Wake-up result determination method, device, storage medium and electronic device

Abstract

The present application discloses a method, device, storage medium and electronic device for determining a wake-up result, and relates to the field of smart home technology. The method for determining the wake-up result comprises: obtaining a wake-up corpus for waking up a device to be tested; when the wake-up corpus is played back in a loop to the device to be tested by a test device, obtaining a first number of times the wake-up corpus is played back in a loop to the device to be tested, and a second number of times the device to be tested is awakened by the wake-up corpus, wherein a plurality of wake-up corpora are pre-stored in the test device; determining the wake-up result of the device to be tested according to the first number and the second number. The above technical solution is adopted to solve the problem of how to accurately determine the wake-up result of the device.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and more specifically, to a method, device, storage medium and electronic device for determining a wake-up result. Background Art

[0002] With the rise of smart homes, technologies in related fields are becoming more mature, and smart devices are beginning to enter people's daily lives. For example, smart speakers in the smart home field can not only play music, but also act as a master device to control other devices. As people have higher and higher requirements for the performance of smart speakers, the performance testing level of smart devices is also constantly improving. Correspondingly, it is also necessary to obtain more accurate performance test results of smart speakers.

[0003] The performance test of smart speakers includes testing the performance indicators of smart speakers. For example, the wake-up success rate of smart speakers is one of the performance indicators. The wake-up success rate refers to the probability that the speaker can be awakened normally after the user issues a wake-up command. Usually, multiple testers will perform repeated voice wake-ups on smart devices and record the wake-up results of voice wake-ups. However, this testing method requires testers to perform a large number of repeated tests. Due to the limited number of testers and the limited data that can be provided by manual testing, it is not possible to use a large amount of data for performance testing. In addition, when testers perform a large amount of repetitive work, they are prone to work errors, which will result in inaccurate wake-up results.

[0004] Therefore, in the related art, there is a problem of how to accurately determine the wake-up result of the device.

[0005] In the related art, there is a problem of how to accurately determine the wake-up result of the device, and no effective solution has been proposed yet. Summary of the invention

[0006] The embodiments of the present application provide a method, device, storage medium and electronic device for determining a wake-up result, so as to at least solve the problem of how to accurately determine the wake-up result of a device in the related art.

[0007] According to an embodiment of the embodiments of the present application, a method for determining a wake-up result is provided, including: obtaining a wake-up corpus for waking up a device to be tested; when the wake-up corpus is played in a loop to the device to be tested through a test device, obtaining a first number of times the wake-up corpus is played in a loop to the device to be tested, and a second number of times the device to be tested is awakened by the wake-up corpus, wherein a plurality of wake-up corpora have been pre-saved in the test device; and determining the wake-up result of the device to be tested based on the first number and the second number.

[0008] In an exemplary embodiment, obtaining a wake-up corpus for waking up a device to be tested includes: obtaining a pre-configured initial wake-up corpus; performing noise elimination processing on the initial wake-up corpus to obtain a pure wake-up corpus; and setting a wake-up parameter of the pure wake-up corpus to obtain a wake-up corpus for waking up the device to be tested.

[0009] In an exemplary embodiment, whether the device to be tested successfully responds to any wake-up language material played is determined in the following manner: determining the feedback duration of the device to be tested to any wake-up language material played and the feedback volume of the device to be tested within the feedback duration; determining a first duration from the feedback duration, wherein the target feedback volume corresponding to the first duration is continuously greater than a first preset value; and determining that the device to be tested is awakened when it is determined that a first ratio of the first duration to the feedback duration is greater than a second preset value.

[0010] In an exemplary embodiment, before determining the first duration from the feedback duration, the method also includes: obtaining the volume of the ambient noise when playing any of the wake-up linguistic materials played; when the ambient noise volume is greater than a third preset value, obtaining a first difference between the ambient noise volume and the third preset value; and adjusting the feedback volume of the device to be tested within the feedback duration according to the first difference.

[0011] In an exemplary embodiment, in the process of looping the wake-up language to the device to be tested through the test device, the method also includes: obtaining a preset test time of the device to be tested, and dividing the preset test time into multiple time periods; determining the earliest first start time and a second start time later than the first start time from the start times of the multiple time periods, and determining a first time period corresponding to the first start time, and a second time period corresponding to the second start time; determining a first number of times the wake-up language is looped through the test device to the device to be tested within the first time period; obtaining the number of times the wake-up language corresponds to the difference between the second start time and the first start time; and determining the sum of the number of times the wake-up language corresponds to the difference and the first number of times the wake-up language is looped through the test device to the device to be tested within the second time period.

