be used to fine-tune the pre-trained artificial intelligence algorithm. This fine-tuning will allow the pre-trained AI algorithm to appropriately respond to text-based user requests regarding the measurement application.

[0196] In one embodiment, another pre-trained algorithm may be provided, trained to provide textual descriptions of images and charts. This pre-trained algorithm can be used to interpret the content of images or charts provided in training data, particularly those provided in user manuals, data sheets, and application notes, in text form to a pre-trained artificial intelligence algorithm, thereby performing the training of the pre-trained artificial intelligence algorithm.

[0197] In another embodiment, which may be combined with all other embodiments of the measurement application processing device mentioned above or below, the pre-trained artificial intelligence algorithm may include a large language model based on at least one of statistical models (such as N-gram), recurrent neural networks (such as long short-term LSTM models), bidirectional encoded representations based on Transformer models, and generative pre-trained Transformer models.

[0198] While two specific types of large language models have been explicitly disclosed above, it should be understood that pre-trained artificial intelligence algorithms can include any algorithm that can be trained on a set of training data, enabling it to generate response data based on text-based user requests.

[0199] In another embodiment, which can be combined with all other embodiments of the measurement application processing device mentioned above or below, a pre-trained artificial intelligence algorithm can be configured to receive a text-based user request regarding the settings of the measurement application and generate settings response data that includes a corresponding explanation of the settings of the measurement application.

[0200] As mentioned above, users can provide questions about measurement applications, especially about the settings of specific measurement applications.

[0201] Users may wish to measure specific types of devices (such as amplifiers) or signals (such as specific bus signals, such as SPI or I2C signals). In an embodiment, a user may more specifically want to measure the voltage level of the output pin of a specific device under test (such as an amplifier).

[0202] Text-based user requests may sound like, but are not limited to, “How do I measure the SPI bus?”, “How do I measure the I2C bus?”, “What settings are needed to measure the voltage level at the output of a type XXX amplifier?”, where XXX is the type of amplifier.

[0203] Pre-trained artificial intelligence algorithms can be trained to generate response data that includes specific explanations about the setup, i.e., information explaining to the user how to create or set up the corresponding measurement application.

[0204] Pre-trained artificial intelligence algorithms can be trained to include, for example, information about how to configure the corresponding measurement application devices in a measurement application within the setup response data. The setup response data may also include information about how to dock or connect multiple measurement application devices in the measurement application. In embodiments, this setup response data may be provided as a block diagram or in combination with a block diagram, as described below. The setup response data may indicate which measurement application devices are required and which ports of the measurement application devices need to be coupled to the ports of other measurement application devices or DUTs.

[0205] In another embodiment, which can be combined with all other embodiments of the measurement application processing device mentioned above or below, a pre-trained artificial intelligence algorithm can be configured to generate setup response data indicating which measurement application devices are used and how to connect these devices to set up the measurement application.

[0206] When implementing a specific measurement application, users may need information about which measurement application devices are used for that application.

[0207] Therefore, pre-trained artificial intelligence algorithms can be trained to indicate to users which measurement application equipment they need to implement the corresponding measurement applications.

[0208] In one embodiment, the pre-trained artificial intelligence algorithm can be configured to provide multiple alternative settings, each using a different measurement application device.

[0209] A pre-trained AI algorithm can be configured to provide information about a single setting without requiring an additional request from the user. The user can then proactively request alternative settings, which the pre-trained AI algorithm can provide.

[0210] If a user points out errors or inaccuracies in the provided measurement application settings, a pre-trained AI algorithm can be configured to correct these settings. For example, a user might indicate that a particular measurement application device in the indicated settings is unavailable. In this case, the pre-trained AI algorithm can provide the user with alternative measurement application settings that do not include the unavailable device, but instead include one or more alternative devices to replace the unavailable one. The pre-trained AI algorithm can also indicate that even if a specific measurement application device is currently unavailable, it is still required to perform the corresponding measurement application task. In this case, the response data can indicate to the user where to obtain the measurement application device. In this context, "obtaining" could also refer to obtaining the module or functionality of a measurement application device that is available to the user, but without having a license for that module or functionality.

[0211] Pre-trained artificial intelligence algorithms can also include indications of measurement application devices, functions, or modules in the response data. These devices, functions, or modules can be added to the measurement application to improve the quality of the measurement, such as accuracy.

[0212] In another embodiment, which can be combined with all other embodiments of the measurement application processing device mentioned above or below, a pre-trained artificial intelligence algorithm can be configured to generate a block diagram of the settings for the measurement application.

[0213] As mentioned above, responses provided by pre-trained artificial intelligence algorithms can be text-based. However, text-based explanations of measurement application settings can be difficult for users to understand, especially when the measurement application setup is complex and includes multiple different measurement application devices.

[0214] Therefore, pre-trained artificial intelligence algorithms can also be trained or configured to output block diagrams of measurement application settings.

[0215] Such block diagrams can be provided, for example, by a pre-trained artificial intelligence algorithm in the form of an ASCII-based diagram, also known as an ASCII art diagram. In other embodiments, the pre-trained artificial intelligence algorithm may also output ASCII codes for an SVG file that includes the corresponding block diagram. In embodiments, combination is possible, where the pre-trained artificial intelligence algorithm can provide both ASCII art diagrams and SVG files.

[0216] In other embodiments that can be combined with the above embodiments, a pre-trained artificial intelligence algorithm can forward a textual description of the block diagram to an image generation algorithm, such as an AI-based image generation algorithm. Such a pre-trained artificial intelligence algorithm may include at least one of a neural network, a Transformer, and a generative adversarial network.

[0217] Using this diagram, the user will be provided with an easy-to-understand representation of the measurement application settings, which will allow him to easily implement the recommended measurement application settings.

[0218] In another embodiment, which can be combined with all other embodiments of the measurement application processing device mentioned above or below, a pre-trained artificial intelligence algorithm can be further configured to generate control response data, which includes corresponding control commands for at least one measurement application device.

[0219] Unlike explaining the different features of a measurement application to a user, control response data can directly provide control commands that the user can implement within the measurement application (e.g., within one or more measurement application devices).

[0220] These control commands can be provided to the user in the form of natural text commands. Example control commands may include, but are not limited to, "Set the voltage range to 0V-100V", "Set the magnification factor to 10x", "Set the scaling of the graph's X-axis to 0.5", "Start measurement", "Stop measurement", "Start signal generation", "Stop signal generation", etc.

[0221] Generally, these control commands may include any options, parameters, or user-input commands that the measurement application device may include or allow in the measurement application settings.

[0222] In another embodiment, which can be combined with all other embodiments of the measurement application processing device mentioned above or below, the measurement application processing device may further include a code generator coupled to or integrated with a pre-trained artificial intelligence algorithm. The code generator may be configured to generate configuration and control commands for the measurement application device in a predetermined control or programming language.

[0223] While the control commands described above are easy for users to understand, measurement application devices may not be directly controlled by such text-based commands.

[0224] However, modern measurement applications include more than just user interfaces for controlling the equipment. Instead, these applications are often programmable and controllable.

[0225] Such control programs can be provided, for example, in a domain-specific scripting or programming language, such as the SCPI language (Standard Commands for Programmable Instruments). In other embodiments, the control programs can be provided in more general programming languages, such as Python or JavaScript, and these control programs can be interpreted in the measurement application device or as a compiled program executed in the measurement application device.

[0226] Therefore, a code generator, or a pre-trained artificial intelligence algorithm with an integrated code generator, can be trained or configured to generate control commands in the response data. These control commands can be provided in any suitable format, such as the control program described above, but are not limited to such a program.

[0227] The code generator can also be configured to use and modify existing sets of control commands or procedures. This modification can adapt the existing sets of control commands or procedures to a specific measurement application or task. For example, the modification could involve optimizing the existing sets of control commands or procedures to provide higher measurement performance or greater measurement accuracy.

[0228] In one embodiment, a pre-trained artificial intelligence algorithm can receive a text-based user request regarding measurement application settings and can output a description of the measurement application settings for any of the embodiments described herein to the user.

[0229] In one embodiment, the pre-trained artificial intelligence algorithm can also output configuration and control commands for one or more measurement application devices in a predetermined control or programming language for setting up the measurement application.

[0230] If an external code generator is used, a pre-trained artificial intelligence algorithm can provide the code generator with the aforementioned text-based control commands. The code generator can then generate corresponding configuration and control commands for one or more measurement application devices in a predetermined control or programming language for the measurement application setup. When generating configuration and control commands for a single measurement application device, the code generator can also consider any number of measurement application devices present in the measurement application setup.

[0231] In the configuration where the measurement application processing device is communicationally coupled to the measurement application device, the measurement application processing device can directly provide configuration and control commands to the corresponding measurement application device.

[0232] Pre-trained artificial intelligence algorithms or code generators can also be configured to generate code that implements the functionality required in the measurement application setup, which may not be provided in the corresponding measurement application equipment.

[0233] This code can be provided, for example, in the form of interpretable code (e.g., Python or JavaScript code) that can be interpreted within the measurement application device, or in the form of executable code (e.g., compiled C or C++ code) that can be executed within the measurement application device. In embodiments, the code can be provided as VHDL code or configuration code for configurable logic elements (such as FPAGs) in the measurement application device.

[0234] This code can implement data processing functions requested by users in text-based user requests, but these functions are not provided in the corresponding measurement application devices.

[0235] To this end, measurement application devices can provide corresponding APIs that allow code to access measurement data and output processed data for further processing within the measurement application device, such as displaying the processed data to a user.

[0236] Using this code generation option, users without programming knowledge can still request measurement application settings that would otherwise require programming knowledge.

[0237] In this embodiment, a pre-trained artificial intelligence algorithm can provide an interpretation of the generated code. This interpretation can be requested, for example, through a preprocessor mentioned below.

[0238] In another embodiment, which may be combined with all other embodiments of the measurement application processing device mentioned above or below, the measurement application processing device may further include a preprocessor coupled to a pre-trained artificial intelligence algorithm. The preprocessor may be configured to provide a pre-processed text-based request to the pre-trained artificial intelligence algorithm before the pre-trained artificial intelligence algorithm operates on the text-based user request.

[0239] A preprocessor can be used to instruct a pre-trained artificial intelligence algorithm on general information that a user might, for example, skip or forget, included in a text-based user request. Other information that can be provided by the preprocessor includes general information about the user's available devices, the user's level of knowledge, or any other information that might be relevant to planning measurement application settings for a human user.

[0240] Preprocessed text-based requests can be fed to pre-trained artificial intelligence algorithms before the actual text-based user requests.

[0241] In an embodiment, the preprocessor may provide the pre-trained artificial intelligence algorithm with information about at least one of the following, but not limited to: the measurement application devices available to the user, the specifications of one or more measurement application devices, and the type or format of the response data required.

[0242] The example preprocessed text-based requests proposed by the preprocessor may include, but are not limited to, the following requests: "Available measurement application equipment includes MEAS1, MEAS2, ..., MEASx. For your answer, please select only from the available measurement application equipment." MEAS1 to MEASx are the available measurement application equipment.

[0243] "The MEAS1 measurement application device is equipped with optional modules MOD1, MOD2, and MOD3. If necessary, include these modules in the recommended measurement application settings." MOD1, MOD2, and MOD3 are optional modules that users can install in the measurement application device.

[0244] In an embodiment, the preprocessor may include another pre-trained artificial intelligence algorithm trained to generate pre-processed text-based requests, as exemplarily noted above. This pre-trained AI algorithm may be trained, for example, based on a set of example descriptions of measurement application settings and corresponding pre-processed text-based requests.

[0245] In other embodiments, the preprocessor may be implemented without using a pre-trained artificial intelligence algorithm. These embodiments of the preprocessor may include, for example, a state machine, which may be configured to append relevant information about the measurement application settings to a corresponding pre-processed text-based request. The information about the measurement application settings may be provided, for example, in tabular form, where each row includes information about the components of the measurement application settings. Generally, this information may be provided in any suitable, particularly structured, format.

[0246] This information can, for example, indicate the type of component, such as a signal generating device, signal acquiring device, device under test, probe, adapter, etc. It can also indicate the number of outputs or inputs of the corresponding component, and the range of values ​​supported by the inputs and outputs. Generally, this data can include any data typically provided in the user manual or datasheet for the relevant measurement application.

[0247] In such an embodiment, the preprocessor can, for example, simply insert information into a template string and concatenate the template strings of all elements in the measurement application settings to generate a corresponding preprocessed text-based request. Combining this with an AI-based preprocessor is possible.

[0248] In embodiments that can be combined with all other embodiments of the measurement application processing device mentioned above or below, the pre-trained artificial intelligence algorithm can be configured to enhance text-based user requests and output the enhanced text-based user requests via an output interface. The pre-trained artificial intelligence algorithm can be configured to generate response data after the user confirms the enhanced text-based user request.

[0249] In this context, enhancement refers to including additional information in a text-based user request that the user may not know or may forget to include in their text-based user request.

[0250] An enhanced text-based user request can be viewed as a technically more precise expression of a text-based user request. Pre-trained AI algorithms can also be configured to offer improvements to the original text-based user request.

[0251] In embodiments, these functionalities of the pre-trained artificial intelligence algorithm can be implemented as a preprocessor. The preprocessor can, for example, provide a pre-processed text-based request that, exemplarily, instruct at least one of "Please provide a more detailed version of the following request for generating measurement application settings, instead of generating the actual measurement application settings." or "Please correct the following request for generating measurement application settings, instead of generating the actual measurement application settings."

[0252] The enhanced text-based user request may also include informing the user that a certain measurement application device referenced in the original text-based user request lacks a specific installable option required to perform the specific measurement application. The user may then be offered the option to install the specific option.

[0253] In another embodiment, which can be combined with all other embodiments of the measurement application processing device mentioned above or below, the measurement application processing device may further include a text-based user request generator configured to receive at least one non-textual description, such as an image or video of the measurement application device, the device under test, or measurement application settings. The text-based user request generator may also be configured to generate a text-based user request based on at least one image or video.

