Voice test method, bracket, device, storage medium and program product

Abstract

An embodiment of the present application provides a voice test method, a bracket, a device, a storage medium, and a program product. The method includes: in response to a test start instruction, controlling the artificial head to reset to the origin position, controlling the artificial head to step along each number axis in sequence from the origin position, and sequentially entering a plurality of target points. For each entered target point, performing a voice test at the target point through the artificial head to obtain a test result, and recording the position information of the artificial head according to the test result, so as to perform a repeated voice test based on the recorded position information. The voice test method provided by the embodiment of the present application can quantify each point in the vehicle interior space by setting a plurality of number axes and controlling the artificial head to step along each number axis, enabling the artificial head to accurately enter the points for testing, which not only improves the test point coverage rate but also facilitates re-entering the same point to reproduce the problems that occur at this point during the test.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of artificial intelligence technology, and in particular, to a voice test method, a bracket, a device, a storage medium, and a program product. Background Art

[0002] With the development of vehicle intelligence, the immersive experience brought by the intelligent cockpit to users is becoming more and more perfect. Among them, the voice interaction function of the in-vehicle computer, as a "bridge" for human-machine information transmission, its voice recognition effect directly affects the user's sensory experience. Therefore, it is crucial to perform voice tests on the in-vehicle computer.

[0003] In the prior art, usually, an artificial head is manually placed at multiple positions for voice tests.

[0004] However, in the process of implementing the present application, the inventors found that there are at least the following problems in the prior art: the coverage rate of test points is low, and the random division of points is not conducive to reproducing the problems that will occur when re-entering the same point. Summary of the Invention

[0005] Embodiments of the present application provide a voice test method, a bracket, a device, a storage medium, and a program product to improve the coverage rate of test points and achieve repeated test of the same point.

[0006] In a first aspect, embodiments of the present application provide a voice test method, including:

[0007] In response to a test start instruction, control the artificial head to reset to the origin position;

[0008] Control the artificial head to step along each number axis in sequence from the origin position, and sequentially enter a plurality of target points;

[0009] For each entered target point, perform a voice test at the target point through the artificial head to obtain a test result;

[0010] Record the position information of the artificial head according to the test result, so as to perform repeated voice tests based on the recorded position information.

[0011] In a possible design, the controlling the artificial head to step along each number axis in sequence from the origin position and sequentially enter a plurality of target points includes:

[0012] Control the artificial head to step along each number axis in sequence from the origin position, and sequentially enter a plurality of target points until the step limits of each number axis are all triggered;

[0013] Determine the initial point set of the three-dimensional range to be detected;

[0014] Control the artificial head to perform step-by-step movements along each axis, and enter each accessible target point in the set of points to be located from the multiple target points that have been entered; the set of points to be located is composed of the remaining points in the initial point set except the multiple target points that have been entered.

[0015] In a possible design, the control of the artificial head to perform step-by-step movements along each axis from the origin position and enter multiple target points in sequence until the step limits of each axis are all triggered includes:

[0016] Control the artificial head to perform a step along the positive direction of the first axis with a first step length until the step limit of the first axis is triggered;

[0017] For each step on the first axis, control the artificial head to perform a step along the positive direction of the second axis with a second step length until the step limit of the second axis is triggered, and then reset the artificial head to the starting limit point of the second axis;

[0018] For each step on the second axis, control the artificial head to perform a step along the positive direction of the third axis with a third step length until the step limit of the third axis is triggered, and then reset the artificial head to the starting limit point of the third axis;

[0019] For each step on the third axis, control the artificial head to enter the corresponding target point.

[0020] In a possible design, the determination of the initial point set of the three-dimensional range to be detected includes:

[0021] Determine the initial point subset corresponding to each step along the third axis; the initial point subset is determined according to the maximum step range of the first axis and the maximum step range of the second axis;

[0022] Form the initial point set by the initial point subsets corresponding to each step within the maximum step range of the third axis;

[0023] The control of the artificial head to perform step-by-step movements along each axis and enter each accessible target point in the set of points to be located from the detected area includes:

[0024] Remove the target points that have been entered from each initial point subset in the initial point set to obtain the subset of points to be located corresponding to each initial point subset in the initial point set;

[0025] Control the artificial head to perform a step along the third axis. For each step on the third axis, control the artificial head to enter each accessible point in the subset of points to be located corresponding to the current step, and determine the accessible points as target points.

[0026] In a possible design, determining the initial point position subsets corresponding to each step along the third number axis includes:

[0027] Controlling the artificial head to step along the first number axis from the origin position with the first step length until reaching the preset termination limit point on the first number axis, to obtain the maximum step range of the first number axis;

[0028] Controlling the artificial head to step along the second number axis from the origin position with the second step length until reaching the preset termination limit point on the first number axis, to obtain the maximum step range of the second number axis;

[0029] Determining the initial point position subsets according to the maximum step range of the first number axis and the maximum step range of the second number axis.

[0030] In a possible design, controlling the artificial head to enter each accessible point in the point position subset corresponding to the current step, and determining the accessible points as target points, includes:

[0031] Repeatedly execute the following steps until there are no candidate points adjacent to the located area in the point position subset to be located:

[0032] Connecting the target points that have been entered in the initial point position subset corresponding to the current step into the located area;

[0033] Searching for candidate points adjacent to the located area from the point position subset to be located;

[0034] Controlling the artificial head to enter the candidate point from the located area;

[0035] If it can enter, marking the candidate point as a target point;

[0036] If it cannot enter, marking the candidate point as an obstacle point.

[0037] In a possible design, before repeatedly executing the following steps until there are no candidate points adjacent to the located area in the point position subset to be located, it further includes:

[0038] Obtaining the point position subset to be located corresponding to the previous step, and the obstacle points marked in the previous step;

[0039] Removing the obstacle points marked in the previous step from the point position subset to be located corresponding to the previous step, to obtain the point position subset to be located corresponding to the current step.