[0012] In an exemplary embodiment, the method also includes: verifying the wake-up parameters in the wake-up corpus; when the parameter values ​​corresponding to the wake-up parameters are not missing and the parameter values ​​corresponding to the wake-up parameters meet the conditions, determining that the verification is passed, and looping the wake-up corpus to the device to be tested through the test device; the conditions met by the parameter values ​​corresponding to the wake-up parameters include at least one of the following: the wake-up frequency of the wake-up parameters is greater than the fourth preset value; the playback speed of the wake-up parameters is less than the fifth preset value; the playback volume of the wake-up parameters is greater than the sixth preset value.

[0013] In an exemplary embodiment, after determining the wake-up result of the device to be tested according to the first number and the second number, the method further includes: when it is determined that the wake-up result is abnormal, determining the abnormal wake-up corpus corresponding to the abnormal wake-up result; sending a prompt message carrying the abnormal wake-up corpus to the first object, wherein the prompt message is used to prompt an analysis of the abnormal wake-up result and the abnormal wake-up corpus.

[0014] According to another embodiment of the embodiments of the present application, a device for determining a wake-up result is also provided, including: an acquisition module, used to obtain a wake-up corpus used to wake up a device to be tested; a first determination module, used to obtain a first number of times the wake-up corpus is played in a loop to the device to be tested, and a second number of times the device to be tested is awakened by the wake-up corpus, when the wake-up corpus is played in a loop to the device to be tested through the test device, wherein a plurality of wake-up corpora have been pre-saved in the test device; and a second determination module, used to determine the wake-up result of the device to be tested based on the first number and the second number.

[0015] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for determining the wake-up result when running.

[0016] According to another aspect of an embodiment of the present application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method for determining the wake-up result through the computer program.

[0017] In an embodiment of the present application, a wake-up corpus for waking up a device to be tested is obtained; when the wake-up corpus is played in a loop to the device to be tested through the test device, a first number of times the wake-up corpus is played in a loop to the device to be tested and a second number of times the device to be tested is awakened by the wake-up corpus are obtained, wherein a plurality of wake-up corpora are pre-saved in the test device; the wake-up result of the device to be tested is determined according to the first number and the second number; the above-mentioned technical solution is adopted to solve the problem of how to accurately determine the wake-up result of the device, thereby improving the accuracy of the wake-up result of the device. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 It is a hardware environment diagram of a method for determining a wake-up result according to an embodiment of the present application;

[0021] Figure 2 is a flowchart of a method for determining a wake-up result according to an embodiment of the present application (I);

[0022] Figure 3 is a schematic diagram of an audio file according to an embodiment of the present application;

[0023] Figure 4 is a flowchart of a method for determining a wake-up result according to an embodiment of the present application (II);

[0024] Figure 5 It is a structural block diagram of a device for determining a wake-up result according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device to be tested that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices to be tested.

[0027] According to one aspect of an embodiment of the present application, a method for determining a wake-up result is provided. The method for determining a wake-up result is widely used in smart home (Smart Home), smart home, smart home test equipment ecology, smart home (IntelligenceHouse) ecology and other whole-house intelligent digital control application scenarios. Optionally, in this embodiment, the above-mentioned method for determining a wake-up result can be applied to Figure 1 In the hardware environment shown in FIG. 1 , the device to be tested 102 and the server 104 are formed. Figure 1 As shown, the server 104 is connected to the device to be tested 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

[0028] The network may include but is not limited to at least one of the following: wired network, wireless network. The wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The device to be tested 102 may be but is not limited to a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing device to be tested, a smart dishwasher, a smart projection device to be tested, a smart TV, a smart clothes rack, a smart curtain, a smart audio and video, a smart socket, a smart speaker, a smart fresh air device to be tested, a smart kitchen and bathroom device to be tested, a smart bathroom device to be tested, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification device to be tested, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc.

[0029] In this embodiment, a method for determining a wake-up result is provided, which is applied to the above-mentioned computer terminal. Figure 2 : is a flowchart of a method for determining a wake-up result according to an embodiment of the present application, the process comprising the following steps:

[0030] Step S202, obtaining a wake-up corpus for waking up the device to be tested;

[0031] It can be understood that the above wake-up corpus can be directly obtained from the corpus or generated by software. The wake-up corpus includes wake-up keywords. For example, for a certain Er speaker, the wake-up corpus can be set to "Xiaoyou Xiaoyou"; for a certain Xiaomi speaker, the wake-up corpus can be "Xiaoai Xiaoai"; for a certain Dong speaker, the wake-up corpus can be "a certain Dong a certain Dong". This application does not impose any restrictions on this.

[0032] It should be noted that the above wake-up corpus may include multiple types of languages, such as Chinese, English, or languages ​​of other countries. Among them, for Chinese, it may include Mandarin and may further include dialects of different regions, but is not limited thereto.