[0254] By utilizing a text-based user request generator, users are provided with an alternative means to submit their requests to the measurement application processing device.

[0255] Users can simply provide one or more images or videos for the corresponding measurement application without having to provide specific text-based user requests to a pre-trained artificial intelligence algorithm.

[0256] The text-based user request generator can then analyze the corresponding image or video and generate a corresponding text-based user request that resembles the measurement application settings shown in the image or video.

[0257] In embodiments that can be combined with all other embodiments of the measurement application processing device mentioned above or below, the pre-trained artificial intelligence algorithm can be configured to receive text-based user requests regarding the maintenance of the measurement application device in the measurement application and generate maintenance response data including a corresponding explanation of the maintenance of the respective measurement application device.

[0258] Maintenance of measurement application equipment is an important task in every measurement application. Therefore, requests concerning the maintenance of measurement application equipment include requests related to measurement applications according to this disclosure.

[0259] To enable pre-trained artificial intelligence algorithms to support users in the proper maintenance and upkeep of measurement application equipment, the algorithms can be trained using the maintenance and upkeep manuals that the equipment manufacturer may provide. As additional training material, documentation of the measurement application equipment's development process can be used as training data for the pre-trained AI algorithm. Generally, training materials may also include at least one of the following: user manuals for the measurement application equipment, data sheets for the measurement application equipment, application notes for the measurement application equipment, user manuals for electronic devices, data sheets for electronic devices, application notes for electronic device user manuals, articles about electronic circuits, online forum discussions about electronic circuits, and videos about electronic circuits.

[0260] In one embodiment, a pre-trained artificial intelligence algorithm can provide response data upon a specific user request, which includes an explanation of how to maintain the corresponding measurement application equipment.

[0261] In other embodiments, a pre-trained artificial intelligence algorithm can provide such an explanation even if the user does not make a specific request. Conversely, a pre-trained artificial intelligence algorithm can provide such an explanation if performing the corresponding service or repair can improve the measurement results in the corresponding measurement application settings. Therefore, the characteristics concerning the maintenance of the measurement application equipment can be combined with all other characteristics of all other embodiments of the measurement application processing equipment.

[0262] In another embodiment, which may be combined with all other embodiments mentioned above or below, the measurement application processing device may further include a warning generator configured to generate warnings from a user regarding configurations of the measurement application device that are detrimental to a predetermined measurement application.

[0263] The term "warning" in this article refers to user-provided information that indicates which specific settings or configuration options should not be set or executed when effectively performing the corresponding measurement application.

[0264] The warning generator can be provided as a standalone unit, or it can be integrated into a pre-trained artificial intelligence algorithm, or it can be a function of a pre-trained artificial intelligence algorithm. If implemented as a standalone unit, the warning generator can include any kind of suitable algorithm. The warning generator can, for example, include a state machine or database that links the measurement application to a list of settings identified as detrimental or negatively impacting the corresponding measurement application. The warning generator can also include an artificial intelligence-based algorithm capable of generating warnings based on the corresponding inputs.

[0265] In embodiments that can be combined with all other embodiments mentioned above or below, the measurement application processing device may further include a feedback interface configured to receive measurement feedback data, wherein a pre-trained artificial intelligence algorithm may be configured to generate another set of response data based on the original text-based user request and the received measurement feedback data.

[0266] User-provided text-based requests may be very general, such as: "Set up I2C measurements for 0.5 seconds, at a data rate of 100 kBaud, and limit the power supply to 20 mA." Using such generic instructions, the general configuration of the measurement application equipment can be generated by a pre-trained artificial intelligence algorithm.

[0267] However, this general measurement configuration may not provide relevant information to users in all situations. For example, if the measurement application's task is to identify errors on the I2C bus, users may not be able to detect these errors through a general configuration.

[0268] Therefore, a feedback interface is provided. This interface allows measurement feedback data to be provided to the measurement application processing device. This feedback data then allows a pre-trained artificial intelligence algorithm to generate a more optimized set of response data, which can be provided to the measurement application device to perform another measurement that better fulfills the specific measurement application task.

[0269] Measurement feedback data may include at least one of the following: waveforms from the display of the measurement application device, screenshots of the measurement application device, user-provided feedback (especially in the form of natural language feedback), information about the current configuration of the measurement application device, and measurement statistics of the measurement application device.

[0270] In the example of the I2C bus, an indication of voltage glitches at each rising edge of the signal might be found in the measurement feedback data. Therefore, a pre-trained artificial intelligence algorithm can generate another set of response data to trigger a measurement at the rising edge of the signal, display the signal a certain time before the rising edge, and provide an appropriate time scale on the X-axis of the measurement application device's display.

[0271] The feedback interface may be or include a data interface that can receive measurement feedback data from the corresponding measurement application device. Measurement feedback data may also include any data acquired during or derived from the measurement.

[0272] Measurement feedback data may include, but is not limited to, raw measurement data and screenshots of the display of the measurement application device showing the waveform of the acquired signal.

[0273] In this embodiment, the pre-trained artificial intelligence algorithm is able to directly manipulate the measurement feedback data.

[0274] Pre-trained artificial intelligence algorithms can be configured to, for example, indicate how to improve measurements in another set of response data. For instance, if measurement feedback data indicates that the measured waveform may be inaccurate, another set of response data can indicate how to improve the accuracy of the measurement. The corresponding indications from the other set of response data can be provided to the user, and / or corresponding configuration options, code, or scripts can be provided.

[0275] While the measurement application is running, the feedback interface can also receive measurement feedback data. This allows pre-trained AI algorithms to provide the user with a further set of response data "in real time." For example, a pre-trained AI algorithm might determine that the measured signal level is approaching a noise level, and therefore the measurement result may no longer be reliable. In another set of response data, the response data can alert the user to this situation in natural language, and / or provide updated configurations for the corresponding measurement application to increase the signal-to-noise ratio of the running measurement.

[0276] Along with tips or suggestions on how to improve measurements, pre-trained AI algorithms can also provide interpretations of measurement results, as well as indications of why the results are the way they are. Another set of response data can also indicate the "cost" of improvement. In this context, the term "cost" refers to technical costs, such as reducing the measurement quality in one aspect to improve the measurement quality in another. This trade-off exists, for example, between measurement accuracy and the possible measurement duration. This other set of response data can also indicate whether the measurement cannot be further improved and whether the best possible measurement results have been achieved.

[0277] In another embodiment, which may be combined with all other embodiments mentioned above or below, the measurement application processing device may further include a feedback data analyzer disposed between the feedback interface and a pre-trained artificial intelligence algorithm. The feedback data analyzer may be configured to generate a text-based feedback description of the measurement feedback data and provide the text-based feedback description to the pre-trained artificial intelligence algorithm.

[0278] The feedback data analyzer may include another pre-trained artificial intelligence algorithm that can be trained to transform measurement feedback data into text-based feedback descriptions.

[0279] This algorithm can be trained to provide text-based descriptions of image or waveform data. Specifically, it can be trained to describe details of measurement data that a user might easily overlook based on general response data. The algorithm may include or be based on a corresponding visual underlying model.

[0280] The training data for the feedback data analyzer can be taken from, for example, user manuals, data sheets, and available measurement reports, which include descriptions of measurement results and, for example, images of measurement waveforms. In an embodiment, the feedback data analyzer may include an image-to-text conversion algorithm trained on general image and text data and fine-tuned based on data from user manuals, data sheets, and available measurement reports as described above.

[0281] In other embodiments, the measurement application device may include a feedback data analyzer that can provide a text-based feedback description to the measurement application device control unit.

[0282] In another embodiment, which may be combined with all other embodiments mentioned above or below, the feedback data analyzer may be configured to identify at least one of anomalies, related measurements, and related measurement waveform portions in the raw measurement data provided in the measurement feedback data, and provide a corresponding text-based feedback description.

[0283] Users may lack experience in identifying relevant data in measurement results, especially in identifying anomalies.

[0284] Therefore, when the feedback data analyzer is configured to identify such anomalies, relevant measurements, or relevant portions of the measurement waveform, the response data can be regenerated to configure the measurement application equipment to better acquire the relevant measurement data.

[0285] The results provided by the feedback data analyzer can, for example, indicate that the error vector magnitude is primarily affected by the frequency response. A pre-trained artificial intelligence algorithm can then use another set of response data to instruct the user on how to improve the measurement, or which measurement application equipment to use to improve it.

[0286] Typical errors in measurement can include, but are not limited to, phase noise, compression, frequency error, and incorrect scan time. Using the measurement feedback data, a pre-trained artificial intelligence algorithm can generate another set of response data that at least indicates to the user that such errors may occur in the measurement. In an embodiment, this additional set of response data may also include configuration data or settings for the measurement application device to compensate for such errors.

[0287] The feedback data analyzer can also be configured to analyze error messages received from the measurement application device and provide another set of corresponding response data that instructs the user on how to resolve the error, and / or provides control or configuration data for the measurement application device to resolve the error.

[0288] In another embodiment, which may be combined with all other embodiments mentioned above or below, the measurement application processing device may further include a feedback output interface configured to output measurement feedback data to a user. A pre-trained artificial intelligence algorithm may be configured to generate another set of response data based on an original text-based user request and another text-based user request received after the measurement feedback data has been output to the user.

[0289] In another embodiment, which may be combined with all other embodiments mentioned above or below, the feedback output interface may output a text-based feedback description to the user.

[0290] Feedback output interfaces can be used to provide users with measurement feedback data, especially text-based feedback descriptions. For this purpose, feedback output interfaces can include a display or an audio interface. Text-based feedback descriptions can be displayed to the user on a display. Text-based feedback descriptions can also be converted into audio using a text-to-speech converter and played back to the user via an audio interface.

[0291] After receiving the measurement feedback data, the user can then decide to provide instructions to the pre-trained artificial intelligence algorithm to generate response data that can be provided to the corresponding measurement application equipment for correction or adjustment.

[0292] This feedback loop can be repeated as needed and can also be combined with the automatic regeneration mechanism of the response data described above.

[0293] Therefore, users can enter a dialogue with the control unit of the measurement application equipment and iteratively improve the measurement results.

[0294] In an embodiment, the pre-trained artificial intelligence algorithm may include a fixed pre-trained model.

[0295] In another embodiment, which may be combined with all other embodiments mentioned above or below, the pre-trained artificial intelligence algorithm may be configured to perform reinforcement learning based on another text-based user request received after the measurement feedback data has been output to the user.

[0296] By using flexible models that can be further trained, for example, using reinforcement learning, the quality of response data can be continuously improved.

[0297] Furthermore, pre-trained AI algorithms can be trained for application-specific measurement tasks. For example, pre-trained AI algorithms can be specifically trained for automotive measurement applications. In such embodiments, another text-based user request can be automatically generated for reinforcement learning.

[0298] To perform reinforcement learning, multiple measurement application device control units can provide their respective learning data to a centrally trained, pre-trained artificial intelligence algorithm. This centrally trained, pre-trained AI algorithm can, for example, be hosted and trained by the manufacturer of the measurement application device control unit. Alternatively, locally trained, pre-trained AI algorithms can be provided to a central model management unit, which can then merge the locally trained, pre-trained AI algorithms. Attached Figure Description

[0299] To gain a more complete understanding of this disclosure and its advantages, the following description will now be made in conjunction with the accompanying drawings. The disclosure will be explained in more detail below using exemplary embodiments detailed in the schematic diagrams of the accompanying drawings, wherein: Figure 1 A block diagram of an embodiment of a measurement application control unit according to the first aspect of this disclosure is shown; Figure 2 A block diagram of another embodiment of the measurement application control unit according to the first aspect of this disclosure is shown; Figure 3 A block diagram of another embodiment of the measurement application control unit according to the first aspect of this disclosure is shown; Figure 4 A block diagram of another embodiment of the measurement application control unit according to the first aspect of this disclosure is shown; Figure 5 A block diagram of another embodiment of the measurement application control unit according to the first aspect of this disclosure is shown; Figure 6 A block diagram of another embodiment of the measurement application control unit according to the first aspect of this disclosure is shown; Figure 7 A block diagram of another embodiment of the measurement application control unit according to the first aspect of this disclosure is shown; Figure 8 A block diagram of another embodiment of the measurement application control unit according to the first aspect of this disclosure is shown; Figure 9 A block diagram of another embodiment of the measurement application control unit according to the first aspect of this disclosure is shown; Figure 10 A block diagram of another embodiment of the measurement application control unit according to the first aspect of this disclosure is shown; Figure 11 A block diagram of an embodiment of a measurement application device according to the first aspect of this disclosure is shown; Figure 12 A flowchart illustrating an embodiment of the method according to the first aspect of this disclosure is shown; Figure 13 A block diagram of an oscilloscope is shown that can be used with embodiments of a measurement application control unit or method according to any embodiment of the first aspect of this disclosure; Figure 14 A block diagram of another oscilloscope is shown that can be used with embodiments of a measurement application control unit or method according to any of the first aspects of this disclosure; Figure 15 A block diagram of an embodiment of a measurement application processing apparatus according to a second aspect of this disclosure is shown; Figure 16 A block diagram of another embodiment of the measurement application processing apparatus according to the second aspect of this disclosure is shown; Figure 17 A block diagram of another embodiment of the measurement application processing apparatus according to the second aspect of this disclosure is shown; Figure 18 A block diagram of another embodiment of the measurement application processing apparatus according to the second aspect of this disclosure is shown; Figure 19 A block diagram of another embodiment of the measurement application processing apparatus according to the second aspect of this disclosure is shown; Figure 20 A block diagram of another embodiment of the measurement application processing apparatus according to the second aspect of this disclosure is shown; Figure 21 A block diagram of another embodiment of the measurement application processing apparatus according to the second aspect of this disclosure is shown; Figure 22 A block diagram of another embodiment of the measurement application processing apparatus according to the second aspect of this disclosure is shown; Figure 23 A block diagram of another embodiment of the measurement application processing apparatus according to the second aspect of this disclosure is shown; Figure 24 A block diagram of another embodiment of the measurement application processing apparatus according to the second aspect of this disclosure is shown; Figure 25 A block diagram illustrating a measurement application according to the second aspect of this disclosure is shown; Figure 26 A flowchart illustrating an embodiment of the method according to the second aspect of this disclosure is shown; Figure 27 A block diagram of an oscilloscope that can be used with an embodiment of a measurement application processing device according to a second aspect of this disclosure is shown; Figure 28 A block diagram of another oscilloscope that can be used with an embodiment of a measurement application processing device according to a second aspect of this disclosure is shown; In the accompanying drawings, unless otherwise specified, the same reference numerals denote the same elements. Detailed Implementation

[0300] Figure 1 A block diagram of the measurement application control unit 10100 is shown.