[0040] In a possible design, obtaining the test result by performing a voice test at the target point by the artificial head includes:

[0041] Control the artificial head at the target point and rotate it back to the starting angle;

[0042] Control the artificial head to perform rotational steps from the starting angle with the fourth step length to enter multiple target angles;

[0043] For each target angle, perform a voice test of the target angle through the artificial head to obtain the test result of the target angle.

[0044] In a possible design, the performing a voice test of the target angle through the artificial head to obtain the test result of the target angle includes:

[0045] Obtain at least one test case and the corresponding preset number of times for different test cases;

[0046] For each test case, perform a voice test corresponding to the preset number of times at the target angle through the artificial head to obtain the test result corresponding to the test case.

[0047] In a possible design, the recording the position information of the artificial head according to the test result to perform repeated voice tests based on the recorded position information includes:

[0048] If the test result is a test failure, record the position information of the artificial head under the current test to perform a reproduction test according to the position information; the position information includes the number of steps and step length corresponding to each number axis, as well as the number of steps of the rotational step corresponding to the current target angle and the fourth step length.

[0049] In a second aspect, an embodiment of the present application provides a voice test bracket, including: a support member, a plurality of moving members, a plurality of driving members, and an artificial head;

[0050] The plurality of moving members are connected to the plurality of driving members in a one-to-one correspondence;

[0051] Each moving member is configured to step relative to the support member along the corresponding number axis under the drive of the corresponding driving member;

[0052] The artificial head is connected to each moving member and is configured to be reset to the origin position under the drive of each moving member, and is further configured to step along each number axis in sequence from the origin position to enter multiple target points in sequence, and is further configured to perform a voice test at each entered target point.

[0053] In a possible design, the plurality of moving members include a first moving member, a second moving member, and a third moving member; the plurality of driving members include a first driving member, a second driving member, and a third driving member;

[0054] The first moving member is connected to the first driving member and is configured to step relative to the support member along the first number axis under the drive of the first driving member;

[0055] The second moving member is connected to the second driving member and is configured to step relative to the support member along the second number axis under the drive of the second driving member;

[0056] The third moving member is connected to the first moving member, the second moving member and the third driving member and is configured to step relative to the support member along the third number axis under the drive of the third driving member, and is also configured to step relative to the support member along the first number axis under the drive of the first moving member, or step relative to the support member along the second number axis under the drive of the second moving member;

[0057] The artificial head is connected to the third moving member and is configured to step following the steps of the third moving member along each number axis.

[0058] In a third aspect, an embodiment of the present application provides a voice test device, including: at least one processor and a memory;

[0059] The memory stores computer-executable instructions;

[0060] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method described in the first aspect and various possible designs of the first aspect as above.

[0061] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the processor executes the computer-executable instructions, the method described in the first aspect and various possible designs of the first aspect as above is implemented.

[0062] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method described in the first aspect and various possible designs of the first aspect as above is implemented.

[0063] The voice test method, support, device, storage medium and program product provided in this embodiment. The method includes responding to a test start instruction, controlling the artificial head to reset to the origin position, controlling the artificial head to step along each number axis in sequence from the origin position, and successively entering multiple target points. For each entered target point, voice testing is performed at the target point through the artificial head to obtain a test result, and the position information of the artificial head is recorded according to the test result, so as to perform repeated voice testing based on the recorded position information. The voice test method provided in the embodiments of the present application can quantify each point in the vehicle interior space by setting multiple number axes and controlling the artificial head to step along each number axis, enabling the artificial head to accurately enter the points for testing. This not only improves the test point coverage rate but also helps to re-enter the same point to reproduce the problems that occurred at this point during testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0065] Figure 1 It is a schematic structural diagram of the voice test system provided in the embodiments of the present application;

[0066] Figure 2 It is a schematic flow diagram of the voice test method provided in the embodiments of the present application;

[0067] Figure 3 It is a schematic diagram of the voice test support provided in the embodiments of the present application;

[0068] Figure 4 It is a schematic diagram of the artificial head provided in the embodiments of the present application;

[0069] Figure 5 It is a schematic diagram of the principle of the path backtracking algorithm provided in the embodiments of the present application;

[0070] Figure 6 It is a schematic structural diagram of the voice test device provided in the embodiments of the present application;

[0071] Figure 7 It is a hardware structure block diagram of the electronic device provided in the embodiments of the present application.

[0072] Reference Signs:

[0073] 110: X-axis start limit switch; 111: X-axis end limit switch; 112: X-axis support rod; 113: X-axis rolling pulley;

[0074] 120: Y-axis starting limit switch; 121: Y-axis end limit switch; 122: Y-axis support rod; 123: Y-axis rolling pulley;

[0075] 130: Stepper motor fixed bracket;

[0076] 210: X-axis stepper motor; 211: X-axis program-controlled connection;

[0077] 220: Y-axis stepper motor; 221: Y-axis program-controlled connection;

[0078] 230: Z-axis stepper motor; 231: Z-axis program-controlled connection;

[0079] 310: X-axis slide bar; 320: Y-axis slide bar;

[0080] 410: X-axis positive limit switch; 411: X-axis negative limit switch;

[0081] 420: Y-axis positive limit switch; 421: Y-axis negative limit switch;

[0082] 431: Z-axis positive limit switch; 432: Z-axis negative limit switch;

[0083] 440: Fixed shaft; 441: Reset rod; 442: Manual head reset limit switch; 443: Rotary stepper motor;

[0084] 510: Front row seat; 520: Rear row seat. Detailed implementation manners

[0085] To make the objectives, technical solutions and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some but not all of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of this application without creative efforts shall fall within the protection scope of this application.

[0086] With the development of automotive intelligence, the immersive experience brought by the intelligent cockpit to users is becoming more and more perfect. Among them, the in-vehicle voice interaction function, as the "bridge" for human-machine information transmission, its voice recognition effect directly affects the sensory experience of users. Therefore, it is crucial to ensure effective voice interaction at any position in the intelligent cockpit.

