CN112908357A - Instrument sound testing method and device, testing equipment and storage medium - Google Patents
Instrument sound testing method and device, testing equipment and storage medium Download PDFInfo
- Publication number
- CN112908357A CN112908357A CN202110070561.9A CN202110070561A CN112908357A CN 112908357 A CN112908357 A CN 112908357A CN 202110070561 A CN202110070561 A CN 202110070561A CN 112908357 A CN112908357 A CN 112908357A
- Authority
- CN
- China
- Prior art keywords
- test
- instrument
- sound data
- tested
- type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 623
- 238000010801 machine learning Methods 0.000 claims abstract description 91
- 238000000034 method Methods 0.000 claims abstract description 53
- 238000012549 training Methods 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 9
- 238000012827 research and development Methods 0.000 abstract description 11
- 238000004422 calculation algorithm Methods 0.000 description 24
- 238000010586 diagram Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000013461 design Methods 0.000 description 8
- 230000004044 response Effects 0.000 description 6
- 238000013515 script Methods 0.000 description 6
- 239000000243 solution Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 206010063385 Intellectualisation Diseases 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The embodiment of the invention provides a method and a device for testing instrument sound, testing equipment and a storage medium. Applied to a test device, the method comprising: acquiring and analyzing an instrument test case to obtain an instrument to be tested indicated by the instrument test case and test parameters corresponding to the instrument to be tested; sending the test parameters to the instrument to be tested to obtain test sound data output by the instrument to be tested based on the test parameters; inputting test sound data into the trained machine learning model to obtain a test result output by the trained machine learning model; and outputting a test result. According to the invention, the test sound data output by the instrument to be tested is tested through the machine learning model, so that the automatic test of the vehicle-mounted instrument in various voice output scenes is realized, and the test efficiency and the test consistency of the instrument in the research and development stage are improved.
Description
Technical Field
The invention relates to the technical field of vehicles, in particular to a method and a device for testing instrument sound, testing equipment and a storage medium.
Background
Along with the development of automobiles towards the direction of electric intellectualization, the functions of automobile instruments become more abundant, abundant instrument display and voice prompt are increased, and whether the voice prompt contents of the instruments in various application scenes meet the design requirements or not is tested in the research and development stage, wherein the voice prompt contents include voice playing contents, whether popping exists or not, whether delay exists in playing voice or not and the like. At present, whether the voice output of the instrument is qualified or not can be judged only through manual work in the research and development stage, and the manual judgment efficiency is low, so that the standard can not be unified.
Disclosure of Invention
In view of the above problems, embodiments of the present invention provide a meter sound testing method, device, testing apparatus, and storage medium to solve the above technical problems.
In a first aspect, an embodiment of the present invention provides a method for testing a sound of a meter, where the method is applied to a test device, and the method includes: acquiring and analyzing an instrument test case to obtain an instrument to be tested indicated by the instrument test case and test parameters corresponding to the instrument to be tested; sending the test parameters to the instrument to be tested to obtain test sound data output by the instrument to be tested based on the test parameters; inputting test sound data into the trained machine learning model to obtain a test result output by the trained machine learning model; and outputting a test result.
In a second aspect, an embodiment of the present invention provides a meter sound testing apparatus, which is applied to a testing device, and includes: the case analysis module is used for acquiring and analyzing the instrument test case to obtain the instrument to be tested indicated by the instrument test case and the test parameters corresponding to the instrument to be tested; the parameter sending module is used for sending the test parameters to the instrument to be tested and obtaining test sound data output by the instrument to be tested based on the test parameters; the sound detection module is used for inputting test sound data into the trained machine learning model to obtain a test result output by the trained machine learning model; and the result output module is used for outputting the test result.
In a third aspect, some embodiments of the invention also provide a test apparatus, including: one or more processors, memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the above-described methods.
In a fourth aspect, the present invention also provides a computer-readable storage medium, in which computer program instructions are stored, and computer program codes can be called by a processor to execute the above method.
The embodiment of the invention provides a method and a device for testing instrument sound, testing equipment and a storage medium. Applied to a test device, the method comprising: acquiring and analyzing an instrument test case to obtain an instrument to be tested indicated by the instrument test case and test parameters corresponding to the instrument to be tested; sending the test parameters to the instrument to be tested to obtain test sound data output by the instrument to be tested based on the test parameters; inputting test sound data into the trained machine learning model to obtain a test result output by the trained machine learning model; and outputting a test result. According to the invention, the test sound data output by the instrument to be tested is tested through the machine learning model, so that the automatic test of the vehicle-mounted instrument in various voice output scenes is realized, and the test efficiency and the test consistency of the instrument in the research and development stage are improved.
These and other aspects of the invention are apparent from and will be elucidated with reference to the embodiments described hereinafter.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of a meter sound testing method according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating an example of a method for testing a sound of a meter according to an embodiment of the present invention;
FIG. 3 is a flow chart of a meter sound testing method according to another embodiment of the present invention;
FIG. 4 is a flow chart illustrating a meter sound testing method according to another embodiment of the present invention;
FIG. 5 shows a flowchart of an embodiment of step S340 of the meter sound testing method provided by the embodiment shown in FIG. 4 of the present application;
FIG. 6 is a flow chart illustrating a method for testing meter sound according to yet another embodiment of the invention;
FIG. 7 is a diagram illustrating an example of a method for testing the sound of a meter according to another embodiment of the present invention;
FIG. 8 is a block diagram of a meter sound testing device provided by an embodiment of the present invention;
FIG. 9 is a block diagram of a test apparatus according to an embodiment of the present invention;
fig. 10 shows a block diagram of a computer-readable storage medium according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In order to make those skilled in the art better understand the solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Along with the development of automobiles towards the direction of electric intellectualization, the functions of automobile instruments become more abundant, abundant instrument display and voice prompt are increased, and whether the voice prompt contents of the instruments in various application scenes meet the design requirements or not is tested in the research and development stage, wherein the voice prompt contents include voice playing contents, whether popping exists or not, whether delay exists in playing voice or not and the like. At present, in the research and development stage, a CAN tool is used for manually or automatically sending CAN messages to control an instrument to send various sounds, whether the sound of the instrument is normal or not is judged manually, the efficiency is low, the reliability is not high, a unified standard does not exist, and different testers CAN have different test results.