[0301] The measurement application control unit 10100 includes a text-based input interface 10101 that receives a text-based user request 10102 regarding a measurement application device. The measurement application control unit 10100 also includes a pre-trained artificial intelligence algorithm 10103 coupled to the text-based input interface 10101, which generates response data 10104 regarding the measurement application device based on the text-based user request 10102. The measurement application control unit 10100 also includes an output interface 10105 coupled to the pre-trained artificial intelligence algorithm 10103, and configured to output the response data 10104. The explanations provided herein regarding any embodiment of the measurement application control unit can also be applied to the measurement application control unit 10200 with necessary modifications.

[0302] The measurement application control unit 10100 can be implemented as a dedicated device, such as laboratory equipment, similar to other laboratory measurement application equipment, such as oscilloscopes, network analyzers, signal generators, etc. This measurement application control unit 10100 may include a housing, a user interface such as a display or touchscreen, buttons, knobs, a mouse, a keyboard, etc., as a text-based input interface 10101, a corresponding processor or processing element, and a corresponding data interface such as a network interface, which can also serve as a text-based input interface 10101. The measurement application control unit 10100 can also be integrated into any type of laboratory measurement application equipment.

[0303] In an embodiment, the measurement application control unit 10100 may be implemented on a computer or server, which executes a computer program product including instructions that, when executed by the computer or server (particularly a processor within the computer or server), cause the computer or server to perform a computer-implemented method according to the first aspect of this disclosure. Such a computer or server may be located remotely from other measurement application devices and coupled to other measurement application devices via a network connection.

[0304] In an embodiment, the pre-trained artificial intelligence algorithm 10103 may be pre-trained using any combination of the following: user manuals for measurement application devices, data sheets for measurement application devices, application notes for measurement application devices, user manuals for electronic devices, data sheets for electronic devices, application notes for electronic devices, articles about electronic circuits, online forum discussions about electronic circuits, and videos about electronic circuits.

[0305] Figure 2 A block diagram of another embodiment of the measurement application control unit 10200 is shown. The measurement application control unit 10200 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10200 includes a text-based input interface 10201 that receives a text-based user request 10202 regarding a measurement application device. The measurement application control unit 10200 also includes a pre-trained artificial intelligence algorithm 10203 coupled to the text-based input interface 10201, which generates response data 10204 regarding the measurement application device based on the text-based user request 10202. The measurement application control unit 10200 also includes an output interface 10205 coupled to the pre-trained artificial intelligence algorithm 10203, and the output interface 10205 is configured to output the response data 10204. The explanations provided herein regarding any embodiment of the measurement application control unit can also be applied to the measurement application control unit 10200 with necessary modifications.

[0306] The measurement application control unit 10200 also includes an audio input interface 10228. The audio input interface 10228 is coupled to a speech recognition unit 10230, and the speech recognition unit 10230 is coupled to a text-based input interface 10201.

[0307] Audio input interface 10228 can receive, for example, spoken requests 10229 from a user. It should be understood that audio input interface 10228 may include, for example, a microphone for recording spoken requests 10229. In embodiments, audio input interface 10228 may include a data interface for receiving spoken requests 10229 provided digitally, which are recorded elsewhere. A combination of both approaches is possible.

[0308] The speech recognition unit 10230 can then convert the spoken request 10229 into a text-based request 10231. This text-based request 10231 can then be forwarded to the text-based input interface 10201, just like a text-based user request 10202. The text-based input interface 10201 can then process the text-based request 10231 as if it were any other text-based user request 10202.

[0309] The speech recognition unit 10230 may include any suitable element of any type. Example embodiments of the speech recognition unit 10230 may be based, for example, on a computer-implemented algorithm, particularly a corresponding artificial intelligence-based computer-implemented algorithm.

[0310] Figure 3 A block diagram of a measurement application control unit 10300 is shown. The measurement application control unit 10300 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10300 includes a text-based input interface 10301 that receives a text-based user request 10302 regarding a measurement application device. The measurement application control unit 10300 also includes a pre-trained artificial intelligence algorithm 10303 coupled to the text-based input interface 10301, which generates response data 10304 regarding the measurement application device based on the text-based user request 10302. The measurement application control unit 10300 also includes an output interface 10305 coupled to the pre-trained artificial intelligence algorithm 10303, and the output interface 10305 is configured to output the response data 10304. The explanations provided herein regarding any embodiment of the measurement application control unit can also be applied to the measurement application control unit 10300 with necessary modifications.

[0311] In the measurement application control unit 10300, the pre-trained artificial intelligence algorithm 10303 includes a large language model 10335 for implementing the functions of the pre-trained artificial intelligence algorithm 10303.

[0312] Large language models 10335 can be based on any appropriate type of algorithm, such as statistical models, recurrent neural networks, bidirectional encoding representations based on Transformer models, and generative pre-trained Transformer models.

[0313] Figure 4 A block diagram of a measurement application control unit 10400 is shown. The measurement application control unit 10400 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10400 includes a text-based input interface 10401 that receives a text-based user request 10402 regarding a measurement application device. The measurement application control unit 10400 also includes a pre-trained artificial intelligence algorithm 10403 coupled to the text-based input interface 10401, which generates response data 10404 regarding the measurement application device based on the text-based user request 10402. The measurement application control unit 10400 also includes an output interface 10405 coupled to the pre-trained artificial intelligence algorithm 10403, and the output interface 10405 is configured to output the response data 10404. The explanations provided herein regarding any embodiment of the measurement application control unit can also be applied to the measurement application control unit 10400 with necessary modifications.

[0314] The measurement application control unit 10400 also includes a user input interface 10438. The user input interface 10438 is depicted only as an exemplary front panel of the measurement application device, having four buttons 10440-1 to 10440-n, two knobs 10441-1 and 10441-2, and a touchscreen 10442. The user input interface 10438 shown is merely exemplary. In other embodiments, any other type of input element and / or arrangement may be selected. Furthermore, in other embodiments, the user input interface 10438 may include a software-based interface, such as an interface to a locally executed application, or an interface to a corresponding website served by a server of the measurement application control unit 10400.

[0315] Using the user input interface 10438, a user can provide user input 10443 to a pre-trained artificial intelligence algorithm 10403, which relates to control measurement application equipment.

[0316] Therefore, the pre-trained artificial intelligence algorithm 10403 is simultaneously provided with text-based user requests 10402 and user input 10443.

[0317] User input 10443 could, for example, refer to a specific element on the display of the corresponding measuring device on the touchscreen 10442. Simultaneously, the user can provide a text-based user request 10402, such as "What is this?".

[0318] Then, the pre-trained artificial intelligence algorithm 10403 can combine the text-based user request 10402 with the user input 10443 and provide corresponding response data 10404.

[0319] In this embodiment, user input 10443 can be provided to a pre-trained artificial intelligence algorithm 10403 as a pre-processed text-based request, which will be referred to below. Figure 6 To explain in more detail, a preprocessor can be coupled to the user input interface 10438 to generate a preprocessed text-based request. This preprocessed text-based request could, for example, include something like, "The user is pointing to the label of the Y-axis of the graph shown on the oscilloscope display and is asking a question," where the original text-based user request 10402 can be provided directly after the preprocessed text-based request.

[0320] The pre-trained artificial intelligence algorithm 10403 can then generate the corresponding response in the response data 10404. In the example above, the response data 10404 may include a response to the user's question. In the case of other text-based user requests 10402, the response data 10404 may include the content requested in the text-based user request 10402.

[0321] Figure 5A block diagram of a measurement application control unit 10500 is shown. The measurement application control unit 10500 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10500 includes a text-based input interface 10501 that receives a text-based user request 10502 regarding a measurement application device. The measurement application control unit 10500 also includes a pre-trained artificial intelligence algorithm 10503 coupled to the text-based input interface 10501, which generates response data 10504 regarding the measurement application device based on the text-based user request 10502. The measurement application control unit 10500 also includes an output interface 10505 coupled to the pre-trained artificial intelligence algorithm 10503, and the output interface 10505 is configured to output the response data 10504. The explanations provided herein regarding any embodiment of the measurement application control unit can also be applied to the measurement application control unit 10500 with necessary modifications.

[0322] The measurement application control unit 10500 also includes a translator 10546. The translator 10546 is positioned between the text-based input interface 10501 and the pre-trained artificial intelligence algorithm 10503.

[0323] The translator 10546 can translate a text-based user request 10502 that is not trained to operate using a pre-trained artificial intelligence algorithm 10503 into a translated text-based user request 10546 that is capable of operating using a pre-trained artificial intelligence algorithm 10503.

[0324] The translator 10546 can also recognize the language of the original text-based user request 10502, and can directly pass any text-based user request 10502 provided in a language that the pre-trained artificial intelligence algorithm 10503 can operate on to the pre-trained artificial intelligence algorithm 10503.

[0325] Alternatively, the text-based input interface 10501 can be adapted to recognize the language of the text-based user request 10502, and the text-based user request 10502 provided in a language that the pre-trained artificial intelligence algorithm 10503 can operate on can be directly provided to the pre-trained artificial intelligence algorithm 10503.

[0326] Figure 6A block diagram of a measurement application control unit 10600 is shown. The measurement application control unit 10600 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10600 includes a text-based input interface 10601 that receives a text-based user request 10602 regarding a measurement application device. The measurement application control unit 10600 also includes a pre-trained artificial intelligence algorithm 10603 coupled to the text-based input interface 10601, which generates response data 10604 regarding the measurement application device based on the text-based user request 10602. The measurement application control unit 10600 also includes an output interface 10605 coupled to the pre-trained artificial intelligence algorithm 10603, and the output interface 10605 is configured to output the response data 10604. The explanations provided herein regarding any embodiment of the measurement application control unit can also be applied to the measurement application control unit 10600 with necessary modifications.

[0327] The measurement application control unit 10600 also includes a preprocessor 10648. The preprocessor 10648 is coupled to a text-based input interface 10601 and can provide preprocessed text-based requests 10649 to the text-based input interface 10601.

[0328] The preprocessed text-based request 10649 is used to preprocess the pre-trained artificial intelligence algorithm 10603, and the preprocessed text-based request 10649 can be provided to the pre-trained artificial intelligence algorithm 10603 before the text-based user request 10602 is provided to the pre-trained artificial intelligence algorithm 10603.

[0329] In this embodiment, a text-based user request 10602 may be provided to a preprocessor 10648 instead of a text-based input interface 10601. The preprocessor 10648 may then combine the preprocessed text-based request 10649 with the received text-based user request 10602.

[0330] Figure 7A block diagram of a measurement application control unit 10700 is shown. The measurement application control unit 10700 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10700 includes a text-based input interface 10701 that receives text-based user requests 10702-1, 10702-2 regarding a measurement application device. The measurement application control unit 10700 also includes a pre-trained artificial intelligence algorithm 10703 coupled to the text-based input interface 10701, which generates response data 10704 regarding the measurement application device based on the text-based user request 10702. The measurement application control unit 10700 also includes an output interface 10705 coupled to the pre-trained artificial intelligence algorithm 10703, and configured to output the response data 10704. The explanations provided herein regarding any embodiment of the measurement application control unit may also be applied to the measurement application control unit 10700 with necessary modifications.

[0331] The measurement application control unit 10700 receives a first type of text-based user request 10702-1, which may include a user request regarding the usage method of the measurement application device. Furthermore, the measurement application control unit 10700 receives a second type of text-based user request 10702-2, which includes a user request regarding the control of the measurement application device.

[0332] Therefore, the pre-trained artificial intelligence algorithm 10703 will provide the use of response data 10752 and control response data 10753 in response data 10704.

[0333] The measurement application control unit 10700 also includes a code generator 10754. The code generator 10754 can receive control response data 10753 or other corresponding instructions from a pre-trained artificial intelligence algorithm 10703, and can generate corresponding configuration and control commands 10755 in any suitable scripting or programming language.

[0334] In an embodiment, the code generator 10754 may be provided as a function or element of the pre-trained artificial intelligence algorithm 10703, or may be included in the pre-trained artificial intelligence algorithm 10703.

[0335] Figure 8A block diagram of a measurement application control unit 10800 is shown. The measurement application control unit 10800 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10800 includes a text-based input interface 10801 that receives a text-based user request 10802 regarding a measurement application device. The measurement application control unit 10800 also includes a pre-trained artificial intelligence algorithm 10803 that generates response data 10804 regarding the measurement application device based on the text-based user request 10802. The measurement application control unit 10800 also includes an output interface 10805 coupled to the pre-trained artificial intelligence algorithm 10803, and the output interface 10805 is configured to output the response data 10804. The explanations provided herein regarding any embodiment of the measurement application control unit can also be applied to the measurement application control unit 10800 with necessary modifications.

[0336] The measurement application control unit 10800 also includes a complexity estimator 10858. The complexity estimator 10858 is used to estimate or calculate the complexity of the text-based user request 10802. In the measurement application control unit 10800, the complexity is calculated by unit C. The calculation of complexity can be performed, for example, based on the length of the text-based user request 10802, or the number of main clauses and / or subordinate clauses, or a combination of both.