[0087] In the related art, usually, the artificial head is manually placed at multiple positions for voice testing, or artificial voice is generated at multiple positions in the intelligent cockpit for voice testing. Although the above methods can meet the requirements of voice testing for the intelligent cockpit to a certain extent, there are still the following deficiencies: the coverage rate of test points in the intelligent cockpit is low, and the division of test points in the space cannot be measured standardly, making it difficult to reproduce the problems that occur during the test.

[0088] To solve the above technical problems, the inventors of the present application have found through research that multiple number axes can be set to control the artificial head to perform step-by-step movement along each number axis, so as to be able to quantify each point in the vehicle interior space, and enable the artificial head to accurately enter the point for testing. This not only improves the coverage rate of test points but also facilitates re-entering the same point to reproduce the problems that occurred at this point during the test. Based on this, an embodiment of the present application provides a voice testing method that can improve the coverage rate of test points and is conducive to re-entering the same point to reproduce the problems that occurred at this point during the test.

[0089] Figure 1 It is a schematic structural diagram of the voice testing system provided by an embodiment of the present application. As Figure 1 shown, the voice testing system includes a server 101, a controller 102, an artificial head 103, and multiple motors 104. The server 101 is connected to the controller 102, the controller 102 is connected to the artificial head 103, and multiple stepper motors 104 are all connected to the controller 102. The server 101 is used to send a test start instruction to the controller 102. The controller 102 is used to control each stepper motor to drive the artificial head 103 to step along the corresponding number axis and enter multiple target points. Different stepper motors are used to drive the artificial head 103 to step along different number axes. The artificial head 103 is used to perform voice testing after entering the target point. Specifically, the stepper motor can drive a sliding member, and the sliding member drives the artificial head to perform step-by-step movement on the corresponding number axis. The stepper motor, the artificial head, and the sliding member form a voice testing bracket.

[0090] In this embodiment, the server 101 can be a cloud server. The server 101 communicates with the controller 102 through a network connection. The server 101 can also be used to send parameter setting information and other control instructions to the controller 102. The parameter setting information can include the step accuracy in each number axis direction and the number of tests within the point. Other control instructions can include a pause test instruction, a continue test instruction, a stop test instruction, and a failed test case reproduction instruction (reproducing the test cases that failed during the test task). The server 101 can also be used for test case maintenance and receiving the test results sent by the controller, and generating a test report based on the test results. It can be understood that the above functions of the server can be integrated into the local controller 102 according to actual situations, and this embodiment does not make any limitations in this regard.

[0091] In the specific implementation process, the server 101 sends a test start instruction to the controller 102. In response to the test start instruction, the controller 102 first controls each stepper motor to drive the artificial head 103 to reset to the origin position, and then controls each stepper motor to drive the artificial head 103 to step along each number axis in sequence from the origin position, and successively enter multiple target points; for each entered target point, the controller 102 controls the artificial head 103 to perform a voice test at the target point, obtains the test result, and records the position information of the artificial head 103 according to the test result, so as to perform a repeated voice test based on the recorded position information. The voice test method provided by the embodiments of the present application can quantify each point in the vehicle interior space by setting multiple number axes and controlling the artificial head 103 to step along each number axis, so that the artificial head 103 can accurately enter the point for testing, which not only improves the test point coverage rate, but also helps to re-enter the same point to reproduce the problems that occur at this point during the test.

[0092] It should be noted that Figure 1 The schematic diagram of the scene shown is only an example. The voice test method and scene described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those of ordinary skill in the art know that with the evolution of the system and the emergence of new service scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0093] The technical solutions of the present application will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0094] Figure 2 It is a flowchart of the voice test method provided by the embodiments of the present application. As Figure 2 shown, the method includes:

[0095] 201. In response to the test start instruction, control the artificial head to reset to the origin position O.

[0096] The execution subject of this embodiment can be a vehicle, specifically the controller of the vehicle.

[0097] Specifically, after receiving the test start instruction, the controller controls the artificial head to move and reset to the origin position O.

[0098] In this embodiment, the artificial head can also be called an artificial mouth, a man-made mouth or a simulation mouth. It is a special artificial sound source, which is composed of a small speaker installed on a baffle with a special shape. The design of the baffle shape is to simulate the average directivity and radiation pattern of the human mouth, and the simulation mouth must have a constant sound pressure output.

[0099] In this embodiment, the source of the test start instruction can be various. It can be sent by the server to the controller, or it can be generated according to the user's touch operation.

[0100] In this embodiment, the origin position O is the intersection of multiple number axes and is the initial position for the start of the test. Each test starts from this initial position so that the coordinates of each point can be marked based on the number of steps starting from the origin position O, enabling accurate entry into the target point for repeated testing based on the recorded number of steps.

[0101] 202. Control the artificial head to step along each number axis in sequence from the origin position O and enter multiple target points in turn.

[0102] Exemplarily, taking multiple number axes including the X-axis and Y-axis in the horizontal direction and the Z-axis perpendicular to the ground as an example, after the test starts, first the artificial head is driven to the origin position O(0, 0, 0) to complete reset. On this basis, there can be various control strategies for controlling the artificial head to enter multiple target points. It can first step along the X-axis and then traverse other number axes, or first step along the Y-axis and then traverse other number axes, or first step along the Z-axis and then traverse other number axes, which can be specifically set according to actual needs. Exemplarily, assuming that it can step 3 times in the directions of the X-axis, Y-axis, and Z-axis, it can first step once along the X-axis and enter the point (1, 0, 0). Secondly, step once along the Y-axis and enter the point (1, 1, 0). Then step 3 times along the Z-axis and enter the points (1, 1, 1), (1, 1, 2), (1, 1, 3) in turn. Then return to the Z-axis origin position O(1, 1, 0), step once along the Y-axis and enter (1, 2, 0). Then step 3 times along the Z-axis and enter the points (1, 2, 1), (1, 2, 2), (1, 2, 3) in turn, and so on, and it can enter each point between (0, 0, 0) and (3, 3, 3).