In order to solve the technical problems, the inventor provides a method, a device, a testing device and a storage medium for testing the sound of the instrument, and tests the test sound data output by the instrument to be tested through a machine learning model, so that the automatic test of the vehicle-mounted instrument in various voice output scenes is realized, and the test efficiency and the test consistency of the instrument in the research and development stage are improved.
The method for testing the sound of the meter provided by the invention is described below by combining specific embodiments.
Referring to fig. 1, fig. 1 schematically illustrates a flow chart of a meter sound testing method according to an embodiment of the present invention. As will be explained in detail below with respect to the embodiment shown in fig. 1, the method may specifically include the following steps:
step S110: and acquiring and analyzing the instrument test case to obtain the instrument to be tested indicated by the instrument test case and the test parameters corresponding to the instrument to be tested.
With the development of automobiles towards the direction of electric intellectualization, the functions of automobile instruments become more abundant, and abundant instrument display and voice prompt are increased, so that the sound output by the instruments in various scenes needs to be tested during research and development. Therefore, in this embodiment, the meter test case may be obtained and analyzed to obtain the meter to be tested indicated by the meter test case and the test parameters corresponding to the meter to be tested.
In some embodiments, the test device may obtain a test requirement input by a user, and generate a corresponding test case according to the test requirement, where the test device may be a Personal Computer (PC). In this embodiment, the test requirement of the user is to test whether the voice prompt content in various application scenarios meets the design requirement, so that a corresponding meter test case can be generated according to the test requirement of the user. In some embodiments, in order to better control each component of the vehicle, a cloud management software system may be configured for the test device, a user may input a test requirement through the cloud management software system, and the cloud management software system may generate an instrument test case according to the test requirement. Further, different application scenarios may correspond to different instrument test cases, for example, the instrument test case a is used for voice prompt content of the test instrument in an application scenario where the vehicle speed is too fast, and the instrument test case B is used for voice prompt content of the test instrument in an application scenario where the road condition is observed. Similarly, different application scenarios may correspond to one meter test case, for example, the meter test case C may be used to test the voice prompt content of the meter in an application scenario where the vehicle speed is too fast, or may be used to test the voice prompt content of the meter in an application scenario where the safety belt is not fastened, and when the meter is tested by using the meter test case C, it may be sequentially tested whether the voice prompt content in each application scenario meets the design requirements.
In some embodiments, the meter test case may include a meter to be tested, a test target, a test environment, input data, a test step, an expected result, a test script, and the like, and the test device may obtain the meter test case and analyze the meter test case to obtain a meter to be tested corresponding to the meter test case and a test parameter corresponding to the meter to be tested, where the test parameter may be the test script, and the meter to be tested may be a vehicle-mounted meter. Further, the number of meters to be tested may be one or more, and is not limited herein.
Step S120: and sending the test parameters to the instrument to be tested to obtain test sound data output by the instrument to be tested based on the test parameters.
In this embodiment, the test parameters may be sent to the meter to be tested, and test sound data output by the meter to be tested based on the test parameters may be obtained. In some embodiments, the test parameter may be a test script, and after the test parameter is sent to the instrument to be tested, the instrument to be tested may download the test script, run the test script file, and output test sound data corresponding to the test parameter. In some embodiments, the test parameter may also be a signal obtained by analyzing the meter test case, and the signal is sent to the meter to be tested, so that the meter to be tested outputs corresponding test sound data.
In some embodiments, the test parameter may correspond to an application scenario, so as to trigger the to-be-tested instrument to respond and output corresponding test sound data, for example, if the application scenario corresponding to the test parameter is that the vehicle speed is too fast, the to-be-tested instrument may output corresponding test sound data when receiving the test parameter. The test sound data may be a complete sentence of voice, a word, or a single word, which is not limited herein.
Step S130: and inputting the test sound data into the trained machine learning model to obtain a test result output by the trained machine learning model.
After the test sound data is acquired, the test sound data can be tested to determine whether the test sound data meets the design requirements, so that the test result of the instrument is determined. In this embodiment, the test sound data may be input into the trained machine learning model, and the test result output by the trained machine learning model may be obtained.
In some embodiments, the test sound data is tested, and a plurality of indexes may be tested, for example, the type of the test sound data, whether the test sound data has an explosive sound, whether the test sound data has a delay, the number of sounds of the test sound data, and the like may be detected, which is not limited herein. The trained machine learning model may output only one index result, for example, the type of the test sound data output by the machine learning model may be obtained by inputting the test sound data into the machine learning model. The machine learning model may output a plurality of index results at the same time, and for example, the type of test sound data output by the machine learning model, whether or not the test sound data has a pop sound, and the like may be obtained by inputting the test sound data to the machine learning model. The training process of the machine learning model is not limited herein.
The machine learning relates to cross learning in multiple fields such as probability theory, statistics, approximation theory, convex analysis and algorithm, and the like, and is used for specially researching how a computer simulates or realizes the learning behavior of human beings so as to obtain new knowledge points or skills and reorganize the existing knowledge structure. Currently, machine learning algorithms may include linear regression algorithms, support vector machine algorithms, nearest neighbor/k-nearest neighbor algorithms, logistic regression algorithms, decision tree algorithms, k-means algorithms, random forest algorithms, naive bayes algorithms, dimension reduction algorithms, gradient enhancement algorithms, and the like.
In some embodiments, the testing device may obtain a plurality of sample sound data as input samples and indexes corresponding to the plurality of sample sound data as output samples, and select at least one of the above machine learning algorithms to train the machine learning model. The plurality of sample voice data may be voice prompt contents of a meter collecting a large amount in various application scenarios. After the training of the machine learning model is completed, the testing device only needs to input the testing sound data output by the instrument to be tested into the trained machine learning model, and then the testing result output by the trained machine learning model can be obtained.
Step S140: and outputting a test result.
In this embodiment, after the test result output by the trained machine learning model is obtained, the test result can be displayed through the display screen of the test equipment, and the user can clearly know whether the test sound data output by the instrument to be tested has problems and which problems exist, so that the user can quickly locate the problems and make adjustments based on the test result.
When the test sound data is tested and a plurality of indexes are tested, the test result may include test results corresponding to the plurality of indexes, for example, the test result may include whether the type of the test sound data is correct, whether the test sound data has pop noise, whether the test sound data has delay, the number of sounds of the test sound data, and the like.
