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 text-based user requests regarding 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 questions related to the meas- urement application based on the text-based user requests, and an output interface coupled to the pre-trained artificial-intelligence algorithm, and configured to output the response data. Fur- ther, the present disclosure provides a measurement application device, and a respective 10 method.

Description

MEASUREMENT APPLICATION CONTROL UNIT, MEASUREMENT APPLICATION DEVICE, AND METHODTECHNICAL FIELD

[0001] A first aspect of the present disclosure relates to a measurement application control unit, a measurement application device, and a respective method.BACKGROUND

[0002] Although applicable to any type of user-controller measurement application device, the present disclosure will mainly be described in conjunction with laboratory-destined measurement application devices, like oscilloscopes.

[0003] Modern measurement application devices comprise a plurality of functions that support specific tasks in measurement applications. To this end, the measurement application devices may comprise a plurality of options and configuration parameters that a user may setup for a specific measurement application.

[0004] Accordingly, there is a need for simplifying measurement application device setup.SUMMARY

[0005] The above stated problem is solved by the features of the independent claims according to the first aspect of the present disclosure. It is understood, that independent claims of a claim category may be formed in analogy to the dependent claims of another claim category.

[0006] Accordingly, it is provided:

[0007] A measurement application control unit comprising a text-based input interface configured to receive text-based user requests regarding a measurement application comprising 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 requests, and an output interface coupled to the pre-trained artificial-intelligence algorithm, and configured to output the response data.

[0008] Further, it is provided:

[0009] A measurement application device comprising a measurement application control unit according to any one of the embodiments disclosed herein, and a measurement application device controller coupled to the measurement application control unit.

[0010] Further, it is provided:

[0011] A method for controlling a measurement application device, the method comprising receiving text-based user requests regarding a measurement application comprising at least one measurement application device, generating response data regarding questions related to the measurement application device based on the text-based user requests with a pre-trained artificial-intelligence algorithm, and outputting the response data.

[0012] The present disclosure is based on the finding that modern measurement applications may provide the possibility to perform a large number of user-configurable measurements or measurement tasks that may be difficult to memorize and understand for users.

[0013] The most important measurements or measurement tasks may be presented prominently on a main screen of a respective measurement application device in the measurement application. However, other measurements or measurement tasks, and the options that may be required only for very specific measurement tasks may e.g., be hidden in sub-menus of the user interface of the measurement application device.

[0014] Especially, inexperienced users may face difficulties when they try to formulate questions regarding their specific measurement problem or measurement task. Such users may also face difficulties when setting-up a measurement application and configuring the measurement application devices. Inexperienced users may even lack the knowledge about the specific functions of prominently presented configuration options, and especially the existence of such configuration options that are e.g., hidden in sub-menus of the user interface of the measurement application device.

[0015] The present disclosure, therefore, provides the measurement application control unit, the method for controlling a measurement application device, and a respective measurement application device. Although not explicitly claimed, the present disclosure also provides a non-transitory computer-readable medium comprising instructions that when executed in a computer cause the computer to perform a method according to any one of the embodiments presented herein.

[0016] The measurement application control unit comprises a text-based input interface. The text-based input interface may receive text-based user requests from a user. Such text-based user requests may comprise natural language text that refers to the measurement application.

[0017] The text-based input interface may be implemented as a data interface that receives the text in a binary form e.g., as ASCII encoded text, or as text encoded in any other character encoding scheme. Such a data interface may be provided as hardware interface e.g., as a network interface, and a program interface, like an API or a callback function, or a combination of both.

[0018] The text-based input interface may comprise any other type of interface, like an API, callback functions, shared memory, a web-based III, a REST-API, a class or interface, like a Python class or Python interface, without being limited to these examples.

[0019] The text-based user requests are then provided to the pre-trained artificial-intelligence algorithm that generates respective response data based on the provided text-based user requests.

[0020] The pre-trained artificial-intelligence algorithm may, especially, be trained to receive text-based user requests that are formulated in a natural language style e.g., as a user would speak the text-based user requests to other users, or as a user would formulate the text-based user requests e.g., in an online forum.

[0021] Questions a user may formulate regarding the measurement application may e.g., arise based on the underlying electrical signals in the measurement application. A user may e.g., be provided with a PWM signal, or with a serial Bus, like an USB bus, or an SPI bus. Especially, inexperienced users may lack the knowledge to pose the right questions, when presented with such a system. The response data may, therefore, refer to such questions that may be related to the respective measurement application. Inexperienced users may e.g., not know what options they have to measure signals in such a measurement application or what characteristics of such signals they may measure. The response data may help the user to formulate questions regarding such signals. It is understood, that such questions may be fed to another artificial-intelligence based system that supports the user in performing respective measurements.

[0022] Just as an example, with a PWM signal, the response data may comprise or refer to questions like: “How do I measure the duty cycle of the PWM signal?” The response data could formulate such a questions in the form of: “Would you like to measure the duty cycle of the PWM signal?” The response data could also comprise an explanation of technical terms, like “duty cycle”. In an example with an SPI-Bus, the response data may comprise or refer to questions like: “How do I determine the bus frequency or the data rate on the bus”, or “How do I ex-tract the digital data transmitted on the bus?” The response data could formulate such a questions in the form of: “Would you like to determine the bus frequency or the data rate on the bus”, or ““Would you like to extract the digital data transmitted on the bus?” Of course, the above examples are not limiting, and the pre-trained artificial-intelligence algorithm may be trained to support a user in formulating any type of questions related to a measurement application or to a measurement application device in a measurement application. After a user acknowledges that the respective question is the questions that he was seeking to formulate, the pre-trained artificial-intelligence algorithm may provide the user with an answer to that question e.g., with an explanation on how to perform the respective measurement tasks.

[0023] During operation, the pre-trained artificial-intelligence algorithm may serve the user to discover functionality in the measurement application or in any one of the respective measurement application devices that the user did not yet know.

[0024] The response data may be provided in different forms, as will be explained in more detail below. Generally, in embodiments the response data may be provided in textual form. The term “textual form” in the context of the present disclosure may refer to any type of text that may include, but is not limited to, natural language text, and text in a programming or scripting language.

[0025] The response data may be generated by the pre-trained artificial-intelligence algorithm based on the text-based user requests only. In embodiments, the pre-trained artificial-intelligence algorithm may also be provided with context data about the measurement application, or at least one measurement application device in the measurement application. In such embodiments, the pre-trained artificial-intelligence algorithm may in addition generate the response data based on the context data e.g., a current setup or configuration of the measurement application. The context data may be provided to the pre-trained artificial-intelligence algorithm by the pre-conditioner mentioned below. The pre-trained artificial-intelligence algorithm may, therefore, kind of guess the underlying measurement problem or measurement context. From such an underlying measurement problem or measurement context the specific questions or measurement tasks may be derived, especially, automatically by the pre-trained artificial-intelligence algorithm.

[0026] The pre-trained artificial-intelligence algorithm may also be trained to derive from the context data e.g., from data about past and current states of a measurement application device, which measurement tasks have already been performed in the measurement application, and take this information into account, when generating the response data.

[0027] In embodiments, the pre-trained artificial-intelligence algorithm may be configured to perform multiple questions - answer iterations with a user in order to generate a final response data. In such an embodiment, the pre-trained artificial-intelligence algorithm may be trained to start questioning the user with rather general questions about the measurement application and moving to more detailed questions based on the answers provided by the user. During multiple question - answer iterations, the responses provided by the user to the measurement application control unit may be seen as a feedback to the measurement application control unit. In embodiments, a user may restart the question - answer iterations by indicating that the response data does not meet his requirements.

[0028] The pre-trained artificial-intelligence algorithm may also be configured to separate an underlying measurement problem or measurement context into different measurement applications or measurement application tasks, and to provide respective response data to a user.

[0029] The measurement application control unit further comprises an output interface that outputs the response data. The explanations provided above for the input interface may apply mutatis mutandis to the output interface. In embodiments, the input interface and the output interface may be implemented as a single data interface.

[0030] In a measurement application device, the response data may e.g., be provided to a measurement application device controller that may further process the response data. The measurement application device controller may e.g., output the response data to a user via a display.

[0031] In embodiments, the measurement application device may comprise an audio output interface e.g., a speaker, and may output the response data as audio output to a user. To this end, a text-to-speech engine may be provided in the measurement application device for receiving the response data from the pre-trained artificial-intelligence algorithm, and converting the response data into audio.

[0032] The response data may in embodiments also comprise or link to sections of manuals, application data sheets, or tutorial videos that comprise an answer to the question that the response data relates to. The response data may in such embodiments directly guide the user to the relevant content. Especially in long manuals or tutorial videos, the user may be directly guided to the relevant section without the need to go through the complete manual or video.

[0033] To this end, the pre-trained artificial-intelligence algorithm may be trained with single sections of respective manuals or with single sections of respective videos. Instead of sections of videos, the pre-trained artificial-intelligence algorithm may also be trained with textual descriptions of the sections of the videos. The manuals or videos may be manually divided intosingle sections. In addition, or as alternative, another artificial-intelligence system may be provided to separate the manuals or videos into respective sections. In other embodiments, the pre-trained artificial-intelligence algorithm may be trained with the full manuals or videos, and may be configured to identify the relevant sections internally.

[0034] It is understood, that the method for controlling a measurement application device according to the present disclosure may not only be performed locally in a single measurement application device. Instead, the method according to the present disclosure may also be performed remotely or in a distributed fashion.

[0035] In embodiments, the measurement application control unit may e.g., be provided remotely to a measurement application device. The measurement application control unit may e.g., be provided as a server, or server-based or cloud-based application, that may be accessed by a user via a web interface. Any control data that the measurement application control unit may generate for the measurement application device may be provided to the measurement application device via a respective network or data connection. To this end, the measurement application device may comprise a respective communication interface.

[0036] In embodiments, the communication interface may comprise any kind of wired and wireless communication interfaces, like for example a network communication interface, especially an Ethernet, wireless LAN or WIFI interface, a USB interface, a Bluetooth interface, an NFC interface, a visible or non-visible light-based interface, especially an infrared interface.

[0037] Further the server or cloud server and the measurement application device may communicate via an intermediary network with each other, and such a network may comprise any type of network devices, like switches, hubs, routers, firewalls, and different types of network technologies.

[0038] Generally, such a server may be a dedicated server that may be implemented as a single hardware device. The server may also be implemented as a distributed system comprising a plurality of servers, optionally with a load balancer, that distributes the load over the servers. The server may also be provided as a so-called cloud or cloud-server system that implements the server via virtualization methods independently of the underlying hardware.

[0039] In embodiments, the measurement application control unit may be operated independently of the measurement application device, and may not even be communicatively coupled to the measurement application device. In such embodiments the user may be the sole recipient of the generated response data, or the generated response data may be stored on a data carriers, like a USB memory, that may be connected to the measurement application device by a user.

[0040] The measurement application control unit may, in embodiments, comprise or may be provided in or as part of at least one of a dedicated processing element e.g., a processing unit, a microcontroller, a field programmable gate array, FPGA, a complex programmable logic device, CPLD, an application specific integrated circuit, ASIC, or the like. A respective program or configuration may be provided to implement the required functionality. The measurement application control unit may at least in part also be provided as a computer program product comprising computer readable instructions that may be executed by a processing element. In a further embodiment, the measurement application control unit may be provided as addition or additional function or method to the firmware or operating system of a processing element that is already present in the respective application as respective computer readable instructions e.g., in the measurement application device. Such computer readable instructions may be stored in a memory that is coupled to or integrated into the processing element, like the measurement application device controller of the measurement application device. The processing element may load the computer readable instructions from the memory and execute them. The same applies to any other element, unit or function disclosed herein as part of the measurement application control unit, the measurement application device, and the method for controlling a measurement application device.

[0041] In addition, it is understood, that any required supporting or additional hardware may be provided like e.g., a power supply circuitry and clock generation circuitry.

[0042] In the context of the present disclosure, a measurement application device may comprise any device that may be used in a measurement application to acquire an input signal or to generate an output signal, or to perform additional or supporting functions in a measurement application. A measurement application device may also comprise or be implemented as program application or program applications, also called measurement program application or measurement program applications, that may be executed on a computer device and that may communicate with other measurement application devices in order to perform a measurement task. A measurement application, also called measurement setup, may e.g., comprise at least one or multiple different measurement application devices for performing electric, magnetic, or electromagnetic measurements, especially on single devices under test. Such electric, magnetic, or electromagnetic measurements may e.g., be performed in a measurement laboratory or in a production facility in the respective production line. A measurement application or measurement setup may serve to qualify the single devices under test i.e., to determine the proper electrical operation of the respective devices under test.

[0043] Measurement application devices to this end may comprise at least one signal acquisition section for acquiring electric, magnetic, or electromagnetic signals to be measuredfrom a device under test, or at least one signal generation section for generating electric, magnetic, or electromagnetic signals that may be provided to the device under test. Such a signal acquisition section may comprise, but is not limited to, a front-end for acquiring, filtering, and attenuating or amplifying electrical signals. The signal generation section may comprise, but is not limited to, respective signal generators, amplifiers, and filters.

[0044] Further, when acquiring signals, measurement application devices may comprise a signal processing section that may process the acquired signals. Processing may comprise converting the acquired signals from analog to digital signals, and any other type of digital signal processing, for example, converting signals from the time-domain into the frequency-domain.

[0045] The measurement application devices may also comprise a user interface to display the acquired signals to a user and allow a user to control the measurement application devices. Of course, a housing may be provided that comprises the elements of the measurement application device. It is understood, that further elements, like power supply circuitry, and communication interfaces may be provided.

[0046] A measurement application device may be a stand-alone device that may be operated without any further element in a measurement application to perform tests on a device under test. Of course, communication capabilities may also be provided for the measurement application device to interact with other measurement application devices.

[0047] A measurement application device may comprise, for example, a signal acquisition device e.g., an oscilloscope, especially a digital oscilloscope, a spectrum analyzer, or a vector network analyzer. Such a measurement application device may also comprise a signal generation device e.g., a signal generator, especially an arbitrary signal generator, also called arbitrary waveform generator, or a vector signal generator. Further possible measurement application devices comprise devices like calibration standards, or measurement probe tips.

[0048] Of course, at least some of the possible functions, like signal acquisition and signal generation, may be combined in a single measurement application device.

[0049] In embodiments, the measurement application device may comprise pure data acquisition devices that are capable of acquiring an input signal and of providing the acquired input signal as digital input signal to a respective data storage or application server. Such pure data acquisition devices not necessarily comprise a user interface or display. Instead, such pure data acquisition devices may be controlled remotely e.g., via a respective data interface, like a network interface or a USB interface. The same applies to pure signal generation devices thatmay generate an output signal without comprising any user interface or configuration input elements. Instead, such signal generation devices may be operated remotely via a data connection.

[0050] With the measurement application control unit, the measurement application device, and the method according to the present disclosure, a user may identify the questions underlying his measurement application, and may interact with measurement application devices, like the ones described above, naturally, like speaking with another user.

[0051] Further embodiments of the present disclosure are subject of the further dependent claims and of the following description, referring to the drawings.

[0052] In the following, the dependent claims referring directly or indirectly to claim 1 according to the first aspect of the present disclosure are described in more detail. For the avoidance of doubt, the features of the dependent claims relating to the measurement application control unit can be combined in all variations with each other and the disclosure of the description is not limited to the claim dependencies as specified in the claim set. Further, the features of the other independent claims may be combined with any of the features of the dependent claims relating to the measurement application control unit in all variations, wherein in the method respective method steps perform the function of the respective elements.

[0053] In an embodiment, which can be combined with all other embodiments mentioned above or below, the measurement application control unit may further comprise an audio input interface configured to receive spoken language 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 language requests into text-based requests, and to provide the text-based requests to the text-based input interface as text-based user requests.

[0054] The audio input interface may be provided as local or hardware audio input interface in the measurement application device controller, or in a measurement application device that implements or comprises the measurement application device controller.

[0055] In other embodiments, the audio input interface may be provided as data interface that receives audio data from another device. Such a data interface may be provided as a hardware interface, or a software interface, or a combination of both. Generally, the hardware interface of the audio interface may comprise any kind of wired and wireless communication interfaces, like for example a network communication interface, especially an Ethernet, wireless LAN or WIFI interface, a USB interface, a Bluetooth interface, an NFC interface, a visible or non-visi- ble light-based interface, especially an infrared interface.

[0056] The audio input interface is coupled to a speech recognition unit that converts the spoken language requests i.e., audio data, received via the audio input interface into text-based user requests. Such text-based user requests may then be provided to the text-based input interface, as any other text-based user requests for further processing by the pre-trained artificialintelligence algorithm.

[0057] The speech recognition unit may be provided as a hardware-based unit, a softwarebased unit, or a combination of both, as already indicated above for the measurement application control unit.

[0058] With the audio input interface, and the speech recognition unit a user may communicate naturally with the measurement application control unit, as if he was speaking with another user.

[0059] In another embodiment, which can 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 manuals regarding at least one measurement application device, datasheets regarding the at least one measurement application device, application notes regarding the at least one measurement application device, application notes regarding at least one measurement application, manuals of electronic devices, datasheets of electronic devices, application notes of electronic devices, articles regarding electronic circuits, online forum discussions regarding electronic circuits, and videos regarding electronic circuits.

[0060] The pre-trained artificial-intelligence algorithm needs to be trained on data regarding the measurement application device that the text-based user requests refer to. Of course, in embodiments, the pre-trained artificial-intelligence algorithm may be trained on information regarding multiple different measurement application devices.

[0061] Usually, a wide selection of training data is already available from the manufacturers of the respective measurement application device(s). Such training data may be provided e.g., in the form of manuals, datasheets, and application notes that a manufacturer of a measurement application device may publish.

[0062] An exemplary extract from a manual of an oscilloscope regarding the setting of the voltage range on an input that may be applied to all aspects of the present disclosure may read as follows:

[0063] “You can select the sensitivity of the analog inputs by using the knob in the VERTICAL section (VOLTS / DIV) in 1-2-5 steps of 1 m / div to 10V / div. The knob is associated with the active channel (push the respective channel key to activate the desired channel). Pushing theknob once will switch to a continuous sensitivity setting. You can use the smaller knob in the VERTICAL section (POSITION) to determine vertical settings for the active channel. Press the MENU key to access advanced options. On page 2|2 of this menu, you can add a DESKEW. To activate this offset push the corresponding soft menu key. You can set the offset value using the universal knob or the KEYPAD key in the CURSOR / MENU section. Each analog channel may be shifted in time by ±32 ns. This deskew setting is used to compensate different signal delays when using different cable lengths or probes.”

[0064] Such an explanation may be accompanied by an image of the oscilloscope, or the section comprising the buttons, switches and knobs for the vertical section.

[0065] Application notes regarding at least one measurement application may comprise application notes that explain a measurement application in a general context, like measurements of PWM signals, or measurements in SPI communication systems. Such application notes may, in addition to the general information, also comprise information specific to one measurement application device or multiple measurement application devices.

[0066] In embodiments, the pre-trained artificial-intelligence algorithm may be pre-trained based on general data that is not specific to any measurement application device.

[0067] The training data relating to one or more measurement application devices may then be used to perform a fine-tuning of the pre-trained artificial-intelligence algorithm. Such a fine- tuning will then allow the pre-trained artificial-intelligence algorithm to respond more adequately to the text-based user requests regarding the measurement application device.

[0068] In an embodiment, a further trained algorithm may be provided that is trained to provide a textual description of images and diagrams. Such a trained algorithm may be used to explain the content of images or diagrams provided in the training data, especially in manuals, datasheets, and application notes, to the pre-trained artificial-intelligence algorithm in textual form for performing the training of the pre-trained artificial-intelligence algorithm. In embodiments, any other type of adequate pre-processing may be applied, like an optical character recognition.

