Method, device, equipment and storage medium for production testing of voice equipment

Abstract

The present application relates to the technical field of intelligent devices, and discloses a method, apparatus, device, and storage medium for production testing of voice equipment. The method comprises: sending current voice command information to the current voice device to be tested that is in the powered-on state on the production line through a voice device, and receiving current voice feedback information played by the current voice device to be tested; determining the current AI recognition model corresponding to the model of the current voice device to be tested based on the correspondence between the saved voice device model and the artificial intelligence AI recognition model; performing AI voice recognition on the current voice feedback information and the current voice command information through the current AI recognition model to obtain the corresponding current voice command test information. In this way, automatic detection of voice functions in the production process of voice equipment is realized, the production efficiency of the production line is improved, too much manpower is not required, and resources are saved.

Description

Technical Field

[0001] The present application relates to the field of intelligent device technology, for example, to methods, devices, equipment and storage media for production testing of voice devices. Background Art

[0002] With the popularization of smart technology, many devices have voice functions, so that users can control devices without contact. For example, a user sends a voice wake-up command "Xiao*, Xiao*", and the device that receives the voice wake-up command can perform voice recognition. If it determines that "Xiao*" is the wake-up command corresponding to this device, the device will be in the wake-up state.

[0003] Therefore, during the production process of voice equipment, the voice function of the device needs to be tested. Currently, the voice function of the device can be tested by manual speaking, listening, and watching. However, this manual testing method is inefficient and has a high probability of false detection. Summary of the Invention

[0004] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical elements or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0005] Embodiments of the present disclosure provide a method, apparatus, device, and storage medium for production testing of voice equipment to solve the technical problem of low efficiency in voice equipment testing.

[0006] In some embodiments, the method comprises:

[0007] Sending current voice command information to the currently tested voice device in the powered-on state on the production line through the voice device, and receiving current voice feedback information played by the currently tested voice device;

[0008] Determine the current AI recognition model corresponding to the model of the current voice device to be tested according to the stored correspondence between the voice device model and the artificial intelligence AI recognition model;

[0009] The current voice feedback information and the current voice command information are subjected to AI voice recognition through the current AI recognition model to obtain corresponding current voice command test information.

[0010] In some embodiments, the apparatus comprises:

[0011] The voice transceiver module is configured to send current voice command information to the current voice device under test that is in the turned-on state on the production line through the voice device, and receive current voice feedback information played by the current voice device under test;

[0012] An AI determination module is configured to determine a current AI recognition model corresponding to the model of the current voice device to be tested based on a stored correspondence between the voice device model and the artificial intelligence AI recognition model;

[0013] The first test module is configured to perform AI voice recognition on the current voice feedback information and the current voice command information through the current AI recognition model to obtain corresponding current voice command test information.

[0014] In some embodiments, the apparatus for voice device production testing includes a processor and a memory storing program instructions, and the processor is configured to perform the above-mentioned method for voice device production testing when executing the program instructions.

[0015] In some embodiments, the production test equipment includes the above-mentioned apparatus for production testing of voice equipment.

[0016] In some embodiments, the storage medium stores program instructions, which, when executed, execute the above-mentioned method for voice device production testing.

[0017] The method, apparatus, and device for voice equipment production testing provided by the embodiments of the present disclosure can achieve the following technical effects:

[0018] During the production and testing process of voice equipment, after the voice command information is sent through the voice device, the corresponding voice feedback information can be received for AI voice recognition, thereby automatically obtaining the corresponding test information. In this way, automatic detection of the voice function in the production process of voice equipment is realized, the production efficiency of the production line is improved, and too much manpower is not required, saving resources.

[0019] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] One or more embodiments are exemplarily described by corresponding drawings. These exemplary descriptions and drawings do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation. In addition,

[0021] Figure 1 This is a flow chart of a method for producing and testing a voice device provided by an embodiment of the present disclosure;

[0022] Figure 2 1 is a schematic diagram of a production line for air conditioner production testing provided by an embodiment of the present disclosure;

[0023] Figure 3 This is a flow chart of a method for producing and testing a voice device provided by an embodiment of the present disclosure;

[0024] Figure 4 This is a structural diagram of a device for producing and testing voice equipment provided by an embodiment of the present disclosure;

[0025] Figure 5 This is a structural diagram of a device for producing and testing voice equipment provided by an embodiment of the present disclosure;

[0026] Figure 6 It is a structural diagram of a production and testing device for voice equipment provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] In order to be able to understand the features and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The accompanying drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the sake of convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0028] In the description and claims of the embodiments of the present disclosure, as well as in the accompanying drawings, the terms "first," "second," and the like are used to distinguish similar items and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate to describe the embodiments of the present disclosure herein. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions.