[0103] In some embodiments, since there are obstacles such as seats in the intelligent cockpit of the vehicle, which hinder the artificial head from continuing to step, sensors can be set for induction in this case. When the sensor senses an obstacle (such as the front row seat 510), it triggers the step limit of the corresponding number axis. The sensor sends the step limit signal to the controller, and the controller controls the artificial head to reset to the origin position O of this number axis so as to continue to traverse other points. However, in this case, the points behind the obstacle cannot be entered according to the preset conventional strategy. Based on this, after the step limits of each number axis are triggered based on the conventional strategy, a path backtracking strategy can be adopted to attempt to enter the points behind the obstacle.

[0104] Based on this, controlling the artificial head to step along each number axis in sequence from the origin position O and enter multiple target points in sequence may include: controlling the artificial head to step along each number axis in sequence from the origin position O and enter multiple target points in sequence until the step limits of each number axis are triggered; determining an initial point set of the three-dimensional range to be detected; controlling the artificial head to step along each number axis and enter each accessible target point in the point set to be located from the multiple target points that have been entered; the point set to be located is composed of the remaining points in the initial point set except the multiple target points that have been entered.

[0105] Optionally, controlling the artificial head to step along each number axis in sequence from the origin position O and enter multiple target points in sequence until the step limits of each number axis are triggered may include: controlling the artificial head to step in the positive direction of the first number axis with a first step length until the step limit of the first number axis is triggered; for each step on the first number axis, controlling the artificial head to step in the positive direction of the second number axis with a second step length until the step limit of the second number axis is triggered, and then resetting the artificial head to the starting limit point of the second number axis; for each step on the second number axis, controlling the artificial head to step in the positive direction of the third number axis with a third step length until the step limit of the third number axis is triggered, and then resetting the artificial head to the starting limit point of the third number axis; for each step on the third number axis, controlling the artificial head to enter the corresponding target point.

[0106] Figure 3 Schematic diagram of the voice test bracket provided by the embodiment of the present application. As Figure 3As shown, the voice test bracket includes a plurality of stepping motors connected to corresponding support rods through a stepping motor fixing bracket 130, an X-axis stepping motor 210, a Y-axis stepping motor 220, and a Z-axis stepping motor 230. Each stepping motor is respectively connected through a corresponding program control for transmission to drive the sliding member to drive the artificial head to perform stepping along each number axis. There can be various ways of this program control. Exemplarily, in the X and Y axis directions, a gear and chain method is used for transmission control. Taking the Y axis as an example, a transmission gear is added at the rotating shaft of the Y-axis stepping motor, and further a transmission gear is added at the support rod on the opposite side of the Y-axis stepping motor (the two gears are connected by a closed-loop chain). Further, the Y-axis slide bar 320 is connected to a point on the chain to drive the Y-axis slide bar 320 to move, thereby completing the program control. The X-axis program connection is similar. The Z-axis program control can also adopt the gear and chain method, or can be simplified to use the form of a fixed pulley, and a soft wire is used to connect the rotating shaft of the stepping motor to the artificial head 103. When the stepping motor rotates forward, the artificial head 103 is pulled upward, and when it rotates backward, the artificial head moves downward by means of gravity, thereby completing the Z-axis program control. Of course, this program connection can also adopt forms such as sliding lead screws and screws, as long as transmission can be achieved so that sliding members such as the X-axis slide bar 310 and the Y-axis slide bar 320 can drive the artificial head 103 to perform stepping movement along each number axis. This embodiment does not limit this.

[0107] After the control receives the test start instruction, a reset operation is first performed. Specifically, the artificial head can be reset in the directions of the Z-axis, Y-axis, and X-axis in sequence. In the Z-axis direction, the Z-axis stepper motor 230 drives the artificial head to step towards the origin position O. When the artificial head touches the connection point of the X-axis slide bar 310 and the Y-axis slide bar 320 upwards, the Z-axis positive limit switch 431 is triggered. At this time, the control stops the Z-axis stepper motor 230 from stepping, and the Z-axis reset is completed. Then the Y-axis stepper motor drives the Y-axis slide bar 320 to step towards the origin position O. When the Y-axis rolling pulley 123 connected to the Y-axis slide bar 320 touches the Y-axis starting limit switch 120 provided on the X-axis support rod 112, the Y-axis starting limit switch 120 is triggered. At this time, the control stops the Y-axis stepper motor 220 from stepping, and the Y-axis reset is completed. Finally, the X-axis stepper motor 210 drives the X-axis slide bar 310 to step towards the origin position O. When the X-axis rolling pulley 113 connected to the X-axis slide bar 310 touches the X-axis starting limit switch 110 provided on the Y-axis support rod 122, when the X-axis starting limit switch 110 is triggered, at this time, the X-axis stepper motor 210 stops stepping, and the X-axis reset is completed. Finally, the artificial head reaches the origin position O, and the system reset is completed. If the reset operation cannot be executed normally, an alarm process can be performed, and the voice test system composed of the server, controller, and voice test bracket stops operating. The reset sequence is only an example, and the reset can be performed according to other sequences according to actual needs. This embodiment does not limit this.

[0108] As Figure 4 shown, six sides of the artificial head 103 are respectively provided with: an X-axis positive limit switch 410, an X-axis negative limit switch 411, a Y-axis positive limit switch 420, a Y-axis negative limit switch 421, a Z-axis positive limit switch 431, and a Z-axis negative limit switch 432, which are respectively used for limit triggering when encountering obstacles.

[0109] After the reset is completed, the following steps can be executed:

[0110] 401. Control the X-axis stepper motor 210 to drive the X-axis slide bar 310 to step along the X-axis through the X-axis program control connection 211, so as to drive the artificial head to step along the X-axis. Determine whether the X-axis step limit is triggered (whether the X-axis end limit switch 111 or the artificial head X-axis positive limit switch 410 is triggered). If the X-axis step limit is triggered (since the maximum number of steps in the horizontal detection area is greater than 0, the first step will not be triggered), the system can be exited to end the test. In order to control the artificial head to enter as many points as possible, a path backtracking strategy can be executed.