[0069] The training of the pre-trained artificial-intelligence algorithm may be performed as unsupervised training of the pre-trained artificial-intelligence algorithm. Alternatively, of in addition, the pre-trained artificial-intelligence algorithm may be trained in a supervised training e.g., supervised by an experienced measurement engineer. Respective prompting may also be performed to train the pre-trained artificial-intelligence algorithm.

[0070] In embodiments, different pre-trained artificial-intelligence algorithms with different levels of training, and or different levels of complexity, and therefore capabilities, may be available to choose from. Choosing a pre-trained artificial-intelligence algorithm may depend on any one of the available hardware resources like, memory, processing power, storage, and licensing costs. Of course, during operation of the measurement application control unit, an updated pretrained artificial-intelligence algorithm may also be provided and installed in the measurement application control unit.

[0071] In a further embodiment, which can be combined with all other embodiments of the mentioned above or below, the pre-trained artificial-intelligence algorithm may comprise a large language model based on at least one of a Bidirectional Encoder Representations from Transformers model, and a Generative Pre-trained Transformer model.

[0072] While above, two specific types of large language models are explicitly disclosed, it is understood, that the pre-trained artificial-intelligence algorithm may comprise any algorithm that may be trained on a set of training data such that it may generate the response data based on text-based user requests.

[0073] Other possible types of algorithms or models include, but are not limited to, any type of language models, like statistical models like N-grams, recurrent neuronal network, like long short term, LSTM, models, and transformer models.

[0074] In another embodiment, which can be combined with all other embodiments mentioned above or below, the measurement application control unit may further comprise a user input interface coupled to the pre-trained artificial-intelligence algorithm, and configured to receive user input. The pre-trained artificial-intelligence algorithm may be configured to generate the response data regarding questions related to the measurement application based on the text-based user requests and the user input.

[0075] The user interface may allow a user to select keywords regarding the measurement application. Such keywords may be selected by the user in the form of tags, words from a word cloud, or by freely typing or inputting the keywords. The pre-trained artificial-intelligence algorithm may be trained to generate the response data based on such keywords.

[0076] In a further embodiment, which can be combined with all other embodiments mentioned above or below, the user input interface may comprise at least one of a button, a switch, a knob, a touchscreen, a keyboard, a mouse, a camera, and a gesture sensor.

[0077] The user input interface is a second interface that allows a user to interact with the measurement application control unit, or a measurement application device that implements or comprises the measurement application control unit.

[0078] The expression “user input interface” refers to a user interface that provides any other interfacing means to a user that is not text-based or natural-language-based.

[0079] The user input interface may, therefore, comprise any other type of physical interface that allows a user to interact physically with the measurement application control unit, or the measurement application device.

[0080] Apart from the above-mentioned physical interaction elements, like buttons, knobs, touchscreens and so on, the interaction may also be gesture based. To this end, a camera, or any other sensor for acquiring gestures, like a LIDAR or ultrasound sensor, may be provided.

[0081] With this user input interface as second input means for a user, the user may formulate text-based user requests that refer to details of the user input or that are further specified by the user input.

[0082] The user may in exemplary embodiments actuate any element of the user input interface, and provide a text-based user requests regarding that element.

[0083] In an example, the user may e.g., actuate a knob, switch, or button, or indicate a section on a display of the measurement application control unit, or the measurement application device, and provide a rather general text-based user request, like “what is this good for”.

[0084] The pre-trained artificial-intelligence algorithm may then fuse information regarding the user input, and the text-based user requests for generating the response data.

[0085] The capability of performing such a fusion may be provided to the pre-trained artificial-intelligence algorithm in the fine-tuning part of the training phase mentioned above. Especially, the information provided in manuals of measurement application devices may identify input elements or sections of a display of the respective measurement application device and explain the respective functions. When trained with that information, the pre-trained artificial-intelligence algorithm may provide response data that explains the respective functions to the user.

[0086] The fusion of the information regarding the user input, and the text-based user requests may also be performed by the pre-conditioner mentioned below.

[0087] In such embodiments, the pre-conditioner may provide preceding request components, that may be provided before the text-based user requests. Such preceding request components may e.g., indicate which input element or display section the user refers to.

[0088] An exemplary preceding request component may be formulated as: “The user touches the rotary knob referred to as ‘voltage level’, and asks:”. The actual text-based user request may then be provided after this preceding request component to the pre-trained artificialintelligence algorithm.

[0089] The full request provided to the pre-trained artificial-intelligence algorithm may then read e.g., “The user touches the rotary knob referred to as ‘voltage level’, and asks: ‘For what types of measurements do I need this?’ ”.

[0090] Other examples may refer to the user indicating a section on the screen e.g., “The user moves the mouse over the left-most button in the lower display section, and asks: ‘what is this good for?’ ”, or “The user gestures toward the vertical axis of a diagram shown in the display, and asks: ‘what is this good for?’ ”

[0091] Of course, the present disclosure is not limited to the above-presented examples, and may be applied to any other input element, or type of user input.

[0092] In another embodiment, which can be combined with all other embodiments mentioned above or below, the measurement application control unit may further comprise a translator coupled to the text-based input interface, and the pre-trained artificial-intelligence algorithm, wherein the translator may be configured to translate text-based user requests in a language that the pre-trained artificial-intelligence algorithm is not trained to operate on into translated text-based user requests in a language that the pre-trained artificial-intelligence algorithm is trained to operate on, and to provide the translated text-based user requests to the pre-trained artificial-intelligence algorithm.

[0093] The pre-trained artificial-intelligence algorithm may be trained to operate on textbased user requests that are provided in specific languages. The pre-trained artificial-intelligence algorithm may, consequently, not be trained to operate on text-based user requests that are provided in languages that the pre-trained artificial-intelligence algorithm is not trained to operate on.

[0094] In order to support the cooperation of multiple users with different language speaking capabilities, the translator may be provided in the measurement application control unit.

[0095] The translator may receive the text-based user requests in languages that the pretrained artificial-intelligence algorithm is not trained to operate on. The translator may thentranslate the text-based user requests into a language the pre-trained artificial-intelligence algorithm is trained to operate on.

[0096] The translator enables multi-lingual teams that have team members with different levels of languages that the pre-trained artificial-intelligence algorithm is trained to operate on, to cooperate easily even when each team member speaks the respective mother tongue instead of a language that the pre-trained artificial-intelligence algorithm is trained to operate on.

[0097] In embodiments, the translator may comprise a trained artificial intelligence algorithm that is trained to translate natural language text from one language into another language. In embodiments, the translator comprises a respective algorithm that is trained on general text data. In other embodiments, such an algorithm trained on general text data may be fined tuned with text data that is specific to the technical field of measurement application devices.

[0098] In an embodiment, which can be combined with all other embodiments mentioned above or below, the measurement application control unit may further comprise a pre-condi- tioner coupled to the pre-trained artificial-intelligence algorithm. The pre-conditioner may be configured to provide a pre-conditioning text-based request to the pre-trained artificial-intelligence algorithm prior to the pre-trained artificial-intelligence algorithm operating on the textbased user requests.

[0099] The pre-conditioner may serve to indicate general information to the pre-trained artificial-intelligence algorithm that a user may e.g., skip or forget to include in the text-based user requests.

[0100] The pre-conditioning text-based request may be provided to the pre-trained artificialintelligence algorithm preceding the actual text-based user requests, as exemplarily explained above for the user input interface.

[0101] In embodiments, the pre-conditioner may provide the pre-trained artificial-intelligence algorithm with information about at least one of, without being limited to, the measurement application device the user may refer to, a measurement application setup a user is using, the measurement application devices present in the measurement application setup, specifications of the measurement application device(s), and a required type or format for the response data.

[0102] Exemplary pre-conditioning text-based requests formulated by the pre-conditioner may comprise, but are not limited to, requests like:

[0103] “Two measurement inputs of an oscilloscope of model OSCI1 are coupled via measurement probes of type PROBE to a device under test. The device under test is a microcontroller, and the measurement probes are coupled to the I2C signal lines of the microcontroller.”

[0104] “In the measurement setup a signal generator is coupled to the input of a device under test that is an amplifier. Further, an oscilloscope is coupled to the output of the amplifier.”

[0105] The pre-conditioner may in embodiments comprise a further trained artificial-intelligence algorithm that is trained to generated pre-conditioning text-based requests as exemplarily indicated above. Such a trained artificial-intelligence algorithm may e.g., be trained based on sets of exemplary descriptions of measurement application setups and the respective pre-conditioning text-based requests. This further trained artificial-intelligence algorithm may comprise a large language model, or any other type of algorithm, as explained herein for the pre-trained artificial-intelligence algorithm.

[0106] In other embodiments, the pre-conditioner may be implemented without a trained artificial intelligence algorithm. Such embodiments of the pre-conditioner may comprise e.g., a state machine, and may be configured to concatenate respective information about a measurement application setup into respective pre-conditioning text-based requests. The information about the measurement application setup may e.g., be provided in tabular form, wherein each line comprises information about a component of the measurement application setup. Generally, the information may be provided in any adequate, especially structured, format.

[0107] Such information may e.g., indicate the type of element, like signal generation device, signal acquisition device, device under test, probe, adapter, or the like. This information may also indicate the number of outputs or inputs of the respective element, and how the inputs and outputs are coupled to other elements.

[0108] In such embodiments, the pre-conditioner may, for example, simply insert the information in template strings, and concatenate the template strings for all elements in the measurement application setup to generate the respective pre-conditioning text-based request.

[0109] In a further embodiment, which can be combined with all other embodiments mentioned above or below, the pre-trained artificial-intelligence algorithm may be configured to receive text-based user requests regarding the usage of the measurement application device, and to generate usage response data that comprises a respective explanation regarding the usage of the measurement application device.

[0110] As already indicated above, a user may provide questions regarding the usage of the measurement application device. Such requests may be answered by the pre-trained artificial-intelligence algorithm with response data that comprises a textual description that is an answer to the user’s question.

[0111] The measurement application control unit, consequently, allows inexperienced users to instantly learn how to use a certain feature of the measurement application device, without the need to consult a training manual or another user that is more knowledgeable.

[0112] In another embodiment, which can be combined with all other embodiments mentioned above or below, the pre-trained artificial-intelligence algorithm may be configured to receive text-based user requests regarding the control of the measurement application device, and to generate control response data that comprises respective control commands regarding the usage of the measurement application device.

[0113] The control response data may, instead of explaining different features of the measurement application device to a user, directly provide control commands that a user may implement in the measurement application device or in multiple measurement application devices of a measurement setup.

[0114] Such control commands may be provided as natural text commands to a user. Exemplary control commands may comprise, but are not limited to, “set the voltage range to 0V - 100V”, “set the amplification factor to 10x”, “set the scaling of the diagram X-axis to 0.5”, “start the measurement”, “stop the measurement”, “start the signal generation”, “stop the signal generation”, and the like.

[0115] Generally, the control commands may comprise a command regarding any option, or parameter, or user input that a measurement application device may comprise or allow.

[0116] In embodiments, the text-based user requests may also refer to former measurements or measurement protocols or measurement results of former measurements. A user may e.g., indicate “repeat the last measurement”, or “repeat the measurement performed yesterday”.

[0117] In an embodiment, which can be combined with all other embodiments mentioned above or below, the measurement application control unit may further comprise a code generator that is coupled to or integrated into the 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 a controller of the measurement application device.

[0118] While the above-explained types of control commands may be easily understood by a user, a measurement application device may not directly be controlled with such commands.

[0119] However, modern measurement application devices not only comprise a user interface for controlling the respective measurement application device. Instead, such measurement application devices may usually also be controlled programmatically.

[0120] Such control programs may be provided e.g., in a domain specific scripting or programming language, like the SCPI language (Standard Commands for Programmable Instruments). In other embodiments, the control programs may be provided in more general programming languages, like Python, or JavaScript, that may be interpreted in the measurement application device, or as compiled programs that are executed in the measurement application device.

[0121] The code generator, or the pre-trained artificial-intelligence algorithm with the integrated code generator may, therefore, be trained or configured to generate control commands in the response data. The control commands may be provided in any adequate format, like the above-mentioned control programs, without being limited to such programs.

[0122] In such an embodiment, the pre-trained artificial-intelligence algorithm may receive text-based user requests, as indicated above. Such user requests may comprise, as indicated above, general information about a measurement application, like the type of bus or serial communication that is used. The code generator, or the pre-trained artificial-intelligence algorithm may then generate the required control commands for measuring specific characteristics in such a measurement setup. In embodiments, the pre-trained artificial-intelligence algorithm may generate such control commands only in a later stage after performing multiple question - answer iterations with the user. Such user requests may also directly request the measurement application device or multiple measurement application devices of a measurement application setup to be configured in a specific manner.

[0123] In embodiments, 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 of the sets for further processing.

[0124] The code generator, or the pre-trained artificial-intelligence algorithm may then generate the respective control commands in the form of direct control commands or control program commands that may be provided to a measurement application device for execution. In embodiments, the generated control commands may be presented to a user prior to providing the control commands to a measurement application device for execution.

[0125] The measurement application control unit may further comprise a code verification unit or code verifier. The code verification unit may be configured to analyze the generated code and detect inadequate commands or configurations in the generated code. Such a code verification unit may comprise any one of, but is not limited to, an artificial-intelligence based code analyzer, and a rule-based code analyzer. If the code verification unit detects an inadequate command or configuration, the code verification unit may present its finding to a user e.g., via a user interface, and ask the user, if the generated code is acceptable or not.

[0126] The term “inadequate” with regard to the generated code may refer to commands or configurations that may damage a device under test or a measurement application device, or that cause costs for a user e.g., because they refer to installing additional applications on a measurement device.

[0127] In a further embodiment, which can be combined with all other embodiments of the measurement application control unit mentioned above or below, the pre-trained artificial-intelligence algorithm may comprise an algorithm that is locally executed on the measurement application device.

[0128] Depending on the measurement application that the measurement application control unit is used in, the measurement data, and also the specific configuration of the measurement setup, may be confidential.

[0129] In such embodiments, the details of the measurement setup, or the measurement application should not be transmitted to a public service that may host the pre-trained artificialintelligence algorithm.

[0130] In such embodiments, the pre-trained artificial-intelligence algorithm may be locally executed in the measurement application device.

[0131] In embodiments, the pre-trained artificial-intelligence algorithm that is executed locally in the measurement application device may comprise an algorithm that is adapted to the processing and memory resources that are available in the measurement application device locally.

[0132] In embodiments, the locally executed pre-trained artificial-intelligence algorithm may be executed on a server or a dedicated computer that is communicatively coupled to the measurement application device via a secured connection. A secured connection may be provided by providing both devices on the same network that is within the premises of the user of the measurement application device, or by establishing a VPN or any other encrypted communication between the measurement application device, and the respective server.

[0133] In another embodiment, which can be combined with all other embodiments mentioned above or below, the measurement application control unit may further comprise 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 requests, and to forward the textbased user requests to an external pre-trained artificial-intelligence algorithm if the estimated complexity is higher than a predetermined threshold.

[0134] As indicated above, a locally executed pre-trained artificial-intelligence algorithm may be adapted to the processing and memory resources that are locally available in the respective measurement application device.

[0135] Consequently, such a pre-trained artificial-intelligence algorithm may not comprise the capacity to answer all possible text-based user requests, and may be limited to answer only simple text-based user requests.

[0136] In order to allow a user to use complex text-based user requests, the measurement application control unit may be provided with the complexity estimator.

[0137] The complexity estimator may analyze the received text-based user requests, and may determine or estimate the complexity of the text-based user requests. If the determined or estimated complexity is higher than a predetermined threshold, the respective text-based user request may be provided to an external, more powerful pre-trained artificial-intelligence algorithm. The external pre-trained artificial-intelligence algorithm may e.g., be provided as network attached server or cloud server, as already indicated above.

[0138] The predetermined threshold may, of course, be adapted to the capabilities of a locally executed pre-trained artificial-intelligence algorithm. An exemplary complexity measure may e.g., comprise the number of letters, or the number of words, or the number of sentences, or a combination of any of these.

[0139] In an embodiment, which can be combined with all other embodiments mentioned above or below, the complexity estimator may be configured to request a user consent via a user interface of the measurement application device prior to providing one of the text-based user requests to the external pre-trained artificial-intelligence algorithm.

[0140] As explained above, data regarding a measurement setup, or a measurement application may be confidential. Therefore, the complexity estimator may ask a user for consent or permission prior to providing or transmitting a text-based user request to an external pre-trained artificial-intelligence algorithm.

[0141] If the user declines, the complexity estimator may inform the user that the textbased user requests may eventually not be answered correctly with the locally executed pretrained artificial-intelligence algorithm, and provide the text-based user requests to the locally executed pre-trained artificial-intelligence algorithm.

[0142] In another embodiment, which can be combined with all other embodiments mentioned above or below, the complexity estimator may be configured to provide the text-based user requests indirectly to the external pre-trained artificial-intelligence algorithm via a request anonymizer.

[0143] The request anonymizer may be an intermediary device that may be contacted by the complexity estimator instead of directly providing the text-based user requests to an external pre-trained artificial-intelligence algorithm.

[0144] Although not explicitly claimed, the request anonymizer is disclosed herein as separate entity that may be used independently from any measurement application device or measurement application control unit. The external pre-trained artificial-intelligence algorithm, and the request anonymizer may both be combined with, and used with any aspect of the present disclosure.

[0145] The request anonymizer may e.g., comprise a server that bundles text-based user requests from multiple measurement application control units, and forwards the text-based user requests to the externally operated pre-trained artificial-intelligence algorithm without including any information that might identify a measurement application control unit or measurement application device. The request anonymizer may e.g., remove such information from the textbased user requests, or replace such information with other predetermined information.

[0146] In another embodiment, which can be combined with all other embodiments mentioned above or below, the measurement application control unit may further comprise a textbased user request generator configured to receive at least one of an image, a video, or a nontextual description of at least one of measurement application device, a device under test, and a measurement application setup, wherein the text-based user request generator may further be configured to generate text-based user requests based on the at least one of the image or the video, and to provide the generated text-based user requests to the pre-trained artificial-intelligence algorithm.

[0147] With the text-based user request generator the user is provided with alternative means for providing his request to the measurement application processing device.

[0148] Instead of providing the pre-trained artificial-intelligence algorithm with a specific text-based user request, the user may simply provide one or more images or videos of a respective measurement application. Other non-textual descriptions may e.g., comprise log files from a measurement application device, like a log file from a cellular tester.

[0149] The text-based user request generator may than analyze the respective images or videos and generate a respective text-based user request that resembles the measurement application setup shown in the images or videos.

[0150] In another embodiment, which can be combined with all other embodiments mentioned above or below, the measurement application control unit may further comprise a confidence estimator configured to calculate and output a confidence value for the response data generated by the pre-trained artificial-intelligence algorithm.

[0151] The confidence estimator may be a dedicated unit or element in the measurement application control unit. Alternatively, the confidence estimator may be integrated into the pretrained artificial-intelligence algorithm. The pre-trained artificial-intelligence algorithm may e.g., automatically output the confidence value with the response data. The confidence value may refer to a measure of how accurate the response data may be for a respective user request.The user may, therefore, determine based on the confidence value, if the response data might be sufficiently accurate to work with.

[0152] In case that the confidence value is below a predetermined threshold value, the user may in embodiments be asked to contact a support of the manufacturer of a respective measurement application device in the measurement application, and ask for support by a human support engineer. Of course, such a support may be offered as a paid service by the respective manufacturer.

[0153] Second Aspect:

[0154] A second aspect of the present disclosure relates to a measurement application processing device, a respective measurement application, and a respective computer-implemented method.The above stated problem is solved by the features of the independent claims. It is understood, that independent claims of a claim category may be formed in analogy to the dependent claims of another claim category.