[0033] Step S204, in the case where the wake-up language material is played in a loop to the device to be tested through the test device, obtaining a first number of times the wake-up language material is played in a loop to the device to be tested, and a second number of times the device to be tested is awakened by the wake-up language material, wherein the test device has pre-stored a plurality of wake-up language materials;

[0034] It should be noted that the above test equipment can work all day, and the above cycle times can be pre-set.

[0035] In the process of cyclically playing the wake-up language material to the device to be tested through the test device, the wake-up language material may be replaced every time the wake-up language material is played to the device to be tested through the test device.

[0036] Step S206: determining a wake-up result of the device to be tested according to the first number of times and the second number of times.

[0037] Through the above steps, the wake-up corpus for waking up the device to be tested is obtained; when the wake-up corpus is played in a loop to the device to be tested through the test device, the first number of times the wake-up corpus is played in a loop to the device to be tested and the second number of times the device to be tested is awakened by the wake-up corpus are obtained, wherein the test device has pre-saved a plurality of wake-up corpora; the wake-up result of the device to be tested is determined according to the first number and the second number, which solves the problem of how to accurately determine the wake-up result of the device in the related art, thereby improving the accuracy of the wake-up result of the device.

[0038] In an exemplary embodiment, in order to better understand how to obtain the wake-up corpus for waking up the device to be tested in the above step S202, it can be achieved through the following steps: obtain a pre-configured initial wake-up corpus; perform noise elimination processing on the initial wake-up corpus to obtain a pure wake-up corpus; set the wake-up parameters of the pure wake-up corpus to obtain the wake-up corpus for waking up the device to be tested.

[0039] Among them, the wake-up corpus for waking up the device to be tested can be obtained through a mobile terminal, wherein the mobile terminal can realize automatic timed acquisition, or respond to acquisition and execute passive acquisition of corpus, and the mobile terminal can include but is not limited to mobile phones, tablets, computers, smart watches, etc.

[0040] The above-mentioned noise processing and elimination process may include a process of eliminating interfering sounds in the environment. Since in this embodiment, the wake-up language material is automatically played to the device to be tested by the test device, the human voice appearing in the environment can be eliminated as an interfering sound.

[0041] The wake-up parameters of the above-mentioned pure wake-up corpus may include the number of wake-up times, the wake-up volume threshold, the wake-up time, etc., but are not limited thereto.

[0042] Through the above method, by processing the wake-up corpus, the test process of the device to be tested can be implemented according to the processed wake-up corpus, thereby improving the accuracy of the wake-up result.

[0043] In an exemplary embodiment, in the process of looping the wake-up language to the device to be tested through the test device, a technical solution is also proposed, and the specific steps include: determining whether the device to be tested successfully responds to any wake-up language played by the test device in the following way: determining the feedback duration of the device to be tested to the wake-up language played at any time and the feedback volume of the device to be tested within the feedback duration; determining a first duration from the feedback duration, wherein the target feedback volume corresponding to the first duration is continuously greater than a first preset value; and determining that the device to be tested is awakened when it is determined that the first ratio of the first duration to the feedback duration is greater than a second preset value.

[0044] Through the above embodiment, whether the above device to be tested successfully responds to the wake-up corpus can be determined from the perspectives of feedback duration and feedback volume, thereby improving the credibility of the device's successful response to the wake-up corpus.

[0045] Optionally, in one embodiment, when it is determined that a first ratio of the first duration to the feedback duration is not greater than a second preset value, it is determined that the device to be tested is not awakened.

[0046] In an optional embodiment, if it is determined that the feedback duration of the device to be tested for any wake-up corpus played is 1s, the feedback volume of the device to be tested within the feedback duration is 20dB, and the first preset value is 10dB, and the second preset value is 0.5, then when it is determined from the feedback duration that the first duration for which the feedback volume continues to be greater than 10dB is 0.6s, it is determined that the device to be tested is awakened. When it is determined from the feedback duration that the first duration for which the feedback volume continues to be greater than 10dB is 0.4s, it is determined that the device to be tested is not awakened.

[0047] In an exemplary embodiment, before determining the first duration from the feedback duration, further, the volume of the ambient noise when playing any of the wake-up language materials played can be obtained; when the ambient noise volume is greater than a third preset value, a first difference between the ambient noise volume and the third preset value is obtained; and the feedback volume of the device to be tested within the feedback duration is adjusted according to the first difference.

[0048] Among them, adjusting the feedback volume of the device under test within the feedback duration according to the first difference may include updating the sum of the first difference B between the ambient noise volume and the third preset value and the feedback volume of the device under test within the feedback duration as the feedback volume of the device under test within the feedback duration.

