Compliance test system and compliance test method
Automatically determine compliance testing through machine learning circuits in the compliance testing system, solving the problem of difficulty in selecting compliance testing and achieving efficient and accurate compliance testing.
Patent Information
- Application Number
- CN202411616649.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2024-01-30
- Filing Date
- 2024-11-13
- Publication Date
- 2025-08-01
AI Technical Summary
Choosing the right compliance test is becoming increasingly difficult for electronic devices, especially mobile communication devices, and highly skilled personnel are required to conduct compliance tests to meet regulations and standards in different countries.
Using a compliance testing system, including a user interface, machine learning circuitry and database, uses machine learning circuitry to process user input, automatically determine applicable regulations and standards, and generate test data and rulesets to guide compliance testing.
Reduces the expertise required by users to choose compliance testing, achieves highly automated compliance testing, and improves testing efficiency and accuracy.
Smart Images
Figure CN120407715A_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present disclosure generally relate to a compliance testing system for testing an electronic device under test. Embodiments of the present disclosure also relate to a compliance testing method for testing an electronic device under test. Background Art
[0002] Certain types of electronic devices (such as mobile communication devices like smartphones) must be tested to ensure that the device under test complies with relevant regulations and standards of the corresponding country.
[0003] With the increasing diversification of electronic devices, communication standards, and regulations, it has become increasingly difficult to select appropriate compliance tests for a specific device under test.
[0004] Therefore, highly skilled personnel are required to select appropriate compliance tests, such as going through the admission process at the responsible national authority.
[0005] Therefore, a compliance testing system and a compliance testing method are needed to facilitate the selection of compliance tests for an electronic device under test. Summary of the Invention
[0006] The following summary of the present disclosure is intended to introduce different concepts in a simplified form, which will be further described in detail in the detailed description provided below. This summary is neither intended to represent the basic features of the present disclosure nor should this summary be used as an aid in determining the scope of the claimed subject matter.
[0007] Embodiments of the present disclosure provide a compliance testing system for testing an electronic device under test. The compliance testing system includes a user interface, a machine learning circuit, and a database. The database includes compliance testing data, where the compliance testing data includes information on regulations and standards for performing compliance tests on different devices under test. The user interface is configured to receive user input, where the user input includes text and / or voice related to the device under test to be tested. The machine learning circuit is configured to determine which regulations and standards apply to the device under test based on the user input. The machine learning circuit is configured to generate a rule set that describes the application of applicable regulations and standards to the device under test. The machine learning circuit is configured to generate test data based on the generated rule set, where the test data includes information on the compliance tests to be performed on the device under test in view of the applicable regulations and standards.
[0008] Hereinafter, the term "circuit" is understood to describe suitable hardware, or a combination of hardware and software configured to have a specific function.
[0009] The hardware may particularly include a CPU, GPU, FPGA, ASIC, or other types of electronic circuits.
[0010] The compliance testing system according to the present disclosure is based on the idea of facilitating the selection of an appropriate compliance test by providing a pre-trained machine learning circuit to select an appropriate compliance test based on user input.
[0011] Wherein, the user can formulate the user input in natural language, such as "I want to test a 5G smartphone that supports a frequency range between 3.3 GHz and 3.8 GHz".
[0012] In fact, the user can input the corresponding text via the user interface.
[0013] Alternatively or additionally, the user interface can have a speech-to-text function, enabling the user to formulate the user input as speech, which is then converted into the corresponding text by the user interface.
[0014] The machine learning circuit processes the user input through any suitable type of language processing technology, particularly through any suitable language processing technology known in the prior art, so as to extract input data regarding the device under test to be tested.
[0015] In fact, the machine learning circuit can be configured to extract keywords and / or key phrases from the user input, that is, the extracted input data can include keywords and / or key phrases.
[0016] In the above exemplary user input, the keywords and / or key phrases can be "smartphone", "5G", and "frequency range between 3.3 GHz and 3.8 GHz".
[0017] In fact, the machine learning circuit can also be configured to process text documents describing different regulations and standards, and can extract corresponding compliance test data from the text documents.
[0018] For example, the machine learning circuit can be configured to extract keywords and / or key phrases from text documents describing different regulations and standards, that is, the compliance test data can include keywords and / or key phrases related to different regulations and standards.
[0019] The machine learning circuit is pre-trained to match the extracted input data with a database, or rather, with the extracted compliance test data, so as to determine which regulations and standards are applicable to the device under test to be tested.
[0020] The determined rule set corresponds to the link, or rather, the mapping, between the applicable regulations and standards and the compliance tests to be performed on the device under test to be tested.