[0155] Accordingly, it is provided:

[0156] A measurement application processing device comprising a text-based input interface configured to receive text-based user requests 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 textbased user requests, and an output interface coupled to the pre-trained artificial-intelligence algorithm, and configured to output the response data.

[0157] Further, it is provided:

[0158] A measurement application comprising a measurement application processing device according to the second aspect of the present disclosure, and at least one measurement application device.

[0159] Further, it is provided:

[0160] A computer-implemented method comprising receiving text-based user requests regarding a measurement application, generating with a pre-trained artificial-intelligence algorithm response data regarding the measurement application based on the text-based user requests, and outputting the response data.

[0161] The present disclosure is based on the finding that modern measurement application devices may comprise a large number of user-configurable parameters that may be difficult to memorize and understand for users.

[0162] The most important options may be presented prominently on a main screen of the respective measurement application device. However, other options that may be required only for very specific measurement tasks may e.g., be hidden in sub-menus of the user interface of the measurement application device.

[0163] With such measurement application devices, a large number of different measurement applications may be set-up and performed.

[0164] Especially, inexperienced users may face difficulties when setting-up a measurement applications and configuring the measurement application devices in such a measurement application. Inexperienced users may even lack the knowledge about the specific function of prominently presented configuration options, and especially the existence of such configuration options that are e.g., hidden in sub-menus of the user interface of the measurement application device. Further, inexperienced users may lack the knowledge of how to connect the different measurement application devices and devices under test to each other.

[0165] The present disclosure, therefore, provides the measurement application processing device, a respective measurement application device, and the computer-implemented method.

[0166] The measurement application processing device comprises a text-based input interface. The text-based input interface may receive text-based user requests from a user. Such text-based user requests may comprise natural language text that refers to the measurement application.

[0167] The text-based input interface may be implemented as a data interface that receives the text in a binary form e.g., as ASCII encoded text, or as text encoded in any other character encoding scheme. Such a data interface may be provided as hardware interface e.g., as a network interface, and a program interface, like an API or a callback function, or a combination of both.

[0168] The text-based input interface may comprise any other type of interface, like an API, callback functions, shared memory, a web-based III, a REST-API, a class or interface, like a Python class or interface, without being limited to these examples.

[0169] The text-based user requests are then provided to the pre-trained artificial-intelligence algorithm that generates respective response data based on the provided text-based user requests.

[0170] The pre-trained artificial-intelligence algorithm may, especially, be trained to receive text-based user requests that are formulated in a natural language style e.g., as a user would speak the text-based user requests to other users, or as a user would formulate the text-based user requests e.g., in an online forum.

[0171] The response data may be provided in different forms, as will be explained in more detail below. Generally, in embodiments the response data may be provided in textual form.The term “textual form” in the context of the present disclosure may refer to any type of text that may include, but is not limited to, natural language text, and text in a programming or scripting language, or a combination of both.

[0172] In case of natural language text being provided as response data, the natural language text may be formulated as guidance or indications to a user on how to configure a respective measurement application device, and how to reach the respective settings or configuration options in a menu structure of the measurement application device.

[0173] The measurement application processing device further comprises an output interface that outputs the response data. The explanations provided above for the input interfacemay apply mutatis mutandis to the output interface. In embodiments, the input interface and the output interface may be implemented as a single data interface.

[0174] In the measurement application, the response data may e.g., be provided to a measurement application device controller of a measurement application device that may further process the response data. The measurement application device controller may e.g., output the response data to a user via a display, or perform internal configurations based on the response data. In such embodiments, the response data may be provided in a form that may be used by the measurement application device controller only. In embodiments, the response data may be provided in multiple forms or styles at the same time. For example, the response data may be provided in a form that may be used by the measurement application device controller, and at the same time in a natural language text form for the user.

[0175] In embodiments, such measurement application device may comprise an audio output interface e.g., a speaker, and may output the response data as audio output to a user. To this end, a text-to-speech engine may be provided in the measurement application device for receiving the response data from the pre-trained artificial-intelligence algorithm, and converting the response data into audio.

[0176] In other embodiments, the method according to the present disclosure may also be performed remotely or in a distributed fashion. In embodiments, the measurement application processing device may e.g., be provided remotely to one or multiple measurement application devices. The measurement application processing device may e.g., be provided as a server, or server-based or cloud-based application, that may be accessed by a user via a web interface. Any control data that the measurement application processing device may generate for the one or more measurement application devices may be provided to the one or more measurement application devices via a respective network or data connection. To this end, the measurement application device may comprise a respective communication interface.

[0177] In embodiments, the communication interface may comprise any kind of wired and wireless communication interfaces, like for example a network communication interface, especially an Ethernet, wireless LAN or WIFI interface, a USB interface, a Bluetooth interface, an NFC interface, a visible or non-visible light-based interface, especially an infrared interface.

[0178] Further, the server or cloud server and the one or more measurement application devices may communicate via an intermediary network with each other, and such a network may comprise any type of network devices, like switches, hubs, routers, firewalls, and different types of network technologies.

[0179] Generally, such a server may be a dedicated server that may be implemented as a single hardware device. The server may also be implemented as a distributed system comprising a plurality of servers, optionally with a load balancer, that distributes the load over the servers. The server may also be provided as a so-called cloud or cloud-server system that implements the server via virtualization methods independently of the underlying hardware.

[0180] In embodiments, the measurement application processing device may be operated independently of the one or more measurement application devices, and may not even be communicatively coupled to the one or more measurement application devices. In such embodiments the user may be the sole recipient of the generated response data, or response data that may be directly interpreted by the one or more measurement application devices may be stored on a respective data carrier.

[0181] The measurement application processing device may, in embodiments, comprise or may be provided in or as part of at least one of a dedicated processing element e.g., a processing unit, a microcontroller, a field programmable gate array, FPGA, a complex programmable logic device, CPLD, an application specific integrated circuit, ASIC, or the like. A respective program or configuration may be provided to implement the required functionality. The measurement application processing device may at least in part also be provided as a computer program product comprising computer readable instructions that may be executed by a processing element. In a further embodiment, the measurement application processing device may be provided as addition or additional function or method to the firmware or operating system of a processing element that is already present in the respective application as respective computer readable instructions e.g., in the measurement application device. Such computer readable instructions may be stored in a memory that is coupled to or integrated into the processing element, like the measurement application device controller of the measurement application device. The processing element may load the computer readable instructions from the memory and execute them. The same applies to any other element, unit or function disclosed herein as part of the measurement application processing device, the measurement application device, and the method for controlling a measurement application device.

[0182] In addition, it is understood, that any required supporting or additional hardware may be provided like e.g., a power supply circuitry and clock generation circuitry.

[0183] In the context of the present disclosure, a measurement application device may comprise any device that may be used in a measurement application to acquire an input signal or to generate an output signal, or to perform additional or supporting functions in a measurement application. A measurement application device may also comprise or be implemented as application or applications, also called measurement application or measurement applications,that may be executed on a computer device and that may communicate with other measurement application devices in order to perform a measurement task. A measurement application, also called measurement setup, may e.g., comprise at least one or multiple different measurement application devices for performing electric, magnetic, or electromagnetic measurements, especially on single devices under test. Such electric, magnetic, or electromagnetic measurements may be performed in a measurement laboratory or in a production facility in the respective production line. A measurement application or measurement setup may serve to qualify the single devices under test i.e., to determine the proper electrical operation of the respective devices under test.

[0184] Measurement application devices to this end may comprise at least one signal acquisition section for acquiring electric, magnetic, or electromagnetic signals to be measured from a device under test, or at least one signal generation section for generating electric, magnetic, or electromagnetic signals that may be provided to the device under test. Such a signal acquisition section may comprise, but is not limited to, a front-end for acquiring, filtering, and attenuating or amplifying electrical signals. The signal generation section may comprise, but is not limited to, respective signal generators, amplifiers, and filters.

[0185] Further, when acquiring signals, measurement application devices may comprise a signal processing section that may process the acquired signals. Processing may comprise converting the acquired signals from analog to digital signals, and any other type of digital signal processing, for example, converting signals from the time-domain into the frequency-domain.

[0186] The measurement application devices may also comprise a user interface to display the acquired signals to a user and allow a user to control the measurement application devices. Of course, a housing may be provided that comprises the elements of the measurement application device. It is understood, that further elements, like power supply circuitry, and communication interfaces may be provided.

[0187] A measurement application device may be a stand-alone device that may be operated without any further element in a measurement application to perform tests on a device under test. Of course, communication capabilities may also be provided for the measurement application device to interact with other measurement application devices.

[0188] A measurement application device may comprise, for example, a signal acquisition device e.g., an oscilloscope, especially a digital oscilloscope, a spectrum analyzer, or a vector network analyzer. Such a measurement application device may also comprise a signal generation device e.g., a signal generator, especially an arbitrary signal generator, also called arbitrarywaveform generator, or a vector signal generator. Further possible measurement application devices comprise devices like calibration standards, or measurement probe tips.

[0189] Of course, at least some of the possible functions, like signal acquisition and signal generation, may be combined in a single measurement application device.

[0190] In embodiments, the measurement application device may comprise pure data acquisition devices that are capable of acquiring an input signal and of providing the acquired input signal as digital input signal to a respective data storage or application server. Such pure data acquisition devices not necessarily comprise a user interface or display. Instead, such pure data acquisition devices may be controlled remotely e.g., via a respective data interface, like a network interface or a USB interface. The same applies to pure signal generation devices that may generate an output signal without comprising any user interface or configuration input elements. Instead, such signal generation devices may be operated remotely via a data connection.

[0191] With the measurement application processing device, the measurement application, and the method according to the present disclosure, a user may describe a measurement application and receive recommendations regarding the respective measurement applications as if he was communicating with another user.

[0192] For example, the text-based user requests may refer to a general description of a measurement application. The response data provided by the pre-trained artificial-intelligence algorithm may then comprise information on how to implement such a measurement application, and what measurement application devices to use for the measurement application.

[0193] In embodiments, the measurement application processing device may adapt the style of the response data to the level of knowledge of the user. This may e.g., be performed by using the below-mentioned pre-conditioner. The pre-conditioner may e.g., generate a respective pre-conditioning text-based request that indicates that the response should comprise a specific level of detail.

[0194] Further embodiments of the present disclosure are subject of the further dependent claims and of the following description, referring to the drawings.

[0195] In the following, the dependent claims referring directly or indirectly to claim 37 according to the second aspect of the present disclosure are described in more detail. For the avoidance of doubt, the features of the dependent claims relating to the measurement application processing device can be combined in all variations with each other and the disclosure of the description is not limited to the claim dependencies as specified in the claim set. Further, thefeatures of the other independent claims may be combined with any of the features of the dependent claims relating to the measurement application processing device in all variations, wherein in the method respective method steps perform the function of the respective measurement application processing device elements.

[0196] In an 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 comprise an audio input interface configured to receive spoken language 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 language requests into text-based requests, and to provide the text-based requests to the textbased input interface as text-based user requests.

[0197] The audio input interface may be provided as local or hardware audio input interface in the measurement application processing device, or a measurement application device that implements or comprises the measurement application processing device.

[0198] In other embodiments, the audio input interface may be provided as data interface that receives audio data from another device. Such a data interface may be provided as a hardware interface, or a software interface, or a combination of both. Generally, the hardware interface of such a data interface as audio interface may comprise any kind of wired and wireless communication interfaces, like for example a network communication interface, especially an Ethernet, wireless LAN or WIFI interface, a USB interface, a Bluetooth interface, an NFC interface, a visible or non-visible light-based interface, especially an infrared interface.

[0199] The audio input interface is coupled to a speech recognition unit that converts the spoken language requests i.e. , audio data, received via the audio input interface into text-based user requests. Such text-based user requests may then be provided to the text-based input interface, as any other text-based user requests for further processing by the pre-trained artificialintelligence algorithm.

[0200] The speech recognition unit may be provided as a hardware-based unit, a softwarebased unit, or a combination of both, as already indicated above for the measurement application processing device.

[0201] With the audio input interface, and the speech recognition unit a user may communicate naturally with the measurement application processing device, as if he was speaking with another user.

[0202] 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 manuals regarding one or more measurement application devices or measurement applications, datasheets regarding one or more measurement application devices or measurement applications, application notes regarding one or more measurement application devices or measurement applications, datasheets of electronic devices, application notes of electronic devices, articles regarding electronic circuits, online forum discussions regarding electronic circuits, and videos regarding electronic circuits.

[0203] The pre-trained artificial-intelligence algorithm needs to be trained on data regarding one or more measurement application devices and measurement applications that may be performed with the one or multiple measurement application devices, that the text-based user requests may refer to.

[0204] Usually, a wide selection of training data is already available from the manufacturers of the respective measurement application device(s). Such training data may be provided e.g., in the form of manuals, datasheets, and application notes that a manufacturer of a measurement application device may publish.

[0205] In embodiments, the pre-trained artificial-intelligence algorithm may be pre-trained based on general data, like freely available texts, that are not specific to any measurement application device.

[0206] The training data relating to the one or more measurement application devices and possible measurement applications may then be used to perform a fine-tuning of the pre-trained artificial-intelligence algorithm. Such a fine-tuning will then allow the pre-trained artificial-intelligence algorithm to respond adequately to the text-based user requests regarding the measurement application.

[0207] In an embodiment, a further trained algorithm may be provided that is trained to provide a textual description of images and diagrams. Such a trained algorithm may be used to explain the content of images or diagrams provided in the training data, especially in manuals, datasheets, and application notes, to the pre-trained artificial-intelligence algorithm in textual form for performing the training of the pre-trained artificial-intelligence algorithm.

[0208] In a further 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 comprise a large language model based on at least one of a statistical model, like an N-gram, a recurrent neuronal network, like a long short term, LSTM,model, a Bidirectional Encoder Representations from Transformers model, and a Generative Pre-trained Transformer model.

[0209] While above, two specific types of large language models are explicitly disclosed, it is understood, that the pre-trained artificial-intelligence algorithm may comprise any algorithm that may be trained on a set of training data such that it may generate the response data based on text-based user requests.

[0210] 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 configured to receive text-based user requests regarding the setup of the measurement application, and to generate set-up response data that comprises a respective explanation regarding the setup of the measurement application.

[0211] As already indicated above, a user may provide questions regarding a measurement application, especially the setup of a specific measurement application.

[0212] A user may e.g., want to measure a specific type of device, like an amplifier, or signal, like a specific bus signal, for example, an SPI or I2C signal. In embodiments, the user may be more specific and may want to measure a voltage level of an output pin of a specific device under test, like an amplifier.

[0213] Possible text-based user requests may sound like, but are not limited to, “How do I measure an SPI bus?”, “How to measure an I2C bus?”, “What set-up do I need to measure the voltage level at the output of an amplifier of type XXX”, XXX being the type of amplifier.

[0214] The pre-trained artificial-intelligence algorithm may be trained to generate response data that comprises specific explanations regarding such a setup i.e. , information that explains to the user how to create or set-up the respective measurement application.

[0215] The pre-trained artificial-intelligence algorithm may be trained to e.g., include in the set-up response data information on how to configure a respective measurement application device in a measurement application. The set-up response data may also comprise information on how to interface or connect multiple measurement application devices in a measurement application. Such set-up response data may in embodiments be provided as or in combination with a block diagram, as indicated below. The set-up response data may indicate which measurement application devices are required, and which ports of the measurement application devices are to be coupled to ports of other measurement application devices or DllTs.

[0216] 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 configured to generate set-up response data that indicates which measurement application devices to use, and how to connect the measurement application devices to set-up the measurement application.

[0217] When implementing a specific measurement application, a user may require information about which measurement application devices to use for the measurement application.

[0218] The pre-trained artificial-intelligence algorithm may, consequently, be trained to indicate which measurement application devices a user requires to implement the respective measurement application.

[0219] In embodiments, the pre-trained artificial-intelligence algorithm may be configured to provide multiple alternative set-ups each using different measurement application devices.

[0220] The pre-trained artificial-intelligence algorithm may be configured to provide information regarding a single set-up without further request by the user. The user may then actively request an alternative set-up, and the pre-trained artificial-intelligence algorithm may provide such an alternative set-up.

[0221] The pre-trained artificial-intelligence algorithm may also be configured to correct a measurement application set-up, if the user indicates errors or inaccuracies in a provided measurement application set-up. A user may e.g., indicate that a certain measurement application device is not available, that is part of an indicated measurement application set-up. In such cases, the pre-trained artificial-intelligence algorithm may provide the user with an alternative measurement application set-up, that does not include the respective measurement application device, but instead includes one or multiple alternative measurement application devices that replace the not-available measurement application device. The pre-trained artificial-intelligence algorithm may also indicate that a specific measurement application device, even if currently not available, would be required to perform a respective measurement application task. The response data may in this case indicate to a user, where to acquire such a measurement application device. Acquiring may in this case also refer to acquiring modules or functions for a measurement application device that is available to a user but does not have a license for the respective module or function.

[0222] The pre-trained artificial-intelligence algorithm may also include in the response data indications of measurement application devices, functions or modules that could be added to the measurement application in order to increase the quality e.g., the accuracy, of the measurements.

[0223] In a further 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 configured to generate a block diagram of the set-up of the measurement application.

[0224] As indicated above, the responses provided by the pre-trained artificial-intelligence algorithm may be text-based. However, a text-based explanation of a measurement application set-up may be difficult to understand for a user, especially, if the measurement application setup is complex and comprises multiple different measurement application devices.

[0225] The pre-trained artificial-intelligence algorithm may, therefore, also be trained to or configured to output a block diagram of the measurement application set-up.

[0226] Such a block diagram may e.g., be provided by the pre-trained artificial-intelligence algorithm in the form of an ASCII based diagram, also called ASCII art diagram. In other embodiments, the pre-trained artificial-intelligence algorithm may also output the ASCII code for an SVG file that comprises the respective block diagram. In embodiments, a combination is possible, and the pre-trained artificial-intelligence algorithm may provide an ASCII art diagram and the SVG file.

[0227] In further embodiments, that may be combined with the above embodiments, the pre-trained artificial-intelligence algorithm may forward a textual description of the block diagram to an image generation algorithm, for example, an artificial intelligence-based image generation algorithm. Such pre-trained artificial-intelligence algorithm may comprise at least one of a neuronal network, a transformer, and a generative adversarial network.

[0228] With the block diagram a user will be provided with an easy-to-understand representation of the measurement application set-up that will allow him to easily implement the suggested measurement application set-up.

[0229] 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 further be configured to generate control response data that comprises respective control commands for at least one measurement application device.

[0230] The control response data may, instead of explaining different features of the measurement application to a user, directly provide control commands that a user may implement in the measurement application i.e. , in one or multiple measurement application devices of a measurement application.

[0231] Such control commands may be provided as natural text commands to a user. Exemplary control commands may comprise, but are not limited to, “set the voltage range to 0V - 100V”, “set the amplification factor to 10x”, “set the scaling of the diagram X-axis to 0.5”, “start the measurement”, “stop the measurement”, “start the signal generation”, “stop the signal generation”, and the like.

[0232] Generally, the control commands may comprise a command regarding any option, or parameter, or user input that a measurement application device of the measurement application set-up may comprise or allow.

[0233] In a further 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 comprise a code generator that is coupled to or integrated into the 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.

[0234] While the above-explained types of control commands may be easily understood by a user, a measurement application device may not directly be controlled with such text-based commands.

[0235] However, modern measurement application devices not only comprise a user interface for controlling the respective measurement application device. Instead, such measurement application devices may usually also be controlled programmatically.

[0236] Such control programs may be provided e.g., in a domain specific scripting or programming language, like the SCPI language (Standard Commands for Programmable Instruments). In other embodiments, the control programs may be provided in more general programming languages, like Python, or JavaScript, that may be interpreted in the measurement application device, or as compiled programs that are executed in the measurement application device.