[0029] Unless otherwise stated, the term "plurality" means two or more.

[0030] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0031] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0032] In the embodiment of the present disclosure, a device with voice function, that is, a voice device, can send voice command information through a voice device when performing voice testing during the production process, and perform AI voice recognition on the corresponding voice feedback information received, thereby automatically obtaining the corresponding test information. In this way, automatic detection of the voice function of the voice device in the production process is realized, the production efficiency of the production line is improved, too much manpower is not required, and resources are saved.

[0033] Figure 1 This is a flow chart of a method for producing and testing a voice device provided by an embodiment of the present disclosure. Figure 1 As shown, the process of voice equipment production testing includes:

[0034] Step 101: Send current voice command information to the current voice device to be tested that is in the powered-on state on the production line through the voice device, and receive current voice feedback information played by the current voice device to be tested.

[0035] Generally, when equipment is mass-produced, an assembly line method can be adopted, that is, the voice equipment will be placed on the production line, and the corresponding process of each workstation will be carried out one by one. Among them, one, two or more workstations in the production line will perform voice testing on the voice equipment, and the voice equipment to be tested is the current voice equipment to be tested.

[0036] Of course, the voice device needs to be in the power-on state when performing voice testing. Therefore, the current voice device to be tested is in the power-on state. The current voice device to be tested can be started manually or through a remote control terminal.

[0037] When conducting a voice test, the current voice command information can be played to the current voice device under test that is in the turned-on state through a voice device, for example, through the speaker in the voice device. The current voice command information includes: the current voice wake-up command information or the current voice operation command information. After the current voice device under test receives the current voice operation command information, it will make a voice response while performing the corresponding operation, that is, the current voice feedback information played by the current voice device under test.

[0038] Step 102: Determine the current AI recognition model corresponding to the model of the current voice device to be tested based on the stored correspondence between the voice device model and the artificial intelligence AI recognition model.

[0039] In the disclosed embodiments, before the current voice command information is sent via the voice device, the production test equipment has already been trained with artificial intelligence (AI) to store the corresponding relationship between the voice device model and the artificial intelligence (AI) voice recognition model. That is, in some embodiments, AI training is performed based on multiple voice command sample information and voice feedback sample information corresponding to each voice device model to obtain an AI voice recognition model corresponding to each model, and the corresponding relationship between the voice device model and the AI ​​voice recognition model is stored.

[0040] Of course, in some embodiments, AI training can be performed based on multiple sample information corresponding to each model of voice device, where the sample information may include: one or more of the sound sample information of the buzzer at startup, voice command sample information, voice feedback sample information, digital tube image sample information, vibration noise sample information, etc. In this way, an AI recognition model corresponding to each model can be obtained. Of course, the AI ​​recognition model may include: one or more of: AI voice recognition model, AI buzzer sound recognition model, AI image recognition model, AI noise recognition model, etc.

[0041] In this way, the current AI recognition model corresponding to the model of the current voice device to be tested can be determined based on the correspondence between the saved voice device model and the artificial intelligence AI voice recognition model, or the correspondence between the saved voice device model and the artificial intelligence AI recognition model.

[0042] The model of the current voice device to be tested can be input manually or automatically identified. In some embodiments, the production test equipment is equipped with a barcode gun, and the code of the current voice device to be tested can be scanned by the barcode gun to obtain the hardware identity information of the current voice device to be tested, and the model of the current voice device to be tested can be obtained.

[0043] Step 103: Perform AI voice recognition on the current voice feedback information and the current voice command information through the current AI recognition model to obtain corresponding current voice command test information.

[0044] The current AI recognition model is obtained through AI training of multiple sample information. Therefore, the current AI recognition model can be used to perform AI voice recognition on the current voice feedback information and the current voice command information, thereby obtaining the corresponding current voice command test information.