[0337] The complexity can then be compared to a complexity threshold 10860. If the complexity exceeds the threshold 10860, the complexity estimator 10858 can provide a text-based user request 10802 to an external pre-trained AI algorithm 10859 instead of to the local pre-trained AI algorithm 10803 in the measurement application control unit 10800. The external pre-trained AI algorithm 10859 can be provided in a cloud system, server, or any other component and can be coupled to the measurement application control unit 10800, such as the complexity estimator 10858, via a data network. The complexity estimator 10858 can request user consent 10861 via user interface 10862 to provide the text-based user request 10802 to the external pre-trained AI algorithm 10859.

[0338] As an optional component, a request anonymizer 10863 is provided between the measurement application control unit 10800 and the external pre-trained artificial intelligence algorithm 10859. The request anonymizer 10863 can be used to anonymize the text-based user request 10802 before providing it to the external pre-trained artificial intelligence algorithm 10859.

[0339] Figure 9 A block diagram of a measurement application control unit 10900 is shown. The measurement application control unit 10900 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10900 includes a text-based input interface 10901 that receives a text-based user request 10902 regarding a measurement application device. The measurement application control unit 10900 also includes a pre-trained artificial intelligence algorithm 10903 coupled to the text-based input interface 10901, which generates response data 10904 regarding the measurement application device based on the text-based user request 10902. The measurement application control unit 10900 also includes an output interface 10905 coupled to the pre-trained artificial intelligence algorithm 10903, and the output interface 10905 is configured to output the response data 10904. The explanations provided herein regarding any embodiment of the measurement application control unit can also be applied to the measurement application control unit 10900 with necessary modifications.

[0340] The measurement application control unit 10900 also includes a text-based request generator 10970. The text-based request generator 10970 can receive non-textual descriptions 10971, such as images, videos, or any other non-textual descriptions, especially visual descriptions. Such non-textual descriptions may include, for example, images or videos of measurement application settings.

[0341] Then the text-based request generator 10970 can generate a corresponding text-based user request 10902 based on the non-text description 10971.

[0342] The text-based request generator 10970 may include any suitable algorithm, such as an artificial intelligence-based algorithm, so that a non-text description 10971 can be converted into a text-based user request 10902.

[0343] Figure 10A block diagram of a measurement application control unit 11000 is shown. The measurement application control unit 11000 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 11000 includes a text-based input interface 11001 that receives a text-based user request 11002 regarding the measurement application. The measurement application control unit 11000 also includes a pre-trained artificial intelligence algorithm 11003 coupled to the text-based input interface 11001, which generates response data 11004 regarding the measurement application device based on the text-based user request 11002. The measurement application control unit 11000 also includes an output interface 11005 coupled to the pre-trained artificial intelligence algorithm 11003, and the output interface 11005 is configured to output the response data 11004. The explanations provided herein regarding any embodiment of the measurement application control unit can also be applied to the measurement application control unit 11000 with necessary modifications.

[0344] The measurement application control unit 11000 also includes a confidence estimator 11073. The confidence estimator 11073 can receive response data 11004 or other corresponding indications from a pre-trained artificial intelligence algorithm 11003, and can generate corresponding confidence values ​​11074.

[0345] In an embodiment, the confidence estimator 11073 may be provided as a function or element of the pre-trained artificial intelligence algorithm 11003, or may be included in the pre-trained artificial intelligence algorithm 11003.

[0346] Figure 11 Measurement application device 11175 is shown. Measurement application device 11175 includes measurement application control unit 11100 and measurement application device controller 11176.

[0347] The measurement application device controller 11176 is coupled to a text-based input interface 11101 to provide a text-based user request 11102 to the measurement application control unit 11100. The measurement application device controller 11176 is also coupled to an output interface 11105 to receive response data 11104 from the measurement application control unit 11100.

[0348] The measurement application device controller 11176 and the measurement application control unit 11100 are provided as separate devices or components in the measurement application device 11175.

[0349] In other embodiments, the measurement application control unit 11100 may be provided as a function or additional function of the measurement application device controller 11176.

[0350] Figure 12 A flowchart is shown for a computer-implemented method for controlling a measurement application device. The method includes: S1 receiving a text-based user request regarding the measurement application device; S2 generating response data about questions related to the measurement application based on the text-based user request using a pre-trained artificial intelligence algorithm; and S3 outputting the response data.

[0351] Pre-trained artificial intelligence algorithms can be pre-trained using at least one of the following: user manuals for measurement application equipment, data sheets for measurement application equipment, application notes for measurement application equipment, user manuals for electronic devices, data sheets for electronic devices, application notes for electronic devices, articles about electronic circuits, online forum discussions about electronic circuits, and videos about electronic circuits.

[0352] Pre-trained artificial intelligence algorithms may include large language models based on at least one of statistical models, recurrent neural networks, bidirectional encoding representations based on Transformer models, and generative pre-trained Transformer models.

[0353] The method may further include receiving user input, wherein a pre-trained artificial intelligence algorithm can generate response data about questions related to the measurement application based on text-based user requests and user input. User input may be provided, for example, via at least one of buttons, switches, knobs, touchscreens, keyboards, mice, cameras, and gesture sensors.

[0354] The method may further include translating a text-based user request in a language that is not trained to operate using a pre-trained artificial intelligence algorithm into a translated text-based user request in a language that is trained to operate using a pre-trained artificial intelligence algorithm, and then providing the translated text-based user request to the pre-trained artificial intelligence algorithm.

[0355] The method may also include providing a pre-processed text-based request to a pre-trained artificial intelligence algorithm before the pre-trained artificial intelligence algorithm operates on the text-based user request.

[0356] In this embodiment, the text-based user request may relate to the use of a measurement application device. Therefore, the usage response data can be generated by a pre-trained artificial intelligence algorithm, which includes a corresponding explanation regarding the use of the measurement application device.

[0357] Text-based user requests can involve the control of measurement application equipment. Therefore, control response data can be generated by a pre-trained artificial intelligence algorithm, including corresponding control commands for the measurement application equipment. Furthermore, configuration and control commands can be generated for the measurement application equipment in a predetermined control or programming language, and these configuration and control commands can be provided to the controller of the measurement application equipment.

[0358] The pre-trained artificial intelligence algorithm can be executed locally on the measurement application device. The method may further include: estimating the complexity of a text-based user request, and if the estimated complexity exceeds a predetermined threshold, forwarding the text-based user request to an external pre-trained artificial intelligence algorithm. In such an embodiment, user consent may be requested via the user interface of the measurement application device before providing one of the text-based user requests to the external pre-trained artificial intelligence algorithm. The text-based user request may be indirectly provided to the external pre-trained artificial intelligence algorithm via a request anonymizer.

[0359] In one embodiment, the method may further include receiving at least one of an image, video, or non-text description of at least one of a measurement application device, a device under test, and a measurement application setting; generating a text-based user request based on at least one of the image or video; and providing the generated text-based user request to a pre-trained artificial intelligence algorithm.

[0360] Figure 13 A block diagram of an oscilloscope OSC1 is shown, which can be used with, or implement, an embodiment of a measurement application device or method according to the first aspect of this disclosure.

[0361] The oscilloscope OSC1 includes a housing HO that houses four measurement inputs MIP1, MIP2, MIP3, and MIP4. These four measurement inputs are coupled to a signal processor SIP for processing any measurement signals. The signal processor SIP is coupled to a display DISP1 for displaying the measurement signals to the user.

[0362] Although not explicitly shown, it should be understood that the oscilloscope OSC1 may also include multiple signal outputs, which may be coupled to a differential measurement probe. Such signal outputs can, for example, be used to output calibration signals. These calibration signals allow measurement settings to be calibrated before any measurement is performed. The process of calibrating and correcting any measurement signal based on calibration can also be referred to as de-embedding and may include applying appropriate algorithms to the measurement signal.

[0363] In the oscilloscope OSC1, a signal processor SIP or additional processing element can perform the functions of the measurement application control unit or method according to this disclosure, or can implement the measurement application control unit or method. Of course, a communication interface can be provided in the oscilloscope OSC1 for communicating with other measurement application devices.

[0364] Figure 14 A block diagram of an oscilloscope OSC is shown, which can be used with, or implement an embodiment of, a measurement application device or method according to the first aspect of this disclosure. The oscilloscope OSC is implemented as a digital oscilloscope. However, this disclosure can also be implemented as any other type of oscilloscope.

[0365] An oscilloscope OSC typically includes five general-purpose sections: Vertical System (VS), Trigger Section (TS), Horizontal System (HS), Processing Section (PS), and Display Section (DISP). It should be understood that this division into five general-purpose sections is a logical arrangement and does not in any way limit the placement and implementation of any components of the oscilloscope OSC.

[0366] The vertical system (VS) is primarily used to offset, attenuate, and amplify the signal to be acquired. This signal can be modified, for example, to fit the available space on the display DISP, or to include a user-configurable vertical dimension.

[0367] To this end, the vertical system VS includes a signal conditioning section SC with an attenuator ATT coupled to an amplifier AMP1 and a digital-to-analog converter DAC. The amplifier AMP1 is coupled to a filter FI1, which is provided as a low-pass filter in the example shown. The vertical system VS also includes an analog-to-digital converter ADC1, which receives the output from the filter FI1 and converts the received analog signal into a digital signal.

[0368] The attenuator ATT and amplifier AMP1 are used to scale the amplitude of the signal to be acquired to match the operating range of the analog-to-digital converter ADC1. The digital-to-analog converter DAC1 is used to modify the DC component of the input signal to be acquired to match the operating range of the analog-to-digital converter ADC1. The filter FI1 is used to filter out unwanted high-frequency components in the signal to be acquired.

[0369] The trigger section TS operates on the signal provided by the amplifier AMP. The trigger section TS includes a filter FI2, which is implemented as a low-pass filter in this embodiment. The filter FI2 is coupled to the trigger system TS1.

[0370] The trigger section (TS) is used to capture predefined signal events and causes the horizontal system (HS) to display, for example, a stable view of the repetitive waveform, or only the portion of the waveform including the corresponding signal event. It should be understood that the predefined signal events can be configured by the user via user input to the oscilloscope's OSC.

[0371] Possible predefined signal events may include, for example, the time it takes for a signal to cross a predefined trigger threshold in a predefined direction (i.e., with an upward or downward slope). This triggering condition is also called edge triggering. Another triggering condition is called "glitch triggering," which is triggered when a pulse with a width greater than or less than a predetermined time appears in the signal to be acquired.

[0372] To achieve precise matching between the trigger event and the waveform shown on the display DISP, a common time base can be provided for the analog-to-digital converter ADC1 and the trigger system TS1.

[0373] It should be understood that, although not explicitly shown, the trigger system TS1 may include at least one of the following: a configurable voltage comparator for setting the trigger threshold voltage, a fixed voltage source for setting the desired slope, a corresponding logic gate (such as an XOR gate), and a flip-flop for generating the trigger signal.

[0374] The trigger section TS is provided as an analog trigger section, by way of example. It should be understood that the oscilloscope OSC can also be equipped with a digital trigger section. This digital trigger section does not operate on the analog signal provided by the amplifier AMP, but it does operate on the digital signal provided by the analog-to-digital converter ADC1.

[0375] The digital triggering section may include processing elements, such as processors, DSPs, CPLDs, ASICs, or FPGAs, to implement digital algorithms for detecting valid triggering events.

[0376] The horizontal system HS is coupled to the output of the trigger system TS1 and is mainly used for horizontal positioning and scaling of the signal to be acquired on the display DISP.

[0377] The oscilloscope OSC also includes a processing section PS that performs digital signal processing and data storage for the oscilloscope OSC. The processing section PS includes an acquisition processing element ACP, which is coupled to the output of the analog-to-digital converter ADC1 and the output of the level system HS, and is also coupled to the memory MEM and the post-processing element PPE.

[0378] The acquisition processing element (ACP) controls the acquisition of digital data from the analog-to-digital converter (ADC1) and the storage of the data in the memory (MEM). The acquisition processing element (ACP) may, for example, include a processing element having a digital interface to the ADC2 and a digital interface to the memory (MEM). The processing element may, for example, include a microcontroller, DSP, CPLD, ASIC, or FPGA with its respective interface. In a microcontroller or DSP, the functionality of the acquisition processing element (ACP) can be implemented as computer-readable instructions executed by the CPU. In a CPLD or FPGA, the functionality of the acquisition processing element (ACP) can be configured within the CPLD or FPGA, rather than as software executed by a processor.

[0379] The processing unit PS also includes a communication processor CP and a communication interface COM.

[0380] The communication processor (CP) can be a device that manages data transmission to and from the oscilloscope's OSC. The communication interface (COM) is used for any suitable communication standard, such as Ethernet, Wi-Fi, Bluetooth, NFC, infrared communication standards, and visible light communication standards.

[0381] The communication processor CP is coupled to the memory MEM, and the memory MEM can be used to store and retrieve data.

[0382] Of course, the communication processor (CP) can also be coupled to any other component of the oscilloscope's OSC to obtain device data or provide device data received from the management server.

[0383] The post-processing element (PPE) can be controlled by the acquisition and processing element (ACP) and can access the memory (MEM) to retrieve data to be displayed on the display (DISP). The PPE can adjust the data stored in the memory (MEM) so that the display (DISP) can display the data to the user, for example, as a waveform. The PPE can also perform analysis functions such as cursor manipulation, waveform measurement, histogram manipulation, or mathematical functions.

[0384] Although not explicitly shown, the display DISP control presents all aspects of the signal representation to the user, which may include receiving the data to be displayed and any components required to control the display device to display the data as needed.

[0385] It should be understood that, even if not shown, an oscilloscope OSC may include a user interface for user interaction with the OSC. Such a user interface may include dedicated input elements, such as knobs and switches. At least in part, the user interface may also be provided as a touch-sensitive display device.

[0386] In an oscilloscope OSC, any processing element or additional processing element in the processing section PS can perform the functions of the measurement application control unit according to this disclosure or the methods according to this disclosure.