[0111] 402. If the artificial head does not trigger the limit switch when stepping along the X-axis, further control the Y-axis stepping motor 220 to drive the Y-axis slide bar 320 to step along the Y-axis through the Y-axis program control connection 221, thereby driving the artificial head to step along the X-axis, and determine whether the Y-axis limit is triggered (whether the Y-axis end limit switch 121 or the artificial head Y-axis positive limit switch 420 is triggered). If the Y-axis stepping limit is triggered (since the maximum number of steps in the horizontal detection area is greater than 0, the first step will not be triggered), the Y-axis is reset and then step 401 is executed. If the Y-axis stepping does not trigger the limit switch, step 403 is executed.

[0112] 403. Control the Z-axis stepping motor 230 to drive the artificial head to perform a stepping operation along the Z-axis through the Z-axis program control connection 231, and determine whether the Z-axis stepping limit is triggered (whether the artificial head Z-axis positive limit switch 431 is triggered). If the Z-axis stepping limit is triggered, the Z-axis is reset and then step 402 is executed.

[0113] Optionally, in the path backtracking strategy, the determination of the initial point set of the to-be-detected three-dimensional range may include: determining the initial point subset corresponding to each step along the third number axis; the initial point subset is determined according to the maximum step range of the first number axis and the maximum step range of the second number axis; and the initial point subsets corresponding to each step within the maximum step range of the third number axis are formed into the initial point set.

[0114] Optionally, the determination of the initial point subset corresponding to each step along the third number axis may include: controlling the artificial head to step along the first number axis from the origin position O with the first step length until reaching the preset termination limit point of the first number axis to obtain the maximum step range of the first number axis; controlling the artificial head to step along the second number axis from the origin position O with the second step length until reaching the preset termination limit point of the first number axis to obtain the maximum step range of the second number axis; and determining the initial point subset according to the maximum step range of the first number axis and the maximum step range of the second number axis.

[0115] Exemplarily, such as Figure 3As shown, the initial point set can be determined by detecting the horizontal area. For each step of the Z-axis, there will be a corresponding subset of initial points. The process of determining the subset of initial points is actually a process that starts from the origin position O and successively finds the maximum number of steps of the X-axis and the Y-axis. The maximum number of steps of the X-axis is related to the positions of the X-axis start limit switch 110 and the X-axis end limit switch 111, and the maximum number of steps of the Y-axis is related to the positions of the Y-axis start limit switch 120 and the Y-axis end limit switch 121. If the maximum number of steps is equal to 0, an alarm can be processed. The subset of initial points is determined in the target plane formed by the X-axis and the Y-axis. Taking the case where both the X-axis and the Y-axis can step 2 times as an example, the subset of initial points in the target plane is (00, 01, 10, 11). Since the maximum number of steps of the X-axis and the Y-axis is the same for each step of the Z-axis, the subset of initial points corresponding to each plane parallel to the target plane for each step of the Z-axis is equal to the subset of initial points in the target plane, which is also (00, 01, 10, 11). It can be represented using Cartesian two-dimensional coordinates. After the area detection is completed, it returns to the origin position O again. In this step, if an abnormality occurs, an alarm can be processed and the entire voice test system stops operating.

[0116] In some embodiments, controlling the artificial head to step along each number axis and enter each target point that can be entered in the set of points to be located from the detected area may include: removing the target points that have been entered from each subset of initial points in the initial point set to obtain the subset of points to be located corresponding to each subset of initial points in the initial point set; controlling the artificial head to step along the third number axis, and for each step on the third number axis, controlling the artificial head to enter each point that can be entered in the subset of points to be located corresponding to the current step, and determining the points that can be entered as target points.

[0117] Optionally, controlling the artificial head to enter each point that can be entered in the subset of points to be located corresponding to the current step and determining the points that can be entered as target points may include: repeating the following steps until there are no candidate points adjacent to the located area in the subset of points to be located: connecting the target points that have been entered in the subset of initial points corresponding to the current step to form the located area; searching in the subset of points to be located for candidate points adjacent to the located area; controlling the artificial head to enter the candidate point from the located area; if it can enter, marking the candidate point as a target point; if it cannot enter, marking the candidate point as an obstacle point.

[0118] Optionally, before repeating the following steps until there are no candidate points adjacent to the located area in the subset of points to be located, the method may further include: obtaining the subset of points to be located corresponding to the previous step, and the obstacle points marked in the previous step; removing the obstacle points marked in the previous step from the subset of points to be located corresponding to the previous step to obtain the subset of points to be located corresponding to the current step.

[0119] In this embodiment, the path backtracking strategy is mainly aimed at the scenario where the artificial head cannot continue to step during the movement on each plane parallel to the target plane formed by the X-axis and the Y-axis corresponding to each step of the Z-axis when the vertical height of the Z-axis is known, and there are obstacles (such as the front row seat 510 and the rear row seat 520).

[0120] The following will be combined with Figure 5 to give an example introduction to the principle of the path backtracking strategy: As Figure 5 shown, in the plane corresponding to a certain step of the Z-axis, there is an initial subset of points, that is, each point within the rectangular frame (including the target points that have been entered, the points to be located, and the obstacle points).

[0121] 501. Connect the target points that have been entered to form area S r .

[0122] 502. Search for candidate point P in the unvisited area adjacent to S r . i .

[0123] 503. The artificial head attempts to enter P r from area S i . If it can enter point P i , then determine point P i as the target point. And add P i to S r . If it cannot enter P i , then mark P i as an obstacle point.

[0124] Repeat steps 502 to 503 until no candidate point P r in the unvisited area adjacent to S i can be found.

[0125] By the above steps, all the obstacle points in the initial subset of points can be obtained, and the set Sb composed of all the obstacle points is recorded. When stepping into the plane corresponding to the next step along the Z-axis, the points corresponding to the set Sb in the X and Y directions can be directly marked as obstacle points (because seats, etc. are usually placed in the bottom area of the intelligent cockpit. Therefore, in the vertical direction of the intelligent cockpit, if the upper layer points are obstacle points and unreachable, then the corresponding lower layer points will also be obstacle points and unreachable).