[0045] Among them, when the current voice command information is the current voice wake-up command information, the wake-up command test information can be obtained; when the current voice command information is the current voice operation command information, the operation command test information can be obtained.

[0046] For example: input the current voice command information into the current AI recognition model to obtain the corresponding current AI voice feedback information, and match the current AI voice feedback information with the current voice feedback information. If the two are consistent, it can be determined that this voice test has passed. If the two are inconsistent, it can be determined that this voice test has failed.

[0047] It can be seen that in the embodiment of the present disclosure, during the production and testing process of the voice equipment, after the voice command information is sent through the voice device, the corresponding voice feedback information can be received for AI voice recognition, thereby automatically obtaining the corresponding test information. In this way, automatic detection of the voice function in the production process of the voice equipment is realized, the production efficiency of the production line is improved, and too much manpower is not required, saving resources.

[0048] When performing a voice test on the voice device under test, the device must be powered on. Therefore, hardware testing can also be performed during the startup process. In some embodiments, a remote control terminal is controlled to send a power-on command to the voice device under test. A current buzzer sound sent by a buzzer device of the voice device under test is obtained through a voice device. Based on the current buzzer sound, a buzzer device test is performed.

[0049] For example, if the voice device under test is an air conditioner with voice functionality, a power-on command can be sent to the air conditioner via the remote control. Upon receiving the power-on command, the air conditioner will start running, and its buzzer will emit a corresponding sound. At this point, the microphone array in the voice device can capture the corresponding current buzzing sound. Therefore, based on the current buzzing sound, it is possible to determine whether the buzzer is sounding normally, whether the buzzer's timbre is normal, and other buzzer test information. The production test equipment can store an AI buzzer sound recognition model corresponding to each model. Therefore, based on the AI ​​buzzer sound recognition model, the current buzzing sound can be subjected to AI sound recognition to determine whether the buzzer is sounding normally, whether the buzzer's timbre is normal, and other buzzer test information.

[0050] In some embodiments, the production test equipment is also equipped with an image acquisition device, including a red, yellow, and blue (RGB) image acquisition device. Thus, when the air conditioner is turned on, the RGB image acquisition device can be used to obtain the startup image information of the digital tube of the current voice device under test that has received the startup command. AI image recognition is performed on the startup image information to obtain hardware detection information for the digital tube. Similarly, the production test equipment can store AI image recognition models corresponding to each model, so that AI image recognition can be performed on the startup image information to determine whether the digital tube display of the current voice device under test is normal, whether there are any missing lines, and so on.

[0051] Since the current voice device under test performs corresponding operation after receiving the current voice operation instruction information, the digital tube will also perform corresponding display. Therefore, in some embodiments, when the current voice instruction information is the current voice operation instruction information, the following is also included: obtaining the current display information of the digital tube of the current voice device under test through a red, yellow, and blue (RGB) image acquisition device; performing corresponding AI image recognition on the current display information to obtain corresponding operation result test information. In other words, AI image recognition can be performed on the current display information to determine whether the current display of the digital tube is the result corresponding to the current voice operation instruction information, further improving the accuracy of production testing.

[0052] In some embodiments, during the production testing of voice devices, not only voice testing but also quality defect testing can be performed. This involves directly measuring the vibration of the surface of the voice device under test using a laser interferometer. Combined with AI training for abnormal noise, this intelligent feedback can be provided regarding potential quality defects, such as excessive shaft eccentricity. Therefore, the testing process also includes: obtaining the current vibration information of the voice device under test that has received the current voice command information through a laser interferometer; and performing AI noise recognition on this vibration information to obtain corresponding quality test information.

[0053] Of course, during the production test of voice equipment, the voice feedback information collected by the voice device can also be wirelessly monitored by the testing workers. In this way, manual testing or manual spot checks and supervision can also be carried out to reduce the probability of artificial intelligence anomalies and further improve the accuracy of voice equipment production testing.

[0054] The following operation flow is aggregated into a specific embodiment to illustrate the voice equipment production test process provided by the embodiment of the present invention.