[0387] It should be understood that all components of an oscilloscope OSC that perform digital data processing can be provided as dedicated components. Alternatively, at least some of the functions described above can be implemented in a single hardware component, such as a microcontroller, DSP, CPLD, or FPGA. Typically, the aforementioned logic functions can be implemented in any suitable hardware component of the oscilloscope OSC and do not necessarily need to be divided into the different parts described above.

[0388] The second part of the attached diagram Figure 15 A block diagram of a measurement application processing device 20100 is shown. The measurement application processing device 20100 includes a text-based input interface 20101 that receives a text-based user request 20102 regarding a measurement application. The measurement application processing device 20100 also includes a pre-trained artificial intelligence algorithm 20103 coupled to the text-based input interface 20101, and the pre-trained artificial intelligence algorithm 20103 is configured to generate response data 20104 regarding the measurement application based on the text-based user request 20102. The measurement application processing device 20100 also includes an output interface 20105 coupled to the pre-trained artificial intelligence algorithm 20103, and the output interface 20105 is configured to output the response data 20104. The explanations provided herein regarding any embodiment of the measurement application processing device can also be applied to the measurement application processing device 20100 with necessary modifications.

[0389] In an embodiment, the measurement application processing device 20100 may be implemented on a computer or server, executing a computer program product including instructions that, when executed by the computer or server (particularly a processor within the computer or server), cause the computer or server to perform a computer-implemented method according to the second aspect of this disclosure, or to perform the functions of the measurement application processing device 20100 according to the second aspect of this disclosure. Such a computer or server may be located remotely from the measurement application device and coupled to the measurement application device via a network connection.

[0390] In an embodiment, the pre-trained artificial intelligence algorithm 20103 may be pre-trained using any combination of the following: user manuals for one or more measurement application devices or measurement applications, data sheets for one or more measurement application devices or measurement applications, application notes for one or more measurement application devices or measurement applications, user manuals for electronic devices, data sheets for electronic devices, application notes for electronic devices, articles about electronic circuits, online forum discussions about electronic circuits, and videos about electronic circuits.

[0391] Figure 16 A block diagram of a measurement application processing device 20200 is shown. The measurement application processing device 20200 is based on the measurement application processing device 20100. The measurement application processing device 20200 includes a text-based input interface 20201 that receives a text-based user request 20202 regarding a measurement application. The measurement application processing device 20200 also includes a pre-trained artificial intelligence algorithm 20203 coupled to the text-based input interface 20201, and the pre-trained artificial intelligence algorithm 20203 is configured to generate response data 20204 regarding the measurement application based on the text-based user request 20202. The measurement application processing device 20200 also includes an output interface 20205 coupled to the pre-trained artificial intelligence algorithm 20203, and the output interface 20205 is configured to output the response data 20204. The explanations provided herein regarding any embodiments of the measurement application processing device can also be applied to the measurement application processing device 20200 with necessary modifications.

[0392] The measurement application processing device 20200 also includes an audio input interface 20228. The audio input interface 20228 is coupled to a speech recognition unit 20230, and the speech recognition unit 20230 is coupled to a text-based input interface 20201.

[0393] Audio input interface 20228 can receive, for example, spoken requests 20229 from a user. It should be understood that audio input interface 20228 may include, for example, a microphone for recording spoken requests 20229. In embodiments, audio input interface 20228 may include a data interface for receiving spoken requests 20229 provided digitally, which are recorded elsewhere. A combination of both approaches is possible.

[0394] The speech recognition unit 20230 can then convert the spoken request 20229 into a text-based request 20231. This text-based request 20231 can then be forwarded to the text-based input interface 20201, just like a text-based user request 20202. The text-based input interface 20201 can then process the text-based request 20231 in the same way as any other text-based user request 20202.

[0395] The speech recognition unit 20230 may include any suitable element of any type. Example embodiments of the speech recognition unit 20230 may be based, for example, on computer-implemented algorithms or methods, particularly corresponding artificial intelligence-based computer-implemented algorithms.

[0396] Figure 17 A block diagram of a measurement application processing device 20300 is shown. The measurement application processing device 20300 is based on the measurement application processing device 20100. The measurement application processing device 20300 includes a text-based input interface 20301 that receives a text-based user request 20302 regarding a measurement application. The measurement application processing device 20300 also includes a pre-trained artificial intelligence algorithm 20303 coupled to the text-based input interface 20301, and the pre-trained artificial intelligence algorithm 20303 is configured to generate response data 20304 regarding the measurement application based on the text-based user request 20302. The measurement application processing device 20300 also includes an output interface 20305 coupled to the pre-trained artificial intelligence algorithm 20303, and the output interface 20305 is configured to output the response data 20304. The explanations provided herein regarding any embodiment of the measurement application processing device can also be applied to the measurement application processing device 20300 with necessary modifications.

[0397] In the measurement application processing device 20300, the pre-trained artificial intelligence algorithm 20303 includes a large language model 20335 for implementing the functions of the pre-trained artificial intelligence algorithm 20303.

[0398] Large language models 20335 can be based on any appropriate type of algorithm, such as statistical models, recurrent neural networks, bidirectional encoding representations based on Transformer models, and generative pre-trained Transformer models.

[0399] Figure 18A block diagram of a measurement application processing device 20400 is shown. The measurement application processing device 20400 is based on the measurement application processing device 20100. The measurement application processing device 20400 includes a text-based input interface 20401 that receives a text-based user request 20402 regarding a measurement application. The measurement application processing device 20400 also includes a pre-trained artificial intelligence algorithm 20403 coupled to the text-based input interface 20401, and the pre-trained artificial intelligence algorithm 20403 is configured to generate response data 20404 regarding the measurement application based on the text-based user request 20402. The measurement application processing device 20400 also includes an output interface 20405 coupled to the pre-trained artificial intelligence algorithm 20403, and the output interface 20405 is configured to output the response data 20404. The explanations provided herein regarding any embodiments of the measurement application processing device can also be applied to the measurement application processing device 20400 with necessary modifications.

[0400] The pre-trained artificial intelligence algorithm 20403 of the measurement application processing device 20400 provides response data 20404 in visual form.

[0401] To this end, the pre-trained artificial intelligence algorithm 20403 provides a block diagram 20438. This is in the response data 20404.

[0402] Exemplary block diagram 20438 illustrates two measurement application devices. The measurement application device on the left includes four ports arranged in a row, generating two test signals, and providing one test signal from the leftmost port and one test signal from the rightmost port to the device under test (DUT). The measurement application device on the right also includes four ports arranged in a row, and obtains a signal from the DUT using the second port from the left.

[0403] Since block diagram 20438 is merely exemplary, no further explanation is provided. In other embodiments, block diagram 20438 may include further information, such as textual descriptions of individual components, and a description of the steps required to set up the measurement application as shown in block diagram 20438. In other embodiments, the number of measuring devices, connection points, and devices under test may vary, and other types or additional types of components may be provided in the measurement application and block diagram 20438.

[0404] Figure 19A block diagram of a measurement application processing device 20500 is shown. The measurement application processing device 20500 is based on the measurement application processing device 20100. The measurement application processing device 20500 includes text-based input interfaces 20501-1 and 20501-2, which receive text-based user requests 20502 regarding the measurement application. The measurement application processing device 20500 also includes a pre-trained artificial intelligence algorithm 20503 coupled to the text-based input interface 20501, and the pre-trained artificial intelligence algorithm 20503 is configured to generate response data 20504 regarding the measurement application based on the text-based user request 20502. The measurement application processing device 20500 also includes an output interface 20505 coupled to the pre-trained artificial intelligence algorithm 20503, and the output interface 20505 is configured to output the response data 20504. The explanations provided herein regarding any embodiment of the measurement application processing device herein, with necessary modifications, can also be applied to the measurement application processing device 20500.

[0405] The measurement application processing device 20500 receives a first type of text-based user request 20502-1, which includes a user request regarding the setup of the measurement application. Furthermore, the measurement application processing device 20500 receives a second type of text-based user request 20502-2, which includes a user request regarding the control of the measurement application or a single measurement application device within the measurement application.

[0406] Therefore, the pre-trained artificial intelligence algorithm 20503 will provide setting response data 20540 and control response data 20541 in the response data 20504.

[0407] The measurement application processing device 20500 also includes a code generator 20542. The code generator 20542 can receive control response data 20541 or other corresponding instructions from a pre-trained artificial intelligence algorithm 20503, and can generate corresponding configuration and control commands 20543 in any suitable script or programming language.

[0408] In an embodiment, code generator 20542 may be provided as a function or element of pre-trained artificial intelligence algorithm 20503, or may be included in pre-trained artificial intelligence algorithm 20503.

[0409] In an embodiment, the measurement application processing device 20500 may include a warning generator as an alternative to or supplement to the code generator 20542. The warning generator may be provided in the same location as the code generator 20542 and operate using the same inputs. Alternatively, the warning generator may be integrated into a pre-trained artificial intelligence algorithm 20503.

[0410] Figure 20 A block diagram of a measurement application processing device 20600 is shown. The measurement application processing device 20600 is based on the measurement application processing device 20100. The measurement application processing device 20600 includes a text-based input interface 20601 that receives a text-based user request 20602 regarding a measurement application. The measurement application processing device 20600 also includes a pre-trained artificial intelligence algorithm 20603 coupled to the text-based input interface 20601, and the pre-trained artificial intelligence algorithm 20603 is configured to generate response data 20604 regarding the measurement application based on the text-based user request 20602. The measurement application processing device 20600 also includes an output interface 20605 coupled to the pre-trained artificial intelligence algorithm 20603, and the output interface 20605 is configured to output the response data 20604. The explanations provided herein regarding any embodiment of the measurement application processing device can also be applied to the measurement application processing device 20600 with necessary modifications.

[0411] The measurement application processing device 20600 also includes a preprocessor 20645. The preprocessor 20645 is coupled to a text-based input interface 20601 and can provide preprocessed text-based requests 20646 to the text-based input interface 20601.

[0412] The preprocessed text-based request 20646 is used to preprocess the pre-trained artificial intelligence algorithm 20603, and the preprocessed text-based request 10649 can be provided to the pre-trained artificial intelligence algorithm 20603 before the text-based user request 20602 is provided to the pre-trained artificial intelligence algorithm 20603.

[0413] In this embodiment, a text-based user request 20602 can be provided to a preprocessor 20645 instead of a text-based input interface 20601. The preprocessor 20645 can then combine the preprocessed text-based request 20646 with the received text-based user request 20602.

[0414] Figure 21A block diagram of a measurement application processing device 20700 is shown. The measurement application processing device 20700 is based on the measurement application processing device 20100. The measurement application processing device 20700 includes a text-based input interface 20701 that receives a text-based user request 20702 regarding a measurement application. The measurement application processing device 20700 also includes a pre-trained artificial intelligence algorithm 20703 coupled to the text-based input interface 20701, and the pre-trained artificial intelligence algorithm 20703 is configured to generate response data 20704 regarding the measurement application based on the text-based user request 20702. The measurement application processing device 20700 also includes an output interface 20705 coupled to the pre-trained artificial intelligence algorithm 20703, and the output interface 20705 is configured to output the response data 20704. The explanations provided herein regarding any embodiment of the measurement application processing device can also be applied to the measurement application processing device 20700 with necessary modifications.

[0415] In the measurement application processing device 20700, a pre-trained artificial intelligence algorithm 20703 can generate an enhanced text-based user request 20750. This enhanced text-based user request 20750 can be provided to the user via an output interface 20705. The user can then view the enhanced text-based user request 20750 and (especially via a text-based input interface 20701) provide a corresponding confirmation 20751 to the measurement application processing device 20700.

[0416] After receiving confirmation 20751, the pre-trained artificial intelligence algorithm 20703 can generate response data 20704 and output the response data 20704 via output interface 20705.

[0417] Figure 22A block diagram of a measurement application processing device 20800 is shown. The measurement application processing device 20800 is based on the measurement application processing device 20100. The measurement application processing device 20800 includes a text-based input interface 20801 that receives a text-based user request 20802 regarding a measurement application. The measurement application processing device 20800 also includes a pre-trained artificial intelligence algorithm 20803 coupled to the text-based input interface 20801, and the pre-trained artificial intelligence algorithm 20803 is configured to generate response data 20804 regarding the measurement application based on the text-based user request 20802. The measurement application processing device 20800 also includes an output interface 20805 coupled to the pre-trained artificial intelligence algorithm 20803, and the output interface 20805 is configured to output the response data 20804. The explanations provided herein regarding any embodiment of the measurement application processing device can also be applied to the measurement application processing device 20800 with necessary modifications.

[0418] The measurement application processing device 20800 also includes a text-based request generator 20855. The text-based request generator 20855 can receive non-textual descriptions 20856, such as images, videos, or any other non-textual descriptions, especially visual descriptions. Such non-textual descriptions may include, for example, images or videos of measurement application settings.

[0419] Then the text-based request generator 20855 can generate a corresponding text-based user request 20802 based on the non-text description 20856.

[0420] The text-based request generator 20855 may include any suitable algorithm, such as an artificial intelligence-based algorithm, so that a non-text description 20856 can be converted into a text-based user request 20802.

[0421] Figure 23A block diagram of another measurement application device control unit 20900 is shown. Measurement application device control unit 20900 is based on measurement application device control unit 20100. Therefore, measurement application device control unit 20900 includes a text-based input interface 20901 that receives a text-based user request 20902 regarding the measurement application device. Measurement application device control unit 20900 also includes a pre-trained artificial intelligence algorithm 20903 coupled to the text-based input interface 20901, which generates configuration data 20904 regarding the measurement application device based on the text-based user request 20902. Measurement application device control unit 20900 also includes an output interface 20905 coupled to the pre-trained artificial intelligence algorithm 20903, and the output interface 20905 is configured to output the configuration data 20904. The explanations provided herein regarding any embodiment of the measurement application device control unit can also be applied to measurement application processing device 20900 with necessary modifications.