Referring to fig. 2 as a specific embodiment, fig. 2 provides a test example diagram of a meter sound test, which includes a test device 11, where the test device 11 includes test software, the test software includes test case injection software and voice recognition judgment software, and further includes a meter to be tested 12. Specifically, the embodiment can run test case injection software and voice recognition software, and start the test after acquiring the instrument test case. Then, the test case injection software can analyze the instrument test case to obtain the instrument to be tested indicated by the instrument test case and the test parameters corresponding to the instrument to be tested, wherein, the testing parameter CAN be a CAN signal, the testing device 11 CAN send the CAN signal to the meter to be tested 12 through an Ethernet-Controller Area Network (ETH-CAN) module, meanwhile, a command is sent through the virtual serial port, the voice recognition software is started to monitor the test sound data output by the instrument to be tested 12 through the USB audio acquisition module, the voice recognition software scans the test sound data, the test sound data is tested through the machine learning model to obtain a test result, the voice recognition software feeds back the test result to the test case injection software through the virtual serial port, and the test case injection software displays the fed-back test result to a software interface. The software can be developed and realized through a Laboratory Virtual instrument Engineering platform (LabVIEW).
Further, the speech recognition software may include a machine learning model to test a plurality of indicators simultaneously, or the speech recognition software may include a plurality of different machine learning models to test different indicators respectively.
According to the instrument sound testing method provided by the embodiment of the invention, an instrument test case is obtained and analyzed, and an instrument to be tested indicated by the instrument test case and a test parameter corresponding to the instrument to be tested are obtained; sending the test parameters to the instrument to be tested to obtain test sound data output by the instrument to be tested based on the test parameters; inputting test sound data into the trained machine learning model to obtain a test result output by the trained machine learning model; and outputting a test result. According to the embodiment of the invention, the test sound data output by the instrument to be tested is tested through the machine learning model, so that the automatic test of the vehicle-mounted instrument in various voice output scenes is realized, and the test efficiency and the test consistency of the instrument in the research and development stage are improved.
Referring to fig. 3, fig. 3 shows a method for testing a sound of a meter according to another embodiment of the present invention, which will be described in detail with reference to the embodiment shown in fig. 3, and the method specifically includes the following steps:
step S210: and loading the test case of the instrument.
In this embodiment, the meter test case may be pre-loaded, where the meter test case may be generated in real time according to a requirement input by a user, and then the meter test case is loaded by the test device. As another mode, the test device may further be preset with a test case library, where the test case library includes a plurality of test cases, and the test device may load the instrument test case from the test case library.
Step S220: and analyzing the instrument test case to obtain the instrument to be tested indicated by the instrument test case and message data corresponding to the instrument test case.
In this embodiment, the instrument test case may be analyzed to obtain the instrument to be tested indicated by the instrument test case and the message data corresponding to the instrument test case. The instrument test case can include a case message, and the message data corresponding to the instrument test case can be obtained by analyzing the instrument test case. In some embodiments, the test device and the device to be tested may transmit signals to each other through a CAN communication protocol, so that the meter test case may be analyzed to obtain a CAN message corresponding to the meter test case.
Step S230: and analyzing the message data based on the DBC file of the instrument to obtain the test parameters corresponding to the instrument to be tested.
In this embodiment, the test equipment may be loaded with a meter DBC file. Wherein, the DBC file is used for describing the information of each logic node in a single CAN network. The loaded DBC file can be analyzed according to the inherent format of the DBC file, all messages, signals and message sending periods in the DBC file are obtained, currently selected message data are analyzed according to the DBC database, attribute information of the messages and information of all signals contained in the messages are obtained, and corresponding test scripts, namely test parameters corresponding to the instrument to be tested, are generated according to the attribute information of the messages and the information of all signals. Further, the process may be performed with a tool that is a program development environment, which may be LabVIEW.
Step S240: and sending the test parameters to the instrument to be tested to obtain test sound data output by the instrument to be tested based on the test parameters.
Step S250: and inputting the test sound data into the trained machine learning model to obtain a test result output by the trained machine learning model.
Step S260: and outputting a test result.
For the detailed description of steps S240 to S260, refer to steps S120 to S140, which are not described herein again.
The instrument sound testing method provided by the embodiment of the invention loads the instrument test case, analyzes the instrument test case to obtain the instrument to be tested indicated by the instrument test case and the message data corresponding to the instrument test case, analyzes the message data based on the instrument DBC file to obtain the test parameters corresponding to the instrument to be tested, sends the test parameters to the instrument to be tested to obtain the test sound data output by the instrument to be tested based on the test parameters, inputs the test sound data into the trained machine learning model, and obtains the test result output by the trained machine learning model. The embodiment of the invention analyzes the message data through the DBC file of the instrument, thereby acquiring accurate test parameters and improving the accuracy of sound test of the instrument.
Referring to fig. 4, fig. 4 shows a meter sound testing method according to another embodiment of the present invention, which will be described in detail with reference to the embodiment shown in fig. 4, and the method specifically includes the following steps:
step S310: and acquiring and analyzing the instrument test case to obtain the instrument to be tested indicated by the instrument test case and the test parameters corresponding to the instrument to be tested.
Step S320: and sending the test parameters to the instrument to be tested to obtain test sound data output by the instrument to be tested based on the test parameters.
For the detailed description of steps S310 to S320, please refer to steps S110 to S120, which are not described herein again.
Step S330: and inputting the test sound data into the trained machine learning model, and obtaining the type of the test sound data output by the trained machine learning model.
In this embodiment, the test sound data may be input into the trained machine learning model, and the type of the test sound data output by the trained machine learning model may be obtained.
In some embodiments, the types of sound data may be classified differently. As an embodiment, the type of the sound data may be classified by scene or content, and different application scenes correspond to different types, for example, the type of the sound data may be a seat belt warning tone, a sound for navigation, a warning tone for too fast vehicle speed, and the like. As an embodiment, the type of the sound data may be a tone scale by a cue, for example, the type of the sound data may be a male sound, a female sound, a child sound, a high pitch, a middle pitch, a low pitch, or the like. As an embodiment, the type of the sound data may also be divided by language, for example, the type of the sound data may be chinese, english, or the like. The type of the sound data is not limited herein, and may be determined according to the content to be tested.