[0049] For example, in an optional embodiment, if it is determined that the ambient noise volume when the wake-up language is played is 6dB, the third preset value is 10dB, and the feedback volume of the device to be tested within the feedback duration is 10dB, then the sum of the first difference of 4dB between the ambient noise volume and the third preset value and the feedback volume of the device to be tested within the feedback duration of 10dB, 14dB, is updated as the feedback volume of the device to be tested within the feedback duration.

[0050] It should be noted that when adjusting the feedback volume of the device under test within the feedback duration according to the first difference, the degree of adjustment is related to the size of the first difference. For example, the larger the first difference, the greater the ambient noise, and the required degree of adjustment also needs to be increased accordingly.

[0051] In an exemplary embodiment, in the process of looping the wake-up language material to the device to be tested through the test device, the following scheme can also be implemented: first, obtain the preset test time of the device to be tested, and divide the preset test time into multiple time periods; then determine the earliest first start time and the second start time later than the first start time from the start times of the multiple time periods, and determine the first time period corresponding to the first start time, and the second time period corresponding to the second start time; then determine the first number of times the wake-up language material is looped through the test device to the device to be tested within the first time period; obtain the number of times the wake-up language material corresponds to the difference between the second start time and the first start time; finally, determine the sum of the number of times the wake-up language material is looped through the test device to the device to be tested within the second time period.

[0052] The time unit of the preset test time may include year, month, day, hour, minute, and second. For example, when the time unit of the preset test time is hour, the preset test time may be set to 24 hours.

[0053] The first playback number may be pre-set, corresponding to the first start time. There may be multiple second playback numbers, corresponding to multiple second time periods corresponding to multiple second start times.

[0054] In an exemplary embodiment, the wake-up corpus can also be verified, specifically: the wake-up parameters in the wake-up corpus are verified; when the parameter values ​​corresponding to the wake-up parameters are not missing and the parameter values ​​corresponding to the wake-up parameters meet the conditions, it is determined that the verification is passed, and the wake-up corpus is played in a loop to the device to be tested through the test device; the conditions satisfied by the parameter values ​​corresponding to the wake-up parameters include at least one of the following: the wake-up frequency of the wake-up parameters is greater than the fourth preset value; the playback speed of the wake-up parameters is less than the fifth preset value; the playback volume of the wake-up parameters is greater than the sixth preset value.

[0055] The parameter values ​​of the wake-up parameters may be determined according to the device data of the device to be tested. For example, the playback volume, wake-up frequency, playback volume, etc. of the wake-up parameters may be determined according to the microphone model of the device to be tested.

[0056] Through the above-mentioned verification process of the wake-up corpus, the authenticity and usability of the wake-up corpus can be improved, the probability of error of invalid wake-up results obtained by using invalid wake-up corpus can be reduced, and the wake-up efficiency and wake-up accuracy in the test process can be improved.

[0057] In an exemplary embodiment, after determining the wake-up result of the device to be tested according to the first number and the second number, further determine whether the wake-up result is abnormal. If it is determined that the wake-up result is abnormal, determine the abnormal wake-up corpus corresponding to the abnormal wake-up result; send a prompt message carrying the abnormal wake-up corpus to the first object, and the prompt message is used to prompt the analysis of the abnormal wake-up result and the abnormal wake-up corpus. If it is determined that the wake-up result is not abnormal, directly send the wake-up result to the first object.

[0058] Among them, the above prompt message can prompt the first object to analyze the abnormal wake-up result and the abnormal wake-up corpus, and can also prompt the device to execute an analysis program to analyze the abnormal wake-up result and the abnormal wake-up corpus, but is not limited to this.

[0059] The first object may be a person, such as a user of a device, but is not limited thereto.

[0060] Through this embodiment, the problem that the speech speed, volume and other parameters of the corpus are difficult to maintain consistency due to artificial voice, and the corpus when the problem occurs cannot be reproduced is solved. By analyzing the saved wake-up results and using the abnormal wake-up corpus to reproduce the wake-up scene when an abnormal wake-up result occurs, the cause of the wake-up abnormality can be accurately located, the processing efficiency of the abnormal wake-up results is improved, and the user experience is improved.

[0061] In one embodiment, when testing the smart speaker, the wake-up corpus is automatically played, and the feedback result of the smart speaker is recorded to obtain a recording file of the feedback result. The recording file can be analyzed to determine whether the speaker is awakened. During the analysis process, two parameters are required to determine whether it is awakened, threshold and time, where threshold represents the threshold of the volume and time represents the time, and the time unit can be seconds. When the volume is greater than the threshold threshold for a time greater than time, it is determined that there is awakening.