[0237] The code generator, or the pre-trained artificial-intelligence algorithm with the integrated code generator may, therefore, be trained or configured to generate control commands in the response data. The control commands may be provided in any adequate format, like the above-mentioned control programs, without being limited to such programs.

[0238] The code generator may also be configured to use existing sets of control commands or programs, and to modify such existing sets of control commands or programs. Themodification may refer to adapting the existing sets of control commands or programs to a specific measurement application or measurement application task. The modification may refer e.g., to optimizing the existing sets of control commands or programs to provide higher measurement performance, or a higher measurement accuracy.

[0239] In an embodiment, the pre-trained artificial-intelligence algorithm may receive a textbased user request regarding the measurement application set-up, and may output any embodiment of a description of the measurement application set-up described herein to the user.

[0240] In an embodiment, the pre-trained artificial-intelligence algorithm may in addition output the configuration and control commands for one or multiple measurement application devices of the measurement application set-up in the predetermined control or programming language.

[0241] If an external code generator is used, the pre-trained artificial-intelligence algorithm may provide the text-based control commands indicated above to the code generator. The code generator may then generate the respective configuration and control commands for one or multiple measurement application devices of the measurement application set-up in the predetermined control or programming language. The code generator may also take into account any number of measurement application devices present in a measurement application set-up, when generating the configuration and control commands for a single measurement application device.

[0242] In a setting, in which the measurement application processing device is communicatively coupled to the measurement application devices, the measurement application processing device may provide the configuration and control commands directly to the respective measurement application devices.

[0243] The pre-trained artificial-intelligence algorithm, or the code generator may also be configured to generate code that implements functions required in a measurement application set-up, that are not available in the respective measurement application devices.

[0244] Such code may be provided e.g., in the form of interpretable code e.g., Python or JavaScript code, that may be interpreted in a measurement application device, or in the form of executable code, like compiled C, or C++ code, that may be executed in a measurement application device. In embodiments, the code may be provided as VHDL code or configuration code for a configurable logic element, like an FPAG, in the measurement application device.

[0245] The code may implement data processing functions that may be requested by the user in the text-based user request, but are not available in the respective measurement application devices.

[0246] To this end, the measurement application devices may provide a respective API that allows the code to access measurement data and output processed data for further processing in the measurement application device e.g., for displaying the processed data to a user.

[0247] With this option of generating code, a user that has no programming knowledge may still request functions for a measurement application set-up that would require such programming knowledge to implement.

[0248] In embodiments, the pre-trained artificial-intelligence algorithm may provide an explanation of the generated code. Such an explanation may e.g., be requested via the pre-condi- tioner mentioned below.

[0249] 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 comprise a pre-conditioner coupled to the pre-trained artificial-intelligence algorithm. The pre-conditioner may be configured to provide a pre-conditioning text-based request to the pre-trained artificial-intelligence algorithm prior to the pretrained artificial-intelligence algorithm operating on the text-based user requests.

[0250] The pre-conditioner may serve to indicate general information to the pre-trained artificial-intelligence algorithm that a user may e.g., skip or forget to include in the text-based user requests. Other information that may be provided by the pre-conditioner includes general information about the equipment available to a user, the knowledge level of the user, or any other information that may be relevant, also for human users, for planning a measurement application set-up.

[0251] The pre-conditioning text-based request may be provided to the pre-trained artificialintelligence algorithm preceding the actual text-based user requests.

[0252] In embodiments, the pre-conditioner may provide the pre-trained artificial-intelligence algorithm with information about at least one of, without being limited to, the measurement application devices that are available to the user, specifications of the measurement application device(s), a required type or format for the response data.

[0253] Exemplary pre-conditioning text-based requests formulated by the pre-conditioner may comprise, but are not limited to, requests like:

[0254] “Available measurement application devices comprise MEAS1 , MEAS2, MEASx. For your response select only from the available measurement application devices.”, wherein MEAS1 to MEASx are the available measurement application devices.

[0255] “The measurement application device MEAS1 is provided with the optional modules MODI , MOD2, MOD3. If necessary, include these modules in the recommended measurement application set-up.”, wherein MODI , MOD2, MOD3 may be optional modules that a user may install in a measurement application device.

[0256] The pre-conditioner may in embodiment comprise a further trained artificial-intelligence algorithm that is trained to generated pre-conditioning text-based requests as exemplarily indicated above. Such a trained artificial-intelligence algorithm may e.g., be trained based on sets of exemplary descriptions of measurement application setups and the respective pre-conditioning text-based requests.

[0257] In other embodiments, the pre-conditioner may be implemented without a trained artificial intelligence algorithm. Such embodiments of the pre-conditioner may comprise e.g., a state machine, and may be configured to concatenate respective information about a measurement application setup into respective pre-conditioning text-based requests. The information about the measurement application setup may e.g., be provided in tabular form, wherein each line comprises information about a component measurement application setup. Generally, the information may be provided in any adequate, especially structured, format.

[0258] Such information may e.g., indicate the type of element, like signal generation device, signal acquisition device, device under test, probe, adapter, or the like. This information may also indicate the number of outputs or inputs of the respective element, and what value ranges the inputs and outputs support. Generally, such data may include any data that is usually provided in manuals or datasheets regarding the respective measurement application devices.

[0259] In such embodiments, the pre-conditioner may, for example, simply insert the information in template strings, and concatenate the template strings for all elements in the measurement application setup to generate the respective pre-conditioning text-based request. A combination with the artificial-intelligence based pre-conditioner is possible.

[0260] In an 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 configured to augment the text-based user requests and output theaugmented text-based user requests via the output interface. The pre-trained artificial-intelligence algorithm may be configured to generate the response data after confirmation of the augmented text-based user requests by the user.

[0261] Augmenting in this contest refers to including additional information in the text-based user requests, that a user may not know or may have forgotten to include in his text-based user requests.

[0262] The augmented text-based user requests may be seen as a kind of technically more precisely formulated text-based user requests. The pre-trained artificial-intelligence algorithm may also be configured to suggest improvements to the original text-based user requests.

[0263] In embodiments, such functions of the pre-trained artificial-intelligence algorithm may be implemented using the pre-conditioner. The pre-conditioner may e.g., provide a preconditioning text-based request that may exemplarily indicate at least one of “Provide a more detailed version of the following request for generating a measurement application set-up, instead of generating the actual measurement application set-up.”, or “Correct the following request for generating a measurement application set-up, instead of generating the actual measurement application set-up.”

[0264] Providing an augmented text-based user requests may also comprise indicating to a user in the augmented text-based user requests that a measurement application device that he referenced in the original text-based user requests lacks a specific installable option required for performing a specific measurement application. The user may then also be provided with the option to install the specific option.

[0265] 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 comprise a text-based user request generator configured to receive at least one of a non-textual description, like an image or a video of a measurement application device, a device under test, or a measurement application set-up. The textbased user request generator may further be configured to generate text-based user requests based on the at least one of the image or the video.

[0266] With the text-based user request generator the user is provided with alternative means for providing his request to the measurement application processing device.

[0267] Instead of providing the pre-trained artificial-intelligence algorithm with a specific text-based user request, the user may simply provide one or more images or videos of a respective measurement application.

[0268] The text-based user request generator may than analyze the respective images or videos and generate a respective text-based user request that resembles the measurement application set-up shown in the images or videos.

[0269] In an 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 configured to receive text-based user requests regarding the maintenance of a measurement application device in a measurement application, and to generate maintenance response data that comprises a respective explanation regarding the maintenance of the respective measurement application device.

[0270] Maintenance of a measurement application device is an important task in every measurement application. Requests referring to the maintenance of a measurement application device, therefore, comprise a request regarding a measurement application according to the present disclosure.

[0271] In order to allow the pre-trained artificial-intelligence algorithm to support the user in correctly servicing and maintaining a respective measurement application device, the pretrained artificial-intelligence algorithm may be trained with respective maintenance and service manuals that a manufacturer of the measurement application device may provide. As additional training material, the documentation of the development process for the respective measurement application device may be used as training data for the pre-trained artificial-intelligence algorithm. Generally, the training material may also comprise at least one of manuals regarding the measurement application device, datasheets regarding the measurement application device, application notes regarding the measurement application device, manuals of electronic devices, datasheets of electronic devices, application notes regarding manuals of electronic devices, articles regarding electronic circuits, online forum discussions regarding electronic circuits, and videos regarding electronic circuits

[0272] In embodiments, the pre-trained artificial-intelligence algorithm may provide the response data that comprises the explanation regarding the maintenance of the respective measurement application device on a specific user request.

[0273] In other embodiments, the pre-trained artificial-intelligence algorithm may provide such explanations without a specific request from the user. Instead, the pre-trained artificial-intelligence algorithm may provide such explanations, if performing the respective service or repair may improve a measurement result in a respective measurement application set-up. The features regarding the maintenance of the measurement application device may, therefore, becombined with all other features of all other embodiments of the measurement application processing device.

[0274] In a further embodiment, which can be combined with all other embodiments mentioned above or below, the measurement application processing device may further comprise a warning generator configured to generate a warning for a user regarding configurations of a measurement application device that are detrimental to a predetermined measurement application.

[0275] The term “warning” in this context refers to information for a user that indicates which specific settings or configuration options a user should not set or perform in order to effectively execute a respective measurement application.

[0276] The warning generator may be provided as a dedicated unit, or may be integrated into or be a function of the pre-trained artificial-intelligence algorithm. If implemented as a dedicated unit, the warning generator may comprise any kind of adequate algorithm. The warning generator may e.g., comprise a state machine or database that links measurement applications to lists of settings that are identified as detrimental or negative for the respective measurement application. The warning generator may also comprise an artificial intelligence-based algorithm that is capable of generating the warning based on a respective input.

[0277] In an embodiment, which can be combined with all other embodiments mentioned above or below, the measurement application processing device may further comprise a feedback interface configured to receive measurement feedback data, wherein the pre-trained artificial-intelligence algorithm may be configured to generate a further set of response data based on the original text-based user request, and the received measurement feedback data.

[0278] A user-provided text-based user request may be very general, like: “Setup an I2C measurement over a 0.5s period with 100kBaud data rate, and limit the power supply to 20mA”. With such a general indication, a general configuration of a measurement application device may be generated by the pre-trained artificial-intelligence algorithm.

[0279] However, such a general measurement configuration may not in all cases provide the user with the relevant information. For example, if the measurement application task is to identify errors on the I2C bus, a user may not find such errors with the general configuration.

[0280] Therefore, the feedback interface is provided. With the feedback interface, the measurement application processing device may be provided with the measurement feedback data. The measurement feedback data will then allow the pre-trained artificial-intelligence algo-rithm to generate a refined set of response data that may be provided to the measurement application device for performing another measurement that better fulfills the specific measurement application task.

[0281] The measurement feedback data may comprise any one of waveforms from the display of a measurement application device, screenshots of a measurement application device, user-provided feedback, especially in the form of natural language feedback, information about the current configuration of a measurement application device, and measurement statistics of a measurement application device.

[0282] In the example of the I2C bus, in the measurement feedback data an indication of voltage glitches at every raising signal flank may be found. The pre-trained artificial-intelligence algorithm may, therefore, generate the further set of response data to trigger on the raising flanks of the signal, and to show the signal for a certain amount of time preceding the raising flank, and to provide an adequate time scale on the X axis of a display of the measurement application device.

[0283] The feedback interface may be or comprise a data interface that may receive measurement feedback data from the respective measurement application device. The measurement feedback data may also comprise any data acquired during a measurement or derived from the measurement.

[0284] The measurement feedback data may exemplarily comprise, but is not limited to, the raw measurement data, and screenshots of a display of the measurement application device showing a waveform of the acquired signal.

[0285] In embodiments, the pre-trained artificial-intelligence algorithm may be capable of operating directly on the measurement feedback data.

[0286] The pre-trained artificial-intelligence algorithm may be configured to e.g., indicate in the further set of response data how to improve a measurement. If for example the measurement feedback data indicates that the measured waveform may be inaccurate, the further set of response data may indicate how to improve the accuracy of the measurement. The user may be provided with respective indications in the further set of response data, and / or respective configuration options, code or scripts may be provided.

[0287] The feedback interface may also receive the measurement feedback data while a measurement application is executed. This allows the pre-trained artificial-intelligence algorithm to provide further set of response data in “real time” to a user. For example, the pre-trained artificial-intelligence algorithm may determine that the measured signal level is nearing the noiselevel, and that, therefore, the measurement may not be reliable any more. In the further set of response data, the response data may hint at this circumstance in a natural language form for a user, and / or an updated configuration for the respective measurement application may be provided to increase the signal-to-noise ratio for the running measurement.

[0288] Together with hints or suggestions on how to improve the measurement, the pretrained artificial-intelligence algorithm may also provide an explanation of the measurement results, and indications as to why the results are measured as they are. The further set of response data may also indicate the “costs” of the improvements. The term “costs” in this regard refers to technical costs that for example comprise reducing the measurement quality in a specific aspect to improve the measurement quality in another aspect. Such a tradeoff for example exists between measurement accuracy and possible measurement duration. The further set of response data may also indicate if no further improvements of the measurement are possible, and the best possible measurement result is achieved.

[0289] In another embodiment, which can be combined with all other embodiments mentioned above or below, the measurement application processing device may further comprise a feedback data analyzer arranged between the feedback interface, and the pre-trained artificialintelligence algorithm. The feedback data analyzer may be configured to generate a text-based feedback description of the measurement feedback data, and to provide the text-based feedback description to the pre-trained artificial-intelligence algorithm.

[0290] The feedback data analyzer may comprise another trained artificial-intelligence algorithm that may be trained to convert the measurement feedback data into the text-based feedback description.

[0291] Such an algorithm may be trained to provide a text-based description of image or waveform data. The algorithm may, especially, be trained to describe details of the measurement data that a user may easily miss based on the general response data. The algorithm may comprise or be based on a respective visual foundation model.

[0292] Training data for the feedback data analyzer may be taken e.g., from manuals, datasheets, and available measurement reports, that comprise descriptions of measurement results, and e.g., images of measured waveforms. In embodiments, the feedback data analyzer may comprise an image-to-text conversion algorithm that is trained on general image and text data, and fine-tuned based on data from manuals, datasheets, and available measurement reports, as indicated above.

[0293] In other embodiments, the measurement application device may comprise the feedback data analyzer, and the feedback data analyzer may provide the text-based feedback description to the measurement application device control unit.

[0294] In a further embodiment, which can be combined with all other embodiments mentioned above or below, the feedback data analyzer may be configured to identify at least one of anomalies, and relevant measurement values, and relevant measurement waveform sections in raw measurement data provided in the measurement feedback data, and to provide a respective text-based feedback description.

[0295] A user may lack the experience to identify relevant data in the measurement results, and especially to identify anomalies.

[0296] Therefore, with the feedback data analyzer being configured to identify such anomalies, relevant measurement values, or relevant measurement waveform sections, the response data may be re-generated to configure the measurement application device to better acquire the relevant measurement data.

[0297] The result provided by the feedback data analyzer may e.g., indicate that the error vector magnitude is mainly influenced by the frequency response. The pre-trained artificial-intelligence algorithm may with the further set of response data indicate to a user how to improve such a measurement, or which measurement application device to use to improve such a measurement.

[0298] Typical errors in a measurement may comprise, but are not limited to, phase noise, compression, frequency errors, wrong sweep time, and the like. With the measurement feedback data, the pre-trained artificial-intelligence algorithm may consequently generate a further set of response data that at least indicates to a user that such errors might occur in the measurement. In embodiments, the further set of response data may also comprise configuration data or settings for measurement application devices to compensates such errors.

[0299] The feedback data analyzer may also be configured to analyze error messages received from a measurement application device, and to provide a respective further set of response data indicating to a user how to overcome the error, and / or providing control or configuration data for a measurement application device to overcome the error.

[0300] In another embodiment, which can be combined with all other embodiments mentioned above or below, the measurement application processing device may further comprise a feedback output interface that is configured to output the measurement feedback data to a user.The pre-trained artificial-intelligence algorithm may be configured to generate a further set of response data based on the original text-based user request, and a further text-based user request received after the measurement feedback data is output to the user.

[0301] In a further embodiment, which can be combined with all other embodiments mentioned above or below, the feedback output interface may output the text-based feedback description to the user.

[0302] With the feedback output interface, the measurement feedback data, especially the text-based feedback description, may be provided to the user. To this end, the feedback output interface may comprise a display or an audio interface. The text-based feedback description may be shown to a user on the display. The text-based feedback description may also be converted into audio with a text-to-speech converter and may be played to the user via an audio interface.

[0303] The user, after receiving the measurement feedback data, may then decide to provide instructions to the pre-trained artificial-intelligence algorithm that result in corrected or amended response data that may be provided to the respective measurement application device.

[0304] This feedback loop may be repeated as many times as required, and may also be combined with the automatic regeneration of the response data described above.

[0305] The user may, therefore, enter into a kind of dialogue with the measurement application device control unit, and iteratively improve the measurement results.

[0306] In embodiments, the pre-trained artificial-intelligence algorithm may comprise a fixed pre-trained model.

[0307] In another embodiment, which can be combined with all other embodiments mentioned above or below, the pre-trained artificial-intelligence algorithm may be configured to perform reinforced learning based on the further text-based user request received after the measurement feedback data is output to the user.

[0308] Using a flexible model that may be further trained e.g., using reinforced learning, the quality of the response data may continuously be improved.

[0309] Further, it is possible to train the pre-trained artificial-intelligence algorithm for application specific measurement tasks. It is for example possible, to train the pre-trained artificial-intelligence algorithm specifically for automotive measurement applications. In such embodiments, the further text-based user request may be automatically generated for the reinforced learning.