In some embodiments, the test device may load a plurality of standard sound data, and may then acquire the plurality of standard sound data and a type of the plurality of standard sound data as a sample training set. The plurality of standard sound data can be obtained from voice prompt contents of massive standard instruments in various application scenes. As an embodiment, a sample training set may be obtained, the sample training set may include an input sample and an output sample, the input sample may include a plurality of standard sound data, and the output sample may include a plurality of types of standard sound data, and the machine learning model is trained by the sample training set, so that the trained machine learning model may output the type of test sound data according to the obtained test sound data.
The machine learning model can be trained by adopting at least one machine learning algorithm such as a linear regression algorithm, a support vector machine algorithm, a nearest neighbor/k-nearest neighbor algorithm, a logistic regression algorithm, a decision tree algorithm, a k-average algorithm, a random forest algorithm, a naive Bayes algorithm, a dimensionality reduction algorithm, a gradient enhancement algorithm and the like.
Step S340: and judging whether the type of the test sound data is correct or not.
In this embodiment, after the type of the test sound data output by the trained machine learning model is obtained, it may be determined whether the type of the test sound data is correct. Specifically, the test sound data may be compared with the standard sound data to determine whether the type of the test sound data is correct. For example, the test parameters corresponding to the test case of the instrument are used for testing the voice prompt which is output by the instrument when the road condition in front is an intersection, when the test sound data output by the instrument to be tested is acquired as 'the intersection in front', the type of the test sound data output by the machine learning model is the voice prompt of the road condition, and meanwhile, the type of the standard sound data can be acquired, and if the type of the standard sound data is also the voice prompt of the road condition, the type of the test sound data can be determined to be consistent with the type of the standard sound data, so that the type of the test sound data can be determined to be correct.
Further, referring to fig. 5, fig. 5 is a flowchart illustrating an embodiment of step S340 of the method for testing meter sound provided by the embodiment shown in fig. 4 of the present application. As will be explained in detail with respect to the flow shown in fig. 5, the method may specifically include the following steps:
step S341: and acquiring the standard sound data type in the instrument test case.
In this embodiment, the standard voice data type in the meter test case may be acquired. The meter test case can represent the content to be tested by the user, and further the meter test case can include standard sound data corresponding to the test content and can also include a standard sound data type. For example, if the meter test case is used to test a voice prompt that the meter should output when the vehicle speed is too fast, the standard voice data type may be a vehicle speed prompt tone, and if the meter test case is used to test a language type that the meter should output when switching to english output, the standard voice data type may be english. The standard sound data type is not limited herein, and may be set according to the content to be tested.
Step S342: the type of the test sound data is compared with the type of the standard sound data.
In the present embodiment, the type of the test sound data obtained as described above may be compared with the standard sound data type. Specifically, it may be determined whether the type of the test sound data is the same as the type of the standard sound data.
Step S343: when the type of the test sound data is identical to the type of the standard sound data, it is determined that the type of the test sound data is correct.
In the present embodiment, the type of the test sound data is compared with the type of the standard sound data, and when the type of the test sound data coincides with the type of the standard sound data, it is determined that the type of the test sound data is correct. For example, the test sound data is "turn left at the intersection ahead", the type of the test sound data is a navigation prompt tone, and if the type of the standard sound data is also a navigation prompt tone, it can be determined that the type of the test sound data is consistent with the type of the standard sound data, and further, it is determined that the type of the test sound data is correct.
Step S344: when the type of the test sound data is not consistent with the type of the standard sound data, it is determined that the type of the test sound data is incorrect.
In the present embodiment, the type of test sound data is compared with the type of standard sound data, and when the type of test sound data does not coincide with the type of standard sound data, it is determined that the type of test sound data is incorrect. For example, the test sound data is "turn left at the intersection ahead", the type of the test sound data is a navigation prompt tone, and if the type of the standard sound data is a vehicle speed prompt tone, it can be determined that the type of the test sound data is inconsistent with the type of the standard sound data, and thus it is determined that the type of the test sound data is incorrect.
Step S350: and outputting a first test result when the type of the test sound data is correct.
In the present embodiment, when the type of the test sound data is correct, the first test result may be output. When the type of the test sound data is correct, the test sound data output by the instrument to be tested can be represented to meet the design requirements, and then a first test result can be output. When the user views the first test result, it can be known that the sound of the meter to be tested is no problem.
Step S360: when the type of the test sound data is incorrect, a second test result is output.
In the present embodiment, when the type of the test sound data is incorrect, the second test result may be output. When the type of the test sound data is incorrect, it can be indicated that the test sound data output by the meter to be tested does not meet the design requirements, and then a second test result can be output. When the user views the first test result, it can be known that the sound of the meter to be tested is problematic. Further, the user can be prompted through voice, so that the user can know that the meter to be tested has problems more quickly.
In some embodiments, it may also be determined whether the content of the test sound data is correct. Specifically, the standard sound data may be acquired, the standard sound data may be subjected to speech recognition to obtain the content of the standard sound data, then the acquired test sound data may be subjected to speech recognition to obtain the content of the test sound data, and the content of the test sound data and the content of the standard sound data are compared to determine whether the content of the test sound data is correct. When the contents of the test sound data and the contents of the standard sound data are completely identical, it can be determined that the contents of the test sound data are correct.
In some embodiments, it may also be determined whether the test sound data has a popping sound. Wherein, the popping means intermittent interference sound occurring in the playing process, and does not include signal 'noise' caused by low signal-to-noise ratio. The pop sound may occur due to scratch verification of a Compact Disk (CD) or damage to an audio file, malfunction during power adjustment, or sudden signal alternation or other strong interference. As an embodiment, the test sound data may be input into the trained plosive recognition model, so as to obtain the plosive test result output by the trained plosive recognition model. As an embodiment, because the plosive is a section of speech with high energy values in each frequency band as seen from a spectrogram, it is possible to determine whether the test sound data has the plosive by calculating the energy values of the test sound data in each frequency band.
In some embodiments, it may also be determined whether there is a delay in the output of the test sound data. Specifically, the response duration of the test sound data can be obtained by obtaining the time for the instrument to be tested to receive the test parameters and the time for the instrument to be tested to output the test sound data, then obtaining the standard response duration in the test case, and comparing the response duration of the test sound data with the standard response duration, thereby determining whether delay exists in the output of the test sound data. When the response time length of the test sound data is longer than the standard response time length, it is described that there is a delay in the output of the test sound data.