[0062] Here, time can be calculated by the duration of the sampling point. For example, if the sampling rate of the recording file is 22050, the duration of each sampling point is 1 / 22050 (seconds). When the number of sampling points with a volume greater than the threshold is greater than time*22050, it is determined that wakeup occurs.

[0063] Among them, threshold can be calculated by librosa library in python, specifically, librosa is used to calculate the audio waveform of the recording file, such as Figure 3As shown, the horizontal axis represents the sampling point and the vertical axis represents the volume. Further, the time series of the audio waveform is determined, and the sampling points in the time series that are greater than the threshold are recorded. When the number of recorded sampling points is greater than time*22050, it is determined that wakeup occurs.

[0064] In order to better understand the process of the above-mentioned method for determining the wake-up result, the implementation process of the method for determining the above-mentioned wake-up result is described below in combination with an optional embodiment, but it is not used to limit the technical solution of the embodiment of the present application.

[0065] In this embodiment, a method for determining a wake-up result is provided. Figure 4 is a schematic diagram of a method for determining a wake-up result according to an embodiment of the present application, such as Figure 4 As shown, this embodiment provides an automated testing method for the wake-up success rate of a smart speaker. The specific steps are as follows:

[0066] Step S401: input verification parameters, including parameters threshold, time, number of plays num, wake-up word path path and email address for receiving wake-up results;

[0067] Where num is N, and N is a natural number.

[0068] In one embodiment, the input parameters are checked to see whether they are correct or missing. If the check fails, the process exits; if the check is correct, the process executes step S402.

[0069] Optionally, in one embodiment, after the wake-up word path is input, the wake-up word path may be processed, for example, the wake-up word path is processed into a full path of each wake-up word;

[0070] Step S402: Play the wake-up corpus;

[0071] Step S403: recording the feedback result of the smart speaker by starting a recording thread;

[0072] Step S404: Analyze the recording file, save the analysis result, and execute step S405;

[0073] Step S405: Determine whether to loop for N times, if yes, go to step s406, if no, go to step S402;

[0074] Step S406: Send the test results, where the test results include the wake-up success rate of the intelligent voice, which can be sent via email or text message.

[0075] Through the above steps, the corpus is automatically played by using the pyaudio library, and the audio file of the recorded speaker feedback is analyzed to obtain the wake-up result. In this method, the volume, speech speed and other parameters of the played corpus are controllable, and there will be no random phenomenon of speech speed, volume and other parameters. When a problem occurs, the recording file can be manually checked to accurately reproduce the problem. Moreover, since the solution does not require human participation, it can be tested 24 hours a day, greatly improving work efficiency.

[0076] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for enabling a device to be tested (which can be a mobile phone, a computer, a server, or a network device to be tested, etc.) to execute the methods of each embodiment of the present application.

[0077] Figure 5 is a structural block diagram of a device for determining a wake-up result according to an embodiment of the present application. Figure 5 As shown, including:

[0078] An acquisition module 52 is used to acquire a wake-up corpus for waking up the device to be tested;

[0079] It can be understood that the above wake-up corpus can be directly obtained from the corpus or generated by software. The wake-up corpus includes wake-up keywords. For example, for a certain Er speaker, the wake-up corpus can be set to "Xiaoyou Xiaoyou"; for a certain Xiaomi speaker, the wake-up corpus can be "Xiaoai Xiaoai"; for a certain Dong speaker, the wake-up corpus can be "a certain Dong a certain Dong". This application does not impose any restrictions on this.

[0080] It should be noted that the above wake-up corpus may include multiple types of languages, such as Chinese, English, or languages ​​of other countries. Among them, for Chinese, it may include Mandarin and may further include dialects of different regions, but is not limited thereto.

[0081] A first determining module 54 is configured to obtain, when the wake-up language material is played back to the device under test through the test device, a first number of times the wake-up language material is played back to the device under test, and a second number of times the device under test is awakened by the wake-up language material, wherein the test device has pre-stored a plurality of wake-up language materials;

[0082] It should be noted that the above test equipment can work all day, and the above cycle times can be pre-set.

[0083] In the process of cyclically playing the wake-up language material to the device to be tested through the test device, the wake-up language material may be replaced every time the wake-up language material is played to the device to be tested through the test device.

[0084] The second determining module 56 is configured to determine a wake-up result of the device under test according to the first number of times and the second number of times.

[0085] Through the above-mentioned device, by obtaining the wake-up corpus used to wake up the device to be tested; when the wake-up corpus is played in a loop to the device to be tested through the test device, the first number of times the wake-up corpus is played in a loop to the device to be tested, and the second number of times the device to be tested is awakened by the wake-up corpus are obtained, wherein the test device has pre-saved multiple wake-up corpora; and the wake-up result of the device to be tested is determined according to the first number and the second number, thereby solving the problem of how to accurately determine the wake-up result of the device in the related art, thereby improving the accuracy of the wake-up result of the device.