[0021] Therefore, the machine learning circuit automatically determines which compliance tests to perform on the device under test to be tested based on the generated rule set. As a result, the expertise required for the user to select the correct compliance tests is greatly reduced because the user only needs to describe the device under test to be tested, and the machine learning circuit automatically selects the correct compliance tests.
[0022] For example, the machine learning circuit may include at least one artificial neural network configured to perform the functions described above and below.
[0023] According to one aspect of the present disclosure, the test data includes information about the individual test steps and / or test sequences to be performed on the device under test in view of the applicable regulations and standards. In other words, the machine learning circuit can be configured to automatically determine the specific compliance tests and the corresponding measurement steps required for the compliance tests. As a result, the expertise required to select the compliance tests is further reduced.
[0024] In one embodiment of the present disclosure, the test data includes a list of applicable regulations and standards. Thus, the user can be automatically informed of the regulations and standards relevant to testing a particular device under test. For example, the user can use this information to verify the compliance tests selected by the machine learning circuit.
[0025] According to another aspect of the present disclosure, the test data includes machine-readable instructions for at least one test instrument to perform the compliance tests. In fact, the machine-readable instructions can be configured such that at least one test instrument can automatically set its operating parameters for performing the compliance tests. Alternatively or additionally, the machine-readable instructions can be configured such that at least one test instrument is controlled to automatically perform the compliance tests. Therefore, the compliance test system according to the present disclosure allows highly automated compliance testing, which further reduces the expertise required by the user.
[0026] In another embodiment of the present disclosure, the compliance test system further includes a visualization circuit, where the visualization circuit is configured to generate visualization data based on the test data. Thus, the test data can be displayed to the user in an illustrative manner.
[0027] The visualization data can be displayed on a display, particularly on the display of a test instrument, an external display, or the display of a computing device, such as a personal computer, laptop, smartphone, tablet, or another type of smart device.
[0028] Another aspect of the present disclosure provides that the machine learning circuit is configured to determine whether the user input is sufficient to generate a rule set and / or to determine which regulations and standards apply to the device under test (DUT) to be tested. In other words, the machine learning circuit automatically determines whether the user input contains sufficient information about the DUT to determine the applicable regulations and standards and / or to determine the rule set.
[0029] For example, the user input may include the query "I want to test a 5G-enabled smartphone". This information may not be sufficient because different countries may have different regulations regarding the allowed frequency ranges associated with 5G standards.
[0030] The machine learning circuit may be configured to generate a user query if it determines that the user input is insufficient, where the generated user query queries for information about the missing data in the user input. In other words, the machine learning circuit may be configured to automatically determine what additional information is needed on the DUT to determine the applicable regulations and standards and / or to determine the rule set. The machine learning circuit may also be configured or rather, pre-trained to automatically query the user for the missing information.
[0031] In the example given above, the user query may be "Please enter the specified country where the smartphone is to be deployed".
[0032] The visualization circuit described above may be configured to generate visualization data associated with the generated user query, and the visualization data may be displayed on a display.
[0033] In another embodiment of the present disclosure, the user query is formulated in natural language. In other words, the compliance testing system is configured to have a conversation with the user in natural language, which helps the user understand what further information is needed.
[0034] For example, the compliance testing system may be configured to initiate a chat with the user, where the generated user query is presented to the user in the chat. The user can directly reply in the chat, for example, by entering the requested additional information.
[0035] In fact, the machine learning circuit may generate further user queries until the user has entered all the information required to determine the applicable regulations and standards and / or to determine the rule set.
[0036] One aspect of the present disclosure provides that the machine learning circuit is configured to determine whether the compliance test data is sufficient to generate a rule set. In other words, the machine learning circuit may be configured to automatically determine whether the existing regulations and standards applicable to the DUT to be tested include sufficient information to determine the compliance tests to be performed.
[0037] For example, existing regulations and standards may not cover all aspects of the performance of newly developed devices under test. In such cases, the machine learning circuit can determine that the compliance test data is insufficient to generate a rule set.
[0038] According to another aspect of the present disclosure, the machine learning circuit is configured to generate a user message if it determines that the compliance test data is insufficient to generate a rule set, where the user message includes information about the missing data in the compliance test data. Thus, the user can be informed that the existing regulations and standards do not cover all the information required to determine the compliance tests to be performed. In addition, the user can be informed of what information is missing from the existing regulations and standards.
[0039] In another embodiment of the present disclosure, the user message includes information about the authority responsible for the relevant regulations and standards. Thus, the user is informed of which authority to contact regarding the regulations and standards applicable to the device under test.
[0040] Hereinafter, the term "authority" is understood to refer to an institution responsible for formulating regulations and standards for different aspects of the performance of the device under test in the corresponding country.