In some embodiments, the number of sounds of the sound data output by the test meter may be required, and therefore, the number of sounds of the test sound data may also be determined. Specifically, the number of sounds of the test sound data may be acquired in the process of receiving the test sound data. Furthermore, whether the test sound data output by the test instrument meets the design requirements can be judged according to the comparison between the sound number of the standard sound data and the sound number of the test sound data in the test case.
The instrument sound testing method provided by the embodiment of the invention obtains and analyzes the instrument test case, obtains the instrument to be tested indicated by the instrument test case and the test parameters corresponding to the instrument to be tested, sends the test parameters to the instrument to be tested, obtains the test sound data output by the instrument to be tested based on the test parameters, inputs the test sound data into the trained machine learning model, obtains the type of the test sound data output by the trained machine learning model, judges whether the type of the test sound data is correct, outputs a first test result when the type of the test sound data is correct, and outputs a second test result when the type of the test sound data is incorrect. The embodiment of the invention judges the type of the test sound data through the machine learning model, thereby testing the sound of the instrument in various voice output scenes and improving the accuracy of the instrument test.
Referring to fig. 2 again, as a specific implementation manner, the meter testing method provided in fig. 2 includes a testing device 11, where the testing device 11 includes testing software, the testing software includes test case injection software and voice recognition judgment software, and further includes a meter to be tested 12. Specifically, the embodiment CAN run test case injection software and voice recognition software, load the CAN DBC file of the instrument and load standard voice data, and start the test after acquiring the test case of the instrument. Then, the test case injection software CAN analyze the instrument test case to obtain a CAN signal, the test equipment 11 CAN send the CAN signal to the instrument 12 to be tested through the ETH-CAN module, meanwhile, a command is sent through the virtual serial port, the voice recognition software is started to monitor test sound data output by the instrument 12 to be tested through the USB audio acquisition module, the voice recognition software scans the test sound data, the type of the test sound data is judged through the machine learning model, whether the test sound data has a popping sound is judged through the popping sound recognition model, a corresponding test result is obtained, the voice recognition software feeds back the test result to the test case injection software through the virtual serial port, and the test case injection software displays the fed back test result to a software interface. The software can be developed and realized through a LabVIEW platform.
Further, the speech recognition software may include a machine learning model to test a plurality of indicators simultaneously, or the speech recognition software may include a plurality of different machine learning models to test different indicators respectively.
Referring to fig. 6, fig. 6 shows a method for testing a sound of a meter according to still another embodiment of the present invention, where the number of meters to be tested is multiple, and the method may specifically include the following steps, as will be described in detail with reference to the embodiment shown in fig. 6:
step S410: and acquiring and analyzing the instrument test case to obtain the instrument to be tested indicated by the instrument test case and the test parameters corresponding to the instrument to be tested.
For detailed description of step S410, please refer to step S110, which is not described herein again.
Step S420: and determining Ethernet-controller converter modules corresponding to the plurality of meters to be tested respectively.
In this embodiment, a plurality of meters to be tested can be tested simultaneously. Specifically, the test device communicates with different meters to be tested through different ETH-CAN modules, so that the ETH-CAN modules respectively corresponding to a plurality of meters to be tested CAN be determined first, for example, meter a to be tested corresponds to ETH-CAN module a, meter B to be tested corresponds to ETH-CAN module B, and the like, where one meter to be tested corresponds to one ETH-CAN module. As an implementation manner, a corresponding relation table between the to-be-tested instrument and the ETH-CAN module may be preset in the test device, and the test device may determine the ETH-CAN module corresponding to each to-be-tested instrument by querying the relation table.
Step S430: and sending the test parameters to each instrument to be tested through the Ethernet-controller converter module corresponding to each instrument to be tested, and obtaining test sound data output by each instrument to be tested based on the test parameters.
In this embodiment, a plurality of meters to be tested are tested simultaneously, and the test standards are consistent, so that the test parameters corresponding to each meter to be tested are the same, and the test parameters CAN be sent to each meter to be tested through the ETH-CAN module corresponding to each meter to be tested, so as to obtain the test sound data output by each meter to be tested based on the test parameters. For example, the test parameter ETH-CAN module a is sent to the instrument a to be tested, the test sound data a output by the instrument a to be tested based on the test parameter is obtained, the test parameter ETH-CAN module B is sent to the instrument B to be tested, and the test sound data B output by the instrument B to be tested based on the test parameter is obtained.
Step S440: and inputting the test sound data into the trained machine learning model to obtain a test result output by the trained machine learning model.
In this embodiment, a plurality of test sound data corresponding to a plurality of meters to be tested may be respectively input to the trained machine learning model, so as to obtain a plurality of test results output by the trained machine learning model. For example, it is required to test an instrument a to be tested, an instrument B to be tested, and an instrument C to be tested simultaneously, it may be determined that the instrument a to be tested corresponds to the ETH-CAN module a, the instrument B to be tested corresponds to the ETH-CAN module B, and the instrument C to be tested corresponds to the ETH-CAN module C, a test parameter is sent to the instrument a to be tested through the ETH-CAN module a to obtain test sound data a output by the instrument a to be tested, a test parameter is sent to the instrument B to be tested through the ETH-CAN module B to obtain test sound data B output by the instrument B to be tested, a test parameter is sent to the instrument C to be tested through the ETH-CAN module C to obtain test sound data C output by the instrument C to be tested, the test sound data a, the test sound data B, and the test sound data C are input to the trained machine learning model respectively to obtain a test result a output by the trained machine learning model, Test result B and test result C.
Step S450: and outputting a test result.
In this embodiment, the test result corresponding to each meter to be tested may be sequentially output, or the test results corresponding to a plurality of meters to be tested may be simultaneously output and displayed on the same interface, which is not limited herein.