[0086] In an exemplary embodiment, the acquisition module 52 is further used to acquire a pre-configured initial wake-up corpus; perform noise elimination processing on the initial wake-up corpus to obtain a pure wake-up corpus; and set the wake-up parameters of the pure wake-up corpus to obtain a wake-up corpus used to wake up the device to be tested.

[0087] Among them, the wake-up corpus for waking up the device to be tested can be obtained through a mobile terminal, wherein the mobile terminal can realize automatic timed acquisition, or respond to acquisition and execute passive acquisition of corpus, and the mobile terminal can include but is not limited to mobile phones, tablets, computers, smart watches, etc.

[0088] The above-mentioned noise processing and elimination process may include a process of eliminating interfering sounds in the environment. Since in this embodiment, the wake-up language material is automatically played to the device to be tested by the test device, the human voice appearing in the environment can be eliminated as an interfering sound.

[0089] The wake-up parameters of the above-mentioned pure wake-up corpus may include the number of wake-up times, the wake-up volume threshold, the wake-up time, etc., but are not limited thereto.

[0090] Through the above method, by processing the wake-up corpus, the test process of the device to be tested can be implemented according to the processed wake-up corpus, thereby improving the accuracy of the wake-up result.

[0091] In an exemplary embodiment, the above-mentioned wake-up result determination device also includes a third determination module, which is used to determine whether the device to be tested successfully responds to any wake-up corpus played in the following manner: determine the feedback duration of the device to be tested to any wake-up corpus played and the feedback volume of the device to be tested within the feedback duration; determine a first duration from the feedback duration, wherein the target feedback volume corresponding to the first duration is continuously greater than a first preset value; when it is determined that the first ratio of the first duration to the feedback duration is greater than a second preset value, determine that the device to be tested is awakened.

[0092] Through the above embodiment, whether the above device to be tested successfully responds to the wake-up corpus can be determined from the perspectives of feedback duration and feedback volume, thereby improving the credibility of the device's successful response to the wake-up corpus.

[0093] Optionally, in one embodiment, when it is determined that a first ratio of the first duration to the feedback duration is not greater than a second preset value, it is determined that the device to be tested is not awakened.

[0094] In an optional embodiment, if it is determined that the feedback duration of the device to be tested for any wake-up corpus played is 1s, the feedback volume of the device to be tested within the feedback duration is 20dB, and the first preset value is 10dB, and the second preset value is 0.5, then when it is determined from the feedback duration that the first duration for which the feedback volume continues to be greater than 10dB is 0.6s, it is determined that the device to be tested is awakened. When it is determined from the feedback duration that the first duration for which the feedback volume continues to be greater than 10dB is 0.4s, it is determined that the device to be tested is not awakened.

[0095] In an exemplary embodiment, before determining the first duration from the feedback duration, the above-mentioned wake-up result determination device also includes a volume adjustment module, which is used to obtain the ambient noise volume when playing any of the wake-up corpus played; when the ambient noise volume is greater than a third preset value, obtain a first difference between the ambient noise volume and the third preset value; and adjust the feedback volume of the device to be tested within the feedback duration according to the first difference.

[0096] The volume adjustment module is further configured to update the sum of the first difference B between the ambient noise volume and the third preset value and the feedback volume of the device under test within the feedback duration to the feedback volume of the device under test within the feedback duration.

[0097] For example, in an optional embodiment, if it is determined that the ambient noise volume when the wake-up language is played is 6dB, the third preset value is 10dB, and the feedback volume of the device to be tested within the feedback duration is 10dB, then the sum of the first difference of 4dB between the ambient noise volume and the third preset value and the feedback volume of the device to be tested within the feedback duration of 10dB, 14dB, is updated as the feedback volume of the device to be tested within the feedback duration.

[0098] It should be noted that when adjusting the feedback volume of the device under test within the feedback duration according to the first difference, the degree of adjustment is related to the size of the first difference. For example, the larger the first difference, the greater the ambient noise, and the required degree of adjustment also needs to be increased accordingly.

[0099] In an exemplary embodiment, the above-mentioned wake-up result determination device also includes a fourth determination module, which is used to obtain the preset test time of the device to be tested and divide the preset test time into multiple time periods during the process of looping the wake-up corpus to the device to be tested through the test device; determine the earliest first start time and the second start time later than the first start time from the start times of the multiple time periods, and determine the first time period corresponding to the first start time and the second time period corresponding to the second start time; determine the first number of times the wake-up corpus is looped to the device to be tested through the test device within the first time period; obtain the number of times the wake-up corpus corresponds to the difference between the second start time and the first start time; and determine the sum of the number of times the wake-up corpus corresponds to the difference and the first number of times the wake-up corpus is looped to the device to be tested through the test device within the second time period.