[0310] For performing the reinforced learning, multiple measurement application device control units may provide respective learning data to a centrally trained pre-trained artificial-intelligence algorithm. Such a centrally trained pre-trained artificial-intelligence algorithm may e.g., be hosted and trained by a manufacturer of the measurement application device control unit. Alternatively, locally trained pre-trained artificial-intelligence algorithms may be provided to a central model management unit that may then merge the locally trained pre-trained artificialintelligence algorithms.BRIEF DESCRIPTION OF THE DRAWINGS

[0311] For a more complete understanding of the present disclosure and advantages thereof, reference is now made to the following description taken in conjunction with the accompanying drawings. The disclosure is explained in more detail below using exemplary embodiments which are specified in the schematic figures of the drawings, in which:

[0312] Figure 1 shows a block diagram of an embodiment of a measurement application control unit according to the first aspect of the present disclosure;

[0313] Figure 2 shows a block diagram of another embodiment of a measurement application control unit according to the first aspect of the present disclosure;

[0314] Figure 3 shows a block diagram of another embodiment of a measurement application control unit according to the first aspect of the present disclosure;

[0315] Figure 4 shows a block diagram of another embodiment of a measurement application control unit according to the first aspect of the present disclosure;

[0316] Figure 5 shows a block diagram of another embodiment of a measurement application control unit according to the first aspect of the present disclosure;

[0317] Figure 6 shows a block diagram of another embodiment of a measurement application control unit according to the first aspect of the present disclosure;

[0318] Figure 7 shows a block diagram of another embodiment of a measurement application control unit according to the first aspect of the present disclosure;

[0319] Figure 8 shows a block diagram of another embodiment of a measurement application control unit according to the first aspect of the present disclosure;

[0320] Figure 9 shows a block diagram of another embodiment of a measurement application control unit according to the first aspect of the present disclosure;

[0321] Figure 10 shows a block diagram of another embodiment of a measurement application control unit according to the first aspect of the present disclosure;

[0322] Figure 11 shows a block diagram of an embodiment of a measurement application device according to the first aspect of the present disclosure;

[0323] Figure 12 shows a flow diagram of an embodiment of a method according to the first aspect of the present disclosure;

[0324] Figure 13 shows a block diagram of an oscilloscope that may be used with an embodiment of a measurement application control unit, or method according to any one of the embodiments of the first aspect of the present disclosure;

[0325] Figure 14 shows a block diagram of another oscilloscope that may be used with an embodiment of a measurement application control unit, or method according to any one of the embodiments of the first aspect of the present disclosure

[0326] Figure 15 shows a block diagram of an embodiment of a measurement application processing device according to the second aspect of the present disclosure;

[0327] Figure 16 shows a block diagram of another embodiment of a measurement application processing device according to the second aspect of the present disclosure;

[0328] Figure 17 shows a block diagram of another embodiment of a measurement application processing device according to the second aspect of the present disclosure;

[0329] Figure 18 shows a block diagram of another embodiment of a measurement application processing device according to the second aspect of the present disclosure;

[0330] Figure 19 shows a block diagram of another embodiment of a measurement application processing device according to the second aspect of the present disclosure;

[0331] Figure 20 shows a block diagram of another embodiment of a measurement application processing device according to the second aspect of the present disclosure;

[0332] Figure 21 shows a block diagram of another embodiment of a measurement application processing device according to the second aspect of the present disclosure;

[0333] Figure 22 shows a block diagram of another embodiment of a measurement application processing device according to the second aspect of the present disclosure;

[0334] Figure 23 shows a block diagram of another embodiment of a measurement application processing device according to the second aspect of the present disclosure;

[0335] Figure 24 shows a block diagram of another embodiment of a measurement application processing device according to the second aspect of the present disclosure;

[0336] Figure 25 shows a block diagram of a measurement application according to the second aspect of the present disclosure;

[0337] Figure 26 shows a flow diagram of an embodiment of a method according to the second aspect of the present disclosure;

[0338] Figure 27 shows a block diagram of an oscilloscope that may be used with an embodiment of a measurement application processing device according to the second aspect of the present disclosure; and

[0339] Figure 28 shows a block diagram of another oscilloscope that may be used with an embodiment of a measurement application processing device according to the second aspect of the present disclosure.

[0340] In the figures like reference signs denote like elements unless stated otherwise.DETAILED DESCRIPTION OF THE DRAWINGS

[0341] Figure 1 shows a block diagram a measurement application control unit 10100.

[0342] The measurement application control unit 10100 comprises a text-based input interface 10101 that receives text-based user requests 10102 regarding a measurement application device. The measurement application control unit 10100 further comprises a pre-trained artificial-intelligence algorithm 10103 coupled to the text-based input interface 10101 that generates response data 10104 regarding the measurement application device based on the text-based user requests 10102. The measurement application control unit 10100 further comprises 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 disclosed herein may, mutatis mutandis, also be applied to the measurement application control unit 10200.

[0343] The measurement application control unit 10100 may be implemented as a dedicated device e.g., laboratory equipment, similar to other laboratory measurement applicationdevices, like oscilloscopes, network analyzers, signal generators, and the like. Such a measurement application control unit 10100 may comprise housing, a user interface, like a display or touchscreen, buttons, knobs, a mouse, a keyboard, or the like, as text-based input interface 10101 , a respective processor or processing element, and respective data interfaces, like a network interface, possibly also as text-based input interface 10101. The measurement application control unit 10100 may also be integrated into any type of laboratory measurement application device.

[0344] In embodiments, the measurement application control unit 10100 may be implemented on a computer or server, that executes a computer-program product that comprises instructions that when executed by the computer or server, especially a processor in the computer or server, causes the computer or server to perform the computer-implemented method of the first aspect according to the present disclosure. Such a computer or server may be located remotely to other measurement application devices and coupled to other measurement application devices via a network connection.

[0345] In embodiments, the pre-trained artificial-intelligence algorithm 10103 may be pretrained using any combination of manuals regarding the measurement application device, datasheets regarding the measurement application device, application notes regarding the measurement application device, manuals of electronic devices, datasheets of electronic devices, application notes of electronic devices, articles regarding electronic circuits, online forum discussions regarding electronic circuits, and videos regarding electronic circuits.

[0346] Figure 2 shows a block diagram of another embodiment of a measurement application control unit 10200. The measurement application control unit 10200 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10200 comprises a text-based input interface 10201 that receives text-based user requests 10202 regarding a measurement application device. The measurement application control unit 10200 further comprises a pre-trained artificial-intelligence algorithm 10203 coupled to the textbased input interface 10201 that generates response data 10204 regarding the measurement application device based on the text-based user requests 10202. The measurement application control unit 10200 further comprises an output interface 10205 coupled to the pre-trained artificial-intelligence algorithm 10203, and configured to output the response data 10204. The explanations provided herein regarding any embodiment of the measurement application control unit disclosed herein may, mutatis mutandis, also be applied to the measurement application control unit 10200.

[0347] The measurement application control unit 10200 further comprises 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 the text-based input interface 10201.

[0348] The audio input interface 10228 may receive spoken language requests 10229 e.g., from a user. It is understood, that the audio input interface 10228 may comprise e.g., a microphone for recording the spoken language requests 10229. In embodiments, the audio input interface 10228 may comprise a data interface for receiving the spoken language requests 10229 in digital form that are recorded elsewhere. A combination of both is possible.

[0349] The speech recognition unit 10230 may then convert the spoken language requests 10229 into text-based requests 10231. Such text-based requests 10231 may then be forwarded to the text-based input interface 10201 , as are the text-based user requests 10202. The textbased input interface 10201 may then process the text-based requests 10231 like any other text-based user requests 10202.

[0350] The speech recognition unit 10230 may comprise any type of adequate element. Exemplary embodiments of the speech recognition unit 10230 may e.g., be based on computer- implemented algorithms, especially respective artificial-intelligence based computer-implemented algorithms.

[0351] Figure 3 shows a block diagram of a measurement application control unit 10300. The measurement application control unit 10300 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10300 comprises a textbased input interface 10301 that receives text-based user requests 10302 regarding a measurement application device. The measurement application control unit 10300 further comprises a pre-trained artificial-intelligence algorithm 10303 coupled to the text-based input interface 10301 that generates response data 10304 regarding the measurement application device based on the text-based user requests 10302. The measurement application control unit 10300 further comprises an output interface 10305 coupled to the pre-trained artificial-intelligence algorithm 10303, and configured to output the response data 10304. The explanations provided herein regarding any embodiment of the measurement application control unit disclosed herein may, mu- tatis mutandis, also be applied to the measurement application control unit 10300.

[0352] In the measurement application control unit 10300, the pre-trained artificial-intelligence algorithm 10303 comprises a large language model 10335 for implementing the functionality of the pre-trained artificial-intelligence algorithm 10303.

[0353] The large language model 10335 may be based on any adequate type of algorithm, like a statistical model, a recurrent neuronal network, a Bidirectional Encoder Representations from Transformers model, and a Generative Pre-trained Transformer model.

[0354] Figure 4 shows a block diagram of a measurement application control unit 10400. The measurement application control unit 10400 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10400 comprises a textbased input interface 10401 that receives text-based user requests 10402 regarding a measurement application device. The measurement application control unit 10400 further comprises a pre-trained artificial-intelligence algorithm 10403 coupled to the text-based input interface 10401 that generates response data 10404 regarding the measurement application device based on the text-based user requests 10402. The measurement application control unit 10400 further comprises an output interface 10405 coupled to the pre-trained artificial-intelligence algorithm 10403, and configured to output the response data 10404. The explanations provided herein regarding any embodiment of the measurement application control unit disclosed herein may, mu- tatis mutandis, also be applied to the measurement application control unit 10400.

[0355] The measurement application control unit 10400 further comprises a user input interface 10438. The user input interface 10438 is depicted only exemplarily as the front of a measurement application device with four buttons 10440-1 to 10440-n, two rotary knobs 10441- 1 , and 10441-2, and with a touchscreen 10442. The shown user input interface 10438 is just exemplarily shown. In other embodiments, any other type of input elements and / or arrangement may be chosen. Further, in other embodiments, the user input interface 10438 may comprise a software-based interface e.g., of a locally executed application or a respective website served by a server-implementation of the measurement application control unit 10400.

[0356] With the user input interface 10438, a user may provide user input 10443 to the pretrained artificial-intelligence algorithm 10403 that refers to controlling a measurement application device.

[0357] The pre-trained artificial-intelligence algorithm 10403 is, consequently, provided with the text-based user requests 10402, and the user input 10443 at the same time.

[0358] The user input 10443 may e.g., refer to a user pointing to a specific element of a display of the respective measurement device on the touchscreen 10442. At the same time, the user may provide a text-based user requests 10402, like “what is this?”.

[0359] The pre-trained artificial-intelligence algorithm 10403 may then combine the textbased user requests 10402 with the user input 10443, and provide a respective response data 10404.

[0360] In embodiments, the user input 10443 may be provided to the pre-trained artificialintelligence algorithm 10403 as a pre-conditioning text-based request, as will be explained in more detail below with regard to figure 6. To this end, the pre-conditioner may be coupled to the user input interface 10438 in order to generate the pre-conditioning text-based request. Such a pre-conditioning text-based request may e.g., comprise a text like “The user is pointing to the label of the Y axis of the diagram shown on the display of the oscilloscope, and asks:”, wherein the original text-based user requests 10402 may be provided directly after the pre-conditioning text-based request.

[0361] The pre-trained artificial-intelligence algorithm 10403 may then generate a respective response in the response data 10404. In case of the above example, the response data 10404 may comprise a response to the user’s question. In case of other text-based user requests 10402, the response data 10404 may comprise the respective content as requested in the text-based user requests 10402.

[0362] Figure 5 shows a block diagram of a measurement application control unit 10500. The measurement application control unit 10500 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10500 comprises a textbased input interface 10501 that receives text-based user requests 10502 regarding a measurement application device. The measurement application control unit 10500 further comprises a pre-trained artificial-intelligence algorithm 10503 coupled to the text-based input interface 10501 that generates response data 10504 regarding the measurement application device based on the text-based user requests 10502. The measurement application control unit 10500 further comprises an output interface 10505 coupled to the pre-trained artificial-intelligence algorithm 10503, and configured to output the response data 10504. The explanations provided herein regarding any embodiment of the measurement application control unit disclosed herein may, mu- tatis mutandis, also be applied to the measurement application control unit 10500.

[0363] The measurement application control unit 10500 further comprises a translator 10546. The translator 10546 is arranged between the text-based input interface 10501 , and the pre-trained artificial-intelligence algorithm 10503.

[0364] The translator 10546 may translate text-based user requests 10502 in a language that the pre-trained artificial-intelligence algorithm 10503 is not trained to operate on into translated text-based user requests 10546 in a language that the pre-trained artificial-intelligence algorithm 10503 may operate on.

[0365] The translator 10546 may also identify the language of the original text-based user requests 10502, and may pass any text-based user requests 10502 directly to the pre-trainedartificial-intelligence algorithm 10503 that are provided in a language that the pre-trained artificial-intelligence algorithm 10503 may operate on.

[0366] Alternatively, the text-based input interface 10501 may be adapted to identify the language of the text-based user requests 10502, and may directly provide a text-based user request 10502 to the pre-trained artificial-intelligence algorithm 10503 that is provided in a language that the pre-trained artificial-intelligence algorithm 10503 may operate on.

[0367] Figure 6 shows a block diagram of a measurement application control unit 10600. The measurement application control unit 10600 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10600 comprises a textbased input interface 10601 that receives text-based user requests 10602 regarding a measurement application device. The measurement application control unit 10600 further comprises a pre-trained artificial-intelligence algorithm 10603 coupled to the text-based input interface 10601 that generates response data 10604 regarding the measurement application device based on the text-based user requests 10602. The measurement application control unit 10600 further comprises an output interface 10605 coupled to the pre-trained artificial-intelligence algorithm 10603, and configured to output the response data 10604. The explanations provided herein regarding any embodiment of the measurement application control unit disclosed herein may, mu- tatis mutandis, also be applied to the measurement application control unit 10600.

[0368] The measurement application control unit 10600 further comprises a pre-conditioner 10648. The pre-conditioner 10648 is coupled to the text-based input interface 10601 and may provide a pre-conditioning text-based request 10649 to the text-based input interface 10601 .

[0369] The pre-conditioning text-based request 10649 serves for pre-conditioning the pretrained artificial-intelligence algorithm 10603, and may be provided to the pre-trained artificialintelligence algorithm 10603 prior to providing the text-based user requests 10602 to the pretrained artificial-intelligence algorithm 10603.

[0370] In embodiments, the text-based user requests 10602 may be provided to the preconditioner 10648 instead of the text-based input interface 10601. The pre-conditioner 10648 may then combine the pre-conditioning text-based request 10649 with the received text-based user requests 10602.

[0371] Figure 7 shows a block diagram of a measurement application control unit 10700. The measurement application control unit 10700 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10700 comprises a textbased input interface 10701 that receives text-based user requests 10702-1 , 10702-2 regarding a measurement application device. The measurement application control unit 10700 furthercomprises a pre-trained artificial-intelligence algorithm 10703 coupled to the text-based input interface 10701 that generates response data 10704 regarding the measurement application device based on the text-based user requests 10702. The measurement application control unit 10700 further comprises 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 disclosed herein may, mutatis mutandis, also be applied to the measurement application control unit 10700.

[0372] The measurement application control unit 10700 receives a first type of text-based user requests 10702-1 that may comprise user requests regarding the usage of measurement application devices in the measurement application. Further, the measurement application control unit 10700 receives a second type of text-based user requests 10702-2 that comprise user requests regarding the control of the measurement application device.

[0373] Accordingly, the pre-trained artificial-intelligence algorithm 10703 will provide usage response data 10752, and control response data 10753 in the response data 10704.

[0374] The measurement application control unit 10700 further comprises a code generator 10754. The code generator 10754 may receive the control response data 10753 or other respective indications from the pre-trained artificial-intelligence algorithm 10703 and may generate respective configuration and control commands 10755 in any adequate scripting or programming language.

[0375] In embodiments, the code generator 10754 may be provided as function of, or as element of, or included in the pre-trained artificial-intelligence algorithm 10703.

[0376] Figure 8 shows a block diagram of a measurement application control unit 10800. The measurement application control unit 10800 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10800 comprises a textbased input interface 10801 that receives text-based user requests 10802 regarding a measurement application device. The measurement application control unit 10800 further comprises a pre-trained artificial-intelligence algorithm 10803 that generates response data 10804 regarding the measurement application device based on the text-based user requests 10802. The measurement application control unit 10800 further comprises an output interface 10805 coupled to the pre-trained artificial-intelligence algorithm 10803, and configured to output the response data 10804. The explanations provided herein regarding any embodiment of the measurement application control unit disclosed herein may, mutatis mutandis, also be applied to the measurement application control unit 10800.

[0377] The measurement application control unit 10800 further comprises a complexity estimator 10858. The complexity estimator 10858 serves for estimating or calculating a complexity of the text-based user requests 10802. In the measurement application control unit 10800 the complexity is calculated by unit C. The calculation of the complexity may e.g., be performed based on a length of the text-based user requests 10802, or the number of main and / or subordinate clauses, or a combination of both.

[0378] The complexity may then be compared to a complexity threshold 10860. If the complexity is higher than the threshold 10860, the complexity estimator 10858 may, instead of providing the text-based user requests 10802 to the local pre-trained artificial-intelligence algorithm 10803 in the measurement application control unit 10800, provide the text-based user requests 10802 to an external pre-trained artificial-intelligence algorithm 10859. The external pretrained artificial-intelligence algorithm 10859 may be provided in a cloud system, or a server, or any other element, and may be coupled to the measurement application control unit 10800 e.g., the complexity estimator 10858 via a data network. The complexity estimator 10858 may request a user consent 10861 via a user interface 10862 for providing the provide the text-based user requests 10802 to the external pre-trained artificial-intelligence algorithm 10859.

[0379] As optional element, 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 may serve to anonymize the text-based user requests 10802 prior to providing the text-based user requests 10802 to the external pre-trained artificialintelligence algorithm 10859.

[0380] Figure 9 shows a block diagram of a measurement application control unit 10900. The measurement application control unit 10900 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 10900 comprises a textbased input interface 10901 that receives text-based user requests 10902 regarding a measurement application device. The measurement application control unit 10900 further comprises a pre-trained artificial-intelligence algorithm 10903 coupled to the text-based input interface 10901 that generates response data 10904 regarding the measurement application device based on the text-based user requests 10902. The measurement application control unit 10900 further comprises an output interface 10905 coupled to the pre-trained artificial-intelligence algorithm 10903, and configured to output the response data 10904. The explanations provided herein regarding any embodiment of the measurement application control unit disclosed herein may, mu- tatis mutandis, also be applied to the measurement application control unit 10900.

[0381] The measurement application control unit 10900 further comprises a text-based request generator 10970. The text-based request generator 10970 may receive a non-textual description 10971 , like an image, a video, or any other non-text-based, especially visual, description. Such a non-textual description may comprise e.g., an image or a video of a measurement application setup.

[0382] The text-based request generator 10970 may then generate a respective text-based user request 10902 based on the non-textual description 10971.

[0383] The text-based request generator 10970 may comprise any adequate algorithm, like an artificial-intelligence based algorithm, that may convert the non-textual description 10971 into a text-based user request 10902.

[0384] Figure 10 shows a block diagram of a measurement application control unit 11000. The measurement application control unit 11000 is based on the measurement application control unit 10100. Therefore, the measurement application control unit 11000 comprises a textbased input interface 11001 that receives text-based user requests 11002 regarding a measurement application. The measurement application control unit 11000 further comprises a pretrained artificial-intelligence algorithm 11003 coupled to the text-based input interface 11001 that generates response data 11004 regarding the measurement application device based on the text-based user requests 11002. The measurement application control unit 11000 further comprises an output interface 11005 coupled to the pre-trained artificial-intelligence algorithm 11003, and configured to output the response data 11004. The explanations provided herein regarding any embodiment of the measurement application control unit disclosed herein may, mu- tatis mutandis, also be applied to the measurement application control unit 11000.

[0385] The measurement application control unit 11000 further comprises a confidence estimator 11073. The confidence estimator 11073 may receive the response data 11004 or other respective indications from the pre-trained artificial-intelligence algorithm 11003 and may generate a respective confidence value 11074.

[0386] In embodiments, the confidence estimator 11073 may be provided as function of, or as element of, or included in the pre-trained artificial-intelligence algorithm 11003.

[0387] Figure 11 shows a measurement application device 11175. The measurement application device 11175 comprises a measurement application control unit 11100, and a measurement application device controller 11176.

[0388] The measurement application device controller 11176 is coupled to the text-based input interface 11101 to provide text-based user requests 11102 to the measurement application control unit 11100. The measurement application device controller 11176 is further coupled to the output interface 11105 in order to receive response data 11104 from the measurement application control unit 11100.

[0389] The measurement application device controller 11176, and the measurement application control unit 11100 are provided as separate devices, or elements in the measurement application device 11175.

[0390] In other embodiments, the measurement application control unit 11100 may be provided as a function of, or addition to the functionality of the measurement application device controller 11176.

[0391] Figure 12 shows a flow diagram of a computer-implemented method for controlling a measurement application device. The method comprises receiving S1 text-based user requests 102 regarding a measurement application device, generating S2 response data regarding questions related to the measurement application based on the text-based user requests with a pretrained artificial-intelligence algorithm, and outputting S2 the response data.

[0392] The pre-trained artificial-intelligence algorithm may be pre-trained using at least one of manuals regarding the measurement application device, datasheets regarding the measurement application device, application notes regarding the measurement application device, manuals of electronic devices, datasheets of electronic devices, application notes regarding electronic devices, articles regarding electronic circuits, online forum discussions regarding electronic circuits, and videos regarding electronic circuits.