Referring to fig. 7, fig. 7 is a corresponding diagram of an example of a method for testing meter sound, which includes a testing device 21, where the testing device 21 includes testing software, and the testing software includes test case injection software and voice recognition judgment software. The test device further comprises a to-be-tested meter 1 and a to-be-tested meter N, wherein the number of the to-be-tested meters can be more than two, three, four and the like, and only two to-be-tested meters 1 and the to-be-tested meter N are shown in FIG. 7 for convenience of description. The testing device 21 is connected with the USB audio acquisition module 1 and the USB audio acquisition module N through the USB hub, and is connected with the ETH-CAN module 1 and the ETH-CAN module N through the switch. Specifically, the embodiment CAN run test case injection software and voice recognition software, load the CAN DBC file of the instrument and load standard voice data, and start the test after acquiring the test case of the instrument. Then, the test case injection software CAN analyze the instrument test case to obtain a CAN signal, the test equipment 21 CAN send the CAN signal to the instrument to be tested 1 through the ETH-CAN module 1, send the CAN signal to the instrument to be tested N through the ETH-CAN module N, simultaneously send a command through the virtual serial port, start the voice recognition software to monitor the test sound data 1 output by the instrument to be tested 1 through the USB audio acquisition module 1, monitor the test sound data N output by the vehicle-mounted instrument N through the USB audio acquisition module N, scan the test sound data 1 and the test sound data N through the voice recognition software, test the test sound data 1 and the test sound data N through the machine learning model to obtain a test result 1 and a test result N, and feed back the test result 1 and the test result N to the test case injection software through the virtual serial port, and the test case injection software displays the feedback test result 1 and the test result N to a software interface. The software can be developed and realized through a LabVIEW platform.
The instrument sound testing method provided by the embodiment of the invention obtains and analyzes the instrument test case, obtains the instruments to be tested indicated by the instrument test case and the test parameters corresponding to the instruments to be tested, determines the Ethernet-controller converter modules corresponding to a plurality of instruments to be tested respectively, sends the test parameters to each instrument to be tested through the Ethernet-controller converter module corresponding to each instrument to be tested, obtains the test sound data output by each instrument to be tested based on the test parameters, inputs the test sound data into the trained machine learning model, obtains the test results output by the trained machine learning model, and outputs the test results. According to the embodiment of the invention, the test parameters are sent to each instrument to be tested through the Ethernet-controller converter module corresponding to each instrument to be tested so as to test each instrument to be tested, so that a plurality of instruments to be tested can be tested simultaneously, and the test efficiency is improved.
Referring to fig. 8, fig. 8 is a block diagram illustrating a meter sound testing apparatus 800 according to an embodiment of the present invention. As will be explained below with respect to the block diagram shown in fig. 8, the meter sound testing apparatus 800 is applied to a testing device, and includes: a case analysis module 810, a parameter sending module 820, a sound detection module 830 and a result output module 840, wherein:
the case analysis module 810 is configured to obtain and analyze an instrument test case to obtain an instrument to be tested indicated by the instrument test case and a test parameter corresponding to the instrument to be tested.
Further, the test device is loaded with a meter DBC file, and the use case parsing module 810 includes: the system comprises a case loading submodule, a case analyzing submodule and a parameter obtaining submodule, wherein:
and the case loading submodule is used for loading the instrument test case.
And the case analysis submodule is used for analyzing the instrument test case to obtain the instrument to be tested indicated by the instrument test case and the message data corresponding to the instrument test case.
And the parameter acquisition submodule is used for analyzing the message data based on the DBC file of the instrument to obtain the test parameters corresponding to the instrument to be tested.
And the parameter sending module 820 is configured to send the test parameters to the instrument to be tested, and obtain test sound data output by the instrument to be tested based on the test parameters.
Further, the number of the meters to be tested is plural, and the parameter sending module 820 includes: the module determines a sub-module and a parameter sending sub-module, wherein:
and the module determination submodule is used for determining the Ethernet-controller converter modules corresponding to the plurality of instruments to be tested respectively.
And the parameter sending submodule is used for sending the test parameters to each instrument to be tested through the Ethernet-controller converter module corresponding to each instrument to be tested, and obtaining test sound data output by each instrument to be tested based on the test parameters.
The sound detection module 830 is configured to input test sound data into the trained machine learning model, and obtain a test result output by the trained machine learning model.
Further, the sound detection module 830 includes: the device comprises a type determining submodule, a type judging submodule, a first result output submodule and a second result output submodule, wherein:
and the type determining submodule is used for inputting the test sound data into the trained machine learning model and obtaining the type of the test sound data output by the trained machine learning model.
And the type judgment submodule is used for judging whether the type of the test sound data is correct or not.
Further, the type judgment sub-module comprises a type obtaining unit, a type comparing unit, a first type determining unit and a second type determining unit, wherein:
and the type acquisition unit is used for acquiring the standard sound data type in the instrument test case.
And the type comparison unit is used for comparing the type of the test sound data with the type of the standard sound data.
And a first type determining unit for determining that the type of the test sound data is correct when the type of the test sound data is identical to the type of the standard sound data.
A second type determining unit for determining that the type of the test sound data is incorrect when the type of the test sound data is not identical to the type of the standard sound data.
And the first result output sub-module is used for outputting a first test result when the type of the test sound data is correct.
And the second result output submodule is used for outputting a second test result when the type of the test sound data is incorrect.
Further, the sound detection module 830 further includes: the plosive detects submodule and third result output submodule, wherein:
and the plosive detection submodule is used for inputting the test sound data into the trained plosive identification model to obtain a plosive test result output by the trained plosive identification model.
And the third result output submodule is used for outputting a plosive test result.
Further, the sound detection module 830 further includes: a sample acquisition submodule and a model training submodule, wherein:
and the sample acquisition submodule is used for acquiring a sample training set, wherein the sample training set comprises input samples and output samples, the input samples are a plurality of standard sound data, and the output samples are types of the plurality of standard sound data.
And the model training submodule is used for inputting the sample training set into the machine learning model and training the machine learning model to obtain the trained machine learning model.
And the result output module is used for outputting the test result.
The instrument sound testing device provided by the embodiment of the invention comprises a case analysis module, a case analysis module and a sound analysis module, wherein the case analysis module is used for acquiring and analyzing an instrument test case to obtain an instrument to be tested indicated by the instrument test case and test parameters corresponding to the instrument to be tested; the parameter sending module is used for sending the test parameters to the instrument to be tested and obtaining test sound data output by the instrument to be tested based on the test parameters; the sound detection module is used for inputting test sound data into the trained machine learning model to obtain a test result output by the trained machine learning model; and the result output module is used for outputting the test result. Therefore, the test sound data output by the instrument to be tested is tested through the machine learning model, so that the automatic test of the vehicle-mounted instrument in various voice output scenes is realized, and the test efficiency and the test consistency of the instrument in the research and development stage are improved.