[0126] The following is an example to illustrate the entire backtracking process.

[0127] Exemplarily, after the step switches on each number axis are all triggered, the regular test is completed. To further expand the test scope, it is possible to attempt to enter each point in the unvisited area based on the path backtracking strategy. Specifically, obtain the position coordinates of each visited point to form a three-dimensional ordered set S sort , and obtain the initial point subset corresponding to each step of the Z-axis, that is, the Cartesian two-dimensional coordinate set C filed . After the artificial head is reset to the origin, with the Z-axis as the main axis, first obtain S sort The target point that has been entered corresponding to the first step along the Z-axis, that is, the two-dimensional data S z , use the two-dimensional coordinate set C filed Compare with the corresponding position points in S z , and select the located point set C r , then the remaining points are processed as points to be located and recorded as the set C n .

[0128] Furthermore, execute the following steps:

[0129] 2021. Traverse the set C n , find the candidate point P r adjacent to the area formed by the located point set C i , then control the artificial head to pass through the located points and attempt to enter the candidate point P i . If the point P i is successfully entered, then include the point in the set C r for voice testing at the point P i . If the point P i cannot be entered, then include the point P i in the obstacle point set C f . Repeat step 2021 until there are no adjacent points to be located in the area of the located point set Cr.

[0130] 2022. The Z-axis continues to step in the positive direction (from top to bottom), obtain the two-dimensional data S sort of the current layer from S zi , and similarly use the two-dimensional coordinate set C filed to compare with the corresponding position points in S zi , select the located point set C ri , then use the two-dimensional coordinate set C filed to compare with the corresponding position points in C f , select the obstacle point set C fi , and then the remaining ones are processed as points to be located and recorded as the set C ni. Obtain the set C of located points ri and the set C of points to be located ni , and repeatedly execute step 2021 until the backtracking of potential accessible points in the X and Y planes at each step height of the Z axis is completed. Thus, the path backtracking positioning operation is completed.

[0131] 203. For each target point entered, perform a voice test at the target point through the artificial head to obtain a test result.

[0132] 204. Record the position information of the artificial head according to the test result, so as to perform repeated voice tests based on the recorded position information.

[0133] In this embodiment, after entering the target point, the artificial head can be controlled to broadcast test cases multiple times, and based on the response of the in-vehicle computer, the test result based on the test case can be obtained. For example, in a wake-up test, when playing "Hello, Xiao A" for waking up, if it is found through the receipt log that it is not woken up, the test case fails. Or after normal waking up, if the receipt of the in-vehicle computer does not meet the assertion of the test case, it is also considered that the test case execution fails.

[0134] In some embodiments, in order to obtain more accurate and comprehensive test results, after entering the point, the artificial head can be controlled to rotate so as to perform voice tests from multiple angles.

[0135] Specifically, the obtaining of the test result by performing a voice test at the target point through the artificial head may include: controlling the artificial head at the target point to rotate and reset to the starting angle; controlling the artificial head to rotate step by step from the starting angle at the fourth step length to enter multiple target angles; for each target angle, performing a voice test at the target angle through the artificial head to obtain the test result of the target angle. Optionally, the obtaining of the test result of the target angle by performing a voice test at the target angle through the artificial head may include: obtaining at least one test case and the corresponding preset number of times for different test cases; for each test case, performing a voice test at the target angle for the corresponding preset number of times through the artificial head to obtain the test result corresponding to the test case.

[0136] Optionally, the recording of the position information of the artificial head according to the test result so as to perform repeated voice tests based on the recorded position information may include: if the test result is a test failure, recording the position information of the artificial head under the current test so as to perform a reproduction test according to the position information; the position information includes the number of steps and the step length corresponding to each number axis, and the number of steps of the rotational step corresponding to the current target angle and the fourth step length.

[0137] Exemplarily, the voice test process for each point can include the following steps.

[0138] 2031. First, reset the artificial head angle.

[0139] Specifically, multi-angle rotation means that after the artificial head 103 completes spatial positioning, taking the vertical direction as the axis, it rotates at multiple angles, and then performs voice test tasks at different angles. The implementation method is as Figure 4 shown: Place the artificial head vertically through the fixed axis 440 in the vertical direction. When reaching each three-dimensional point, first perform rotation reset, that is, rotate counterclockwise. When the artificial head direction reset lever 441 triggers the artificial head reset limit switch 442, the artificial head angle reset motor, that is, the rotation stepper motor 443 stops stepping, and initializes the current angle offset to 0. Then, according to the set stepping accuracy (set according to the angle in the vertical direction), step by step in the clockwise direction, and perform voice tests at the corresponding angles after each step. Add the angle offset each time a step is taken. When the offset reaches one week (greater than 360°), stop stepping, or when the stepper motor triggers the artificial head direction reset limit switch in the clockwise direction, stop stepping. In this way, the multi-angle test of each point is completed.

[0140] To improve the positioning accuracy, the artificial head needs to be able to perform precise displacement in the X, Y, and Z three-dimensional spaces, and can perform fine-grained angle rotation in the vertical direction, which is mainly achieved through the micro-stepping drive technology of the stepper motor. The stepper motor can control the rotation angle at any angle within 360° in one week. The stroke s of each step step can be calculated by the following expression (1). In actual use, the user can set the stroke s of each step step and then inversely deduce the stepper rotation angle θ (where r is the radius of the transmission shaft of the stepper motor). The stepper motor rotates correspondingly in the specified direction (positive direction, negative direction) according to the rotation angle θ. The user controls the moving step size of the artificial head box positioning by setting the stroke s of each step step of each step. The smaller s step is, the more spatial points there are, and the higher the accuracy.

[0141]

[0142] where θ is the rotation angle, r is the radius of the transmission shaft of the stepper motor, and s step is the stroke of each step.