[0393] The pre-trained artificial-intelligence algorithm may comprise a large language model based on at least one of a statistical model, a recurrent neuronal network, a Bidirectional Encoder Representations from Transformers model, and a Generative Pre-trained Transformer model.

[0394] The method may further comprise receiving user input, wherein the pre-trained artificial-intelligence algorithm may generate the response data regarding questions related to the measurement application based on the text-based user requests and the user input. The user input may e.g., be provided via at least one of a button, a switch, a knob, a touchscreen, a keyboard, a mouse, a camera, and a gesture sensor.

[0395] The method may further comprise translating text-based user requests in a language that the pre-trained artificial-intelligence algorithm is not trained to operate on into translated text-based user requests in a language that the pre-trained artificial-intelligence algorithm is trained to operate on, the translated text-based user requests may then be provided to the pre-trained artificial-intelligence algorithm.

[0396] The method may further comprises providing a pre-conditioning text-based request to the pre-trained artificial-intelligence algorithm prior to the pre-trained artificial-intelligence algorithm operating on the text-based user requests.

[0397] In embodiments, the text-based user requests may refer to the usage of the measurement application device. Usage response data may, therefore, be generated by the pretrained artificial-intelligence algorithm that comprises a respective explanation regarding the usage of the measurement application device.

[0398] The text-based user requests may refer to the control of the measurement application device. Control response data may, therefore, be generated by the pre-trained artificial-intelligence algorithm that comprises respective control commands regarding the measurement application device. Further, configuration and control commands may be generated for the measurement application device in a predetermined control or programming language, and may be provided to a controller of the measurement application device.

[0399] The pre-trained artificial-intelligence algorithm may be locally executed on the measurement application device. The method may further comprise estimating the complexity of the text-based user requests, and forwarding the text-based user requests to an external pretrained artificial-intelligence algorithm if the estimated complexity is higher than a predetermined threshold. In such an embodiment, a user consent may be requested via a user interface of the measurement application device prior to providing one of the text-based user requests to the external pre-trained artificial-intelligence algorithm. The text-based user requests may be provided indirectly to the external pre-trained artificial-intelligence algorithm via a request anonymizer.

[0400] In an embodiment, the method may further comprise receiving at least one of an image, a video, or a non-textual description of at least one of measurement application device, a device under test, and a measurement application setup, generating text-based user requests based on the at least one of the image or the video, and providing the generated text-based user requests to the pre-trained artificial-intelligence algorithm.

[0401] Figure 13 shows a block diagram of an oscilloscope OSC1 that may be used with, or implement an embodiment of a measurement application device or method according to the first aspect of the present disclosure.

[0402] The oscilloscope OSC1 comprises a housing HO that accommodates four measurement inputs MIP1 , MIP2, MIP3, MIP4 that are coupled to a signal processor SIP for processing any measured signals. The signal processor SIP is coupled to a display DISP1 for displaying the measured signals to a user.

[0403] Although not explicitly shown, it is understood, that the oscilloscope OSC1 may also comprise signal outputs that may also be coupled to the differential measurement probe. Such signal outputs may for example serve to output calibration signals. Such calibration signals allow calibrating the measurement setup prior to performing any measurement. The process of calibrating and correcting any measurement signals based on the calibration may also be called de-embedding and may comprise applying respective algorithms on the measured signals.

[0404] In the oscilloscope OSC1 the signal processor SIP or an additional processing element may perform the function of the measurement application control unit or the method according to the present disclosure, or may implement the measurement application control unit, or method. Of course, a communication interface may be provided in the oscilloscope OSC1 for communication with other measurement application devices.

[0405] Figure 14 shows a block diagram of an oscilloscope OSC that may be used with, or implement an embodiment of a measurement application device or method according to the first aspect of the present disclosure. The oscilloscope OSC is implemented as a digital oscilloscope. However, the present disclosure may also be implemented with any other type of oscilloscope.

[0406] The oscilloscope OSC exemplarily comprises five general sections, the vertical system VS, the triggering section TS, the horizontal system HS, the processing section PS and the display DISP. It is understood, that the partitioning into five general sections is a logical partitioning and does not limit the placement and implementation of any of the elements of the oscilloscope OSC in any way.

[0407] The vertical system VS mainly serves for offsetting, attenuating and amplifying a signal to be acquired. The signal may for example be modified to fit in the available space on the display DISP or to comprise a vertical size as configured by a user.

[0408] To this end, the vertical system VS comprises a signal conditioning section SC with an attenuator ATT and a digital-to-analog-converter DAC that are coupled to an amplifier AMP1.The amplifier AMP1 is coupled to a filter Fl 1 , which in the shown example is provided as a low pass filter. The vertical system VS also comprises an analog-to-digital converter ADC1 that receives the output from the filter FI1 and converts the received analog signal into a digital signal.

[0409] The attenuator ATT and the amplifier AMP1 serve to scale the amplitude of the signal to be acquired to match the operation range of the analog-to-digital converter ADC1. The digital-to-analog-converter DAC1 serves to modify the DC component of the input signal to be acquired to match the operation range of the analog-to-digital converter ADC1. The filter FI1 serves to filter out unwanted high frequency components of the signal to be acquired.

[0410] The triggering section TS operates on the signal as provided by the amplifier AMP. The triggering section TS comprises a filter FI2, which in this embodiment is implemented as a low pass filter. The filter FI2 is coupled to a trigger system TS1.

[0411] The triggering section TS serves to capture predefined signal events and allows the horizontal system HS to e.g., display a stable view of a repeating waveform, or to simply display waveform sections that comprise the respective signal event. It is understood, that the predefined signal event may be configured by a user via a user input of the oscilloscope OSC.

[0412] Possible predefined signal events may for example include, but are not limited to, when the signal crosses a predefined trigger threshold in a predefined direction i.e. , with a rising or falling slope. Such a trigger condition is also called an edge trigger. Another trigger condition is called “glitch triggering” and triggers, when a pulse occurs in the signal to be acquired that has a width that is greater than or less than a predefined amount of time.

[0413] In order to allow an exact matching of the trigger event and the waveform that is shown on the display DISP, a common time base may be provided for the analog-to-digital converter ADC1 and the trigger system TS1.

[0414] It is understood, that although not explicitly shown, the trigger system TS1 may comprise at least one of configurable voltage comparators for setting the trigger threshold voltage, fixed voltage sources for setting the required slope, respective logic gates like e.g., a XOR gate, and FlipFlops to generate the triggering signal.

[0415] The triggering section TS is exemplarily provided as an analog trigger section. It is understood, that the oscilloscope OSC may also be provided with a digital triggering section. Such a digital triggering section will not operate on the analog signal as provided by the amplifier AMP but will operate on the digital signal as provided by the analog-to-digital converter ADC1.

[0416] A digital triggering section may comprise a processing element, like a processor, a DSP, a CPLD, an ASIC or an FPGA to implement digital algorithms that detect a valid trigger event.

[0417] The horizontal system HS is coupled to the output of the trigger system TS1 and mainly serves to position and scale the signal to be acquired horizontally on the display DISP.

[0418] The oscilloscope OSC further comprises a processing section PS that implements digital signal processing and data storage for the oscilloscope OSC. The processing section PS comprises an acquisition processing element ACP that is couple to the output of the analog-to- digital converter ADC1 and the output of the horizontal system HS as well as to a memory MEM and a post processing element PPE.

[0419] The acquisition processing element ACP manages 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 comprise a processing element with a digital interface to the analog-to-digital converter ADC2 and a digital interface to the memory MEM. The processing element may for example comprise a microcontroller, a DSP, a CPLD, an ASIC or an FPGA with respective interfaces. In a microcontroller or DSP, the functionality of the acquisition processing element ACP may be implemented as computer readable instructions that are executed by a CPU. In a CPLD or FPGA the functionality of the acquisition processing element ACP may be configured in to the CPLD or FPGA opposed to software being executed by a processor.

[0420] The processing section PS further comprises a communication processor CP and a communication interface COM.

[0421] The communication processor CP may be a device that manages data transfer to and from the oscilloscope OSC. The communication interface COM for any adequate communication standard like for example, Ethernet, WIFI, Bluetooth, NFC, an infra-red communication standard, and a visible-light communication standard.

[0422] The communication processor CP is coupled to the memory MEM and may use the memory MEM to store and retrieve data.

[0423] Of course, the communication processor CP may also be coupled to any other element of the oscilloscope OSC to retrieve device data or to provide device data that is received from the management server.

[0424] The post processing element PPE may be controlled by the acquisition processing element ACP and may access the memory MEM to retrieve data that is to be displayed on thedisplay DISP. The post processing element PPE may condition the data stored in the memory MEM such that the display DISP may show the data e.g., as waveform to a user. The post processing element PPE may also realize analysis functions like cursors, waveform measurements, histograms, or math functions.

[0425] The display DISP controls all aspects of signal representation to a user, although not explicitly shown, may comprise any component that is required to receive data to be displayed and control a display device to display the data as required.

[0426] It is understood, that even if it is not shown, the oscilloscope OSC may also comprise a user interface for a user to interact with the oscilloscope OSC. Such a user interface may comprise dedicated input elements like for example knobs and switches. At least in part the user interface may also be provided as a touch sensitive display device.

[0427] In the oscilloscope OSC, any one of the processing elements in the processing section PS or an additional processing element may perform the function of the measurement application control unit, or the method according to the first aspect of the present disclosure.

[0428] It is understood, that all elements of the oscilloscope OSC that perform digital data processing may be provided as dedicated elements. As alternative, at least some of the abovedescribed functions may be implemented in a single hardware element, like for example a microcontroller, DSP, CPLD or FPGA. Generally, the above-describe logical functions may be implemented in any adequate hardware element of the oscilloscope OSC and not necessarily need to be partitioned into the different sections explained above.

[0429] Figures of the second aspect

[0430] Figure 15 shows a block diagram of a measurement application processing device 20100. The measurement application processing device 20100 comprises a text-based input interface 20101 that receives text-based user requests 20102 regarding a measurement application. The measurement application processing device 20100 further comprises a pre-trained artificial-intelligence algorithm 20103 coupled to the text-based input interface 20101 , and configured to generate response data 20104 regarding the measurement application based on the text-based user requests 20102. The measurement application processing device 20100 further comprise an output interface 20105 coupled to the pre-trained artificial-intelligence algorithm 20103, and configured to output the response data 20104. The explanations provided herein regarding any embodiment of the measurement application processing device disclosed herein may, mutatis mutandis, also be applied to the measurement application processing device 20100.

[0431] In embodiments, the measurement application processing device 20100 may be implemented on a computer or server, that executes a computer-program product that comprises instructions that when executed by the computer or server, especially a processor in the computer or server, causes the computer or server to perform the computer-implemented method, or the function of the measurement application processing device 20100 of the second aspect according to the present disclosure. Such a computer or server may be located remotely to measurement application devices and coupled to measurement application devices via a network connection.

[0432] In embodiments, the pre-trained artificial-intelligence algorithm 20103 may be pretrained using any combination of manuals regarding one or more measurement application devices or measurement applications, datasheets regarding one or more measurement application devices or measurement applications, application notes regarding one or more measurement application devices or measurement applications, datasheets of electronic devices, application notes of electronic devices, articles regarding electronic circuits, online forum discussions regarding electronic circuits, and videos regarding electronic circuits.

[0433] Figure 16 shows a block diagram of a measurement application processing device 20200. The measurement application processing device 20200 is based on the measurement application processing device 20100. The measurement application processing device 20200 comprises a text-based input interface 20201 that receives text-based user requests 20202 regarding a measurement application. The measurement application processing device 20200 further comprises a pre-trained artificial-intelligence algorithm 20203 coupled to the text-based input interface 20201 , and configured to generate response data 20204 regarding the measurement application based on the text-based user requests 20202. The measurement application processing device 20200 further comprise an output interface 20205 coupled to the pre-trained artificial-intelligence algorithm 20203, and configured to output the response data 20204. The explanations provided herein regarding any embodiment of the measurement application processing device disclosed herein may, mutatis mutandis, also be applied to the measurement application processing device 20200.

[0434] The measurement application processing device 20200 further comprises 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 the text-based input interface 20201.

[0435] The audio input interface 20228 may receive spoken language requests 20229 e.g., from a user. It is understood, that the audio input interface 20228 may comprise e.g., a micro-phone for recording the spoken language requests 20229. In embodiments, the audio input interface 20228 may comprise a data interface for receiving the spoken language requests 20229 in digital form that are recorded elsewhere. A combination of both is possible.

[0436] The speech recognition unit 20230 may then convert the spoken language requests 20229 into text-based requests 20231. Such text-based requests 20231 may then be forwarded to the text-based input interface 20201 , as are the text-based user requests 20202. The textbased input interface 20201 may then process the text-based requests 20231 like any other text-based user requests 20202.

[0437] The speech recognition unit 20230 may comprise any type of adequate element. Exemplary embodiments of the speech recognition unit 20230 may e.g., be based on computer- implemented algorithms or methods, especially respective artificial-intelligence based computer- implemented algorithms.

[0438] Figure 17 shows a block diagram of a measurement application processing device 20300. The measurement application processing device 20300 is based on the measurement application processing device 20100. The measurement application processing device 20300 comprises a text-based input interface 20301 that receives text-based user requests 20302 regarding a measurement application. The measurement application processing device 20300 further comprises a pre-trained artificial-intelligence algorithm 20303 coupled to the text-based input interface 20301 , and configured to generate response data 20304 regarding the measurement application based on the text-based user requests 20302. The measurement application processing device 20300 further comprise an output interface 20305 coupled to the pre-trained artificial-intelligence algorithm 20303, and configured to output the response data 20304. The explanations provided herein regarding any embodiment of the measurement application processing device disclosed herein may, mutatis mutandis, also be applied to the measurement application processing device 20300.

[0439] In the measurement application processing device 20300, the pre-trained artificialintelligence algorithm 20303 comprises a large language model 20335 for implementing the functionality of the pre-trained artificial-intelligence algorithm 20303.

[0440] The large language model 20335 may be based on any adequate type of algorithm, like a statistical model, a recurrent neuronal network, a Bidirectional Encoder Representations from Transformers model, and a Generative Pre-trained Transformer model.

[0441] Figure 18 shows a block diagram of a measurement application processing device 20400. The measurement application processing device 20400 is based on the measurement application processing device 20100. The measurement application processing device 20400comprises a text-based input interface 20401 that receives text-based user requests 20402 regarding a measurement application. The measurement application processing device 20400 further comprises a pre-trained artificial-intelligence algorithm 20403 coupled to the text-based input interface 20401 , and configured to generate response data 20404 regarding the measurement application based on the text-based user requests 20402. The measurement application processing device 20400 further comprise an output interface 20405 coupled to the pre-trained artificial-intelligence algorithm 20403, and configured to output the response data 20404. The explanations provided herein regarding any embodiment of the measurement application processing device disclosed herein may, mutatis mutandis, also be applied to the measurement application processing device 20400.

[0442] The pre-trained artificial-intelligence algorithm 20403 of the measurement application processing device 20400 provides the response data 20404 in a visual form.

[0443] To this end, the pre-trained artificial-intelligence algorithm 20403 provides a block diagram 20438. In the response data 20404.

[0444] The exemplary block diagram 20438 shows two measurement application devices. The left measurement application device comprises four ports arranged in a row, generates two test signals, and provides one of the test signals from the leftmost port, and one of the test signals from the rightmost port to a device under test. The right measurement application device also comprises four ports arranged in a row, and acquires one signal from the device under test with the second port from the left.

[0445] Since the block diagram 20438 is only exemplary, no further indications are provided. In other embodiments, the block diagram 20438 may comprise further information, like a textual description of the single elements, and a description of the steps that need to be performed to set-up the measurement application as it is shown in the block diagram 20438. In other embodiments, the number of measurement devices, connections, and devices under test may be different, and other types, or additional types of elements may be provided in the measurement application, and the block diagram 20438.

[0446] Figure 19 shows a block diagram of a measurement application processing device 20500. The measurement application processing device 20500 is based on the measurement application processing device 20100. The measurement application processing device 20500 comprises a text-based input interface 20501-1 , 20501-2 that receives text-based user requests 20502 regarding a measurement application. The measurement application processing device 20500 further comprises a pre-trained artificial-intelligence algorithm 20503 coupled to the textbased input interface 20501 , and configured to generate response data 20504 regarding themeasurement application based on the text-based user requests 20502. The measurement application processing device 20500 further comprise an output interface 20505 coupled to the pre-trained artificial-intelligence algorithm 20503, and configured to output the response data 20504. The explanations provided herein regarding any embodiment of the measurement application processing device disclosed herein may, mutatis mutandis, also be applied to the measurement application processing device 20500.

[0447] The measurement application processing device 20500 receives a first type of textbased user requests 20502-1 that comprise user requests regarding the setup of the measurement application. Further, the measurement application processing device 20500 receives a second type of text-based user requests 20502-2 that comprise user requests regarding the control of the measurement application, or single measurement application devices in the measurement application.

[0448] Accordingly, the pre-trained artificial-intelligence algorithm 20503 will provide set-up response data 20540, and control response data 20541 in the response data 20504.

[0449] The measurement application processing device 20500 further comprises a code generator 20542. The code generator 20542 may receive the control response data 20541 or other respective indications from the pre-trained artificial-intelligence algorithm 20503 and may generate respective configuration and control commands 20543 in any adequate scripting or programming language.

[0450] In embodiments, the code generator 20542 may be provided as function of, or as element of, or included in the pre-trained artificial-intelligence algorithm 20503.

[0451] In embodiments, the measurement application processing device 20500 may comprise a warning generator instead or in addition to the code generator 20542. The warning generator may be provided at the same position as the code generator 20542 and work with the same input as the code generator 20542. Alterantively, the warning generator may be integrated into the pre-trained artificial-intelligence algorithm 20503.

[0452] Figure 20 shows a block diagram of a measurement application processing device 20600. The measurement application processing device 20600 is based on the measurement application processing device 20100. The measurement application processing device 20600 comprises a text-based input interface 20601 that receives text-based user requests 20602 regarding a measurement application. The measurement application processing device 20600 further comprises a pre-trained artificial-intelligence algorithm 20603 coupled to the text-based input interface 20601 , and configured to generate response data 20604 regarding the measurement application based on the text-based user requests 20602. The measurement applicationprocessing device 20600 further comprise an output interface 20605 coupled to the pre-trained artificial-intelligence algorithm 20603, and configured to output the response data 20604. The explanations provided herein regarding any embodiment of the measurement application processing device disclosed herein may, mutatis mutandis, also be applied to the measurement application processing device 20600.

[0453] The measurement application processing device 20600 further comprises a pre-con- ditioner 20645. The pre-conditioner 20645 is coupled to the text-based input interface 20601 and may provide a pre-conditioning text-based request 20646 to the text-based input interface 20601.

[0454] The pre-conditioning text-based request 20646 serves for pre-conditioning the pretrained artificial-intelligence algorithm 20603, and may be provided to the pre-trained artificialintelligence algorithm 20603 prior to providing the text-based user requests 20602 to the pretrained artificial-intelligence algorithm 20603.

[0455] In embodiments, the text-based user requests 20602 may be provided to the preconditioner 20645 instead of the text-based input interface 20601. The pre-conditioner 20645 may then combine the pre-conditioning text-based request 20646 with the received text-based user requests 20602.