[0041] For example, in the United States, the authority that administers the regulations related to radio equipment is the Federal Communications Commission (FCC), while in the European Union, the corresponding regulations are administered by the national authorities organized by the European Regulators Group (ERG).
[0042] In particular, the user message can include a pre-formulated query to the authority. In fact, the pre-formulated query can include a query for the missing data or information in the existing regulations and standards. Thus, the user can obtain the necessary additional standard and regulation information from the responsible authority.
[0043] According to another aspect of the present disclosure, the user interface is configured to receive feedback data, where the feedback data includes information about errors in the rule set and / or the test data, and where the machine learning circuit is configured to adjust its operating parameters to minimize the errors. In other words, the machine learning circuit can be trained or retrained based on the feedback data, thereby improving the accuracy of the determined regulations and standards applicable to the device under test, the accuracy of the generated rule set, and / or the accuracy of the generated test data.
[0044] For example, the feedback data can be provided by the user.
[0045] As another example, the feedback data can be provided by an expert or a group of experts. For example, it can also be envisaged that the determined regulations and standards applicable to the device under test, the determined rule set, and / or the determined test data can be accessed via a cloud computing network, in particular together with the corresponding user input, where multiple experts can access this information and provide feedback data. In this way, the machine learning circuit can be trained or retrained in a test facility including a compliance test system without the presence of an expert.
[0046] Another aspect of the present disclosure provides that the compliance test system further includes at least one test instrument, where the at least one test instrument is configured to determine, based on the test data, whether at least one test instrument is capable of performing the compliance test to be performed on the device under test. In other words, the test instrument can check whether at least one test instrument meets the requirements of the compliance test to be performed, such as the necessary frequency analysis range, the necessary frequency generator range, the necessary bandwidth, the necessary sampling rate, the necessary error correction ability, the target measurement accuracy, etc. Thus, it can be ensured that the selected compliance test can actually be performed by at least one test instrument.
[0047] The machine learning circuit can be configured to generate a user query if it is determined that at least one test instrument is unable to perform the test, where the user query includes information about the necessary adjustments to the test setup and / or the necessary changes to the compliance test to be performed.
[0048] Therefore, the user can be informed of the necessary changes to the test setup including at least one test instrument. For example, the user query can include information about the necessary additional test instruments or the necessary replacement of at least one test instrument.
[0049] Alternatively or additionally, the user can be informed of the necessary changes to the compliance test to be performed, such as a reduction in the frequency range to be tested, a reduction in the target measurement accuracy, etc.
[0050] According to one aspect of the present disclosure, the compliance test system further includes at least one test instrument, where the at least one test instrument is configured to perform the compliance test to be performed on the device under test to obtain measurement data, and where the machine learning circuit is configured to generate a test report based on the measurement data. Thus, the user is assisted in generating a test report for the performed compliance test.
[0051] In fact, the machine learning circuit can be configured to generate the test report in a format required by the authority responsible for the applicable regulations and standards. Thus, for example, the user is assisted when providing the measurement data of the access procedure of the device under test to the responsible authority.
[0052] In one embodiment of the present disclosure, the test report is formulated in natural language. Thus, the test report is presented to the user in an easy-to-understand manner.
[0053] Embodiments of the present disclosure also provide a compliance testing method for testing a DUT (Device Under Test). The compliance testing method includes the following steps:
[0054] - Receiving user input through a user interface, where the user input includes text and / or voice related to the DUT to be tested;
[0055] - Determining, by a machine learning circuit, based on the user input and based on compliance testing data, which regulations and standards apply to the DUT to be tested, where the compliance testing data includes information on regulations and standards for performing compliance testing on different DUTs;
[0056] - Generating, by the machine learning circuit, a rule set that describes applying the applicable regulations and standards to the DUT to be tested; and
[0057] - Generating, by the machine learning circuit, test data based on the generated rule set, where the test data includes information on the compliance tests to be performed on the DUT in view of the applicable regulations and standards.
[0058] In fact, the above compliance testing system can be configured to execute the compliance testing method.
[0059] For the advantages and further attributes of the compliance testing method, please refer to the above explanations regarding the compliance testing system, which also apply to the compliance testing method, and vice versa. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] When taken in conjunction with the accompanying drawings, the above aspects of the claimed subject matter and many attendant advantages will become more readily appreciated, in which:
[0061] - Figure 1 Schematically shows a compliance testing system according to the present disclosure;
[0062] - Figure 2 Shows a flowchart of a compliance testing method according to the present disclosure;
[0063] - Figure 3 Shows in more detail Figure 1 the machine learning circuit of the compliance testing system; and - Figure 4 Shows a further flowchart of a compliance testing method according to the present disclosure. DETAILED DESCRIPTION
[0064] The following detailed description is presented in conjunction with the accompanying drawings, in which like numerals refer to like elements, and the detailed description is intended as a description of various embodiments of the disclosed subject matter and is not intended to represent the only embodiments. Each embodiment described in this disclosure is provided only as an example or illustration and should not be construed as being preferred or advantageous over other embodiments. The illustrative examples provided herein are not intended to be exhaustive or to limit the claimed subject matter to the precise forms disclosed.