[0100] The time unit of the preset test time may include year, month, day, hour, minute, and second. For example, when the time unit of the preset test time is hour, the preset test time may be set to 24 hours.

[0101] The first playback number may be pre-set, corresponding to the first start time. There may be multiple second playback numbers, corresponding to multiple second time periods corresponding to multiple second start times.

[0102] In an exemplary embodiment, the above-mentioned wake-up result determination device also includes a verification module for verifying the wake-up parameters in the wake-up corpus; when the parameter value corresponding to the wake-up parameter is not missing and the parameter value corresponding to the wake-up parameter meets the conditions, it is determined that the verification is passed, and the wake-up corpus is played in a loop to the device to be tested through the test device; the conditions satisfied by the parameter value corresponding to the wake-up parameter include at least one of the following: the wake-up frequency of the wake-up parameter is greater than the fourth preset value; the playback speed of the wake-up parameter is less than the fifth preset value; the playback volume of the wake-up parameter is greater than the sixth preset value.

[0103] The parameter values ​​of the wake-up parameters may be determined according to the device data of the device to be tested. For example, the playback volume, wake-up frequency, playback volume, etc. of the wake-up parameters may be determined according to the microphone model of the device to be tested.

[0104] Through the above-mentioned verification process of the wake-up corpus, the authenticity and usability of the wake-up corpus can be improved, the probability of error of invalid wake-up results obtained by using invalid wake-up corpus can be reduced, and the wake-up efficiency and wake-up accuracy in the test process can be improved.

[0105] In an exemplary embodiment, the apparatus for determining the wake-up result further includes a sending module, which is used to determine the wake-up result of the device to be tested according to the first number of times and the second number of times, and when it is determined that the wake-up result is abnormal, determine the abnormal wake-up corpus corresponding to the abnormal wake-up result; and send a prompt message carrying the abnormal wake-up corpus to the first object, wherein the prompt message is used to prompt the analysis of the abnormal wake-up result and the abnormal wake-up corpus. When it is determined that the wake-up result is not abnormal, the wake-up result is directly sent to the first object.

[0106] The first object may be a person, such as a user of a device, but is not limited thereto.

[0107] Through this embodiment, the problem that the speech speed, volume and other parameters of the corpus are difficult to maintain consistency due to artificial voice, and the corpus when the problem occurs cannot be reproduced is solved. By analyzing the saved wake-up results and using the abnormal wake-up corpus to reproduce the wake-up scene when an abnormal wake-up result occurs, the cause of the wake-up abnormality can be accurately located, the processing efficiency of the abnormal wake-up results is improved, and the user experience is improved.

[0108] An embodiment of the present application further provides a storage medium, which includes a stored program, wherein the program executes any of the above methods when it is run.

[0109] Optionally, in this embodiment, the storage medium may be configured to store program codes for executing the following steps:

[0110] S1, obtaining a wake-up corpus for waking up the device to be tested;

[0111] S2, in the case where the wake-up language material is played cyclically to the device to be tested by the test device, obtaining a first number of times the wake-up language material is played cyclically to the device to be tested, and a second number of times the device to be tested is awakened by the wake-up language material, wherein the test device has pre-stored a plurality of wake-up language materials;

[0112] S3: Determine a wake-up result of the device to be tested according to the first number of times and the second number of times.

[0113] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0114] Optionally, the electronic device may further include a transmission device to be tested and an input / output device to be tested, wherein the transmission device to be tested is connected to the processor, and the input / output device to be tested is connected to the processor.

[0115] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0116] S1, obtaining a wake-up corpus for waking up the device to be tested;

[0117] S2, in the case where the wake-up language material is played cyclically to the device to be tested by the test device, obtaining a first number of times the wake-up language material is played cyclically to the device to be tested, and a second number of times the device to be tested is awakened by the wake-up language material, wherein the test device has pre-stored a plurality of wake-up language materials;

[0118] S3: Determine a wake-up result of the device to be tested according to the first number of times and the second number of times.