[0143] 2302. Conduct a voice wake-up conversation test, and further determine whether the test result passes. If the test result fails, record the position information and rotation angle information of the current mannequin head, and upload them to the cloud as the reproduction data for the failed test cases. This data is equivalent to the 3D point position information, the rotation angle of the mannequin head at that time, and the test case executed when the test case fails. The purpose of this data is to reproduce the test failure scenario, restore the problem, and further involve developers to solve the problem. If the test result passes, no processing is performed. Specifically, the reproduction of voice test failure cases refers to reproducing the problems in the failed test cases. When the voice test is performed at different angles of each point in the cockpit by the mannequin head 103, if the test case fails, record the three-dimensional coordinate position of the current mannequin head 103, the rotation angle of the current mannequin head, and the test case, and upload them to the cloud. After the system test is completed, but problem reproduction is required. According to these recorded test failure cases, the mannequin head 103 directly goes to the corresponding point and angle, executes the corresponding use case, and reproduces the problem.

[0144] 2303. After one round of testing, further determine whether the point test times have been reached. If not, enter step 2302. Otherwise, enter step 2304. The setting of the point test times can be set according to actual needs. The underlying voice test involves many models. For the wake-up aspect, there is a definition of the wake-up rate. For example, under the same conditions, if the test is performed 100 times and the normal wake-up occurs 98 times, the test wake-up rate is 98%. Also, for the same conversation, if the test is performed multiple times, count the number of times that can be correctly answered, etc.

[0145] 2304. After completing one round of point testing, the Z-axis stepper motor 230 controls the mannequin head to rotate clockwise at a set angle. First, determine whether the mannequin head has rotated one full circle (such as Figure 2 whether the S25 mannequin head reset switch is triggered clockwise or the cumulative rotation angle has exceeded 360° in the figure). If the mannequin head has not rotated one full circle, enter step 2302. If it has rotated one full circle, it can be reset to enter the next point.

[0146] The voice test method provided in this embodiment can quantify each point in the vehicle interior space by setting multiple number axes and controlling the mannequin head to perform steps along each number axis, enabling the mannequin head to accurately enter the points for testing. This not only improves the test point coverage rate but also facilitates re-entering the same point to reproduce the problems that occurred at that point during the test.

[0147] Figure 6 It is a schematic structural diagram of the voice test device provided in the embodiment of the present application. As Figure 6 shown, the voice test device 60 includes: a reset control module 601, a step control module 602, a test control module 603, and a recording module 604.

[0148] A reset control module 601, configured to control the artificial head to reset to the origin position O in response to a test start instruction;

[0149] A step control module 602, configured to control the artificial head to step along each number axis in sequence from the origin position O and enter multiple target points in sequence;

[0150] A test control module 603, configured to perform a voice test at each entered target point through the artificial head to obtain a test result;

[0151] A recording module 604, configured to record the position information of the artificial head according to the test result, so as to perform repeated voice tests based on the recorded position information.

[0152] The voice test device provided by the embodiment of the present application can quantify each point in the vehicle interior space by setting multiple number axes and controlling the artificial head to step along each number axis, so that the artificial head can accurately enter the point for testing, which not only improves the test point coverage rate, but also facilitates re-entering the same point to reproduce the problems that occur at this point during the test.

[0153] The voice test device provided by the embodiment of the present application can be used to execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0154] The embodiment of the present application further provides a voice test bracket, including: a support member, a plurality of moving members, a plurality of driving members, and an artificial head;

[0155] The plurality of moving members are respectively connected to the plurality of driving members in one-to-one correspondence;

[0156] Each moving member is configured to step relative to the support member along the corresponding number axis under the drive of the corresponding driving member;

[0157] The artificial head is connected to each moving member, and is configured to be reset to the origin position O under the drive of each moving member, and is further configured to step along each number axis in sequence from the origin position O and enter multiple target points in sequence, and is further configured to perform a voice test at each entered target point.

[0158] The voice test bracket provided by the embodiment of the present application can drive the moving members to step on each number axis through each driving member to drive the artificial head to step along each number axis, so as to quantify each point in the vehicle interior space, make the artificial head accurately enter the point for testing, which not only improves the test point coverage rate, but also facilitates re-entering the same point to reproduce the problems that occur at this point during the test.

[0159] In some embodiments, the plurality of moving members include a first moving member, a second moving member, and a third moving member; the plurality of driving members include a first driving member, a second driving member, and a third driving member.

[0160] The first moving member is connected to the first driving member and is configured to step relative to the support member along the first number axis under the drive of the first driving member.

[0161] The second moving member is connected to the second driving member and is configured to step relative to the support member along the second number axis under the drive of the second driving member.

[0162] The third moving member is connected to the first moving member, the second moving member, and the third driving member, and is configured to step relative to the support member along the third number axis under the drive of the third driving member, and is further configured to step relative to the support member along the first number axis under the drive of the first moving member, or step relative to the support member along the second number axis under the drive of the second moving member.

[0163] The artificial head is connected to the third moving member and is configured to step following the steps of the third moving member along each number axis.

[0164] The voice test bracket provided by the embodiment of the present application drives the first moving member to step along the first number axis through the first driving member, drives the second moving member to step along the second number axis through the second driving member, drives the third moving member to step along the third number axis through the third driving member, and the third moving member steps along the first number axis and the second number axis under the drive of the first moving member and the second moving member, so that the artificial head connected to the third moving member steps along the first number axis, the second number axis, and the third number axis under the drive of the third moving member, thereby being able to quantify each point in the vehicle interior space and enabling the artificial head to accurately enter the point for testing, not only improving the test point coverage rate, but also facilitating re-entering the same point to reproduce the problems that occurred at this point during the test.

[0165] The voice test bracket provided by the embodiment of the present application can be used to execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0166] Figure 7 It is a structural block diagram of a voice test device provided by an embodiment of the present application, and this device can be a computer, a message receiving and transmitting device, a tablet device, a medical device, a vehicle-mounted device, etc.