[0065] For the purposes of this disclosure, the phrase "at least one of A, B, and C" refers, for example, to (A), (B), (C), (A and B), (A and C), (B and C), or (A, B, and C), including all further possible combinations when more than three elements are listed. In other words, the term "at least one of A and B" generally refers to "A and / or B", i.e., A alone, B alone, or A and B.
[0066] Figure 1 A compliance test system 10 for testing the compliance of a device under test 12 is schematically shown.
[0067] Generally, the device under test 12 can be any type of electronic device configured to generate and / or process signals, particularly radio frequency (RF) signals.
[0068] For example, the device under test 12 can be a mobile communication device, such as a smartphone, a tablet computer, an RF antenna, a base station, etc.
[0069] As another example, the device under test 12 can be an electronic computing device, such as a personal computer, a laptop computer, a chip (such as a central processing unit, a graphics processing unit), a gaming console, or any other type of computer device.
[0070] In another example, the device under test 12 can be a wireless communication device, such as a WLAN router, a handheld radio, a fixed radio, etc.
[0071] As another example, the device under test 12 can be a radar system (particularly an automotive radar system) or a LiDAR system (particularly an automotive LiDAR system).
[0072] The compliance test system 10 further includes at least one test instrument 14 and a computer device 16.
[0073] Generally, at least one test instrument 14 is configured to perform a compliance test on the device under test 12.
[0074] The type of at least one test instrument 14 can depend on the type of the device under test 12 to be tested.
[0075] For example, at least one test instrument 14 can be or include an oscilloscope, a spectrum analyzer, a signal analyzer, a vector network analyzer, a mobile communication tester, a power meter, a signal generator such as an arbitrary waveform generator, an over-the-air test system, a radar test system, a LiDAR test system, etc.
[0076] However, it should be understood that the compliance test system can include any other suitable type of test instrument.
[0077] Hereinafter, without limiting generality, it is assumed that the compliance test system 10 includes one test instrument 14.
[0078] The computer device 16 is connected to the test instrument 14 in a signal transmission manner, that is, through any suitable type of wired or wireless connection.
[0079] For example, the computer device 16 can be a personal computer, a laptop, a smartphone, a tablet computer, or any other suitable type of intelligent device.
[0080] The computer device 16 can include or be connected to peripheral input devices, such as a keyboard, a computer mouse, a microphone, a touchpad, etc.
[0081] The computer device 16 includes a user interface 18, a machine learning circuit 20, a memory 22, and a visualization circuit 24.
[0082] The memory 22 includes a database of compliance test data, where the compliance test data includes information on regulations and standards for performing compliance tests on different devices under test.
[0083] It should be noted that the database can alternatively or additionally be partially or fully integrated into another computing device connected to the computer device 16, such as a server.
[0084] In particular, the other computing device can be connected to the computer device 16 via the Internet (via a wide area network, a local area network) or another suitable network.
[0085] Hereinafter, an exemplary case where the database is integrated into the memory 22 of the computer device 16 is described without limiting generality.
[0086] Generally speaking, the compliance test system 10 is configured to assist a user in selecting and performing appropriate compliance tests for testing the device under test 12.
[0087] In fact, the compliance test system 10 is configured to perform the compliance test method described below with reference to Figures 2 to 4 the described compliance test method.
[0088] Figure 2A flowchart of a compliance testing method is shown, where Figure 2 The left side marked "User" indicates steps performed by the user, while the right side marked "Compliance Testing System" indicates steps performed by the compliance testing system 10.
[0089] The user provides user input related to the device under test 12 to the user interface 18, i.e., the user input is received by the user interface 18 (step S1).
[0090] In fact, the user input can be received in text form and / or voice form.
[0091] If the user input is received in voice form, the user interface 18 can have a speech-to-text function, enabling the user to formulate the user input as speech, which is then converted to the corresponding text by the user interface 18.
[0092] Any suitable speech recognition technology known in the prior art can be used therein.
[0093] Therefore, the user input is received in text form or converted to text form.
[0094] The user interface 18 is configured to forward the user input (i.e., the user input in text form) to the machine learning circuit 20.
[0095] As Figure 3 shown, the machine learning circuit 20 includes a text processing sub-circuit 26 and an analysis sub-circuit 28. The former is configured to receive the user input in text form, and the latter is connected to the text processing sub-circuit 26.