It can be clearly understood by those skilled in the art that the instrument sound testing device provided in the embodiment of the present invention can implement each process implemented by the test board in the method embodiments of fig. 1 to fig. 7, and for convenience and simplicity of description, the specific working processes of the above-described device and module may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments of the present invention, the coupling or direct coupling or communication connection between the modules shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or modules may be in an electrical, mechanical or other form. In addition, functional modules in the embodiments of the present invention may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
Referring to fig. 9, a block diagram of a test apparatus 900 according to an embodiment of the invention is shown. The test apparatus 900 of the present invention may include one or more of the following components: a processor 910, a memory 920, and one or more applications, wherein the one or more applications may be stored in the memory 920 and configured to be executed by the one or more processors 910, the one or more programs configured to perform a method as described in the aforementioned method embodiments.
The memory 920 may include a Random Access Memory (RAM) or a read-only memory (ROM). The memory 920 may be used to store instructions, programs, code sets, or instruction sets. The memory 920 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, and the like. The data storage area may also store data created by the testing device 900 during use (e.g., phone book, audio-video data, chat log data), etc.
Referring to fig. 10, a block diagram of a computer-readable storage medium according to an embodiment of the invention is shown. The computer-readable storage medium 1000 stores program code that can be called by a processor to execute the methods described in the above-described method embodiments.
The computer-readable storage medium 1000 may be an electronic memory such as a flash memory, an electrically-erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a hard disk, or a ROM. Alternatively, the computer-readable storage medium 1000 includes a non-volatile computer-readable storage medium. The computer readable storage medium 1000 has storage space for a program medium 1010 for performing any of the method steps of the method described above. The program code can be read from or written to one or more computer program products. The program medium 1010 may be compressed, for example, in a suitable form.
In summary, the meter sound testing method, device, testing apparatus and storage medium provided in the embodiments of the present invention. Applied to a test device, the method comprising: acquiring and analyzing an instrument test case to obtain an instrument to be tested indicated by the instrument test case and test parameters corresponding to the instrument to be tested; sending the test parameters to the instrument to be tested to obtain test sound data output by the instrument to be tested based on the test parameters; inputting test sound data into the trained machine learning model to obtain a test result output by the trained machine learning model; and outputting a test result. According to the invention, the test sound data output by the instrument to be tested is tested through the machine learning model, so that the automatic test of the vehicle-mounted instrument in various voice output scenes is realized, and the test efficiency and the test consistency of the instrument in the research and development stage are improved.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not necessarily depart from the spirit and scope of the corresponding technical solutions.
Claims (10)
1. A meter sound testing method is applied to testing equipment, and the method comprises the following steps:
acquiring and analyzing an instrument test case to obtain an instrument to be tested indicated by the instrument test case and test parameters corresponding to the instrument to be tested;
sending the test parameters to the instrument to be tested to obtain test sound data output by the instrument to be tested based on the test parameters;
inputting the test sound data into a trained machine learning model to obtain a test result output by the trained machine learning model;
and outputting the test result.
2. The method according to claim 1, wherein the test equipment is loaded with a meter DBC file, and the obtaining and analyzing a meter test case to obtain a meter to be tested indicated by the test case and test parameters corresponding to the meter to be tested comprises:
loading an instrument test case;
analyzing the instrument test case to obtain an instrument to be tested indicated by the instrument test case and message data corresponding to the instrument test case;
and analyzing the message data based on the DBC file of the instrument to obtain the test parameters corresponding to the instrument to be tested.
3. The method of claim 1, wherein inputting the test sound data into a trained machine learning model to obtain a test result output by the trained machine learning model comprises:
inputting the test sound data into the trained machine learning model to obtain the type of the test sound data output by the trained machine learning model;
judging whether the type of the test sound data is correct or not;
when the type of the test sound data is correct, outputting a first test result;
when the type of the test sound data is incorrect, outputting a second test result.
4. The method of claim 3, wherein determining whether the type of the test sound data is correct comprises:
acquiring a standard sound data type in the instrument test case;
comparing the type of the test sound data with the type of the standard sound data;
when the type of the test sound data is consistent with the type of the standard sound data, determining that the type of the test sound data is correct;
determining that the type of the test sound data is incorrect when the type of the test sound data is not consistent with the type of the standard sound data.
5. The method of claim 3, further comprising:
inputting the test sound data into a trained plosive recognition model to obtain a plosive test result output by the trained plosive recognition model;
and outputting the plosive test result.
6. The method of claim 3, wherein prior to inputting the test sound data into a trained machine learning model and obtaining the type of the test sound data output by the trained machine learning model, the method further comprises:
acquiring a sample training set, wherein the sample training set comprises input samples and output samples, the input samples are a plurality of standard sound data, and the output samples are types of the plurality of standard sound data;
and inputting the sample training set into a machine learning model, and training the machine learning model to obtain a trained machine learning model.
7. The method of claim 1, wherein the number of meters under test is plural, and the sending the test parameters to the meters under test to trigger the meters under test to output test sound data comprises:
determining Ethernet-controller converter modules corresponding to the plurality of meters to be tested respectively;
and sending the test parameters to each instrument to be tested through the Ethernet-controller converter module corresponding to each instrument to be tested, and obtaining test sound data output by each instrument to be tested based on the test parameters.
8. A meter sound testing device, applied to a testing apparatus, the device comprising:
the case analysis module is used for acquiring and analyzing an instrument test case to obtain an instrument to be tested indicated by the instrument test case and test parameters corresponding to the instrument to be tested;
the parameter sending module is used for sending the test parameters to the instrument to be tested and obtaining test sound data output by the instrument to be tested based on the test parameters;
the sound detection module is used for inputting the test sound data into a trained machine learning model to obtain a test result output by the trained machine learning model;
and the result output module is used for outputting the test result.
9. A test apparatus, comprising:
a memory;
one or more processors coupled with the memory;
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-7.