[0119] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0120] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0121] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0122] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining a wake-up result, characterized in that: include: Obtaining a wake-up corpus for waking up the device to be tested; The wake-up corpus includes the wake-up keywords, and the wake-up corpus is obtained in at least one of the following ways: directly obtained from a corpus, generated by software; In the case where the wake-up language material is played cyclically to the device to be tested through the test device, a first number of times the wake-up language material is played cyclically to the device to be tested, and a second number of times the device to be tested is awakened by the wake-up language material are acquired, wherein a plurality of wake-up language materials are pre-stored in the test device; wherein each time the wake-up language material is played cyclically to the device to be tested through the test device, the wake-up language material is replaced; Determine a wake-up result of the device to be tested according to the first number of times and the second number of times; The method further comprises: Verifying the wake-up parameters in the wake-up corpus; Determine the parameter value corresponding to the wake-up parameter according to the device data of the device to be tested, and if the parameter value corresponding to the wake-up parameter is not missing and the parameter value corresponding to the wake-up parameter meets the condition, determine that the verification is passed, and loop-play the wake-up corpus to the device to be tested through the test device; The parameter value corresponding to the wake-up parameter satisfies at least one of the following conditions: The wake-up frequency of the wake-up parameter is greater than a fourth preset value; The playing speed of the wake-up parameter is less than a fifth preset value; The playback volume of the wake-up parameter is greater than a sixth preset value.

2. The method for determining the wake-up result according to claim 1, characterized in that: Obtain the wake-up corpus used to wake up the device under test, including: Get the pre-configured initial wake-up corpus; Performing noise elimination processing on the initial wake-up corpus to obtain pure wake-up corpus; The wake-up parameters of the pure wake-up corpus are set to obtain the wake-up corpus used for waking up the device to be tested.

3. The method for determining the wake-up result according to claim 1, characterized in that: Whether the device under test successfully responds to any wake-up language played is determined by the following method: Determine the feedback duration of the device under test for the wake-up language material played at any time and the feedback volume of the device under test within the feedback duration; Determining a first duration from the feedback durations, wherein a target feedback volume corresponding to the first duration is continuously greater than a first preset value; When it is determined that a first ratio of the first duration to the feedback duration is greater than a second preset value, it is determined that the device to be tested is awakened.

4. The method for determining the wake-up result according to claim 3, characterized in that: Before determining the first duration from the feedback duration, the method further includes: Obtaining the volume of the ambient noise when playing any of the wake-up corpora played; When the volume of the ambient noise is greater than a third preset value, obtaining a first difference between the volume of the ambient noise and the third preset value; The feedback volume of the device under test within the feedback duration is adjusted according to the first difference.

5. The method for determining the wake-up result according to claim 3, characterized in that: In the process of looping the wake-up language material to the device to be tested through the testing device, the method further includes: Obtaining a preset test time for the device to be tested, and dividing the preset test time into a plurality of time periods; Determine, from the start times of the multiple time periods, an earliest first start time and a second start time later than the first start time, and determine a first time period corresponding to the first start time and a second time period corresponding to the second start time; Determine a first number of times of cyclically playing the wake-up language material to the device to be tested by the test device within the first time period; Obtain the number of playbacks corresponding to the difference between the second start time and the first start time; determine the sum of the number of playbacks corresponding to the difference and the first number of playbacks as the second number of playbacks of the wake-up corpus in a loop by the test device to the device to be tested during the second time period.

6. The method for determining the wake-up result according to any one of claims 1 to 5, characterized in that: After determining the wake-up result of the device to be tested according to the first number of times and the second number of times, the method further includes: In the case where it is determined that the awakening result is abnormal, determining an abnormal awakening corpus corresponding to the abnormal awakening result; A prompt message carrying the abnormal awakening corpus is sent to the first object, where the prompt message is used to prompt an analysis of the abnormal awakening result and the abnormal awakening corpus.

7. A device for determining a wake-up result, characterized in that: include: An acquisition module, used to acquire a wake-up corpus for waking up the device to be tested; The wake-up corpus includes the wake-up keywords, and the wake-up corpus is obtained in at least one of the following ways: directly obtained from a corpus, generated by software; A first determining module is used to obtain a first number of times the wake-up language material is played in a loop to the device to be tested, and a second number of times the device to be tested is awakened by the wake-up language material, when the wake-up language material is played in a loop to the device to be tested by the test device, wherein a plurality of wake-up language materials are pre-stored in the test device; The first determining module is further configured to replace the wake-up language material once each time the wake-up language material is played to the device to be tested by the testing device; A second determining module, configured to determine a wake-up result of the device to be tested according to the first number of times and the second number of times; A verification module is used to determine the parameter value corresponding to the wake-up parameter according to the device data of the device to be tested, and to verify the wake-up parameter in the wake-up corpus; if the parameter value corresponding to the wake-up parameter is not missing and the parameter value corresponding to the wake-up parameter meets the conditions, it is determined that the verification is passed, and the wake-up corpus is played in a loop to the device to be tested through the test device; the conditions met by the parameter value corresponding to the wake-up parameter include at least one of the following: the wake-up frequency of the wake-up parameter is greater than a fourth preset value; the playback speed of the wake-up parameter is less than a fifth preset value; the playback volume of the wake-up parameter is greater than a sixth preset value.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 6 when executed.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 6 through the computer program.

Images