[0096] The text processing sub-circuit 26 and / or the analysis sub-circuit 28 can be or include an artificial neural network configured to perform the functions described below.
[0097] The text processing sub-circuit 26 is configured to process the user input by any suitable type of language processing technology (in particular, any suitable language processing technology known in the prior art), so as to extract input data regarding the device under test 12 to be tested.
[0098] For example, the text processing sub-circuit 26 can be configured to extract keywords and / or key phrases from the user input, i.e., the extracted input data can include keywords and / or key phrases.
[0099] In a specific example, the user can input "I want to test a handheld radio for civilian communication". In this case, the extracted input data can include keywords, or rather, the key phrases "handheld radio" and "civilian communication".
[0100] The text processing sub - circuit 26 is configured to forward the extracted input data (in particular, the extracted keywords and / or key phrases) to the analysis sub - circuit 28.
[0101] The analysis sub - circuit 28 is configured to receive the input data extracted by the text processing sub - circuit 26 and the compliance test data from the memory 22.
[0102] The analysis sub - circuit 28 determines which regulations and standards apply to the device under test 12 to be tested (step S2) based on the user input and the compliance test data.
[0103] In fact, the analysis sub - circuit 28 is pre - trained to determine which regulations and standards apply to the device under test 12 based on the user input and based on the compliance test data.
[0104] More precisely, the analysis sub - circuit 28 is pre - trained to determine which regulations and standards apply to the device under test 12 based on the input data extracted from the user input and based on the compliance test data.
[0105] In fact, the analysis sub - circuit 28 can match the extracted keywords and / or key phrases with the compliance test data to determine which regulations and standards apply to the device under test 12.
[0106] The information contained in the user input may not be sufficient to determine the regulations and standards applicable to the device under test 12 and / or to select an appropriate compliance test for the device under test 12.
[0107] Therefore, the machine learning circuit 20 or more precisely, the analysis sub - circuit 28 can determine whether the user input is sufficient to determine the regulations and standards applicable to the device under test 12 and / or to select an appropriate compliance test for the device under test 12 based on the user input and based on the compliance test data (step S3).
[0108] In fact, the analysis sub - circuit 28 can be pre - trained to determine whether the user input is based on the input information extracted from the user input and based on the compliance test data.
[0109] If the analysis sub - circuit 28 determines that the user input is insufficient, the analysis sub - circuit 28 can automatically determine what additional information is needed about the device under test to determine the applicable regulations and standards and / or to determine the rule set.
[0110] In the exemplary user input given above, “I want to test a handheld radio for civilian communication”, the analysis sub - circuit 28 can determine that the user input is insufficient because the user input neither states one or more countries in which the handheld radio should be utilized nor the frequency range in which the handheld radio will be used.
[0111] The analysis sub - circuit 28 can generate a user query that queries for information determined to be missing from the user input, and the user query can be visualized by the visualization circuit 24 on the display 30.
[0112] In fact, a chat including the user query can be opened and displayed on the display 30, where the user query can be formulated in natural language.
[0113] In the example given above, the user query can be a text message stating "Please specify the country of intended use and the supported frequency range."
[0114] Then, the user can provide the missing information via the user interface 18 (step S4), and the machine - learning circuit 20 can continue to determine the applicable regulations and standards, rule sets, and test data, as described above and below.
[0115] In fact, the analysis sub - circuit 28 can continue to generate user queries for missing information until the user has provided all the necessary information about the device under test 12.
[0116] The machine - learning circuit 20, or rather, the analysis sub - circuit 28, can also determine whether the compliance test data is sufficient to generate a rule set, i.e., whether the existing regulations and standards cover all relevant aspects of performing a compliance test on the device under test 12 (step S5).
[0117] If it is determined that the compliance test data is not sufficient to generate a rule set, the analysis sub - circuit 28 can generate a user message, where the user message includes information about the data missing from the compliance test data.
[0118] The user message can be formulated in natural language and can be displayed on the display 30.
[0119] For example, the user message can include information about which regulations and standards apply to the device under test 12, and / or what information is missing from the existing regulations and standards.
[0120] Alternatively or additionally, the user message can include information about the authority responsible for the relevant regulations and standards.
[0121] In fact, the user message can include a pre - formulated query to the authority that includes the data or information missing from the existing regulations and standards.
[0122] Based on the user message, the user can contact the authority responsible for the regulations and standards applicable to the device under test 12 (step S6).
[0123] If both the user input and the compliance test data are sufficient, the analysis sub-circuit 28 can generate a rule set that describes how to apply the applicable regulations and standards to the device under test 12 (step S7).
[0124] Generally speaking, the rule set provides a link, or rather a mapping, between the applicable regulations and standards and the compliance tests to be performed on the device under test 12.