[0422] The measurement application device control unit 20900 also includes a feedback interface 20910 for receiving measurement feedback data 20911. In an embodiment, the measurement feedback data 20911 can be directly provided to a pre-trained artificial intelligence algorithm 20903. In the measurement application device control unit 20900, a feedback data analyzer 20912 is arranged between the feedback interface 20910 and the pre-trained artificial intelligence algorithm 20903.

[0423] In the measurement application device control unit 20900, the feedback data analyzer 20912 generates a text-based feedback description 20913 of the measurement feedback data 20911 and provides the text-based feedback description 20913 to the pre-trained artificial intelligence algorithm 20903.

[0424] The pre-trained artificial intelligence algorithm 20903 generates another set of configuration data 20904 based on the original text-based user request 20902 and the received measurement feedback data 20911 (especially the text-based feedback description 20913).

[0425] The feedback data analyzer 20912 can identify at least one of the following: anomalies, relevant measured values, and relevant measured waveform portions in the raw measurement data. The raw measurement data can be provided in the measurement feedback data 20911, or provided as measurement feedback data 20911. The feedback data analyzer 20912 can then provide a corresponding text-based feedback description 20913.

[0426] This text-based feedback description 20913 could include, for example, a statement such as, “The relevant information in the acquired waveform is in the frequency range between 1 GHz and 5 GHz. Please zoom in on this part of the acquired waveform for measurement.”

[0427] Figure 24 A block diagram of another measurement application device control unit 21000 is shown. Measurement application device control unit 21000 is based on measurement application device control unit 20200. Therefore, measurement application device control unit 21000 includes a text-based input interface 21001 that receives text-based user requests 21002 regarding the measurement application device. Measurement application device control unit 21000 also includes a pre-trained artificial intelligence algorithm 21003 coupled to the text-based input interface 21001, which generates configuration data 21004 regarding the measurement application device based on the text-based user request 21002. Measurement application device control unit 21000 also includes an output interface 21005 coupled to the pre-trained artificial intelligence algorithm 21003, and the output interface 21005 is configured to output the configuration data 21004. Measurement application device control unit 21000 also includes a feedback interface 21010 for receiving measurement feedback data 21011. A feedback data analyzer 21012 is positioned between the feedback interface 21010 and the pre-trained artificial intelligence algorithm 21003. The feedback data analyzer 21012 generates a text-based feedback description 21013 of the measurement feedback data 21011 and provides this text-based feedback description 21013 to the pre-trained artificial intelligence algorithm 21003. The explanations provided herein regarding any embodiment of the measurement application device control unit can also be applied to the measurement application processing device 21000 with necessary modifications.

[0428] The measurement application equipment control unit 21000 also includes a feedback output interface 21014 coupled to the feedback data analyzer 21012.

[0429] The feedback output interface 21014 outputs measurement feedback data 21011 to the user, especially text-based feedback descriptions 20213.

[0430] Then the pre-trained artificial intelligence algorithm 21003 can generate another set of configuration data 21004 based on the original text-based user request 21002 and another text-based user request 21002 received after the measurement feedback data 21011 is output to the user.

[0431] The pre-trained AI algorithm 21003 can also perform reinforcement learning based on another text-based user request 21002 received after the measurement feedback data 21011 has been output to the user. It should be understood that this is merely an example of performing further training with the pre-trained AI algorithm 21003. Any other form of further or continuous learning can be implemented with the pre-trained AI algorithm 21003.

[0432] Figure 25 Measurement application 21160 is illustrated. This measurement application 21160 exemplarily includes a measurement application processing device 21100 coupled to three measurement application devices 21161-1, 21161-2, and 21161-3. In other embodiments, more or fewer measurement application devices are possible, and the measurement application processing device 21100 can be integrated into any one of the measurement application devices.

[0433] Similar to Figure 15 The measurement application processing device 20100 includes a text-based input interface 21101, a pre-trained artificial intelligence algorithm 21103, and an output interface 21105. Of course, any other embodiment of the measurement application processing device can be used in the measurement application 21160.

[0434] Measurement application devices 21161-1, 21161-2, and 21161-3 can be coupled to measurement application processing device 21100 via a private or public data network. In embodiments where measurement application processing device 21100 includes a code generator, measurement application processing device 21100 can directly provide generated configuration and control commands to measurement application devices 21161-1, 21161-2, and 21161-3.

[0435] In this embodiment, the measurement application processing device 21100 can be used as a remote control device for measurement application devices 21161-1, 21161-2, and 21161-3, and can provide a corresponding control interface to the user. Measurement application devices 21161-1, 21161-2, and 21161-3 can be, for example, measurement application devices 21161-1, 21161-2, and 21161-3 according to any of the embodiments described herein.

[0436] Figure 26 A flowchart of an embodiment of a computer-implemented method according to the present disclosure is shown. The method includes: S1 receiving a text-based user request regarding a measurement application; S2 generating response data regarding the measurement application based on the text-based user request using a pre-trained artificial intelligence algorithm; and S3 outputting the response data.

[0437] Pre-trained artificial intelligence algorithms can be pre-trained using at least one of the following: user manuals for one or more measurement application devices or applications, data sheets for one or more measurement application devices or applications, and application notes for one or more measurement application devices or applications. Pre-trained artificial intelligence algorithms may include, for example, large language models based on at least one of statistical models, recurrent neural networks, bidirectional encoding representations based on Transformer models, and generative pre-trained Transformer models.

[0438] In an embodiment, the method may further include: receiving a spoken request, converting the spoken request into a text-based request, and providing the text-based request as a text-based user request to a text-based input interface.

[0439] In a further embodiment, a pre-trained artificial intelligence algorithm can enhance a text-based user request and output the enhanced text-based user request via an output interface. After the user confirms the enhanced text-based user request, the pre-trained artificial intelligence algorithm can further generate response data.

[0440] A pre-trained AI algorithm can receive text-based user requests regarding measurement application settings and generate setup response data that includes a corresponding explanation of the measurement application settings. The pre-trained AI algorithm can then generate setup response data indicating which measurement application device to use and how to connect it to set up the measurement application. The pre-trained AI algorithm can, for example, generate a block diagram of the measurement application setup.

[0441] The pre-trained artificial intelligence algorithm can also generate control response data, which may include corresponding control commands for at least one measurement application device. Control commands may, for example, include instructions given to a user. Alternatively or additionally, control commands may include configuration and control commands generated for the measurement application device in a predetermined control or programming language.

[0442] The method may also include providing a pre-processed text-based request to a pre-trained artificial intelligence algorithm before the pre-trained artificial intelligence algorithm operates on the text-based user request.

[0443] The method may also include receiving at least one of a non-text-based description, image, or video of a measurement application device, a device under test, or measurement application settings, and generating a text-based user request based on at least one of the images or videos.

[0444] Furthermore, the pre-trained artificial intelligence algorithm can receive text-based user requests regarding the maintenance of measurement application equipment in measurement applications, and can generate corresponding maintenance response data, which includes an explanation of the maintenance of the corresponding measurement application equipment.

[0445] Figure 27 A block diagram of an oscilloscope OSC1 is shown, which can be used with, or implement with, an embodiment of a measurement application processing apparatus or method according to the second aspect of this disclosure.

[0446] The oscilloscope OSC1 includes a housing HO that houses four measurement inputs MIP1, MIP2, MIP3, and MIP4. These four measurement inputs are coupled to a signal processor SIP for processing any measurement signals. The signal processor SIP is coupled to a display DISP1 for displaying the measurement signals to the user.

[0447] Although not explicitly shown, it should be understood that the oscilloscope OSC1 may also include multiple signal outputs, which may be coupled to a differential measurement probe. Such signal outputs can, for example, be used to output calibration signals. These calibration signals allow measurement settings to be calibrated before any measurement is performed. The process of calibrating and correcting any measurement signal based on calibration can also be referred to as de-embedding and may include applying appropriate algorithms to the measurement signal.

[0448] In the oscilloscope OSC1, the signal processor SIP or additional processing elements can perform the functions of the measurement application processing apparatus or method according to this disclosure, or can implement the measurement application processing apparatus or method. Of course, a communication interface can be provided in the oscilloscope OSC1 for communicating with other measurement application apparatuses.

[0449] Figure 28 A block diagram of an oscilloscope OSC is shown. The oscilloscope OSC may include, or implement, a measurement application processing apparatus or method according to the second aspect of this disclosure. The oscilloscope OSC is implemented as a digital oscilloscope. However, this disclosure may also be implemented as any other type of oscilloscope.

[0450] An oscilloscope OSC typically includes five general-purpose sections: Vertical System (VS), Trigger Section (TS), Horizontal System (HS), Processing Section (PS), and Display Section (DISP). It should be understood that this division into five general-purpose sections is a logical arrangement and does not in any way limit the placement and implementation of any components of the oscilloscope OSC.

[0451] The vertical system (VS) is primarily used to offset, attenuate, and amplify the signal to be acquired. This signal can be modified, for example, to fit the available space on the display DISP, or to include a user-configurable vertical dimension.

[0452] To this end, the vertical system VS includes a signal conditioning section SC with an attenuator ATT coupled to an amplifier AMP1 and a digital-to-analog converter DAC. The amplifier AMP1 is coupled to a filter FI1, which is provided as a low-pass filter in the example shown. The vertical system VS also includes an analog-to-digital converter ADC1, which receives the output from the filter FI1 and converts the received analog signal into a digital signal.

[0453] The attenuator ATT and amplifier AMP1 are used to scale the amplitude of the signal to be acquired to match the operating range of the analog-to-digital converter ADC1. The digital-to-analog converter DAC1 is used to modify the DC component of the input signal to be acquired to match the operating range of the analog-to-digital converter ADC1. The filter FI1 is used to filter out unwanted high-frequency components in the signal to be acquired.

[0454] The trigger section TS operates on the signal provided by the amplifier AMP. The trigger section TS includes a filter FI2, which is implemented as a low-pass filter in this embodiment. The filter FI2 is coupled to the trigger system TS1.

[0455] The trigger section (TS) is used to capture predefined signal events and causes the horizontal system (HS) to display, for example, a stable view of the repetitive waveform, or only the portion of the waveform including the corresponding signal event. It should be understood that the predefined signal events can be configured by the user via user input to the oscilloscope's OSC.

[0456] Possible predefined signal events may include, for example, the time it takes for a signal to cross a predefined trigger threshold in a predefined direction (i.e., with an upward or downward slope). This triggering condition is also called edge triggering. Another triggering condition is called "glitch triggering," which is triggered when a pulse with a width greater than or less than a predetermined time appears in the signal to be acquired.

[0457] To achieve precise matching between the trigger event and the waveform shown on the display DISP, a common time base can be provided for the analog-to-digital converter ADC1 and the trigger system TS1.

[0458] It should be understood that, although not explicitly shown, the trigger system TS1 may include at least one of the following: a configurable voltage comparator for setting the trigger threshold voltage, a fixed voltage source for setting the desired slope, a corresponding logic gate (such as an XOR gate), and a trigger for generating the trigger signal.

[0459] The trigger section TS is provided as an analog trigger section, by way of example. It should be understood that the oscilloscope OSC can also be equipped with a digital trigger section. This digital trigger section does not operate on the analog signal provided by the amplifier AMP, but it does operate on the digital signal provided by the analog-to-digital converter ADC1.

[0460] The digital triggering section may include processing elements, such as processors, DSPs, CPLDs, ASICs, or FPGAs, to implement digital algorithms for detecting valid triggering events.

[0461] The horizontal system HS is coupled to the output of the trigger system TS1 and is mainly used for horizontal positioning and scaling of the signal to be acquired on the display DISP.

[0462] The oscilloscope OSC also includes a processing section PS that performs digital signal processing and data storage for the oscilloscope OSC. The processing section PS includes an acquisition processing element ACP, which is coupled to the output of the analog-to-digital converter ADC1 and the output of the level system HS, and is also coupled to the memory MEM and the post-processing element PPE.

[0463] The acquisition processing element (ACP) controls the acquisition of digital data from the analog-to-digital converter (ADC1) and the storage of the data in the memory (MEM). The acquisition processing element (ACP) may, for example, include a processing element having a digital interface to the ADC2 and a digital interface to the memory (MEM). The processing element may, for example, include a microcontroller, DSP, CPLD, ASIC, or FPGA with its respective interface. In a microcontroller or DSP, the functionality of the acquisition processing element (ACP) can be implemented as computer-readable instructions executed by the CPU. In a CPLD or FPGA, the functionality of the acquisition processing element (ACP) can be configured within the CPLD or FPGA, rather than as software executed by a processor.

[0464] The processing unit PS also includes a communication processor CP and a communication interface COM.

[0465] The communication processor (CP) can be a device that manages data transmission to and from the oscilloscope's OSC. The communication interface (COM) is used for any suitable communication standard, such as Ethernet, Wi-Fi, Bluetooth, NFC, infrared communication standards, and visible light communication standards.

[0466] The communication processor CP is coupled to the memory MEM, and the memory MEM can be used to store and retrieve data.

[0467] Of course, the communication processor (CP) can also be coupled to any other component of the oscilloscope's OSC to retrieve device data or provide device data received from the management server.

[0468] The post-processing element (PPE) can be controlled by the acquisition and processing element (ACP) and can access the memory (MEM) to retrieve data to be displayed on the display (DISP). The PPE can adjust the data stored in the memory (MEM) so that the display (DISP) can display the data to the user, for example, as a waveform. The PPE can also perform analysis functions such as cursor manipulation, waveform measurement, histogram manipulation, or mathematical functions.

[0469] Although not explicitly shown, the display DISP control presents all aspects of the signal representation to the user, which may include receiving the data to be displayed and any components required to control the display device to display the data as needed.

[0470] It should be understood that, even if not shown, an oscilloscope OSC may include a user interface for user interaction with the OSC. Such a user interface may include dedicated input elements, such as knobs and switches. At least in part, the user interface may also be provided as a touch-sensitive display device.