[0055] In one embodiment of the present disclosure, the voice device to be tested may be an air conditioner with voice function. Figure 2 Schematic diagram of a production line for air conditioner production testing provided by an embodiment of the present disclosure. Figure 2 As shown, the production line is equipped with a barcode gun, a voice device, an image acquisition device, an infrared remote control, and a laser interferometer. The voice device may include: a speaker array, a microphone array, and the image acquisition device may include: a depth camera and an RGB camera. These devices can communicate with the production test equipment. Of course, the production test equipment stores the AI ​​recognition models obtained after AI training through samples, including: AI voice recognition model, AI buzzer sound recognition model, AI image recognition model, and AI noise recognition model.

[0056] Figure 3 This is a flow chart of a method for producing and testing a voice device provided by an embodiment of the present disclosure. Figure 3, the voice equipment production test process includes:

[0057] Step 301: Determine the location information of each air conditioner on the production line using the image information of the air conditioners on the production line collected by the depth camera and the flow rate information of the production line.

[0058] Step 302: Obtain the coding information of each air conditioner through a barcode gun.

[0059] Step 303: When it is determined that the current air conditioner to be tested is located at the voice test position through the air conditioner image information, the model of the current air conditioner to be tested is determined, and the infrared remote controller is controlled to send a power-on command to the current air conditioner to be tested.

[0060] Step 304: Focus the current air conditioner to be tested through the microphone array, and obtain the current buzzing sound emitted by the buzzer of the current air conditioner to be tested, and perform AI buzzer recognition on the current buzzing sound according to the AI ​​recognition model corresponding to the model of the current air conditioner to be tested to obtain buzzing device test information.

[0061] Step 305: Obtain the power-on image information of the digital tube of the current air conditioner to be tested through the RGB camera, and perform AI image recognition on the power-on image information according to the AI ​​recognition model corresponding to the model of the current air conditioner to be tested to obtain the hardware detection information of the digital tube.

[0062] Steps 304 and 305 may be performed synchronously.

[0063] Step 306: Play the current voice wake-up command information to the air conditioner under test through the speaker array.

[0064] Step 307: The microphone array focuses on the current air conditioner to be tested, and records and obtains the current voice feedback information. The current voice feedback information is subjected to AI voice recognition according to the AI ​​recognition model corresponding to the model of the current air conditioner to be tested, and the wake-up command test information is obtained.

[0065] Step 308: Play the current voice operation instruction information to the air conditioner under test through the speaker array.

[0066] Step 309: The microphone array focuses on the current air conditioner to be tested, and records and obtains the current voice feedback information. The current voice feedback information is subjected to AI voice recognition based on the AI ​​recognition model corresponding to the model of the current air conditioner to be tested, and the operation instruction test information is obtained.

[0067] Step 310: Obtain the current display information of the digital tube of the current air conditioner to be tested through the RGB camera, and perform AI image recognition on the current display information according to the AI ​​recognition model corresponding to the model of the current air conditioner to be tested to obtain the operation result test information.

[0068] Step 309 and step 310 may be performed simultaneously.

[0069] Step 311: When it is determined through the air conditioner image information that the current air conditioner to be tested is located at the quality test position, the current vibration information of the current air conditioner to be tested is obtained through a laser interferometer, and AI noise recognition is performed on the current vibration information based on the AI ​​recognition model corresponding to the model of the current air conditioner to be tested to obtain corresponding quality test information.

[0070] It can be seen that in this embodiment, during the production test of the air conditioner, voice command information can be sent through the voice device, and AI voice recognition can be performed on the corresponding voice feedback information received, thereby automatically obtaining the corresponding test information. In this way, automatic detection of the voice function in the production process of the voice equipment is realized, which improves the production efficiency of the production line, does not require excessive manpower, and saves resources. Of course, AI image recognition and AI noise recognition of the corresponding air conditioner can also be performed to realize automatic testing of the air conditioner hardware, quality, etc., further improving the efficiency and automation of air conditioner production testing and also improving the accuracy of the test.

[0071] According to the above process for production testing of voice equipment, an apparatus for production testing of voice equipment can be constructed.

[0072] Figure 4 This is a schematic diagram of a structure of a voice equipment production test device provided by an embodiment of the present disclosure. Figure 4 As shown, the production test apparatus for voice equipment includes: a voice transceiver module 410, an AI determination module 420 and a first test module 430.

[0073] The voice transceiver module 410 is configured to send current voice command information to the current voice device under test that is in the turned-on state on the production line through the voice device, and receive current voice feedback information played by the current voice device under test.

[0074] The AI ​​determination module 420 is configured to determine the current AI recognition model corresponding to the model of the current voice device to be tested based on the stored correspondence between the voice device model and the artificial intelligence AI recognition model.

[0075] The first test module 430 is configured to perform AI voice recognition on the current voice feedback information and the current voice command information through the current AI recognition model to obtain corresponding current voice command test information.

[0076] In some embodiments, it also includes: a training and saving module, which is configured to perform AI training based on multiple sample information corresponding to each model of voice device, obtain an AI recognition model corresponding to each model, and save the correspondence between the voice device model and the AI ​​recognition model, wherein the AI ​​recognition model includes: one or more of: AI voice recognition model, AI buzzer sound recognition model, AI image recognition model, AI noise recognition model, etc.

[0077] In some embodiments, the second test module is further configured to control the remote control terminal to send a power-on command to the current voice device to be tested; obtain the current buzzing sound sent by the buzzing device of the current voice device to be tested through the voice device; and perform buzzing device testing based on the current buzzing sound.

[0078] In some embodiments, it also includes: a third test module, which is configured to obtain the power-on image information of the digital tube of the current voice device under test that has received the power-on command through a red, yellow, and blue (RGB) image acquisition device; perform AI image recognition on the power-on image information to obtain hardware detection information of the digital tube.

[0079] In some embodiments, the first test module 430 is specifically configured to obtain wake-up instruction test information when the current voice instruction information is current voice wake-up instruction information; and obtain run instruction test information when the current voice instruction information is current voice run instruction information.

[0080] In some embodiments, the first test module 430 is further configured to obtain the current display information of the digital tube of the current voice device to be tested through a red, yellow, and blue (RGB) image acquisition device; perform corresponding AI image recognition on the current display information to obtain corresponding operation result test information.

[0081] In some embodiments, it also includes: a fourth test module, which is configured to obtain current vibration information of the current voice device to be tested that receives the current voice command information through a laser interferometer; perform AI noise recognition on the current vibration information to obtain corresponding quality test information.

[0082] The voice equipment production test process used in the voice equipment production test apparatus is further described below in conjunction with embodiments.

[0083] In this embodiment, the production test line diagram of the air conditioner is as follows: Figure 2 shown.

[0084] Figure 5 This is a schematic diagram of a structure of a voice equipment production test device provided by an embodiment of the present disclosure. Figure 5As shown, the production test device for voice equipment includes: a voice transceiver module 410, an AI determination module 420, a first test module 430, a training and storage module 440, a second test module 450, a third test module 460 and a fourth test module 470.

[0085] The training and saving module 440 performs AI training based on multiple sample information corresponding to each model of voice device, obtains an AI recognition model corresponding to each model, and saves the correspondence between the voice device model and the AI ​​recognition model, wherein the AI ​​recognition model includes: AI voice recognition model, AI buzzer sound recognition model, AI image recognition model, and AI noise recognition model.

[0086] In this way, after the production line is turned on, the location information of each air conditioner is determined by using the image information of the air conditioners on the production line captured by the depth camera and the flow rate information of the production line. The barcode gun is used to obtain the coding information of each air conditioner. When the air conditioner image information determines that the current air conditioner to be tested is located in the voice test position, the second test module 450 determines the model of the current air conditioner to be tested, and can control the infrared remote control to send a power-on command to the current air conditioner to be tested, and focus the current air conditioner to be tested through the microphone array, and obtain the current buzzing sound emitted by the buzzer of the current air conditioner to be tested, and perform AI recognition on the current buzzing sound according to the AI ​​recognition model corresponding to the model of the current air conditioner to be tested, to obtain buzzer device test information. The third test module 460 obtains the power-on image information of the digital tube of the current air conditioner to be tested through the RGB camera, and performs AI image recognition on the power-on image information according to the AI ​​recognition model corresponding to the model of the current air conditioner to obtain hardware detection information of the digital tube.

[0087] Then, the voice transceiver module 410 can play the current voice wake-up command information to the current air conditioner to be tested through the speaker array, and control the microphone array to focus on the current air conditioner to be tested, and record and obtain the current voice feedback information. In this way, according to the AI ​​recognition model saved in the training and storage module 440, the AI ​​determination module 420 determines the AI ​​recognition model corresponding to the model of the current air conditioner to be tested, so that the first test module 430 can perform AI voice recognition on the current voice feedback information to obtain the wake-up command test information. Afterwards, the voice transceiver module 410 can also play the current voice operation instruction information to the current air conditioner to be tested through the speaker array, and control the microphone array to focus on the current air conditioner to be tested, and record and obtain the current voice feedback information. In this way, according to the AI ​​recognition model saved in the training and storage module 440, the AI ​​determination module 420 determines the AI ​​recognition model corresponding to the model of the current air conditioner to be tested, so that the first test module 430 can perform AI voice recognition on the current voice feedback information to obtain operation instruction test information, and the first test module 430 can also obtain the current display information of the digital tube of the current air conditioner to be tested through the RGB camera, and perform AI image recognition on the current display information according to the AI ​​recognition model corresponding to the model of the current air conditioner to be tested to obtain operation result test information.

[0088] During the operation of the production line, when it is determined through the air-conditioning image information that the current air-conditioning to be tested is located at the quality test position, the fourth test module 470 obtains the current vibration information of the current air-conditioning to be tested through a laser interferometer, and performs AI noise recognition on the current vibration information based on the AI ​​recognition model corresponding to the model of the current air-conditioning to be tested to obtain corresponding quality test information.

[0089] It can be seen that in this embodiment, during the production test process of the air conditioner, the device for production testing of the voice equipment can send voice command information through the voice device, and perform AI voice recognition on the corresponding voice feedback information received, thereby automatically obtaining the corresponding test information. In this way, the automatic detection of the voice function in the production process of the voice equipment is realized, the production efficiency of the production line is improved, and excessive manpower is not required, saving resources. Of course, the device for production testing of the voice equipment can also perform AI image recognition and AI noise recognition of the corresponding air conditioner, and realize automatic testing of the air conditioner hardware, quality, etc., further improving the efficiency and automation of air conditioner production testing, and also improving the accuracy of the test.

[0090] The embodiment of the present disclosure provides a device for production testing of a voice device, the structure of which is as follows: Figure 6 As shown, including:

[0091] Processor 1000 and memory 1001 may also include a communication interface 1002 and a bus 1003. Processor 1000, communication interface 1002, and memory 1001 may communicate with each other via bus 1003. Communication interface 1002 may be used for information transmission. Processor 1000 may invoke logic instructions in memory 1001 to execute the method for voice device production testing described in the above embodiment.

[0092] In addition, the logic instructions in the memory 1001 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0093] Memory 1001, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present disclosure. Processor 1000 executes the program instructions / modules stored in memory 1001 to perform functional applications and data processing, thereby implementing the method for voice device production testing in the above-mentioned method embodiment.

[0094] The memory 1001 may include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data generated based on the use of the terminal device. Furthermore, the memory 1001 may include high-speed random access memory and non-volatile memory.

[0095] An embodiment of the present disclosure provides a device for production testing of a voice device, comprising: a processor and a memory storing program instructions, wherein the processor is configured to execute a method for production testing of a voice device when executing the program instructions.

[0096] An embodiment of the present disclosure provides a production test device, including the above-mentioned production test apparatus for voice equipment.

[0097] An embodiment of the present disclosure provides a storage medium storing program instructions, which, when executed, execute the above-mentioned method for production testing of a voice device.

[0098] An embodiment of the present disclosure provides a computer program product, which includes a computer program stored on a storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the above-mentioned method for voice device production testing.

[0099] The aforementioned storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0100] The technical solution of the embodiments of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present disclosure. The aforementioned storage medium may be a non-transitory storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program code, or a transient storage medium.

[0101] The above description and accompanying drawings sufficiently illustrate the embodiments of the present disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. The embodiments represent only possible variations. Unless expressly required, individual components and functions are optional, and the order of operations may vary. Portions and features of some embodiments may be included in or substituted for portions and features of other embodiments. The scope of the embodiments of the present disclosure includes the entire scope of the claims and all available equivalents thereof. When used in this application, although the terms "first," "second," etc. may be used in this application to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element can be called a second element, and similarly, a second element can be called a first element, without changing the meaning of the description, as long as all occurrences of "first element" are consistently renamed and all occurrences of "second element" are consistently renamed. The first element and the second element are both elements, but they may not be the same element. Furthermore, the terms used in this application are only used to describe the embodiments and are not intended to limit the claims. As used in the description of the embodiments and claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more of the associated listings. In addition, when used in this application, the term "comprise" and its variations "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups of these. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method or apparatus comprising the element. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can be referred to the description of the method part.

[0102] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present disclosure. The technicians will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0103] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units can be merely a logical functional division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, and can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected to implement this embodiment according to actual needs. In addition, the functional units in the embodiments of the present disclosure may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0104] The flowcharts and block diagrams in the accompanying drawings show the possible implementation architectures, functions and operations of the systems, methods and computer program products according to the embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of the code, and the module, program segment or part of the code contains one or more executable instructions for implementing the specified logical functions. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, which can depend on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in an order different from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified function or action, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for production testing of a voice device, characterized in that: include: Sending current voice command information to the currently tested voice device in the powered-on state on the production line through the voice device, and receiving current voice feedback information played by the currently tested voice device; Determine, based on the stored correspondence between voice device models and artificial intelligence (AI) recognition models, a current AI recognition model corresponding to the model of the voice device currently under test, wherein the correspondence between the voice device models and the AI ​​recognition models is obtained by performing AI training based on multiple sample information corresponding to each voice device model, and saving the AI ​​recognition model corresponding to each model. The AI ​​recognition model includes one or more of an AI voice recognition model, an AI buzzer sound recognition model, an AI image recognition model, and an AI noise recognition model; The current voice feedback information and the current voice command information are subjected to AI voice recognition through the current AI recognition model to obtain corresponding current voice command test information.

2. The method according to claim 1, characterized in that Also includes: Controlling the remote control terminal to send a power-on command to the current voice device to be tested; Obtaining, through the voice device, a current buzzing sound sent by the buzzing device of the current voice device to be tested; A buzzer device test is performed according to the current buzzer sound.

3. The method according to claim 2, characterized in that Also includes: Obtaining, through a red, yellow, and blue (RGB) image acquisition device, power-on image information of the digital tube of the current voice device to be tested that has received the power-on command; Perform AI image recognition on the power-on image information to obtain hardware detection information of the digital tube.

4. The method according to claim 1, wherein Obtaining the corresponding current voice command test information includes: When the current voice command information is current voice wake-up command information, obtaining wake-up command test information; In a case where the current voice instruction information is current voice operation instruction information, operation instruction test information is obtained.

5. The method according to claim 4, characterized in that In the case where the current voice instruction information is current voice operation instruction information, the method further includes: Obtain the current display information of the digital tube of the current voice device to be tested through a red, yellow, and blue (RGB) image acquisition device; Perform corresponding AI image recognition on the current display information to obtain corresponding operation result test information.

6. The method according to any one of claims 1 to 5, characterized in that Also includes: Obtaining, by means of a laser interferometer, current vibration information of the current voice device to be tested that has received the current voice command information; Perform AI noise recognition on the current vibration information to obtain corresponding quality test information.

7. A device for production testing of voice equipment, characterized in that: include: The voice transceiver module is configured to send current voice command information to the current voice device under test that is in the turned-on state on the production line through the voice device, and receive current voice feedback information played by the current voice device under test; An AI determination module is configured to determine a current AI recognition model corresponding to the model of the current voice device to be tested based on a stored correspondence between the voice device model and the artificial intelligence AI recognition model; A first testing module is configured to perform AI voice recognition on the current voice feedback information and the current voice command information through the current AI recognition model to obtain corresponding current voice command test information; It also includes: a training and saving module, which is configured to perform AI training based on multiple sample information corresponding to each model of voice device, obtain an AI recognition model corresponding to each model, and save the correspondence between the voice device model and the AI ​​recognition model, wherein the AI ​​recognition model includes: one or more of: AI voice recognition model, AI buzzer sound recognition model, AI image recognition model, and AI noise recognition model.

8. A device for production testing of a voice device, the device comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to perform the method for voice device production testing according to any one of claims 1 to 6 when executing the program instructions.

9. A production test equipment, characterized in that, include: An apparatus for production testing of a voice device as claimed in claim 7 or 8.

10. A storage medium storing program instructions, characterized in that: When the program instructions are executed, the method for voice device production testing according to any one of claims 1 to 6 is executed.

Images