[0125] For example, the rule set can include information about the types of operating parameters to be tested in view of the applicable regulations and standards, information about the ranges of operating parameters to be tested in view of the applicable regulations and standards, and / or information about the specific types of compliance tests to be performed in view of the applicable regulations and standards.
[0126] The analysis sub-circuit 28 generates test data based on the generated rule set (step S8).
[0127] Generally speaking, the test data includes information about the compliance tests to be performed on the device under test 12 in view of the regulations and standards applicable to the device under test 12.
[0128] In fact, the test data can include the individual test steps of the compliance tests to be performed on the device under test and / or the sequence of compliance tests to be performed on the device under test 12 in view of the regulations and standards applicable to the device under test 12.
[0129] In particular, the compliance tests to be performed can be automatically optimized by the machine learning circuit 20 or rather by the analysis sub-circuit 28 such that the compliance tests to be performed are an optimal test set.
[0130] For example, the machine learning circuit 20 or rather the analysis sub-circuit can consider exclusion criteria to determine the order of the individual compliance tests, where the exclusion criteria are related to the interdependencies of the individual tests.
[0131] In a specific example, if the device under test 12 passes certain compliance tests related to the 5G sub-protocol, the corresponding 4G sub-protocol does not need to be tested because they have been automatically passed by the device under test 12.
[0132] Alternatively or additionally, the test data can include machine-readable instructions for at least one test instrument 14. Based on the machine-readable instructions, the test instrument 14 can be controlled to automatically perform the compliance tests selected by the analysis sub-circuit 28.
[0133] Optionally, the test data can also include a list of the regulations and standards applicable to the device under test 12.
[0134] In a specific example, a user can input the information "mobile phone, size 12″, supported frequency bands, and RAT: LTE band 89, sales region: US".
[0135] In this case, the test data can include the information that "the device under test with the above parameters must perform TRP measurements according to the CTIA test plan and SAR tests according to the IEC-1 low-medium-high frequency channels".
[0136] The test data generated by the analysis sub-circuit 28 is forwarded to the visualization circuit 24.
[0137] The visualization circuit 24 is configured to generate visualization data associated with the test data generated by the analysis sub-circuit 28.
[0138] In Figure 1 the illustrated exemplary embodiment, the visualization data can be displayed on an external display 30 provided separately from the computer device 16 and the test instrument 14.
[0139] However, it is also conceivable that the display 30 can be integrated into the computer device 16 or the test instrument 14.
[0140] The user can request further details about the compliance tests to be performed and / or applicable regulations and standards by providing corresponding user inputs to the user interface 18 (step S9).
[0141] The analysis sub-circuit 28 can update the test data according to the user's request, and the updated test data can be displayed on the display 30.
[0142] Among them, the machine learning circuit 20, particularly the analysis sub-circuit 28, has been pre-trained to perform the above functions.
[0143] However, the machine learning circuit 20, particularly the analysis sub-circuit 28, can be further trained and / or re-trained by providing feedback data.
[0144] In fact, the feedback data can be received from the user, an expert, or a group of experts via the user interface 18.
[0145] For example, the feedback data can include information about errors in the rule set and / or the test data.
[0146] The machine learning circuit 20, particularly the analysis sub-circuit 28, can adjust its operating parameters or weighting factors to minimize the error (step S10).
[0147] Therefore, the machine learning circuit 20, or rather the analysis sub-circuit 28, can be trained or re-trained by reinforcement learning.
[0148] The test data can also be forwarded to the test instrument 14, especially if the test data includes machine-readable instructions.
[0149] Figure 4 A flowchart showing corresponding further steps of the compliance testing method is shown, where Figure 4 The left side labeled "machine learning circuit" indicates steps performed by the machine learning circuit 20, while the right side labeled "test instrument" indicates steps performed by the test instrument 14 or by measurement software or test sequencer associated with the test instrument 14.
[0150] Hereinafter, without loss of generality, it is assumed that the test instrument 14 performs the corresponding steps described below.
[0151] The machine learning circuit 20 provides the test data to the test instrument 14 (step S11).
[0152] The test instrument 14 determines, based on the test data, whether the test instrument 14 is capable of performing a compliance test associated with the test data on the device under test 12 (step S12).
[0153] For example, the test instrument 14 can evaluate whether the test instrument 14 meets the requirements of the compliance test related to the operating parameters of the test instrument 14, such as the necessary frequency analysis range, the necessary frequency generator range, the necessary bandwidth, the necessary sampling rate, the necessary error correction ability, the target measurement accuracy, etc.
[0154] If the test instrument 1 determines that the test instrument 14 is unable to perform the compliance test, a corresponding message can be sent by the test instrument 14 to the machine learning circuit 20, where the message includes information about the reason why the compliance test cannot be performed.