[0471] In an oscilloscope OSC, any processing element or additional processing element in the processing section PS can perform the functions of a measurement application processing device according to this disclosure or the methods according to this disclosure.

[0472] It should be understood that all components of an oscilloscope OSC that perform digital data processing can be provided as dedicated components. Alternatively, at least some of the functions described above can be implemented in a single hardware component, such as a microcontroller, DSP, CPLD, or FPGA. Typically, the aforementioned logic functions can be implemented in any suitable hardware component of the oscilloscope OSC and do not necessarily need to be divided into the different parts described above.

[0473] The processes, methods, or algorithms disclosed herein are deliverable to / implemented by a processing device, controller, or computer, which may include any existing programmable electronic control unit or dedicated electronic control unit. Similarly, processes, methods, or algorithms may be stored in various forms as data and instructions executable by a controller or computer, including but not limited to information permanently stored on non-writable storage media such as ROM devices and information alternatively stored on writable storage media such as floppy disks, magnetic tapes, CDs, RAM devices, and other magnetic and optical media. Processes, methods, or algorithms may also be implemented as software executable objects. Alternatively, these processes, methods, or algorithms may be implemented, wholly or partially, using suitable hardware components such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), state machines, controllers, or other hardware components or devices, or a combination of hardware, software, and firmware components.

[0474] While exemplary embodiments have been described above, this does not mean that these embodiments describe all possible forms included in the claims. The language used in this specification is descriptive and not restrictive, and it should be understood that various changes may be made without departing from the spirit and scope of this disclosure. As previously stated, features of various embodiments may be combined to form another embodiment of the invention that may not have been explicitly described or illustrated. While various embodiments may have been described as providing an advantage or superiority over other embodiments or prior art implementations in terms of one or more desired characteristics, those skilled in the art will recognize that one or more features or characteristics may be compromised to achieve desired overall system properties depending on the particular application and implementation. These properties may include, but are not limited to, cost, strength, durability, lifecycle cost, merchantability, appearance, packaging, size, suitability, weight, manufacturability, ease of assembly, etc. Therefore, with respect to one or more features, if any embodiment is described to the extent that it is less desirable than other embodiments or prior art implementations, these embodiments are not outside the scope of this disclosure and may be ideal for a particular application.

[0475] Regarding the processes, systems, methods, heuristics, etc., described herein, it should be understood that although the steps of these processes are described as occurring according to a specific ordered sequence, these processes can be practiced with the described steps performed in a different order than that described herein. It should also be understood that some steps can be performed simultaneously, other steps can be added, or some steps described herein can be deleted. In other words, the process descriptions herein are provided for the purpose of illustrating certain embodiments and should not be construed as limiting the claims in any way.

[0476] Therefore, it should be understood that the above description is illustrative and not restrictive. Many embodiments and applications beyond the examples provided will become apparent after reading the above description. The scope should not be determined by reference to the above description, but rather by reference to the appended claims and the full scope of their equivalents. It is anticipated and intended that future developments occur in the art discussed herein, and that the disclosed systems and methods will be incorporated into such future embodiments. In conclusion, it should be understood that this application is capable of modifications and variations.

[0477] All terms used in the claims are intended to be given their broadest reasonable interpretation and their conventional meaning as understood by one of ordinary skill in the art described herein, unless expressly indicated otherwise herein. In particular, the use of singular articles such as “a,” “the,” “the,” etc., should be understood to refer to one or more of the indicated elements, unless the claims expressly limit this to the contrary.

[0478] An abstract of this disclosure is provided to allow the reader to quickly determine the nature of the technical disclosure. It is submitted on the understanding that it will not be used to interpret or limit the scope or meaning of the claims. Furthermore, as can be seen in the foregoing detailed description, various features have been combined in various embodiments for the purpose of simplifying this disclosure. This method of disclosure should not be construed as reflecting an intention that the claimed embodiments require more features than expressly recited in each claim. Rather, as reflected in the claims, the inventive subject matter lies in fewer than all features of a single disclosed embodiment. Therefore, the claims are thus incorporated into the detailed description, each claim on its own as a separately claimed subject matter.

[0479] While exemplary embodiments have been described above, this does not mean that these embodiments describe all possible forms of the invention. Rather, the language used in this specification is descriptive and not restrictive, and it should be understood that various changes can be made without departing from the spirit and scope of the invention. Furthermore, features of various embodiments can be combined to form other embodiments of the invention.

[0480] List of reference numerals 10100, 10200, 10300, 10400, 10500, Measurement Application Control Unit 10600, 10700, 10800, 10900 Measurement Application Control Unit 11000, 11100 Measurement Application Control Unit Text-based input interfaces 10101, 10201, 10301, 10401, and 10501 10601, 10701, 10801, 10901 Text-based input interfaces 11001 and 11101 are text-based input interfaces. 10102, 10202, 10302, 10402, 10505 Text-based user requests 10602, 10702-1, 10702-2, 10802 Text-based user requests 10902, 11002, 11105 Text-based user requests 10103, 10203, 10303, 10403, 10503: Pre-trained artificial intelligence algorithms 10603, 10703, 10803, 10903 Pre-trained artificial intelligence algorithms 11003 and 11103 are pre-trained artificial intelligence algorithms. Response data for 10104, 10204, 10304, 10404, and 10504 10604, 10704, 10804, 10904, Response Data Response data for 11004 and 11104 Output interfaces: 10105, 10205, 10305, 10405, 10505 10605, 10705, 10805, 10905, Output Interface 11005 and 11105 output interfaces 10228 Audio Input Interface 10229 Speaking Request 10230 Speech Recognition Unit 10231 Text-based request 10335 Large Language Model 10438 User Output Interface 10439 User Input Buttons 10440-1 - 10440-n 10441-1, 10441-2 knobs 10442 Touchscreen 10443 User Input 10545 Translator 10546 User requests based on translated text 10648 Preprocessor 10649 Preprocessed text-based requests 10752 Using response data 10753 Control Response Data 10754 Code Generator 10755 Configuration and Control Commands 10858 Complexity Estimator 10859 Externally pre-trained artificial intelligence algorithms 10860 Preset threshold 10861 User agrees 10862 User Interface 10863 Request Anonymous 10970 Text-based User Request Generator 10971 Non-textual description 11073 Confidence Estimator 11074 confidence level 11175 Measurement Application Equipment 11176 Measurement Application Equipment Controller S1–S3 Method Steps 20100, 20200, 20300, 20400, 20500 Measurement Application Processing Equipment 20600, 20700, 20800, 20900, 21000 Measurement Application Processing Equipment 21100 Measurement Application Processing Equipment 20101, 20201, 20301, 20401, 20501 Text-based input interfaces 20601, 20701, 20801, 20901 Text-based input interfaces 21001, 21101 Text-based input interfaces 20102, 20202, 20302, 20402, 20502-1 Text-based user requests 20502-2, 20602, 20702, 20802 Text-based user requests 20902, 21002, 21102 Text-based user requests 20103, 20203, 20303, 20403, 20503: Pre-trained artificial intelligence algorithms 20603, 20703, 20803, 20903: Pre-trained artificial intelligence algorithms 21003 and 21103 are pre-trained artificial intelligence algorithms. Response data for 20104, 20204, 20304, 20404, and 20504. Response data for 20604, 20704, 20804, and 20904 Response data for 21004 and 21104 Output interfaces: 20105, 20205, 20305, 20405, 20505 Output interfaces 20605, 20705, 20805, 20905 21005 and 21105 output interfaces 20228 Audio Input Interface 20229 Speaking Request 20230 Speech Recognition Unit 20231 Text-based requests 20335 Large-scale language model 20438 Block Diagram 20540 Set response data 20541 Control Response Data 20542 Code Generator 20543 Configuration and Control Commands 20645 Preprocessor 20646 Preprocessed text-based requests Enhanced text-based user requests in version 20750 20751 Confirmed 20855 Text-based User Request Generator 20856 Non-textual description Feedback interfaces 20910 and 21010 Measurement feedback data for 20911 and 21011 20912, 21012 Measurement Data Analyzer 20913, 21013 Text-based feedback descriptions 21014 Feedback Output Interface 21160 Measurement Applications 21161-1, 21161-2, 21161-3 Measurement Application Equipment S21–S23 Method Steps OSC1 Oscilloscope HO shell MIP1, MIP2, MIP3, MIP4 measurement outputs SIP signal processing DISP1 monitor OSC Oscilloscope VS Vertical System SC signal conditioning ATT Attenuator DAC1 Analog-to-Digital Converter AMP1 amplifier FI1 filter ADC1 Analog-to-Digital Converter TS trigger section AMP2 amplifier FI2 filter TS1 Triggering System HS Horizontal System PS processing section ACP Acquisition and Processing Components MEM memory PPE post-processing components DISP monitor

Claims

1. A measurement application control unit, comprising: A text-based input interface is configured to receive text-based user requests about a measurement application, which includes at least one measurement application device. A pre-trained artificial intelligence algorithm is coupled to the text-based input interface, and the pre-trained artificial intelligence algorithm is configured to generate response data on questions related to the measurement application based on the text-based user request; and An output interface is coupled to the pre-trained artificial intelligence algorithm, and the output interface is configured to output the response data.

2. The measurement application control unit of claim 1 further includes an audio input interface configured to receive spoken requests; and It also includes a speech recognition unit coupled to the audio input interface and the text-based input interface; in, The speech recognition unit is configured to convert the spoken request into a text-based request and provide the text-based request as a text-based user request to the text-based input interface.

3. The measurement application control unit according to any one of the preceding claims, wherein, The pre-trained artificial intelligence algorithm is pre-trained using at least one of the following: a user manual for at least one measurement application device, a data sheet for the at least one measurement application device, application notes for the at least one measurement application device, application notes for at least one measurement application, a user manual for an electronic device, a data sheet for an electronic device, application notes for an electronic device, articles about electronic circuits, online forum discussions about electronic circuits, and videos about electronic circuits.

4. The measurement application control unit according to any one of the preceding claims, wherein, The pre-trained artificial intelligence algorithm includes a large language model, which is based on at least one of a statistical model, a recurrent neural network, a bidirectional encoding representation based on a Transformer model, and a generative pre-trained Transformer model.

5. The measurement application control unit according to any one of the preceding claims further includes a user input interface coupled to the pre-trained artificial intelligence algorithm, and the user input interface is configured to receive user input; in, The pre-trained artificial intelligence algorithm is configured to generate response data about questions related to the measurement application based on the text-based user request and the user input.

6. The measurement application control unit according to claim 5, wherein, The user input interface includes at least one of a button, switch, knob, touchscreen, keyboard, mouse, camera, and gesture sensor.

7. The measurement application control unit according to any one of the preceding claims further includes a translator coupled to the text-based input interface and the pre-trained artificial intelligence algorithm; in, The translator is configured to translate a text-based user request that operates in a language not trained by the pre-trained artificial intelligence algorithm into a translated text-based user request that operates in the language trained by the pre-trained artificial intelligence algorithm, and to provide the translated text-based user request to the pre-trained artificial intelligence algorithm.

8. The measurement application control unit according to any one of the preceding claims further includes a preprocessor coupled to the pre-trained artificial intelligence algorithm; in, The preprocessor is configured to provide a preprocessed text-based request to the pretrained artificial intelligence algorithm before the pretrained artificial intelligence algorithm operates on the text-based user request.

9. The measurement application control unit according to any one of the preceding claims, wherein, The pre-trained artificial intelligence algorithm is configured to receive a text-based user request regarding the use of the at least one measurement application device and generate usage response data, which includes a corresponding explanation of the use of the measurement application device.

10. The measurement application control unit according to any one of the preceding claims, wherein, The pre-trained artificial intelligence algorithm is configured to receive text-based user requests regarding control of the at least one measurement application device and generate control response data, which includes corresponding control commands regarding the use of the measurement application device.

11. The measurement application control unit of claim 10, further comprising a code generator coupled to or integrated into a pre-trained artificial intelligence algorithm; in, The code generator is configured to generate configuration and control commands for the measurement application device in a predetermined control or programming language, and to provide the generated configuration and control commands to the controller of the measurement application device.

12. The measurement application control unit according to any one of the preceding claims, wherein, The pre-trained artificial intelligence algorithm includes an algorithm that is executed locally on the at least one measurement application device.

13. The measurement application control unit according to any one of the preceding claims further includes a complexity estimator coupled to the text-based input interface; in, The complexity estimator is configured to estimate the complexity of the text-based user request, and if the estimated complexity is higher than a predetermined threshold, forward the text-based user request to an external pre-trained artificial intelligence algorithm.

14. The measurement application control unit according to claim 13, wherein, The complexity estimator is configured to request user consent via the user interface in the measurement application before providing one of the text-based user requests to an external, pre-trained artificial intelligence algorithm.

15. The measurement application control unit according to any one of claims 13 and 14, wherein, The complexity estimator is configured to indirectly provide the text-based user request to the external pre-trained artificial intelligence algorithm via a request anonymizer.

16. The measurement application control unit according to any one of the preceding claims further includes a text-based user request generator configured to receive at least one of an image, video, or non-text description of at least one of the at least one measurement application device, the device under test, and the measurement application settings; in, The text-based user request generator is also configured to generate a text-based user request based on at least one of the images or videos, and to provide the generated text-based user request to the pre-trained artificial intelligence algorithm.

17. The measurement application control unit according to any one of the preceding claims further includes a confidence estimator configured to calculate and output a confidence value of the response data generated by the pre-trained artificial intelligence algorithm.

18. Measuring application equipment, including: Measurement application control unit according to any one of the preceding claims; and Measurement application device controller coupled to the measurement application control unit.

19. A computer-implemented method, comprising: Receive a text-based user request regarding a measurement application, which includes at least one measurement application device; Using a pre-trained artificial intelligence algorithm, response data is generated based on the text-based user request to answer questions related to the measurement application. and Output the response data.

20. The computer-implemented method according to claim 19, further comprising: Receive spoken requests; Convert the spoken request into a text-based request; and The text-based request is provided to the pre-trained artificial intelligence algorithm as a text-based user request.