[0456] Figure 21 shows a block diagram of a measurement application processing device 20700. The measurement application processing device 20700 is based on the measurement application processing device 20100. The measurement application processing device 20700 comprises a text-based input interface 20701 that receives text-based user requests 20702 regarding a measurement application. The measurement application processing device 20700 further comprises a pre-trained artificial-intelligence algorithm 20703 coupled to the text-based input interface 20701 , and configured to generate response data 20704 regarding the measurement application based on the text-based user requests 20702. The measurement application processing device 20700 further comprise an output interface 20705 coupled to the pre-trained artificial-intelligence algorithm 20703, and configured to output the response data 20704. The explanations provided herein regarding any embodiment of the measurement application processing device disclosed herein may, mutatis mutandis, also be applied to the measurement application processing device 20700.

[0457] In the measurement application processing device 20700 the pre-trained artificialintelligence algorithm 20703 may generate an augmented text-based user request 20750. This augmented text-based user request 20750 may be provided to a user via the output interface 20705. The user may then review the augmented text-based user request 20750, and provide arespective confirmation 20751 to the measurement application processing device 20700, especially via the text-based input interface 20701 .

[0458] After receiving the confirmation 20751 , the pre-trained artificial-intelligence algorithm 20703 may generate the response data 20704, and output the response data 20704 via the output interface 20705.

[0459] Figure 22 shows a block diagram of a measurement application processing device 20800. The measurement application processing device 20800 is based on the measurement application processing device 20100. The measurement application processing device 20800 comprises a text-based input interface 20801 that receives text-based user requests 20802 regarding a measurement application. The measurement application processing device 20800 further comprises a pre-trained artificial-intelligence algorithm 20803 coupled to the text-based input interface 20801 , and configured to generate response data 20804 regarding the measurement application based on the text-based user requests 20802. The measurement application processing device 20800 further comprise an output interface 20805 coupled to the pre-trained artificial-intelligence algorithm 20803, and configured to output the response data 20804. The explanations provided herein regarding any embodiment of the measurement application processing device disclosed herein may, mutatis mutandis, also be applied to the measurement application processing device 20800.

[0460] The measurement application processing device 20800 further comprises a textbased request generator 20855. The text-based request generator 20855 may receive a nontextual description 20856, like an image, a video, or any other non-text-based, especially visual, description. Such a non-textual description may comprise e.g., an image or a video of a measurement application setup.

[0461] The text-based request generator 20855 may then generate a respective text-based user requests 20802 based on the non-textual description 20856.

[0462] The text-based request generator 20855 may comprise any adequate algorithm, like an artificial-intelligence based algorithm, that may convert the non-textual description 20856 into a text-based user request 20802.

[0463] Figure 23 shows a block diagram of another measurement application device control unit 20900. The measurement application device control unit 20900 is based on the measurement application device control unit 20100. Therefore, the measurement application device control unit 20900 comprises a text-based input interface 20901 that receives text-based user requests 20902 regarding a measurement application device. The measurement application device control unit 20900 further comprises a pre-trained artificial-intelligence algorithm 20903coupled to the text-based input interface 20901 that generates configuration data 20904 regarding the measurement application device based on the text-based user requests 20902. The measurement application device control unit 20900 further comprises an output interface 20905 coupled to the pre-trained artificial-intelligence algorithm 20903, and configured to output the configuration data 20904. The explanations provided herein regarding any embodiment of the measurement application device control unit disclosed herein may, mutatis mutandis, also be applied to the measurement application processing device 20900.

[0464] The measurement application device control unit 20900 further comprises a feedback interface 20910 that receives measurement feedback data 20911 . The measurement feedback data 20911 may in embodiments be provided directly to the 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.

[0465] 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 artificialintelligence algorithm 20903.

[0466] The pre-trained artificial-intelligence algorithm 20903 generates further sets 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.

[0467] The feedback data analyzer 20912 may identify at least one of anomalies, and relevant measurement values, and relevant measurement waveform sections in raw measurement data. The raw measurement data may be provided in, or as the measurement feedback data 20911 . The feedback data analyzer 20912 may then provide a respective text-based feedback description 20913.

[0468] Such a text-based feedback description 20913 may e.g., be comprise statements like “the relevant information in the acquired waveform is in the frequency range between 1GHz and 5GHz. Please zoom into this section of the acquired waveform for a measurement”.

[0469] Figure 24 shows a block diagram of another measurement application device control unit 21000. The measurement application device control unit 21000 is based on the measurement application device control unit 20200. Therefore, the measurement application device control unit 21000 comprises a text-based input interface 21001 that receives text-based user requests 21002 regarding a measurement application device. The measurement application device control unit 21000 further comprises a pre-trained artificial-intelligence algorithm 21003coupled to the text-based input interface 21001 that generates configuration data 21004 regarding the measurement application device based on the text-based user requests 21002. The measurement application device control unit 21000 further comprises an output interface 21005 coupled to the pre-trained artificial-intelligence algorithm 21003, and configured to output the configuration data 21004. The measurement application device control unit 21000 further comprises a feedback interface 21010 that receives measurement feedback data 21011. A feedback data analyzer 21012 is arranged between the feedback interface 21010, and the pretrained artificial-intelligence algorithm 21003, and generates a text-based feedback description 21013 of the measurement feedback data 21011, and provides the 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 disclosed herein may, mutatis mutandis, also be applied to the measurement application processing device 21000.

[0470] The measurement application device control unit 21000 further comprises a feedback output interface 21014 that is coupled to the feedback data analyzer 21012.

[0471] The feedback output interface 21014 outputs the measurement feedback data 21011 , especially the text-based feedback description 20213, to a user.

[0472] The pre-trained artificial-intelligence algorithm 21003 may then generate a further set of configuration data 21004 based on the original text-based user request 21002, and a further text-based user request 21002 received after the measurement feedback data 21011 is output to the user.

[0473] The pre-trained artificial-intelligence algorithm 21003 may also perform reinforced learning based on the further text-based user request 21002 received after the measurement feedback data 21011 is output to the user. It is understood, that this is just an example of performing further training with the pre-trained artificial-intelligence algorithm 21003. Any other form of further or continuous learning may be implemented for the pre-trained artificial-intelligence algorithm 21003.

[0474] Figure 25 shows a measurement application 21160. The measurement application 21160 exemplarily comprises a measurement application processing device 21100 that is coupled to three measurement application devices 21161-1 , 21161-2, 21161-3. In other embodiments, more or less measurement application devices are possible, and the measurement application processing device 21100 may be integrated into any one of the measurement application devices.

[0475] The measurement application processing device 21100 comprises a text-based input interface 21101 , a pre-trained artificial-intelligence algorithm 21103, and an output interface 21105, like the measurement application processing device 20100 of figure 15. Of course, any other embodiment of the measurement application processing device may be used in the measurement application 21160.

[0476] The measurement application devices 21161-1, 21161-2, 21161-3 may be coupled to the measurement application processing device 21100 via a private or public data network. In embodiments with a code generator in the measurement application processing device 21100, the measurement application processing device 21100 may directly provide the generated configuration and control commands to the measurement application devices 21161-1, 21161-2, 21161-3.

[0477] In embodiments, the measurement application processing device 21100 may serve as a remote-control device for the measurement application devices 21161-1, 21161-2, 21161- 3, and may provide a user with a respective control interface. The measurement application devices 21161-1 , 21161-2, 21161-3 may e.g., be measurement application devices 21161-1 , 21161-2, 21161-3 according to any one of the embodiments described herein.

[0478] Figure 26 shows a flow diagram of an embodiment of a computer-implemented method according to the present disclosure. The method comprises receiving S1 text-based user requests regarding a measurement application, generating S2 with a pre-trained artificialintelligence algorithm response data regarding the measurement application based on the textbased user requests, and outputting S3 the response data.

[0479] The pre-trained artificial-intelligence algorithm may be pre-trained using at least one of manuals regarding one or more measurement application devices or measurement applications, datasheets regarding one or more measurement application devices or measurement applications, and application notes regarding one or more measurement application devices or measurement applications. The pre-trained artificial-intelligence algorithm may e.g., comprise a large language model based on at least one of a statistical model, a recurrent neuronal network, a Bidirectional Encoder Representations from Transformers model, and a Generative Pretrained Transformer model.

[0480] In embodiments, the method may further comprise receiving spoken language requests, converting the spoken language requests into text-based requests, and providing the text-based requests to the text-based input interface as text-based user requests.

[0481] In further embodiments, the pre-trained artificial-intelligence algorithm may augment the text-based user requests, and output the augmented text-based user requests via the outputinterface. The pre-trained artificial-intelligence algorithm may further generate the response data after confirmation of the augmented text-based user requests by the user.

[0482] The pre-trained artificial-intelligence algorithm may receive text-based user requests regarding the setup of the measurement application, and may generate set-up response data that comprises a respective explanation regarding the setup of the measurement application. The pre-trained artificial-intelligence algorithm may then generate set-up response data that indicates which measurement application devices to use, and how to connect the measurement application devices to set-up the measurement application. The pre-trained artificial-intelligence algorithm may e.g., generate a block diagram of the set-up of the measurement application.

[0483] The pre-trained artificial-intelligence algorithm may also generate control response data that may comprise respective control commands for at least one measurement application device. The control commands may e.g., comprise instructions to a user. Alternatively, or in addition, the control commands may comprise generating configuration and control commands for the measurement application device in a predetermined control or programming language.

[0484] The method may also comprise providing a pre-conditioning text-based request to the pre-trained artificial-intelligence algorithm prior to the pre-trained artificial-intelligence algorithm operating on the text-based user requests.

[0485] The method may further comprise receiving at least one of a non-text based description, an image or a video of a measurement application device, a device under test, or a measurement application set-up, and generating text-based user requests based on the at least one of the image or the video.

[0486] Further, the pre-trained artificial-intelligence algorithm may receive text-based user requests regarding the maintenance of a measurement application device in a measurement application, and may generate respective maintenance response data that comprises a respective explanation regarding the maintenance of the respective measurement application device.

[0487] Figure 27 shows a block diagram of an oscilloscope OSC1 that may be used with or implement an embodiment of a measurement application processing device or method according to the second aspect of the present disclosure.

[0488] The oscilloscope OSC1 comprises a housing HO that accommodates four measurement inputs MIP1 , MIP2, MIP3, MIP4 that are coupled to a signal processor SIP for processing any measured signals. The signal processor SIP is coupled to a display DISP1 for displaying the measured signals to a user.

[0489] Although not explicitly shown, it is understood, that the oscilloscope OSC1 may also comprise signal outputs that may also be coupled to the differential measurement probe. Such signal outputs may for example serve to output calibration signals. Such calibration signals allow calibrating the measurement setup prior to performing any measurement. The process of calibrating and correcting any measurement signals based on the calibration may also be called de-embedding and may comprise applying respective algorithms on the measured signals.

[0490] In the oscilloscope OSC1 the signal processor SIP or an additional processing element may perform the function of the measurement application processing device, or the method according to the present disclosure, or may implement the measurement application processing device, or the method. Of course, a communication interface may be provided in the oscilloscope OSC1 for communication with other measurement application devices.

[0491] Figure 28 shows a block diagram of an oscilloscope OSC that may be an comprise or implement a measurement application processing device or method according to the second aspect of the present disclosure. The oscilloscope OSC is implemented as a digital oscilloscope. However, the present disclosure may also be implemented with any other type of oscilloscope.

[0492] The oscilloscope OSC exemplarily comprises five general sections, the vertical system VS, the triggering section TS, the horizontal system HS, the processing section PS and the display DISP. It is understood, that the partitioning into five general sections is a logical partitioning and does not limit the placement and implementation of any of the elements of the oscilloscope OSC in any way.

[0493] The vertical system VS mainly serves for offsetting, attenuating and amplifying a signal to be acquired. The signal may for example be modified to fit in the available space on the display DISP or to comprise a vertical size as configured by a user.

[0494] To this end, the vertical system VS comprises a signal conditioning section SC with an attenuator ATT and a digital-to-analog-converter DAC that are coupled to an amplifier AMP1. The amplifier AMP1 is coupled to a filter Fl 1 , which in the shown example is provided as a low pass filter. The vertical system VS also comprises an analog-to-digital converter ADC1 that receives the output from the filter FI1 and converts the received analog signal into a digital signal.

[0495] The attenuator ATT and the amplifier AMP1 serve to scale the amplitude of the signal to be acquired to match the operation range of the analog-to-digital converter ADC1. The digital-to-analog-converter DAC1 serves to modify the DC component of the input signal to be acquired to match the operation range of the analog-to-digital converter ADC1. The filter FI1 serves to filter out unwanted high frequency components of the signal to be acquired.

[0496] The triggering section TS operates on the signal as provided by the amplifier AMP. The triggering section TS comprises a filter FI2, which in this embodiment is implemented as a low pass filter. The filter FI2 is coupled to a trigger system TS1.

[0497] The triggering section TS serves to capture predefined signal events and allows the horizontal system HS to e.g., display a stable view of a repeating waveform, or to simply display waveform sections that comprise the respective signal event. It is understood, that the predefined signal event may be configured by a user via a user input of the oscilloscope OSC.

[0498] Possible predefined signal events may for example include, but are not limited to, when the signal crosses a predefined trigger threshold in a predefined direction i.e. , with a rising or falling slope. Such a trigger condition is also called an edge trigger. Another trigger condition is called “glitch triggering” and triggers, when a pulse occurs in the signal to be acquired that has a width that is greater than or less than a predefined amount of time.

[0499] In order to allow an exact matching of the trigger event and the waveform that is shown on the display DISP, a common time base may be provided for the analog-to-digital converter ADC1 and the trigger system TS1.

[0500] It is understood, that although not explicitly shown, the trigger system TS1 may comprise at least one of configurable voltage comparators for setting the trigger threshold voltage, fixed voltage sources for setting the required slope, respective logic gates like e.g., a XOR gate, and FlipFlops to generate the triggering signal.

[0501] The triggering section TS is exemplarily provided as an analog trigger section. It is understood, that the oscilloscope OSC may also be provided with a digital triggering section. Such a digital triggering section will not operate on the analog signal as provided by the amplifier AMP but will operate on the digital signal as provided by the analog-to-digital converter ADC1.

[0502] A digital triggering section may comprise a processing element, like a processor, a DSP, a CPLD, an ASIC or an FPGA to implement digital algorithms that detect a valid trigger event.

[0503] The horizontal system HS is coupled to the output of the trigger system TS1 and mainly serves to position and scale the signal to be acquired horizontally on the display DISP.

[0504] The oscilloscope OSC further comprises a processing section PS that implements digital signal processing and data storage for the oscilloscope OSC. The processing section PS comprises an acquisition processing element ACP that is couple to the output of the analog-to-digital converter ADC1 and the output of the horizontal system HS as well as to a memory MEM and a post processing element PPE.

[0505] The acquisition processing element ACP manages 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 comprise a processing element with a digital interface to the analog-to-digital converter ADC2 and a digital interface to the memory MEM. The processing element may for example comprise a microcontroller, a DSP, a CPLD, an ASIC or an FPGA with respective interfaces. In a microcontroller or DSP, the functionality of the acquisition processing element ACP may be implemented as computer readable instructions that are executed by a CPU. In a CPLD or FPGA the functionality of the acquisition processing element ACP may be configured in to the CPLD or FPGA opposed to software being executed by a processor.

[0506] The processing section PS further comprises a communication processor CP and a communication interface COM.

[0507] The communication processor CP may be a device that manages data transfer to and from the oscilloscope OSC. The communication interface COM for any adequate communication standard like for example, Ethernet, WIFI, Bluetooth, NFC, an infra-red communication standard, and a visible-light communication standard.

[0508] The communication processor CP is coupled to the memory MEM and may use the memory MEM to store and retrieve data.

[0509] Of course, the communication processor CP may also be coupled to any other element of the oscilloscope OSC to retrieve device data or to provide device data that is received from the management server.

[0510] The post processing element PPE may be controlled by the acquisition processing element ACP and may access the memory MEM to retrieve data that is to be displayed on the display DISP. The post processing element PPE may condition the data stored in the memory MEM such that the display DISP may show the data e.g., as waveform to a user. The post processing element PPE may also realize analysis functions like cursors, waveform measurements, histograms, or math functions.

[0511] The display DISP controls all aspects of signal representation to a user, although not explicitly shown, may comprise any component that is required to receive data to be displayed and control a display device to display the data as required.

[0512] It is understood, that even if it is not shown, the oscilloscope OSC may also comprise a user interface for a user to interact with the oscilloscope OSC. Such a user interface may comprise dedicated input elements like for example knobs and switches. At least in part the user interface may also be provided as a touch sensitive display device.

[0513] In the oscilloscope OSC, any one of the processing elements in the processing section PS or an additional processing element may perform the function of the measurement application processing device, or the method according to the present disclosure.

[0514] It is understood, that all elements of the oscilloscope OSC that perform digital data processing may be provided as dedicated elements. As alternative, at least some of the abovedescribed functions may be implemented in a single hardware element, like for example a microcontroller, DSP, CPLD or FPGA. Generally, the above-describe logical functions may be implemented in any adequate hardware element of the oscilloscope OSC and not necessarily need to be partitioned into the different sections explained above.

[0515] The processes, methods, or algorithms disclosed herein can be deliverable to / imple- mented by a processing device, controller, or computer, which can include any existing programmable electronic control unit or dedicated electronic control unit. Similarly, the processes, methods, or algorithms can be stored as data and instructions executable by a controller or computer in many forms including, but not limited to, information permanently stored on non- writable storage media such as ROM devices and information alterably stored on writeable storage media such as floppy disks, magnetic tapes, CDs, RAM devices, and other magnetic and optical media. The processes, methods, or algorithms can also be implemented in a software executable object. Alternatively, the processes, methods, or algorithms can be embodied in whole or in part 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.

[0516] While exemplary embodiments are described above, it is not intended that these embodiments describe all possible forms encompassed by the claims. The words used in the specification are words of description rather than limitation, and it is understood that various changes can be made without departing from the spirit and scope of the disclosure. As previously described, the features of various embodiments can be combined to form further embodiments of the invention that may not be explicitly described or illustrated. While various embodiments could have been described as providing advantages or being preferred over other embodiments or prior art implementations with respect to one or more desired characteristics, those of ordinary skill in the art recognize that one or more features or characteristics can becompromised to achieve desired overall system attributes, which depend on the specific application and implementation. These attributes can include, but are not limited to cost, strength, durability, life cycle cost, marketability, appearance, packaging, size, serviceability, weight, manufacturability, ease of assembly, etc. As such, to the extent any embodiments are described as less desirable than other embodiments or prior art implementations with respect to one or more characteristics, these embodiments are not outside the scope of the disclosure and can be desirable for particular applications.

[0517] With regard to the processes, systems, methods, heuristics, etc. described herein, it should be understood that, although the steps of such processes, etc. have been described as occurring according to a certain ordered sequence, such processes could be practiced with the described steps performed in an order other than the order described herein. It further should be understood that certain steps could be performed simultaneously, that other steps could be added, or that certain steps described herein could be omitted. In other words, the descriptions of processes herein are provided for the purpose of illustrating certain embodiments, and should in no way be construed so as to limit the claims.

[0518] Accordingly, it is to be understood that the above description is intended to be illustrative and not restrictive. Many embodiments and applications other than the examples provided would be apparent upon reading the above description. The scope should be determined, not with reference to the above description, but should instead be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled. It is anticipated and intended that future developments will occur in the technologies discussed herein, and that the disclosed systems and methods will be incorporated into such future embodiments. In sum, it should be understood that the application is capable of modification and variation.

[0519] All terms used in the claims are intended to be given their broadest reasonable constructions and their ordinary meanings as understood by those knowledgeable in the technologies described herein unless an explicit indication to the contrary in made herein. In particular, use of the singular articles such as “a,” “the,” “said,” etc. should be read to recite one or more of the indicated elements unless a claim recites an explicit limitation to the contrary.

[0520] The abstract of the disclosure is provided to allow the reader to quickly ascertain the nature of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing Detailed Description, it can be seen that various features are grouped together in various embodiments for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are expresslyrecited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby incorporated into the Detailed Description, with each claim standing on its own as a separately claimed subject matter.