[0155] For example, the message sent by the test instrument 14 can include information about insufficient operating parameter ranges or other limitations of the test instrument 14.
[0156] A user query can be generated by the machine learning circuit 20, especially by the analysis sub-circuit 28, and the user query can be displayed on the display 30 (step S13).
[0157] The user query can include information about the necessary adjustments to the test setup and / or the necessary changes to the compliance test to be performed.
[0158] For example, the user query can include information about the necessary changes to the test setup including the test instrument 14, such as the necessary additional test instruments or the necessary replacement of the test instrument 14.
[0159] Alternatively or additionally, the user may be informed of the necessary changes to the compliance test to be performed, such as a reduction in the frequency range to be tested, a decrease in the target measurement accuracy, etc.
[0160] In fact, the user may be required to confirm the necessary changes to the compliance test to be performed, and the corresponding changed compliance test can then be executed by the test instrument 14, especially automatically.
[0161] It should be noted that the machine learning circuit 20 or rather, the analysis sub - circuit 28 can be pre - trained to determine based on the test data whether the test instrument 14 is capable of performing the compliance test associated with the test data on the device under test 12.
[0162] In this case, the user can input the corresponding relevant data about the test instrument 14 via the user interface 18.
[0163] If data about the test instrument 14 is missing to evaluate whether the test instrument 14 is capable of performing the compliance test, a corresponding user query can be generated by the analysis sub - circuit 28, prompting the user to input the missing data about the test instrument 14.
[0164] If the test instrument 14 determines that it is capable of performing the compliance test, the test instrument 14 can evaluate the test sequence included in the test data, i.e., the test sequence of the selected compliance test (step S14).
[0165] For example, the test instrument 14 may determine that another order of individual tests may be more optimal, there are redundant test steps in the test sequence, one or more test steps should be repeated, or there are missing test steps in the test sequence.
[0166] The test instrument 14 can send a corresponding message to the machine learning circuit 20, where the message includes information about the proposed adjustment of the test sequence.
[0167] The machine learning circuit 20 or rather, the analysis sub - circuit 28 can generate a corresponding user query asking the user to confirm the adapted test sequence, and the user query can be displayed on the display 30.
[0168] The user can confirm or reject the proposed adjustment by providing a corresponding user input to the user interface 18.
[0169] If the user confirms the proposed adjustment, the corresponding feedback data provided to the machine learning circuit 20 can be generated by the test instrument 14.
[0170] In a specific example, if the test data includes a test sequence with multiple test steps, the feedback data may include information about errors regarding the order of individual steps in the test sequence, about test steps that can be omitted in the test sequence, and / or about missing test steps in the test sequence.
[0171] The machine learning circuit 20, and in particular the analysis sub-circuit 28, can adjust its operating parameters, or rather its weighting factors, based on the feedback data.
[0172] The compliance test can be performed by the test instrument 14 based on the test data to obtain measurement data (step S15).
[0173] In particular, the compliance test can be automatically performed based on machine-readable instructions included in the test data.
[0174] The measurement data can be transmitted to the machine learning circuit 20, or rather to the analysis sub-circuit 28, and the analysis sub-circuit 28 can generate a test report based on the measurement data (step S16).
[0175] The test report can be visualized on the display 30 by the visualization circuit 24, in particular in natural language.
[0176] Alternatively or additionally, the test report can be generated in a format required by an authority responsible for the regulations and standards applicable to the device under test 12.
[0177] For example, the user can request further details and / or another format of the test report via the user interface 18, and the analysis sub-circuit 28 can adjust the test report according to the user's request.
[0178] In other words, the user can customize the test report by providing corresponding user input to the user interface 18.
[0179] Certain embodiments disclosed herein, and in particular the various modules and / or units, utilize circuits (e.g., one or more circuits) to implement the standards, protocols, methods, or techniques disclosed herein, operably couple two or more components, generate information, process information, analyze information, generate signals, encode / decode signals, convert signals, transmit and / or receive signals, control other devices, etc. Any type of circuit can be used.
[0180] In one embodiment, among other aspects, the circuit includes one or more computing devices, such as a processor (e.g., a microprocessor), a central processing unit (CPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a system on a chip (SoC), etc., or any combination thereof, and may include discrete digital or analog circuit elements or electronic devices, or a combination thereof. In one embodiment, the circuit includes a hardware circuit implementation (e.g., an analog circuit implementation, a digital circuit implementation, etc., and combinations thereof).