10. A computer-readable storage medium, having stored thereon program code that can be invoked by a processor to perform the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110070561.9A CN112908357A (en) | 2021-01-19 | 2021-01-19 | Instrument sound testing method and device, testing equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110070561.9A CN112908357A (en) | 2021-01-19 | 2021-01-19 | Instrument sound testing method and device, testing equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112908357A true CN112908357A (en) | 2021-06-04 |
Family
ID=76115869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110070561.9A Pending CN112908357A (en) | 2021-01-19 | 2021-01-19 | Instrument sound testing method and device, testing equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112908357A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113805834A (en) * | 2021-08-23 | 2021-12-17 | 桂林未来鹏创软件有限公司 | Automobile intelligent cabin testing method, system, device and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102752059A (en) * | 2011-04-19 | 2012-10-24 | 上海博泰悦臻电子设备制造有限公司 | Automatic equipment test method and system |
| CN103578463A (en) * | 2012-07-27 | 2014-02-12 | 腾讯科技（深圳）有限公司 | Automatic testing method and automatic testing device |
| CN108600929A (en) * | 2017-12-08 | 2018-09-28 | 佛山慧明电子科技有限公司 | A kind of multinomial audio frequency parameter automatic test approach and its test system |
| CN109491902A (en) * | 2018-11-01 | 2019-03-19 | 京东方科技集团股份有限公司 | Interactive testing method, apparatus and system |
| CN110086692A (en) * | 2019-05-14 | 2019-08-02 | 广州云智易物联网有限公司 | A kind of automated testing method based on Internet of Things, device and computer equipment |
| CN110362434A (en) * | 2019-03-22 | 2019-10-22 | 斑马网络技术有限公司 | Object test method and equipment |
| CN110399294A (en) * | 2019-06-26 | 2019-11-01 | 平安科技（深圳）有限公司 | Method for generating test case, device, computer equipment and storage medium |
| CN110415724A (en) * | 2019-08-08 | 2019-11-05 | 中南大学湘雅二医院 | Transmission method, device, system and the computer readable storage medium of alert data |
| CN110543300A (en) * | 2019-08-20 | 2019-12-06 | 延锋伟世通电子科技（南京）有限公司 | automatic generation method and tool for automatic test script of automobile instrument |
| US10629224B1 (en) * | 2016-07-28 | 2020-04-21 | United Services Automobile Association (Usaa) | Vehicle sound analysis |
| CN111145737A (en) * | 2018-11-06 | 2020-05-12 | 中移（杭州）信息技术有限公司 | Voice test method and device and electronic equipment |
| CN111724782A (en) * | 2020-06-18 | 2020-09-29 | 中汽院智能网联科技有限公司 | Response time testing system, method and equipment of vehicle-mounted voice interaction system |
-
2021
- 2021-01-19 CN CN202110070561.9A patent/CN112908357A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102752059A (en) * | 2011-04-19 | 2012-10-24 | 上海博泰悦臻电子设备制造有限公司 | Automatic equipment test method and system |
| CN103578463A (en) * | 2012-07-27 | 2014-02-12 | 腾讯科技（深圳）有限公司 | Automatic testing method and automatic testing device |
| US10629224B1 (en) * | 2016-07-28 | 2020-04-21 | United Services Automobile Association (Usaa) | Vehicle sound analysis |
| CN108600929A (en) * | 2017-12-08 | 2018-09-28 | 佛山慧明电子科技有限公司 | A kind of multinomial audio frequency parameter automatic test approach and its test system |
| CN109491902A (en) * | 2018-11-01 | 2019-03-19 | 京东方科技集团股份有限公司 | Interactive testing method, apparatus and system |
| CN111145737A (en) * | 2018-11-06 | 2020-05-12 | 中移（杭州）信息技术有限公司 | Voice test method and device and electronic equipment |
| CN110362434A (en) * | 2019-03-22 | 2019-10-22 | 斑马网络技术有限公司 | Object test method and equipment |
| CN110086692A (en) * | 2019-05-14 | 2019-08-02 | 广州云智易物联网有限公司 | A kind of automated testing method based on Internet of Things, device and computer equipment |
| CN110399294A (en) * | 2019-06-26 | 2019-11-01 | 平安科技（深圳）有限公司 | Method for generating test case, device, computer equipment and storage medium |
| CN110415724A (en) * | 2019-08-08 | 2019-11-05 | 中南大学湘雅二医院 | Transmission method, device, system and the computer readable storage medium of alert data |
| CN110543300A (en) * | 2019-08-20 | 2019-12-06 | 延锋伟世通电子科技（南京）有限公司 | automatic generation method and tool for automatic test script of automobile instrument |
| CN111724782A (en) * | 2020-06-18 | 2020-09-29 | 中汽院智能网联科技有限公司 | Response time testing system, method and equipment of vehicle-mounted voice interaction system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113805834A (en) * | 2021-08-23 | 2021-12-17 | 桂林未来鹏创软件有限公司 | Automobile intelligent cabin testing method, system, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108802511B (en) | Method and system for testing battery management unit | |
| CN111724781B (en) | Audio data storage method, device, terminal and storage medium | |
| CN111782266B (en) | Software performance benchmark determination method and device | |
| CN112749081A (en) | User interface testing method and related device | |
| CN111563029A (en) | Testing method, system, storage medium and computer equipment for conversation robot | |
| CN112908357A (en) | Instrument sound testing method and device, testing equipment and storage medium | |
| CN110322587B (en) | Evaluation recording method, device and equipment in driving process and storage medium | |
| CN110737900A (en) | Webpage function testing method and device, server and computer readable storage medium | |
| CN112365883B (en) | Cabin system voice recognition test method, device, equipment and storage medium | |
| CN111190786A (en) | UVM-based test framework, test platform and test method | |
| CN115629930A (en) | Fault detection method, device and equipment based on DSP system and storage medium | |
| CN114398250A (en) | Vehicle test evaluation method and device based on functional scene | |
| CN116991706B (en) | Vehicle automatic test method, device, equipment and storage medium | |
| CN107766238B (en) | Software testing method, device, equipment and computer readable storage medium | |
| CN110988661A (en) | FPGA prototype verification development board time division analysis system, method, medium and terminal | |
| CN113485914B (en) | Vehicle-mounted voice SDK testing method, device and system | |
| CN115314413B (en) | CAN signal testing method and device | |
| CN116680171B (en) | Test method, device, storage medium and electronic equipment | |
| CN116072142B (en) | High-power radio frequency transmission line monitoring method and device and electronic equipment | |
| CN115981941A (en) | Chip clock testing method and device, storage medium and electronic equipment | |
| CN116089282A (en) | Automobile automatic test method and device, electronic equipment and storage medium | |
| US20230161926A1 (en) | Manufacturing system design verification device | |
| CN115980557A (en) | Chip testing method and device | |
| EP4290509A1 (en) | Computer implemented method for evaluating one or more speech recognition systems | |
| CN112346957B (en) | Automatic test equipment and method for vehicle-mounted voice system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |