Household appliance testing method and related device

Abstract

The invention discloses a household appliance testing method and a related device, and relates to the technical field of testing, the household appliance testing method is applied to intelligent testing equipment, the household appliance testing method comprises the steps that a testing instruction issued by a tester is received, and the testing instruction comprises a testing object, position information of the testing object and testing content; generating a test case set according to the test object and the test content; testing the test object by using the test case set and combining the position information of the test object, and determining a test result of the test object on the test case in the test case set; and performing statistical analysis on a test result of the test object on the test case in the test case set to obtain a final test result of the test object. Compared with the prior art, the household appliance testing method disclosed by the invention is relatively low in manual dependence degree and relatively high in testing efficiency, and since the execution of the test and the determination of the test result are both completed by the intelligent testing equipment without participation of testers, the influence of human subjective factors on the test result is avoided.

Description

Technical Field

[0001] The present application relates to the field of testing technology, and in particular to a household appliance testing method and related devices. Background Art

[0002] In the current research and development and production of smart home appliances, all major appliance companies need to test the home appliances they develop. The test results directly provide important technical parameters of the products for research and development work, and provide data basis for the iterative evolution of products. At the same time, they can make a comprehensive comparison between their own products and those of competitors to comprehensively measure the competitiveness of their own products.

[0003] The current home appliance testing method is a manual testing method, that is, the home appliance is tested by a tester. Taking the voice interaction performance test of an air conditioner as an example, the manual testing method is that the tester issues a voice test command to test the air conditioner, determines the test results, and performs statistical analysis on the test results.

[0004] Current home appliance testing methods are highly dependent on manual operation, which results in low testing efficiency. In addition, the high-intensity, repetitive working mode easily causes fatigue and sleepiness of testers, which in turn affects the accuracy of the test results. Summary of the invention

[0005] In view of this, the present application provides a household appliance testing method and related devices, which are used to solve the problem that the existing household appliance testing method is highly dependent on manual operation, resulting in low testing efficiency and the accuracy of the test results is easily affected by human subjective factors. The technical solution is as follows:

[0006] A first aspect of the present application provides a home appliance testing method, which is applied to a smart testing device. The home appliance testing method comprises:

[0007] Receiving a test instruction issued by a tester, wherein the test instruction includes a test object, location information of the test object, and test content for the test object;

[0008] Generate a test case set according to the test object and test content;

[0009] Using the test case set and combining with the location information of the test object, testing the test object, and determining the test result of the test object on the test case in the test case set;

[0010] Statistical analysis is performed on the test results of the test object on the test cases in the test case set to obtain a final test result of the test object.

[0011] In a possible implementation, the test content includes: test items and test requirements corresponding to the test items;

[0012] Generating a test case set according to the test object and the test content includes:

[0013] Determine the test strategy based on the fine-tuned large model and the test object, the test items and the test requirements corresponding to the test items;

[0014] Based on the fine-tuned large model and according to the test strategy, a test case set is generated;

[0015] The fine-tuned large model is obtained by fine-tuning the pre-trained large model on a specific task, and the specific task includes a test case generation task.

[0016] In a possible implementation, generating a test case set based on the fine-tuned large model and according to the test strategy includes:

[0017] Based on the fine-tuned large model, and according to the test strategy, generate a test corpus and a test condition set;

[0018] Based on the fine-tuned large model, a test case set is generated based on the test corpus and the test condition set, wherein each test case in the test case set includes a test corpus in the test corpus and a test condition in the test condition set.

[0019] In a possible implementation, each test case in the test case set includes a test condition and a test corpus under the test condition, and the test condition in each test case in the test case set includes a test distance;

[0020] The step of testing the test object by using the test case set and combining the location information of the test object, and determining the test result of the test object on the test case in the test case set includes:

[0021] For each test case in the test case set:

[0022] Determine the test position corresponding to the test case according to the position information of the test object and the test distance in the test case;

[0023] Move to the test position corresponding to the test case, and test the test object with the test case;

[0024] Determine a test result of the test object on the test case.

[0025] In a possible implementation, the test conditions in each test case in the test case set further include testing speech attributes;

[0026] The testing of the test object using the test case includes:

[0027] According to the test speech attribute in the test case, synthesize the audio of the test corpus in the test case to obtain the speech test instruction corresponding to the test case;

[0028] Play the voice test instructions corresponding to the test case.

[0029] In a possible implementation, the intelligent testing device is configured with an audio acquisition module;

[0030] Determining the test result of the test object on the test case includes:

[0031] Using the audio acquisition module to collect voice feedback information corresponding to the test case, wherein the voice feedback information corresponding to the test case is voice information fed back by the test subject in response to the voice test instruction corresponding to the test case played;

[0032] Converting the voice feedback information corresponding to the test case into text to obtain the test feedback text corresponding to the test case;

[0033] The test result of the test object on the test case is determined according to the test corpus in the test case and the test feedback text corresponding to the test case.

[0034] In a possible implementation, determining the test result of the test object on the test case according to the test corpus in the test case and the test feedback text corresponding to the test case includes:

[0035] Based on the fine-tuned large model, and based on the test corpus in the test case and the test feedback text corresponding to the test case, determine whether the test object passes the test on the test case, and obtain the test result of the test object on the test case;

[0036] The fine-tuned large model is obtained by fine-tuning the pre-trained large model on a specific task, and the specific task includes a task determined by a test result on a test case.

[0037] In a possible implementation, the performing statistical analysis on the test results of the test object on the test cases in the test case set includes:

[0038] Performing statistical analysis in multiple dimensions on the test results of the test object on each test case in the test case set to obtain test indicators in multiple dimensions as the final test results of the test object;

[0039] The household appliance testing method further comprises:

[0040] Determining test optimization suggestions for the test object according to the test indicators of the multiple dimensions;

[0041] Generate a test report including the final test results of the test object and the test optimization suggestions.

[0042] In a possible implementation, determining a test optimization suggestion for the test object according to the test indicators of the multiple dimensions; and generating a test report including a final test result of the test object and the test optimization suggestion include:

[0043] Based on the fine-tuned large model, and taking the test indicators of the multiple dimensions as a basis, determining a test optimization suggestion for the test object, and generating a test report including the test indicators of the multiple dimensions and the test optimization suggestion;

[0044] The fine-tuned large model is obtained by fine-tuning the pre-trained large model on specific tasks, and the specific tasks include test indicator analysis and test report generation tasks.

[0045] A second aspect of the present application provides a home appliance testing device, which is applied to an intelligent testing device, and the home appliance testing device comprises: a test instruction receiving module, a test case generating module, a testing module, a first test result determining module and a second test result determining module;

[0046] The test instruction receiving module is used to receive a test instruction issued by a tester, wherein the test instruction includes a test object, location information of the test object, and test content for the test object;

[0047] The test case generation module is used to generate a test case set according to the test object and test content;

[0048] The test module is used to test the test object by using the test case set and combining the location information of the test object;

[0049] The first test result determination module is used to determine the test result of the test object on the test case in the test case set;

[0050] The second test result determination module is used to perform statistical analysis on the test results of the test object on the test cases in the test case set to obtain the final test results of the test object.

[0051] A third aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0052] The memory is used to store computer programs;

[0053] The processor is used to execute the computer program so that the electronic device can implement the steps of any one of the household appliance testing methods described above.

[0054] A fourth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the steps of any one of the above-mentioned home appliance testing methods.

[0055] A fifth aspect of the present application provides a computer program product, comprising computer-readable instructions, which, when executed on an electronic device, enables the electronic device to implement the steps of any one of the above-described methods for testing household appliances.

[0056] By means of the above technical scheme, the home appliance testing method provided by the present application first receives the test instruction issued by the tester, then generates a test case set according to the test object and the test content in the test instruction, then uses the test case set, combined with the position information of the test object in the test instruction, to test the test object, and determines the test result of the test object on the test case in the test case set, and finally performs statistical analysis on the test result of the test object on the test case in the test case set to obtain the final test result of the test object. The home appliance testing method provided by the present application enables the intelligent testing device to automatically generate a test case set according to the test instruction issued by the tester, automatically test the test object with the test case set, and automatically perform statistical analysis on the test result of the test object on the test case in the test case set, that is, the tester only needs to issue a test instruction to the intelligent testing device (the tester only needs to issue the instruction once), and the intelligent testing device can automatically complete the test of the test object and determine the test result. It can be seen that the home appliance testing method provided by the present application has a low degree of manual dependence and a high testing efficiency. Moreover, since the execution of the test and the determination of the test results are all completed by intelligent testing equipment without the participation of testers, the influence of human subjective factors on the test results is avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present invention 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, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0058] Figure 1 A schematic diagram of the structure of an intelligent testing device provided in an embodiment of the present application;

[0059] Figure 2 A schematic diagram of a flow chart of a household appliance testing method provided in an embodiment of the present application;

[0060] Figure 3 A schematic diagram of a process for generating a test case set according to a test object and a test content provided in an embodiment of the present application;

[0061] Figure 4 A flow chart of using a test case set provided in an embodiment of the present application to test a test object in combination with the location information of the test object, and determining the test result of the test object on the test case in the test case set;

[0062] Figure 5 A schematic diagram of a smart test device planning a path to a test location provided in an embodiment of the present application;

[0063] Figure 6 A schematic diagram of the structure of a household appliance testing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0064] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0065] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0066] 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 need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0067] The household appliance testing method provided in this application can be applied to mobile intelligent testing equipment. Figure 1 As shown, the intelligent test device may include components such as a processor 101 , a memory 102 , an audio circuit 103 , a speaker 104 , a microphone 105 , and a power supply 106 .

[0068] Those skilled in the art will understand that Figure 1 This is merely an example of an intelligent testing device and does not constitute a limitation on the intelligent testing device. The intelligent testing device may include more or fewer components than shown in the figure, or a combination of certain components, or different components.

[0069] The speaker 104 can play audio. The microphone 105 can collect audio played by the speaker 104, and can also collect voice information output by an external device.

[0070] The memory 102 can be used to store instructions and data. The memory 102 can mainly include an instruction storage area and a data storage area. The data storage area can store various data, such as multimedia files, texts, etc.; the instruction storage area can store software units such as operating systems, applications, instructions required for at least one function, or their subsets and extensions. It can also include non-volatile random access memory; provide the processor with hardware, software and data resources including management of computing and processing equipment, and support control software and applications. It is also used for the storage of multimedia files, and the storage of running programs and applications.

[0071] Processor 101 is the control center of the intelligent test device. It uses various interfaces and lines to connect various parts of the entire device. By running or executing instructions stored in the memory and calling data stored in the memory, it performs various functions of the intelligent test device and processes data, thereby controlling the device as a whole.

[0072] The memory 102 may be used to store software codes related to the household appliance testing method. The processor 101 may execute the software codes in the memory 102 and may also schedule other units to implement corresponding functions.

[0073] In some embodiments, the processor 101 and the memory 102 may be implemented on a single chip, and in some embodiments, they may be implemented on separate chips. The processor 101 may also be used to generate corresponding operation control signals, send them to corresponding components of the computing and processing device, read and process data in the software, and especially read and process data and programs in the memory, so that each functional module therein performs corresponding functions, thereby controlling the corresponding components to act according to the requirements of the instructions.

[0074] The intelligent testing device may also include a power supply 106 (such as a battery) for supplying power to each component. Preferably, the power supply 106 may be logically connected to the processor 101 through a power management system, thereby managing charging, discharging, and power consumption through the power management system.

[0075] Optionally, the smart test device may further include an external interface, which may be a standard Micro USB interface or a multi-pin connector, and may be used to connect the smart test device to communicate with other devices, or to connect a charger to charge the smart test device.

[0076] Optionally, the intelligent testing device may further include: a camera, an input unit, and a display unit.

[0077] The camera can be used to collect image data in the environment where the smart test equipment is located.

[0078] The input unit can be used to receive input digital or character information, and generate key signal input related to the user settings and function control of the portable multifunctional device. Specifically, the input unit may include a touch screen (optional) and / or other input devices. The touch screen can collect the user's touch operation on or near it (such as the user's operation on or near the touch screen using any suitable object such as fingers, joints, stylus, etc.), and drive the corresponding connection device according to a pre-set program. The touch screen can detect the user's touch action on the touch screen, convert the touch action into a touch signal and send it to the processor 101, and can receive and execute the command sent by the processor 101; the touch signal at least includes contact point coordinate information. The touch screen can provide an input interface and an output interface between the intelligent test device and the user. In addition, the touch screen can be implemented using multiple types such as resistive, capacitive, infrared and surface acoustic wave. In addition to the touch screen, the input unit can also include other input devices that can receive input data. Specifically, other input devices may include but are not limited to one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), an operating rod, etc.

[0079] The display unit may be used to display information input by a user or provided to a user, various menus of the intelligent test device, an interactive interface, file display, and / or playback of any multimedia file.

[0080] Optionally, the intelligent testing device may also include a wireless fidelity (WiFi) module, a Bluetooth module, sensors with different functions, and the like.

[0081] The processor 101 in the intelligent testing equipment can be a hardware circuit (such as an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a general-purpose processor, a digital signal processor (DSP), a microprocessor or a microcontroller, etc.), or a combination of these hardware circuits. For example, the processor 101 can be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0082] The inventor of this case discovered in the process of implementing this case that the current method of testing home appliances is that the tester issues test instructions one by one. After each test instruction is issued, the tester needs to observe whether the test object makes correct feedback on the test instruction to obtain the test result of the test object on each test instruction. Finally, the tester will also conduct statistical analysis on the test results of the test object on each test instruction to obtain the final test result. It is not difficult to find from the above test process that the current method of testing home appliances is highly dependent on manual operation, which leads to low test efficiency. Moreover, during the test process, the tester needs to perform repeated work many times, which will cause the tester to be easily fatigued and sleepy, thereby affecting the objective accuracy of the test results. In view of the defects of the existing home appliance testing method, the inventor of this case conducted research, and through continuous research, finally proposed a home appliance testing method, which overcomes the defects of the existing home appliance testing method.

[0083] Next, the household appliance testing method provided by the present application is introduced through the following embodiments.

[0084] See also Figure 2 , shows a schematic flow chart of a home appliance testing method provided in an embodiment of the present application, the home appliance testing method is applied to a movable intelligent testing device, and the home appliance testing method may include:

[0085] Step S201: receiving a test instruction issued by a tester.

[0086] The test instruction includes the test object, the location information of the test object and the test content for the test object, and the test content for the test object may include test items and test requirements corresponding to the test items. The test object in this embodiment may be a home appliance capable of voice interaction, such as an air conditioner, a refrigerator, etc. capable of voice interaction, and the home appliance testing method provided in this embodiment is a voice interaction testing method for home appliances.

[0087] Exemplarily, the test instruction is "Please test the air conditioner of xx brand at xx location, use voice command to test the air conditioner temperature adjustment, and be 1 to 2 meters away from the air conditioner. The test corpus covers middle-aged and young men and women." In this example, the test object is "xx brand air conditioner," the location of the test object is "xx location," and the test item is "voice command to test the air conditioner temperature adjustment." The test requirement corresponding to the test item is to be 1 to 2 meters away from the air conditioner, and the tone and timbre of the test instruction cover middle-aged and young men and women.

[0088] Step S202: Generate a test case set according to the test object and test content.

[0089] In one possible implementation, the test instructions issued by the tester may be voice test instructions. After receiving the voice test instructions issued by the tester, the intelligent testing device may convert the voice test instructions into text, and then obtain the test object, the location information of the test object, and the test content for the test object from the text.

[0090] After obtaining the test content for the test object, the intelligent test device can determine the test strategy according to the test object and the test content, and then generate a test case set according to the test strategy.

[0091] Step S203: Use the test case set and the location information of the test object to test the test object, and determine the test results of the test object on the test cases in the test case set.

[0092] For each test case in the test case set, the intelligent testing device can determine the test position corresponding to the test case based on the test case and the location information of the test object, and then move to the test position corresponding to the test case, test the test object with the test case, and determine the test result of the test object on the test case.

[0093] The test result of the test object on a test case can indicate whether the test object passes the test on the test case.

[0094] Step S204: Perform statistical analysis on the test results of the test object on the test cases in the test case set to obtain the final test results of the test object.

[0095] Perform statistical analysis on the test results of the test object on the test cases in the test case set to obtain test indicators that can reflect the performance of the test object during the test process as the final test results of the test object.

[0096] In this embodiment, the tester only needs to send a test instruction including the test object, the location information of the test object and the test content for the test object to the intelligent test device, and the intelligent test device can automatically complete the test of the test object and determine the test result.

[0097] The home appliance testing method provided in the embodiment of the present application first receives the test instruction issued by the tester, then generates a test case set according to the test object and the test content in the test instruction, then uses the test case set, and at the same time combines the position information of the test object in the test instruction to test the test object, and determines the test result of the test object on the test case in the test case set, and finally statistically analyzes the test result of the test object on the test case in the test case set to obtain the final test result of the test object. The home appliance testing method provided in the embodiment of the present application enables the intelligent testing device to automatically generate a test case set according to the test instruction issued by the tester, automatically test the test object with the test case set, and automatically statistically analyze the test result of the test object on the test case in the test case set, that is, the tester only needs to issue the test instruction to the intelligent testing device (the tester only needs to issue the instruction once), and the intelligent testing device can automatically complete the test of the test object and the determination of the test result. It can be seen that the home appliance testing method provided in the embodiment of the present application has a low degree of manual dependence and a high test efficiency, and since the execution of the test and the determination of the test result are all completed by the intelligent testing device without the participation of the tester, the influence of human subjective factors on the test result is avoided.

[0098] In another embodiment of the present invention, the specific implementation process of "step S202: generating a test case set according to the test object and the test content" in the above embodiment is introduced.

[0099] See also Figure 3 , shows a flow chart of generating a test case set according to the test object and test content, which may include:

[0100] Step S301: Based on the fine-tuned large model, the test strategy is determined according to the test object and test content.

[0101] In a possible implementation, the smart test device may have a built-in fine-tuned large model, and the smart test device may determine a test strategy based on the built-in fine-tuned large model and the test object and test content.

[0102] The above embodiment mentioned that the test content may include test items and test requirements corresponding to the test items. The test strategy may be determined based on the fine-tuned large model, the test objects, the test items and the test requirements corresponding to the test items.

[0103] The test strategy is used to indicate the test positions (such as 1 meter away from the test object, 2 meters away from the test object), which test instructions are needed, the tone and timbre used to play the test instructions, etc.

[0104] Step S302: Generate a test case set based on the fine-tuned large model and the test strategy.

[0105] Specifically, based on the fine-tuned large model and according to the test strategy, the process of generating a test case set may include:

[0106] Step a1: Based on the fine-tuned large model, generate a test corpus and a test condition set according to the test strategy.

[0107] Exemplarily, the test instruction issued by the tester is "Please test the air conditioner of xx brand at xx location, use voice commands to test the air conditioner temperature adjustment, and be 1 to 2 meters away from the air conditioner. The test corpus covers young and middle-aged men and women", where the test content is "Use voice commands to test the air conditioner temperature adjustment, and be 1 to 2 meters away from the air conditioner. The test corpus covers young and middle-aged men and women". The fine-tuned large model formulates a test strategy based on the test object and the above test content, and then generates a test corpus set including test corpora such as "Adjust the air conditioner to 26 degrees" and "Heating at 26 degrees" according to the formulated test strategy, and can also generate a test condition set including test conditions such as (distance: 1 meter; voice attributes: young male), (distance: 1 meter; voice attributes: young female), (distance: 1 meter; voice attributes: young male dialect), (distance: 1 meter; voice attributes: young female dialect), and (distance: 2 meters; voice attributes: young male).

[0108] Step a2: Based on the fine-tuned large model, generate a test case set based on the test corpus and test condition set.

[0109] Among them, each test case in the test case set includes a test corpus in the test corpus set and a test condition in the test condition set. For example, a test case in the test case set is, "play "Set the air conditioner to 26 degrees" in Mandarin by a young male at a distance of 1m."

[0110] The following table shows some examples of test corpora, test conditions, and test cases:

[0111] Table 1 Test corpus, test conditions, and examples of test cases

[0112]

[0113] When generating a test case set based on the fine-tuned large model, the test object, test content and the preset first instruction prompt template can be organized into a first prompt instruction (the first prompt instruction includes instruction prompt information, test object and test content, and the first prompt instruction is used to prompt the fine-tuned large model to generate a test case set according to the test object and test content), and then the first prompt instruction is input into the fine-tuned large model. The fine-tuned large model obtains the task to be performed (i.e., the test case generation task) according to the instruction prompt information in the first prompt instruction, formulates a test strategy according to the test object and test content in the first prompt instruction, and then generates a test case set according to the formulated test strategy.

[0114] In another embodiment of the present application, the specific implementation process of "Step S203: using a test case set, combined with the location information of the test object, to test the test object, and determining the test results of the test object on the test cases in the test case set" in the above embodiment is introduced.

[0115] See also Figure 4 , showing a flow chart of using a test case set and combining the location information of the test object to test the test object and determining the test result of the test object on the test case in the test case set, which may include:

[0116] Step S401: for each test case in the test case set, determine the test position corresponding to the test case according to the position information of the test object and the test distance in the test case.

[0117] The test instructions issued by the tester may include requirements for the test distance, such as "1 to 2 meters away from the air conditioner" in the above example. Accordingly, each test condition in the above test condition set includes the test distance. Furthermore, each test case in the generated test case set includes the test distance, such as "1m distance" in "playing "Adjust the air conditioner to 26 degrees" in young male Mandarin".

[0118] The intelligent testing device can determine the test position corresponding to the test case according to the position information of the test object and the test distance in the test case.

[0119] Step S402: Move to the test position corresponding to the test case, and use the test case to test the test object.

[0120] After the intelligent test device determines the test location corresponding to the test case, it can start the path finding algorithm and move to the test location corresponding to the test case, and then use the test case to test the test object at the test location corresponding to the test case. Figure 5 As shown, the intelligent test equipment can perform intelligent obstacle avoidance during the path-finding process and adjust its optimal path to the test location in real time according to the obstacles on the route.

[0121] The test instructions issued by the tester may include requirements for test voice attributes (such as pronunciation timbre, gender, accent, etc.), such as "the test corpus covers middle-aged and young men and women" in the above example. Accordingly, each test condition in the above test condition set may include test voice attributes, and further, each test case in the generated test case set contains test voice attributes, such as "young male Mandarin" in the test case "play "Adjust the air conditioner to 26 degrees" in young male Mandarin at a distance of 1m".

[0122] In a possible implementation, the process of testing the test object using the test case may include:

[0123] Step b1: synthesize the audio of the test corpus in the test case according to the test speech attributes in the test case to obtain the speech test instruction corresponding to the test case.

[0124] The intelligent testing equipment can pre-store sound information corresponding to multiple voice attributes, such as sound information corresponding to young male Mandarin, sound information corresponding to young male dialects, sound information corresponding to old male Mandarin, sound information corresponding to old male dialects, sound information corresponding to young female Mandarin, sound information corresponding to young female dialects, etc. The sound information corresponding to the test voice attribute can be obtained from the pre-stored multiple sound information, and the audio of the test corpus in the test case can be synthesized according to the sound information corresponding to the test voice attribute, and the synthesized audio is used as the voice test instruction corresponding to the test case.

[0125] Step b2: Play the voice test instruction corresponding to the test case.

[0126] The intelligent testing device may be configured with an audio playback module, and after obtaining the voice test instruction corresponding to the test case, the voice test instruction corresponding to the test case may be played based on the audio playback module.

[0127] Step S403: Determine the test result of the test object on the test case.

[0128] Specifically, the process of determining the test result of the test object on the test case may include: step c1, collecting voice feedback information corresponding to the test case.

[0129] The voice feedback information corresponding to the test case is the voice information fed back by the test subject in response to the voice test instruction corresponding to the test case played.

[0130] For example, the voice test instruction corresponding to the test case is "adjust the air conditioner to 26 degrees", and the test subject feedback voice information "adjusted to 26 degrees", and the test subject feedback voice information "adjusted to 26 degrees" is the voice feedback information corresponding to the test case.

[0131] In a possible implementation, the intelligent test device is configured with an audio acquisition module. During the test process, the audio acquisition module can be used to collect voice information fed back by the test subject in response to the played voice test instructions.

[0132] It should be noted that during the test process, the audio acquisition module can be kept in an on state to collect audio, and the intelligent test equipment can extract the voice feedback information corresponding to each test case from the audio collected by the audio acquisition module.

[0133] Step c2: convert the voice feedback information corresponding to the test case into text, and use the converted text as the test feedback text corresponding to the test case.

[0134] In one possible implementation, the voice feedback information corresponding to the test case may be converted into text based on the fine-tuned large model.

[0135] Step c3: Determine the test result of the test object on the test case according to the test corpus in the test case and the test feedback text corresponding to the test case.

[0136] In one possible implementation, based on the fine-tuned large model, the test corpus in the test case and the test feedback text corresponding to the test case can be used as the basis to determine whether the test object passes the test on the test case to obtain the test result of the test object on the test case.

[0137] When determining the test result of the test object on the test case based on the fine-tuned large model, the test corpus in the test case, the test feedback text corresponding to the test case, and the preset second instruction prompt template can be organized into a second prompt instruction (the second prompt instruction includes instruction prompt information, the test corpus in the test case, and the test feedback text corresponding to the test case, and the second prompt instruction is used to prompt the fine-tuned large model to determine the test result of the test object on the test case according to the test corpus in the test case and the test feedback text corresponding to the test case), and then the second prompt instruction is input into the fine-tuned large model. The fine-tuned large model obtains the task to be performed according to the instruction prompt information in the second prompt instruction, and then analyzes the test corpus in the test case and the test feedback text corresponding to the test case, and outputs a test result indicating whether the test object has passed the test on the test case.

[0138] It should be noted that this embodiment does not limit the intelligent testing equipment to determine the test result of the test object on the test case based on the fine-tuned large model. Other methods can also be used to determine the test result of the test object on the test case. For example, a pre-designed matching algorithm can be directly used to determine whether the test feedback text corresponding to the test case matches the test corpus in the test case. If the test feedback text corresponding to the test case matches the test corpus in the test case (for example, the test expectation corresponding to the test case is "Set the air conditioner to 26 degrees", and the test feedback text corresponding to the test case is "The air conditioner has been adjusted to 26 degrees"), it is determined that the test object has passed the test on the test case; otherwise, it is determined that the test object has failed the test on the test case.

[0139] It should be noted that a test case can be tested once or multiple times.

[0140] In another embodiment of the present application, the specific implementation process of "step S204: performing statistical analysis on the test results of the test object on the test cases in the test case set to obtain the final test results of the test object" in the above embodiment is introduced.

[0141] The process of performing statistical analysis on the test results of the test object on the test cases in the test case set to obtain the final test results of the test object may include: performing multi-dimensional statistical analysis on the test results of the test object on the test cases in the test case set to obtain test indicators in multiple dimensions as the final test results of the test object.

[0142] Among them, the test indicators of multiple dimensions may include but are not limited to: the total success rate of all tests, the test success rate at different test distances, the test success rate under different test speech attributes, the test success rate under different test corpora, etc.

[0143] It should be noted that the total success rate of all tests is the ratio of the total number of successful interactions to the total number of interactions. The total number of interactions refers to the number of times the smart test device plays voice test instructions. The total number of successful interactions refers to the number of times the test subject correctly responds to the voice test instructions played by the smart test device. The test success rate at any test distance is the ratio of the number of successful interactions at the test distance to the total number of interactions at the test distance. The total number of interactions at the test distance refers to the number of times the smart test device plays voice test instructions at the test distance. The number of successful interactions at the test distance refers to the number of times the test subject correctly responds to the voice test instructions played by the smart test device at the test distance. The test success rate under any test voice attribute is the interaction success rate under the test voice attribute. The ratio of the number of successful interactions to the total number of interactions under the test voice attribute, the total number of interactions under the test voice attribute refers to the number of times the smart test device plays the voice test instructions under the test voice attribute, the number of successful interactions under the test voice attribute refers to the number of times the test subject correctly responds to the voice test instructions under the test voice attribute played by the smart test device, the test success rate under any test corpus is the ratio of the number of successful interactions under the test corpus to the total number of interactions under the test corpus, the total number of interactions under the test corpus refers to the number of times the smart test device plays the voice test instructions expected by the test, the number of successful interactions under the test corpus refers to the number of times the test subject correctly responds to the voice test instructions expected by the test played by the smart test device.

[0144] In one possible implementation, after obtaining test indicators of multiple dimensions, the test indicators of each dimension may be weighted and summed, and then a hierarchical test result may be given based on the weighted summed indicator (the test result is a test result given by integrating the test indicators of each dimension).

[0145] In another embodiment of the present application, the household appliance testing method, in addition to the above-mentioned steps S201 to S204, may also include: determining test optimization suggestions for the test object based on the final test results of the test object; generating a test report including the final test results of the test object (of course, it may also include intermediate test results, such as the test results of the test object on each test case) and test optimization suggestions; and outputting the generated test report to the tester.

[0146] The above embodiment mentioned that the final test result of the test object can be a test indicator of multiple dimensions. After obtaining the test indicators of multiple dimensions, the test optimization suggestions for the test object can be determined based on the test indicators of multiple dimensions. For example, if the success rate of the wake-up interaction test at a distance of 3 meters is low, the following test suggestion can be given: strengthen the wake-up interaction test at a distance of 3 meters.

[0147] In one possible implementation, the test results of the test object on each test case in the test case set can be statistically analyzed in multiple dimensions based on the fine-tuned big model to obtain test indicators in multiple dimensions as the final test results of the test object. Based on the fine-tuned big model and the test indicators in multiple dimensions, test optimization suggestions for the test object are determined, and a test report containing test indicators in multiple dimensions and test optimization suggestions is generated.

[0148] Specifically, the test indicators of multiple dimensions and the preset third instruction prompt template can be organized into a third prompt instruction (the third prompt instruction includes instruction prompt information and test indicators of multiple dimensions, and the third prompt instruction is used to prompt the fine-tuned large model to analyze the test indicators of multiple dimensions to generate test optimization suggestions and a test report), and then the third prompt instruction is input into the fine-tuned large model. The fine-tuned large model obtains the task to be performed according to the instruction prompt information in the third prompt instruction, and then analyzes the test indicators of multiple dimensions, generates test optimization suggestions, and generates a test report containing test indicators of multiple dimensions and test optimization suggestions.

[0149] It should be noted that this embodiment is not limited to performing multi-dimensional statistical analysis on the test results of the test object on each test case in the test case set based on the model. For example, it is also possible to perform multi-dimensional statistical analysis on the test results of the test object on each test case in the test case set based on pre-set statistical rules and statistical logic. This embodiment is also not limited to determining test optimization suggestions for the test object and generating a test report based on the model. For example, a rule-based method may be used to determine the test optimization suggestions for the test object, and a preset text integration strategy may be used to integrate the final test results of the test object and the test optimization suggestions into a test report.

[0150] In addition, it should be noted that the fine-tuned large model mentioned in the above embodiments can be the same large model, which can be built into the intelligent test device. The large model is obtained by fine-tuning the pre-trained large model on a specific task, and the specific task is a home appliance test task. The task may include multiple subtasks, such as a test case generation task, a speech-to-text task, a test result determination task on a test case, a statistical analysis task on test results on several test cases, an analysis of several test indicators and a test report generation task, etc. For the above tasks, corresponding training data can be constructed, and the pre-trained large model can be fine-tuned using the constructed training data, so that it has the ability to generate a test case set, the ability to convert speech to text, the ability to determine the test results of the test object on the test case, the ability to perform statistical analysis on the test results of the test object on multiple test cases to obtain test indicators, and the ability to generate test optimization suggestions and test reports based on the test indicators, that is, the present application uses the training data corresponding to the home appliance test task to fine-tune the pre-trained large model so that it can be applied to home appliance testing (performing relevant tasks in the home appliance testing process).

[0151] The above describes the home appliance testing method provided in the embodiment of the present application. The following describes a device corresponding to the home appliance testing method.

[0152] See also Figure 6 , Figure 6 A structural schematic diagram of a home appliance testing device provided in an embodiment of the present application, the home appliance testing device is applied to an intelligent testing device, and the home appliance testing device may include: a test instruction receiving module 601, a test case generating module 602, a testing module 603, a first test result determining module 604 and a second test result determining module 605.

[0153] The test instruction receiving module 601 is used to receive the test instruction issued by the tester.

[0154] The test instruction includes a test object, location information of the test object, and test content for the test object.

[0155] The test case generation module 602 is used to generate test cases according to the test object and test content.

[0156] The testing module 603 is used to test the test object using a test case set and combining the location information of the test object.

[0157] The first test result determination module 604 is used to determine the test result of the test object on the test case in the test case set.

[0158] The second test result determination module 605 is used to perform statistical analysis on the test results of the test object on the test cases in the test case set to obtain the final test result of the test object.

[0159] In a possible implementation, the test content includes: test items and test requirements corresponding to the test items.

[0160] When the test case generation module 602 generates a test case set according to the test object and the test content, it is specifically used to:

[0161] Based on the fine-tuned large model, the test strategy is determined based on the test object, test items and the test requirements corresponding to the test items; based on the fine-tuned large model, a test case set is generated according to the test strategy. The fine-tuned large model is obtained by fine-tuning the pre-trained large model on a specific task, and the specific task includes a test case generation task.

[0162] In a possible implementation, when the test case generation module 602 generates a test case set based on the fine-tuned large model and the test strategy, it is specifically used to:

[0163] Based on the fine-tuned large model, a test corpus and a test condition set are generated according to the test strategy; based on the fine-tuned large model, a test case set is generated based on the test corpus and the test condition set.

[0164] Each test case in the test case set includes a test corpus in the test corpus set and a test condition in the test condition set.

[0165] In a possible implementation, each test case in the test case set includes a test condition and a test corpus under the test condition, and the test condition in each test case in the test case set includes a test distance.

[0166] When the test module 603 uses the test case set and the location information of the test object to test the test object, it is specifically used to:

[0167] For each test case in a test suite:

[0168] Determine the test position corresponding to the test case according to the position information of the test object and the test distance in the test case;

[0169] Move to the test position corresponding to the test case, and use the test case to test the test object.

[0170] In a possible implementation, the test conditions in each test case in the test case set also include a test speech attribute.

[0171] When the test module 603 uses the test case to test the test object, it is specifically used to:

[0172] According to the test speech attribute in the test case, synthesize the audio of the test corpus in the test case to obtain the speech test instruction corresponding to the test case;

[0173] Play the voice test instructions corresponding to the test case.

[0174] In a possible implementation, the intelligent testing device is configured with an audio acquisition module.

[0175] When determining the test result of the test object on a test case, the first test result determination module 604 is specifically used to:

[0176] Using an audio acquisition module to collect voice feedback information corresponding to the test case, wherein the voice feedback information corresponding to the test case is voice information fed back by the test subject in response to the voice test instruction corresponding to the played test case;

[0177] Converting the voice feedback information corresponding to the test case into text to obtain the test feedback text corresponding to the test case;

[0178] The test result of the test object on the test case is determined according to the test corpus in the test case and the test feedback text corresponding to the test case.

[0179] In a possible implementation, when determining the test result of the test object on the test case according to the test corpus in the test case and the test feedback text corresponding to the test case, the first test result determination module 604 is specifically configured to:

[0180] Based on the fine-tuned large model, the test corpus in the test case and the test feedback text corresponding to the test case are used as the basis to determine whether the test object passes the test on the test case, and obtain the test result of the test object on the test case. The fine-tuned large model is obtained by fine-tuning the pre-trained large model on a specific task, and the specific task includes a test result determination task on the test case.

[0181] In a possible implementation, when performing statistical analysis on the test results of the test object on the test cases in the test case set, the second test result determination module 605 is specifically configured to:

[0182] The test results of the test object on each test case in the test case set are statistically analyzed in multiple dimensions to obtain test indicators in multiple dimensions as the final test results of the test object.

[0183] The home appliance testing device provided in the embodiment of the present application may further include: a test optimization suggestion determination module and a test report generation module.

[0184] The test optimization suggestion determination module is used to determine the test optimization suggestions for the test object according to the test indicators of multiple dimensions.

[0185] The test report generation module is used to generate a test report containing the final test results of the test object and test optimization suggestions.

[0186] In a possible implementation, when the test optimization suggestion determination module determines the test optimization suggestion for the test object according to the test indicators of multiple dimensions, it is specifically used to:

[0187] Based on the fine-tuned large model and the test indicators of the multiple dimensions, test optimization suggestions for the test object are determined.

[0188] The test report generation module is used to generate a test report containing the final test results of the test object and test optimization suggestions.

[0189] Based on the fine-tuned large model, a test report containing test indicators in multiple dimensions and test optimization suggestions is generated.

[0190] Among them, the fine-tuned large model is obtained by fine-tuning the pre-trained large model on specific tasks, and the specific tasks include test indicator analysis and test report generation tasks.

[0191] The home appliance testing device provided in the embodiment of the present application first receives the test instruction issued by the tester, then generates a test case set according to the test object and the test content in the test instruction, then uses the test case set, and at the same time combines the position information of the test object in the test instruction to test the test object, and determines the test result of the test object on the test case in the test case set, and finally performs statistical analysis on the test result of the test object on the test case in the test case set to obtain the final test result of the test object. The home appliance testing device provided in the embodiment of the present application enables the intelligent testing device to automatically generate a test case set according to the test instruction issued by the tester, automatically test the test object with the test case set, and automatically perform statistical analysis on the test result of the test object on the test case in the test case set, that is, the tester only needs to issue the test instruction to the intelligent testing device (the tester only needs to issue the instruction once), and the intelligent testing device can automatically complete the test of the test object and the determination of the test result. It can be seen that the home appliance testing device provided in the embodiment of the present application has a low degree of manual dependence and a high test efficiency, and since the execution of the test and the determination of the test result are all completed by the intelligent testing device without the participation of the tester, the influence of human subjective factors on the test result is avoided.

[0192] An embodiment of the present application also provides an electronic device, which may include: at least one processor, at least one communication interface, at least one memory and at least one communication bus.

[0193] In the embodiment of the present application, the number of the processor, the communication interface, the memory, and the communication bus is at least one, and the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0194] The processor may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application;

[0195] The memory may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory;

[0196] The memory stores a program, and the processor can call the program stored in the memory, and the program is used to implement the steps of the home appliance testing method provided in the above embodiment.

[0197] An embodiment of the present application also provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the steps of the home appliance testing method provided in the above embodiment.

[0198] An embodiment of the present application also provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the steps of the home appliance testing method provided in the above embodiment.

[0199] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0200] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0201] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0202] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A household appliance testing method, characterized in that: Applied to intelligent testing equipment, the household appliance testing method includes: Receiving a test instruction issued by a tester, wherein the test instruction includes a test object, location information of the test object, and test content for the test object; Generate a test case set according to the test object and the test content; Using the test case set and combining with the location information of the test object, testing the test object, and determining the test result of the test object on the test case in the test case set; Statistical analysis is performed on the test results of the test object on the test cases in the test case set to obtain a final test result of the test object.

2. The household appliance testing method according to claim 1, characterized in that: The test content includes: test items and test requirements corresponding to the test items; The generating a test case set according to the test object and the test content includes: Determine the test strategy based on the fine-tuned large model and the test object, the test items and the test requirements corresponding to the test items; Based on the fine-tuned large model and according to the test strategy, a test case set is generated; The fine-tuned large model is obtained by fine-tuning the pre-trained large model on a specific task, and the specific task includes a test case generation task.

3. The household appliance testing method according to claim 2, characterized in that: The step of generating a test case set based on the fine-tuned large model and according to the test strategy includes: Based on the fine-tuned large model, and according to the test strategy, generate a test corpus and a test condition set; Based on the fine-tuned large model, a test case set is generated based on the test corpus and the test condition set, wherein each test case in the test case set includes a test corpus in the test corpus and a test condition in the test condition set.

4. The household appliance testing method according to claim 1, characterized in that: Each test case in the test case set includes a test condition and a test corpus under the test condition, and the test condition in each test case in the test case set includes a test distance; The step of testing the test object by using the test case set and combining the location information of the test object, and determining the test result of the test object on the test case in the test case set includes: For each test case in the test case set: Determine the test position corresponding to the test case according to the position information of the test object and the test distance in the test case; Move to the test position corresponding to the test case, and test the test object with the test case; Determine a test result of the test object on the test case.

5. The household appliance testing method according to claim 4, characterized in that: The test conditions in each test case in the test case set also include testing speech attributes; The testing of the test object using the test case includes: According to the test speech attribute in the test case, synthesize the audio of the test corpus in the test case to obtain the speech test instruction corresponding to the test case; Play the voice test instructions corresponding to the test case.

6. The household appliance testing method according to claim 5, characterized in that: The intelligent testing device is equipped with an audio acquisition module; Determining the test result of the test object on the test case includes: Using the audio acquisition module to collect voice feedback information corresponding to the test case, wherein the voice feedback information corresponding to the test case is voice information fed back by the test subject in response to the voice test instruction corresponding to the test case played; Converting the voice feedback information corresponding to the test case into text to obtain the test feedback text corresponding to the test case; The test result of the test object on the test case is determined according to the test corpus in the test case and the test feedback text corresponding to the test case.

7. The household appliance testing method according to claim 6, characterized in that: The step of determining the test result of the test object on the test case according to the test corpus in the test case and the test feedback text corresponding to the test case includes: Based on the fine-tuned large model, and based on the test corpus in the test case and the test feedback text corresponding to the test case, determine whether the test object passes the test on the test case, and obtain the test result of the test object on the test case; The fine-tuned large model is obtained by fine-tuning the pre-trained large model on a specific task, and the specific task includes a task determined by a test result on a test case.

8. The household appliance testing method according to claim 1, characterized in that: The statistical analysis of the test results of the test object on the test cases in the test case set includes: Performing statistical analysis in multiple dimensions on the test results of the test object on each test case in the test case set to obtain test indicators in multiple dimensions as the final test results of the test object; The household appliance testing method further comprises: Determining test optimization suggestions for the test object according to the test indicators of the multiple dimensions; Generate a test report including the final test results of the test object and the test optimization suggestions.

9. The household appliance testing method according to claim 8, characterized in that: Determining test optimization suggestions for the test object based on the test indicators of the multiple dimensions; Generate a test report containing the final test results of the test object and the test optimization suggestions, including: Based on the fine-tuned large model, and taking the test indicators of the multiple dimensions as a basis, determining a test optimization suggestion for the test object, and generating a test report including the test indicators of the multiple dimensions and the test optimization suggestion; The fine-tuned large model is obtained by fine-tuning the pre-trained large model on specific tasks, and the specific tasks include test indicator analysis and test report generation tasks.

10. A household appliance testing device, characterized in that: Applied to intelligent testing equipment, the household appliance testing device comprises: a test instruction receiving module, a test case generating module, a testing module, a first test result determining module and a second test result determining module; The test instruction receiving module is used to receive a test instruction issued by a tester, wherein the test instruction includes a test object, location information of the test object, and test content for the test object; The test case generation module is used to generate a test case set according to the test object and test content; The test module is used to test the test object by using the test case set and combining the location information of the test object; The first test result determination module is used to determine the test result of the test object on the test case in the test case set; The second test result determination module is used to perform statistical analysis on the test results of the test object on the test cases in the test case set to obtain the final test results of the test object.

11. An electronic device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the steps of the household appliance testing method as described in any one of claims 1 to 9.

12. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the steps of the home appliance testing method as described in any one of claims 1 to 9.

13. A computer program product, characterized in that The method comprises computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the steps of the household appliance testing method as claimed in any one of claims 1 to 9.

Images