21. The computer-implemented method according to any one of the preceding method-based claims, wherein, The pre-trained artificial intelligence algorithm is pre-trained using at least one of the following: user manuals for the at least one measurement application device, data sheets for the at least one measurement application device, application notes for the at least one measurement application device, application notes for at least one measurement application, user manuals for electronic devices, data sheets for electronic devices, application notes for electronic devices, articles about electronic circuits, online forum discussions about electronic circuits, and videos about electronic circuits.

22. The computer-implemented method according to any one of the preceding method-based claims, wherein, The pre-trained artificial intelligence algorithm includes a large language model, which is based on at least one of a statistical model, a recurrent neural network, a bidirectional encoding representation based on a Transformer model, and a generative pre-trained Transformer model.

23. The computer-implemented method according to any one of the preceding method-based claims further comprises: Receive user input; The pre-trained artificial intelligence algorithm generates response data about questions related to the measurement application based on the text-based user request and the user input.

24. The computer-implemented method according to claim 23, wherein, The user input is provided via at least one of buttons, switches, knobs, touchscreens, keyboards, mice, cameras, and gesture sensors.

25. The computer-implemented method according to any one of the preceding method-based claims further comprises: The text-based user request, which uses the pre-trained artificial intelligence algorithm but is not trained to operate, is translated into a translated text-based user request using the pre-trained artificial intelligence algorithm trained to operate. and The translated text-based user request is provided to the pre-trained artificial intelligence algorithm.

26. The computer-implemented method according to any one of the preceding method-based claims further comprises: Before the pre-trained artificial intelligence algorithm processes the text-based user request, a pre-processed text-based request is provided to the pre-trained artificial intelligence algorithm.

27. The computer-implemented method according to any one of the preceding method-based claims, wherein, The text-based user request relates to the use of at least one of the measurement application devices; and The response data is generated by the pre-trained artificial intelligence algorithm and includes corresponding explanations regarding the use of the measurement application equipment.

28. The computer-implemented method according to any one of the preceding method-based claims, wherein, The text-based user request relates to the control of at least one of the measurement application devices; The control response data is generated by the pre-trained artificial intelligence algorithm and includes corresponding control commands regarding the use of the measurement application device.

29. The computer-implemented method according to claim 28, further comprising: Generate configuration and control commands for the measurement application device using a predetermined control or programming language; and The generated configuration and control commands are provided to the controller of the measurement application device.

30. The computer-implemented method according to any one of the preceding method-based claims, wherein, The pre-trained artificial intelligence algorithm is executed locally on at least one measurement application device.

31. The computer-implemented method according to any one of the preceding method-based claims further comprises: Estimate the complexity of the text-based user request; and If the estimated complexity exceeds a predetermined threshold, the text-based user request is forwarded to an external pre-trained artificial intelligence algorithm.

32. The computer-implemented method according to claim 31, further comprising: Before providing one of the text-based user requests to the external pre-trained artificial intelligence algorithm, user consent is requested via the user interface in the measurement application.

33. The computer-implemented method according to any one of claims 31 and 32 further comprises: The text-based user request is indirectly provided to the external pre-trained artificial intelligence algorithm via a request anonymizer.

34. The computer-implemented method according to any one of the preceding method-based claims further comprises: Receive at least one of the following: an image, video, or non-text description from at least one of the at least one measurement application device, the device under test, and the measurement application settings; Generate a text-based user request based on at least one of the image or the video; and The generated text-based user requests are provided to the pre-trained artificial intelligence algorithm.

35. The computer-implemented method according to any one of the preceding method-based claims further includes calculating and outputting a confidence value of the response data generated by the pre-trained artificial intelligence algorithm.

36. A non-transitory computer program product including instructions that, when executed by a processor, cause the processor to perform the method according to any one of the preceding method-based claims.

37. A measurement application processing device, comprising: The text-based input interface is configured to receive text-based user requests about the measurement application. A pre-trained artificial intelligence algorithm is coupled to the text-based input interface, and the pre-trained artificial intelligence algorithm is configured to generate response data about the measurement application based on the text-based user request; and An output interface is coupled to the pre-trained artificial intelligence algorithm, and the output interface is configured to output the response data.

38. The measurement application processing device of claim 37, further comprising an audio input interface configured to receive spoken requests; and It also includes a speech recognition unit coupled to the audio input interface and the text-based input interface; in, The speech recognition unit is configured to convert the spoken request into a text-based request and provide the text-based request as a text-based user request to the text-based input interface.

39. The measurement application processing device according to any one of claims 37 to 38, wherein, The pre-trained artificial intelligence algorithm is pre-trained using at least one of the following: user manuals for one or more measurement application devices or applications, data sheets for one or more measurement application devices or applications, application notes for one or more measurement application devices or applications, data sheets for electronic devices, application notes for electronic devices, articles about electronic circuits, online forum discussions about electronic circuits, and videos about electronic circuits.

40. The measurement application processing device according to any one of claims 37 to 39, wherein, The pre-trained artificial intelligence algorithm includes a large language model, which is based on at least one of a statistical model, a recurrent neural network, a bidirectional encoding representation based on a Transformer model, and a generative pre-trained Transformer model.

41. The measurement application processing apparatus according to any one of claims 37 to 40, wherein, The pre-trained artificial intelligence algorithm is configured to receive text-based user requests regarding settings of the measurement application and generate setting response data, which includes a corresponding explanation of the settings of the measurement application.

42. The measurement application processing device according to claim 41, wherein, The pre-trained artificial intelligence algorithm is configured to generate setup response data, which indicates at least one of the following: which measurement application device is used, and how to connect the measurement application device to set up the measurement application.

43. The measurement application processing device according to claim 42, wherein, The pre-trained artificial intelligence algorithm is configured to generate a block diagram of the settings for the measurement application.

44. The measurement application processing apparatus according to any one of claims 37 to 43, wherein, The pre-trained artificial intelligence algorithm is also configured to generate control response data, which includes corresponding control commands for at least one measurement application device.

45. The measurement application processing device of claim 44, further comprising a code generator coupled to or integrated into the pre-trained artificial intelligence algorithm; in, The code generator is configured to generate configuration and control commands for the at least one measurement application device in a predetermined control or programming language.

46. ​​The measurement application processing device according to any one of claims 37 to 45 further includes a preprocessor coupled to the pre-trained artificial intelligence algorithm; in, The preprocessor is configured to provide the pre-processed text-based request to the pre-trained artificial intelligence algorithm before the pre-trained artificial intelligence algorithm operates on the text-based user request.

47. The measurement application processing apparatus according to any one of claims 37 to 46, wherein, The pre-trained artificial intelligence algorithm is configured to enhance the text-based user request and output the enhanced text-based user request via the output interface. The pre-trained artificial intelligence algorithm is configured to generate the response data after the user confirms the enhanced text-based user request.

48. The measurement application processing apparatus according to any one of claims 37 to 47 further includes a text-based user request generator configured to receive at least one of an image, video, and non-text description of the measurement application apparatus, the device under test, or the measurement application settings; in, The text-based user request generator is also configured to generate text-based user requests based on at least one of the image, video, and non-text description, and to provide the generated text-based user requests to the pre-trained artificial intelligence algorithm.

49. The measurement application processing device according to any one of claims 37 to 48, wherein, The pre-trained artificial intelligence algorithm is configured to receive text-based user requests regarding the maintenance of measurement application equipment in a measurement application, and to generate maintenance response data, which includes a corresponding explanation of the maintenance of the relevant measurement application equipment.

50. The measurement application processing apparatus according to any one of claims 37 to 49 further includes a warning generator configured to generate a warning to a user regarding the configuration of the measurement application apparatus that is detrimental to a predetermined measurement application.

51. The measurement application processing device according to any one of claims 37 to 50 further includes a feedback interface configured to receive measurement feedback data; in, The pre-trained artificial intelligence algorithm is configured to generate another set of response data based on the original text-based user request and the received measurement feedback data.

52. The measurement application processing apparatus of claim 51, further comprising a feedback data analyzer disposed between the feedback interface and the pre-trained artificial intelligence algorithm; in, The feedback data analyzer is configured to generate a text-based feedback description of the measured feedback data and provide the text-based feedback description to the pre-trained artificial intelligence algorithm.

53. The measurement application processing device according to claim 52, wherein, The feedback data analyzer is configured to identify at least one of anomalies, relevant measurements, and relevant measurement waveform portions in the raw measurement data provided in the measurement feedback data, and to provide a corresponding text-based feedback description.

54. The measurement application processing device according to any one of claims 51 to 53 further includes a feedback output interface configured to output measurement feedback data to a user; in, The pre-trained artificial intelligence algorithm is configured to generate another set of response data based on the original text-based user request and another text-based user request received after the measurement feedback data has been output to the user.

55. The measurement application processing apparatus according to claims 52 and 54, wherein, The feedback output interface outputs the text-based feedback description to the user.

56. The measurement application processing device according to any one of claims 54 and 55, wherein, The pre-trained artificial intelligence algorithm is configured to perform reinforcement learning based on the other text-based user request received after the measurement feedback data is output to the user.

57. A measurement application, comprising: Measurement application processing device according to any one of the preceding claims; and At least one measuring application device.

58. The measurement application according to claim 57, wherein, The at least one measurement application device is communicatively coupled to the measurement application processing device to receive configuration and control commands from the measurement application processing device.

59. A computer-implemented method, comprising: Receive text-based user requests regarding the measurement application; Using a pre-trained artificial intelligence algorithm, response data about the measurement application is generated based on the text-based user request; and Output the response data.

60. The computer-implemented method according to claim 59, further comprising: Receive spoken requests; Convert the spoken request into a text-based request; and The text-based request is provided to the text-based input interface as a text-based user request.

61. The computer-implemented method according to any one of claims 59 to 60 of the preceding method-based method, wherein, The pre-trained artificial intelligence algorithm is pre-trained using at least one of the following: user manuals for one or more measurement application devices or applications, data sheets for one or more measurement application devices or applications, application notes for one or more measurement application devices or applications, data sheets for electronic devices, application notes for electronic devices, articles about electronic circuits, online forum discussions about electronic circuits, and videos about electronic circuits.

62. The measurement application processing device according to any one of claims 59 to 61, wherein, The pre-trained artificial intelligence algorithm includes a large language model, which is based on at least one of a statistical model, a recurrent neural network, a bidirectional encoding representation based on a Transformer model, and a generative pre-trained Transformer model.

63. The computer-implemented method according to any one of claims 59 to 62 of the preceding method-based method, wherein, The pre-trained artificial intelligence algorithm receives a text-based user request regarding the settings of the measurement application and generates setting response data, which includes a corresponding explanation of the settings of the measurement application.

64. The computer-implemented method according to claim 63, wherein, The pre-trained artificial intelligence algorithm generates setup response data, which indicates which measurement application devices to use and how to connect the measurement application devices to set up the measurement application.

65. The computer-implemented method according to claim 64, wherein, The pre-trained artificial intelligence algorithm generates a block diagram of the settings for the measurement application.

66. The computer-implemented method according to any one of claims 59 to 65 of the preceding method-based method, wherein, The pre-trained artificial intelligence algorithm generates control response data, which includes corresponding control commands for at least one measurement application device.

67. The computer-implemented method of claim 66 further includes generating configuration and control commands to the measurement application device in a predetermined control or programming language.

68. The computer-implemented method according to any one of claims 59 to 67 of the preceding method-based method, further comprising providing a pre-processed text-based request to the pre-trained artificial intelligence algorithm before the pre-trained artificial intelligence algorithm operates on the text-based user request.

69. The computer-implemented method according to any one of claims 59 to 68 of the preceding method-based method, wherein, The pre-trained artificial intelligence algorithm enhances the text-based user request and outputs the enhanced text-based user request via the output interface; and The pre-trained artificial intelligence algorithm generates the response data after the user confirms the enhanced text-based user request.

70. The computer-implemented method according to any one of claims 59 to 69 of the preceding method-based method, further comprising: Receive at least one of the following: an image or video from a measurement application device, a device under test, or a measurement application setting; and Generate a text-based user request based on at least one of the images or the video.

71. The computer-implemented method according to any one of claims 59 to 70 of the preceding method-based method, wherein, The pre-trained artificial intelligence algorithm receives a text-based user request regarding the maintenance of measurement application equipment in the measurement application and generates maintenance response data, which includes a corresponding explanation of the maintenance of the relevant measurement application equipment.

72. The computer-implemented method according to any one of claims 59 to 71 of the foregoing method-based method further includes generating a warning for the user regarding the configuration of a measurement application device that is detrimental to a predetermined measurement application.

73. The computer-implemented method according to any one of claims 59 to 72 of the preceding method-based method further includes receiving measurement feedback data; in, The pre-trained artificial intelligence algorithm generates another set of response data based on the original text-based user request and the received measurement feedback data.

74. The computer-implemented method of claim 73 further includes generating a text-based feedback description of the measurement feedback data and providing the text-based feedback description to the pre-trained artificial intelligence algorithm.

75. The computer-implemented method according to claim 74, wherein, Generating a text-based feedback description includes identifying at least one of anomalies, relevant measurement values, and relevant measurement waveform portions in the raw measurement data provided in the measurement feedback data, and providing a corresponding text-based feedback description.

76. The computer-implemented method according to any one of claims 73 to 75 further includes outputting measurement feedback data to the user; in, The pre-trained artificial intelligence algorithm generates another set of response data based on the original text-based user request and another text-based user request received after outputting the measurement feedback data to the user.

77. The computer-implemented method according to claims 74 and 75, wherein, The text-based feedback description is output to the user.

78. The computer-implemented method according to any one of claims 76 and 77, wherein, The pre-trained artificial intelligence algorithm performs reinforcement learning based on the other text-based user request received after the measurement feedback data is output to the user.

79. A non-transitory computer program product including instructions that, when executed by a processor, cause the processor to perform the method according to any one of claims 59 to 78 of the preceding method-based method.

Images