[0521] While exemplary embodiments are described above, it is not intended that these embodiments describe all possible forms of the invention. Rather, the words used in the specification are words of description rather than limitation, and it is understood that various changes may be made without departing from the spirit and scope of the invention. Additionally, the features of various implementing embodiments may be combined to form further embodiments of the invention.LIST OF REFERENCE SIGNS10100, 10200, 10300, 10400, 10500, measurement application control unit10600, 10700, 10800, 10900measurement application control unit11000, 11100 measurement application control unit10101 , 10201 , 10301 , 10401 , 10501 text-based input interface10601 , 10701 , 10801 , 10901 text-based input interface11001 , 11101 text-based input interface10102, 10202, 10302, 10402, 10505 text-based user request10602, 10702-1 , 10702-2, 10802 text-based user request10902, 11002, 11105 text-based user request10103, 10203, 10303, 10403, 10503 pre-trained artificial-intelligence algorithm10603, 10703, 10803, 10903 pre-trained artificial-intelligence algorithm11003, 11103 pre-trained artificial-intelligence algorithm10104, 10204, 10304, 10404, 10504 response data10604, 10704, 10804, 10904, response data11004, 11104 response data10105, 10205, 10305, 10405, 10505 output interface10605, 10705, 10805, 10905, output interface11005, 11105 output interface10228 audio input interface10229 spoken language requests10230 speech recognition unit10231 text-based requests10335 large language model10438 user input interface10439 user input10440-1 - 10440-n button10441-1 , 10441-2 knob10442 touchscreen10443 user input10545 translator10546 translated text-based user request10648 pre-conditioner10649 pre-conditioning text-based request10752 usage response data10753 control response data10754 code generator10755 configuration and control command10858 complexity estimator10859 external pre-trained artificial-intelligence algorithm10860 predetermined threshold10861 user consent10862 user interface10863 request anonymizer10970 text-based user request generator10971 non-textual description11073 confidence estimator11074 confidence value11175 measurement application device11176 measurement application device controllerS1 - S3 method steps20100, 20200, 20300, 20400, 20500 measurement application processing device20600, 20700, 20800, 20900, 21000 measurement application processing device21100 measurement application processing device20101 , 20201 , 20301 , 20401 , 20501 text-based input interface20601 , 20701 , 20801 , 20901 text-based input interface21001 , 21101 text-based input interface20102, 20202, 20302, 20402, 20502-1 text-based user request20502-2, 20602, 20702, 20802 text-based user request20902, 21002, 21102 text-based user request20103, 20203, 20303, 20403, 20503 pre-trained artificial-intelligence algorithm20603, 20703, 20803, 20903 pre-trained artificial-intelligence algorithm21003, 21103 pre-trained artificial-intelligence algorithm20104, 20204, 20304, 20404, 20504 response data20604, 20704, 20804, 20904 response data21004, 21104 response data20105, 20205, 20305, 20405, 20505 output interface20605, 20705, 20805, 20905 output interface21005, 21105 output interface20228 audio input interface20229 spoken language requests20230 speech recognition unit20231 text-based requests20335 large language model20438 block diagram20540 set-up response data20541 control response data20542 code generator20543 configuration and control command20645 pre-conditioner20646 pre-conditioning text-based request20750 augmented text-based user request20751 confirmation20855 text-based user request generator20856 non-textual description20910, 21010 feedback interface20911 , 21011 measurement feedback data20912, 21012 feedback data analyzer20913, 21013 text-based feedback description21014 feedback output interface21160 measurement application21161-1 , 21161-2, 21161-3 measurement application deviceS21 - S23 method stepsOSC1 oscilloscopeHO housingMIP1 , MIP2, MIP3, MIP4 measurement inputSIP signal processingDISP1 displayOSC oscilloscopeVS vertical systemSC signal conditioningATT attenuatorDAC1 analog-to-digital converterAMP1 amplifierFI1 filterADC1 analog-to-digital converterTS triggering sectionAMP2 amplifierFI2 filterTS1 trigger systemHS horizontal systemPS processing sectionACP acquisition processing elementMEM memoryPPE post processing elementDISP display

Claims

CLAIMS1. Measurement application control unit comprising: a text-based input interface configured to receive text-based user requests regarding a measurement application comprising 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 based on the text-based user requests; and an output interface coupled to the pre-trained artificial-intelligence algorithm, and configured to output the response data.

2. Measurement application control unit according to claim 1 , further comprising an audio input interface configured to receive spoken language requests; and further comprising a speech recognition unit coupled to the audio input interface and the textbased input interface; wherein the speech recognition unit is configured to convert the spoken language requests into text-based requests, and to provide the text-based requests to the text-based input interface as text-based user requests.

3. 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 manuals regarding at least one measurement application device, datasheets regarding the at least one measurement application device, application notes regarding the at least one measurement application device, application notes regarding at least one measurement application, manuals of electronic devices, datasheets of electronic devices, application notes of electronic devices, articles regarding electronic circuits, online forum discussions regarding electronic circuits, and videos regarding electronic circuits.

4. Measurement application control unit according to any one of the preceding claims, wherein the pre-trained artificial-intelligence algorithm comprises a large language model based on at least one of a statistical model, a recurrent neuronal network, a Bidirectional Encoder Representations from Transformers model, and a Generative Pre-trained Transformer model.

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

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

7. Measurement application control unit according to any one of the preceding claims, further comprising a translator coupled to the text-based input interface, and the pre-trained artificial-intelligence algorithm; wherein the translator is configured to translate text-based user requests in a language that the pre-trained artificial-intelligence algorithm is not trained to operate on into translated text-based user requests in a language that the pre-trained artificial-intelligence algorithm is trained to operate on, and to provide the translated text-based user requests to the pre-trained artificial-intelligence algorithm.

8. Measurement application control unit according to any one of the preceding claims, further comprising a pre-conditioner coupled to the pre-trained artificial-intelligence algorithm; wherein the pre-conditioner is configured to provide a pre-conditioning text-based request to the pre-trained artificial-intelligence algorithm prior to the pre-trained artificial-intelligence algorithm operating on the text-based user requests.

9. 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 the usage of the at least one measurement application device, and to generate usage response data that comprises a respective explanation regarding the usage of the measurement application device.

10. 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 the control of the at least one measurement application device, and to generate control response data that comprises respective control commands regarding the usage of the measurement application device.11 . Measurement application control unit according to claim 10, further comprising a code generator that is coupled to or integrated into the pre-trained artificial-intelligence algorithm;wherein 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 a controller of the measurement application device.

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

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

14. Measurement application control unit according to claim 13, wherein the complexity estimator is configured to request a user consent via a user interface in the measurement application prior to providing one of the text-based user requests to the external pre-trained artificialintelligence algorithm.

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

16. Measurement application control unit according to any one of the preceding claims, further comprising a text-based user request generator configured to receive at least one of an image, a video, or a non-textual description of at least one of the at least one measurement application device, a device under test, and a measurement application setup; wherein the text-based user request generator is further configured to generate text-based user requests based on the at least one of the image or the video, and to provide the generated textbased user requests to the pre-trained artificial-intelligence algorithm.

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

18. Measurement application device comprising: a measurement application control unit according to any one of the preceding claims; anda measurement application device controller coupled to the measurement application control unit.

19. Computer-implemented method comprising: receiving text-based user requests regarding a measurement application comprising at least one measurement application device; generating response data regarding questions related to the measurement application based on the text-based user requests with a pre-trained artificial-intelligence algorithm; and outputting the response data.

20. Computer-implemented method according to claim 19, further comprising: receiving spoken language requests; converting the spoken language requests into text-based requests; and providing the text-based requests to the pre-trained artificial-intelligence algorithm as text-based user requests.

21. 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 manuals regarding the at least one measurement application device, datasheets regarding the at least one measurement application device, application notes regarding the at least one measurement application device, application notes regarding at least one measurement application, manuals of electronic devices, datasheets of electronic devices, application notes regarding electronic devices, articles regarding electronic circuits, online forum discussions regarding electronic circuits, and videos regarding electronic circuits.

22. Computer-implemented method according to any one of the preceding method-based claims, wherein the pre-trained artificial-intelligence algorithm comprises a large language model based on at least one of a statistical model, a recurrent neuronal network, a Bidirectional Encoder Representations from Transformers model, and a Generative Pre-trained Transformer model.

23. Computer-implemented method according to any one of the preceding method-based claims, further comprising: receiving user input;wherein the pre-trained artificial-intelligence algorithm generates the response data regarding questions related to the measurement application based on the text-based user requests and the user input.

24. Computer-implemented method according to claim 23, wherein the user input is provided via at least one of a button, a switch, a knob, a touchscreen, a keyboard, a mouse, a camera, and a gesture sensor.

25. Computer-implemented method according to any one of the preceding method-based claims, further comprising: translating text-based user requests in a language that the pre-trained artificial-intelligence algorithm is not trained to operate on into translated text-based user requests in a language that the pre-trained artificial-intelligence algorithm is trained to operate on; and providing the translated text-based user requests to the pre-trained artificial-intelligence algorithm.

26. Computer-implemented method according to any one of the preceding method-based claims, further comprising: providing a pre-conditioning text-based request to the pre-trained artificial-intelligence algorithm prior to the pre-trained artificial-intelligence algorithm operating on the text-based user requests.

27. Computer-implemented method according to any one of the preceding method-based claims, wherein the text-based user requests refer to the usage of the at least one measurement application device; and wherein usage response data is generated by the pre-trained artificial-intelligence algorithm that comprises a respective explanation regarding the usage of the measurement application device.

28. Computer-implemented method according to any one of the preceding method-based claims, wherein the text-based user requests refer to the control of the at least one measurement application device: wherein control response data is generated by the pre-trained artificial-intelligence algorithm that comprises respective control commands regarding the usage of the measurement application device.

29. Computer-implemented method according to claim 28, further comprising:generating configuration and control commands for the measurement application device in a predetermined control or programming language; and providing the generated configuration and control commands to a controller of the measurement application device.

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

31. Computer-implemented method according to any one of the preceding method-based claims, further comprising: estimating the complexity of the text-based user requests; and forwarding the text-based user requests to an external pre-trained artificial-intelligence algorithm if the estimated complexity is higher than a predetermined threshold.

32. Computer-implemented method according to claim 31 , further comprising: requesting a user consent via a user interface in the measurement application prior to providing one of the text-based user requests to the external pre-trained artificial-intelligence algorithm.

33. Computer-implemented method according to any one of the preceding claims 31 and 32, further comprising: providing the text-based user requests indirectly to the external pre-trained artificial-intelligence algorithm via a request anonymizer.

34. Computer-implemented method according to any one of the preceding method-based claims, further comprising: receiving at least one of an image, a video, or a non-textual description of at least one of the at least one measurement application device, a device under test, and a measurement application setup; generating text-based user requests based on the at least one of the image or the video; and providing the generated text-based user requests to the pre-trained artificial-intelligence algorithm.

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

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

37. Measurement application processing device comprising: a text-based input interface configured to receive text-based user requests 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 textbased user requests; and an output interface coupled to the pre-trained artificial-intelligence algorithm, and configured to output the response data.

38. Measurement application processing device according to claim 37, further comprising an audio input interface configured to receive spoken language requests; and further comprising a speech recognition unit coupled to the audio input interface and the textbased input interface; wherein the speech recognition unit is configured to convert the spoken language requests into text-based requests, and to provide the text-based requests to the text-based input interface as text-based user requests.

39. Measurement application processing device according to any one of the preceding claims 37 to 38, wherein the pre-trained artificial-intelligence algorithm is pre-trained using at least one of manuals regarding one or more measurement application devices or measurement applications, datasheets regarding one or more measurement application devices or measurement applications, application notes regarding one or more measurement application devices or measurement applications, datasheets of electronic devices, application notes of electronic devices, articles regarding electronic circuits, online forum discussions regarding electronic circuits, and videos regarding electronic circuits.

40. Measurement application processing device according to any one of the preceding claims 37 to 39, wherein the pre-trained artificial-intelligence algorithm comprises a large language model based on at least one of a statistical model, a recurrent neuronal network, a Bidirectional Encoder Representations from Transformers model, and a Generative Pre-trained Transformer model.

41. Measurement application processing device according to any one of the preceding claims 37 to 40, wherein the pre-trained artificial-intelligence algorithm is configured to receive text-based user requests regarding the setup of the measurement application, and to generate set-up response data that comprises a respective explanation regarding the setup of the measurement application.

42. Measurement application processing device according to claim 41 , wherein the pretrained artificial-intelligence algorithm is configured generate set-up response data that indicates at least one of which measurement application devices to use, and how to connect the measurement application devices to set-up the measurement application.

43. Measurement application processing device according to claim 42, wherein the pretrained artificial-intelligence algorithm is configured to generate a block diagram of the set-up of the measurement application.

44. Measurement application processing device according to any one of the preceding claims 37 to 43, wherein the pre-trained artificial-intelligence algorithm is further configured to generate control response data that comprises respective control commands for at least one measurement application device.

45. Measurement application processing device according to claim 44, further comprising a code generator that is coupled to or integrated into the pre-trained artificial-intelligence algorithm; wherein 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. Measurement application processing device according to any one of the preceding claims 37 to 45, further comprising a pre-conditioner coupled to the pre-trained artificial-intelligence algorithm; wherein the pre-conditioner is configured to provide a pre-conditioning text-based request to the pre-trained artificial-intelligence algorithm prior to the pre-trained artificial-intelligence algorithm operating on the text-based user requests.

47. Measurement application processing device according to any one of the preceding claims 37 to 46, wherein the pre-trained artificial-intelligence algorithm is configured to augment the text-based user requests and output the augmented text-based user requests via the output interface; wherein the pre-trained artificial-intelligence algorithm is configured to generate the response data after confirmation of the augmented text-based user requests by the user.

48. Measurement application processing device according to any one of the preceding claims 37 to 47, further comprising a text-based user request generator configured to receive at least one of an image, a video, and a non-textual description of a measurement application device, a device under test, or a measurement application set-up; wherein the text-based user request generator is further configured to generate text-based user requests based on the at least one of the image, the video, and the non-textual description, and to provide the generated text-based user requests to the pre-trained artificial-intelligence algorithm.

49. Measurement application processing device according to any one of the preceding claims 37 to 48, wherein the pre-trained artificial-intelligence algorithm is configured to receive text-based user requests regarding the maintenance of a measurement application device in a measurement application, and to generate maintenance response data that comprises a respective explanation regarding the maintenance of the respective measurement application device.

50. Measurement application processing device according to any one of the preceding claims 37 to 49, further comprising a warning generator configured to generate a warning for a user regarding configurations of a measurement application device that are detrimental to a predetermined measurement application.51 . Measurement application processing device according to any one of the preceding claims 37 to 50, further comprising a feedback interface configured to receive measurement feedback data; wherein the pre-trained artificial-intelligence algorithm is configured to generate a further set of response data based on the original text-based user request, and the received measurement feedback data.

52. Measurement application processing device according to claim 51 , further comprising a feedback data analyzer arranged between the feedback interface, and the pre-trained artificialintelligence algorithm;wherein the feedback data analyzer is configured to generate a text-based feedback description of the measurement feedback data, and to provide the text-based feedback description to the pre-trained artificial-intelligence algorithm.

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

54. Measurement application processing device according to any one of the preceding claims 51 - 53, further comprising a feedback output interface that is configured to output the measurement feedback data to a user; wherein the pre-trained artificial-intelligence algorithm is configured to generate a further set of response data based on the original text-based user request, and a further text-based user request received after the measurement feedback data is output to the user.

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

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

57. Measurement application comprising: a measurement application processing device according to any one of the preceding claims; and at least one measurement application device.

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

59. Computer-implemented method comprising: receiving text-based user requests regarding a measurement application;generating with a pre-trained artificial-intelligence algorithm response data regarding the measurement application based on the text-based user requests; and outputting the response data.

60. Computer-implemented method according to claim 59, further comprising: receiving spoken language requests; converting the spoken language requests into text-based requests; and providing the text-based requests to the text-based input interface as text-based user requests.

61. Computer-implemented method according to any one of the preceding method-based claims 59 to 60, wherein the pre-trained artificial-intelligence algorithm is pre-trained using at least one of manuals regarding one or more measurement application devices or measurement applications, datasheets regarding one or more measurement application devices or measurement applications, application notes regarding one or more measurement application devices or measurement applications, datasheets of electronic devices, application notes of electronic devices, articles regarding electronic circuits, online forum discussions regarding electronic circuits, and videos regarding electronic circuits.

62. Measurement application processing device according to any one of the preceding claims 59 to 61 , wherein the pre-trained artificial-intelligence algorithm comprises a large language model based on at least one of a statistical model, a recurrent neuronal network, a Bidirectional Encoder Representations from Transformers model, and a Generative Pre-trained Transformer model..

63. Computer-implemented method according to any one of the preceding method-based claims 59 to 62, wherein the pre-trained artificial-intelligence algorithm receives text-based user requests regarding the setup of the measurement application, and generates set-up response data that comprises a respective explanation regarding the setup of the measurement application.

64. Computer-implemented method according to claim 63, wherein the pre-trained artificialintelligence algorithm generates set-up response data that indicates which measurement application devices to use, and how to connect the measurement application devices to set-up the measurement application.

65. Computer-implemented method according to claim 64, wherein the pre-trained artificialintelligence algorithm generates a block diagram of the set-up of the measurement application.

66. Computer-implemented method according to any one of the preceding method-based claims 59 to 65, wherein the pre-trained artificial-intelligence algorithm generates control response data that comprises respective control commands for at least one measurement application device.

67. Computer-implemented method according to claim 66, further comprising generating configuration and control commands for the measurement application device in a predetermined control or programming language.

68. Computer-implemented method according to any one of the preceding method-based claims 59 to 67, further comprising providing a pre-conditioning text-based request to the pretrained artificial-intelligence algorithm prior to the pre-trained artificial-intelligence algorithm operating on the text-based user requests.

69. Computer-implemented method according to any one of the preceding method-based claims 59 to 68, wherein the pre-trained artificial-intelligence algorithm augments the text-based user requests, and outputs the augmented text-based user requests via the output interface; and wherein the pre-trained artificial-intelligence algorithm generates the response data after confirmation of the augmented text-based user requests by the user.

70. Computer-implemented method according to any one of the preceding method-based claims 59 to 69, further comprising: receiving at least one of an image or a video of a measurement application device, a device under test, or a measurement application set-up; and generating text-based user requests based on the at least one of the image or the video.

71. Computer-implemented method according to any one of the preceding method-based claims 59 to 70, wherein the pre-trained artificial-intelligence algorithm receives text-based user requests regarding the maintenance of a measurement application device in a measurement application, and generates maintenance response data that comprises a respective explanation regarding the maintenance of the respective measurement application device.

72. Computer-implemented method according to any one of the preceding method-based claims 59 to 71 , further comprising generating a warning for a user regarding configurations of a measurement application device that are detrimental to a predetermined measurement application.

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

74. Computer-implemented method according to claim 73, further comprising generating a text-based feedback description of the measurement feedback data, and providing the textbased feedback description to the pre-trained artificial-intelligence algorithm.

75. Computer-implemented method according to claim 74, wherein generating a text-based feedback description comprises identifying at least one of anomalies, and relevant measurement values, and relevant measurement waveform sections in raw measurement data provided in the measurement feedback data, and providing a respective text-based feedback description.

76. Computer-implemented method according to any one of the preceding claims 73 - 75, further comprising outputting the measurement feedback data to a user; wherein the pre-trained artificial-intelligence algorithm generates a further set of response data based on the original text-based user request, and a further text-based user request received after the measurement feedback data is output to the user.

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

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

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

Images