[0181] In one embodiment, the circuit includes a combination of a circuit and a computer program product having software or firmware instructions stored on one or more computer-readable memories that work together to cause the device to perform one or more of the protocols, methods, or techniques described herein. In one embodiment, the circuit includes a circuit that requires software, firmware, etc. to operate, such as, for example, a microprocessor or a portion of a microprocessor. In one embodiment, the circuit includes one or more processors or portions thereof and accompanying software, firmware, hardware, etc.
[0182] This application may refer to quantities and numbers. Unless otherwise specified, these quantities and numbers should not be considered restrictive, but rather examples of possible quantities or numbers associated with this application. Also in this regard, this application may use the term "plurality" to refer to a quantity or number. In this regard, the term "plurality" means any number greater than one, e.g., two, three, four, five, etc. The terms "about", "approximately", "close to", etc. indicate plus or minus 5% of the stated value.
Claims
1. A compliance testing system for testing a device under test (DUT), the compliance testing system comprising a user interface, a machine learning circuit, and a database, Among them, The database includes compliance testing data, where the compliance testing data includes information on regulations and standards for performing compliance tests on different devices under test. Wherein, the user interface is configured to receive user input, where the user input includes text and / or speech related to the device under test to be tested. Wherein, the machine learning circuit is configured to determine, based on the user input, which regulations and standards apply to the device under test to be tested. Wherein, the machine learning circuit is configured to generate a rule set that describes applying the applicable regulations and standards to the device under test to be tested, and Wherein, the machine learning circuit is configured to generate test data based on the generated rule set, where the test data includes information on compliance tests to be performed on the device under test in view of the applicable regulations and standards.
2. The compliance testing system according to claim 1, wherein, The test data includes information on individual test steps and / or test sequences to be performed on the device under test in view of the applicable regulations and standards.
3. The compliance testing system according to claim 1, wherein The test data includes a list of the applicable regulations and standards.
4. The compliance testing system according to claim 1, wherein, The test data includes machine-readable instructions for at least one test instrument for performing the compliance test.
5. The compliance testing system according to claim 1, the compliance testing system further comprising a visualization circuit, where the visualization circuit is configured to generate visualization data based on the test data.
6. The compliance testing system according to claim 1, wherein, The machine learning circuit is configured to determine whether the user input is sufficient to generate the rule set and / or to determine which regulations and standards apply to the device under test to be tested.
7. The compliance testing system according to claim 6, wherein, The machine learning circuit is configured to generate a user query if it determines that the user input is insufficient, where the generated user query queries for information on the missing data in the user input.
8. The compliance testing system according to claim 7, wherein, The user query is formulated in natural language.
9. The compliance testing system according to claim 1, wherein The machine learning circuit is configured to determine whether the compliance testing data is sufficient to generate the rule set.
10. The compliance testing system according to claim 9, wherein, The machine learning circuit is configured to generate a user message if it determines that the compliance testing data is insufficient to generate the rule set, where the user message includes information on the missing data in the compliance testing data.
11. The compliance testing system according to claim 10, wherein, The user message includes information on the authority responsible for the relevant regulations and standards.
12. The compliance testing system according to claim 11, wherein, The user message includes a pre-formulated query to the authority.
13. The compliance testing system according to claim 1, wherein, The user interface is configured to receive feedback data, where the feedback data includes information on errors in the rule set and / or the test data, and where the machine learning circuit is configured to adjust its operating parameters to minimize the errors.
14. The compliance testing system according to claim 1, wherein The compliance testing system further comprises at least one test instrument, where the at least one test instrument is configured to determine, based on the test data, whether the at least one test instrument is capable of performing the compliance test to be performed on the device under test.
15. The compliance testing system according to claim 14, wherein, The machine learning circuit is configured to generate a user query if it is determined that the at least one test instrument is unable to perform the test, wherein the user query includes information about necessary adjustments to the test setup and / or necessary changes to the compliance test to be performed.
16. The compliance testing system according to claim 1, wherein, The compliance test system further includes at least one test instrument, wherein the at least one test instrument is configured to perform the compliance test to be performed on the device under test to obtain measurement data, and the machine learning circuit is configured to generate a test report based on the measurement data.
17. The compliance testing system according to claim 16, wherein, The test report is formulated in natural language.
18. A method for testing the compliance of an electronic device under test, the method comprising the steps of: - receiving user input through a user interface, wherein the user input includes text and / or voice related to the device under test to be tested; - determining, by a machine learning circuit, based on the user input and based on the compliance test data, which regulations and standards apply to the device under test to be tested, wherein the compliance test data includes information about regulations and standards for performing compliance tests on different devices under test; - generating, by the machine learning circuit, a rule set that describes the application of applicable regulations and standards to the device under test to be tested; and - generating, by the machine learning circuit, test data based on the generated rule set, wherein the test data includes information about the compliance test to be performed on the device under test in view of the applicable regulations and standards.