[0167] The apparatus 70 may include one or more of the following components: a processing component 701, a memory 702, a power supply component 703, a multimedia component 704, an audio component 705, an input / output (I / O) interface 706, a sensor component 707, and a communication component 708.

[0168] The processing component 701 generally controls the overall operation of the device 70, such as operations associated with display, telephone calls, data communication, camera operations, and recording operations. The processing component 701 may include one or more processors 709 to execute instructions to complete all or part of the steps of the above-mentioned methods. In addition, the processing component 701 may include one or more modules to facilitate the interaction between the processing component 701 and other components. For example, the processing component 701 may include a multimedia module to facilitate the interaction between the multimedia component 704 and the processing component 701.

[0169] The memory 702 is configured to store various types of data to support the operation of the device 70. Examples of such data include instructions for any application or method operating on the device 70, contact data, phone book data, messages, pictures, videos, etc. The memory 702 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disks, or optical disks.

[0170] The power component 703 provides power to various components of the device 70. The power component 703 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 70.

[0171] The multimedia component 704 includes a screen that provides an output interface between the device 70 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can not only sense the boundaries of touch or swipe actions, but also detect the duration and pressure associated with the touch or swipe operation. In some embodiments, the multimedia component 704 includes a front camera and / or a rear camera. When the device 70 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each of the front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capabilities.

[0172] The audio component 705 is configured to output and / or input audio signals. For example, the audio component 705 includes a microphone (MIC), which is configured to receive external audio signals when the device 70 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory 702 or transmitted via the communication component 708. In some embodiments, the audio component 705 further includes a speaker for outputting audio signals.

[0173] The I / O interface 706 provides an interface between the processing component 701 and a peripheral interface module, and the peripheral interface module can be a keyboard, a click wheel, buttons, etc. These buttons can include, but are not limited to: a home button, a volume button, a power-on button, and a lock button.

[0174] The sensor component 707 includes one or more sensors for providing status assessments of various aspects of the device 70. For example, the sensor component 707 can detect the on / off state of the device 70, the relative positioning of components, such as the display and keypad of the device 70. The sensor component 707 can also detect a change in the position of the device 70 or a component of the device 70, the presence or absence of user contact with the device 70, the orientation or acceleration / deceleration of the device 70, and the temperature change of the device 70. The sensor component 707 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor component 707 can also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor component 707 can further include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0175] The communication component 708 is configured to facilitate communication between the device 70 and other devices in a wired or wireless manner. The device 70 can access a wireless network based on a communication standard, such as WiFi, 2G, or 3G, or a combination thereof. In an exemplary embodiment, the communication component 708 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 708 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0176] In an exemplary embodiment, the apparatus 70 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above method.

[0177] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 702 including instructions, and the above instructions can be executed by a processor 709 of the apparatus 70 to complete the above method. For example, the non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0178] The above computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk. The readable storage medium may be any available medium accessible by a general-purpose or special-purpose computer.

[0179] An exemplary readable storage medium is coupled to the processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium may also be a component of the processor. The processor and the readable storage medium may be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium may also exist as discrete components in the device.

[0180] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program may be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes various media such as ROM, RAM, magnetic disks, or optical disks that can store program codes.

[0181] The embodiments of the present application also provide a computer program product including a computer program, and when the computer program is executed by a processor, it implements the voice test method performed by the above voice test device.

[0182] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A voice test method, characterized in that The method includes: In response to a test start instruction, controlling the artificial head to reset to the origin position; Controlling the artificial head to step along each number axis in sequence from the origin position, and successively enter a plurality of target points until the step limits of each number axis are all triggered; Determining an initial point set of the three-dimensional range to be detected; Controlling the artificial head to step along each number axis, and enter the accessible target points in the point set to be located from the plurality of target points that have been entered; the point set to be located is composed of the remaining points in the initial point set except the plurality of target points that have been entered; For each entered target point, performing a voice test at the target point through the artificial head to obtain a test result; Recording the position information of the artificial head according to the test result, so as to perform a repeated voice test based on the recorded position information.

2. The method according to claim 1, characterized in that The controlling the artificial head to step along each number axis in sequence from the origin position, and successively enter a plurality of target points until the step limits of each number axis are all triggered includes: Controlling the artificial head to step in the positive direction of the first number axis with a first step length until the step limit of the first number axis is triggered; For each step on the first number axis, controlling the artificial head to step in the positive direction of the second number axis with a second step length until the step limit of the second number axis is triggered, and then resetting the artificial head to the starting limit point of the second number axis; For each step on the second number axis, controlling the artificial head to step in the positive direction of the third number axis with a third step length until the step limit of the third number axis is triggered, and then resetting the artificial head to the starting limit point of the third number axis; For each step on the third number axis, controlling the artificial head to enter the corresponding target point.

3. The method according to claim 2, wherein The determining the initial point set of the three-dimensional range to be detected includes: Determining an initial point subset corresponding to each step along the third number axis; the initial point subset is determined according to the maximum step range of the first number axis and the maximum step range of the second number axis; Forming an initial point set by the initial point subsets corresponding to each step within the maximum step range of the third number axis; The controlling the artificial head to step along each number axis, and enter the accessible target points in the point set to be located from the detected area includes: Removing the entered target points from each initial point subset in the initial point set to obtain a to-be-located point subset corresponding to each initial point subset in the initial point set; Controlling the artificial head to step along the third number axis, and for each step on the third number axis, controlling the artificial head to enter the accessible points in the to-be-located point subset corresponding to the current step, and determining the accessible points as target points.

4. The method according to claim 3, wherein The determining the initial point subset corresponding to each step along the third number axis includes: Controlling the artificial head to step along the first number axis from the origin position with a first step length until reaching the preset termination limit point of the first number axis to obtain the maximum step range of the first number axis; Controlling the artificial head to step along the second number axis from the origin position with a second step length until reaching the preset termination limit point of the first number axis to obtain the maximum step range of the second number axis; Determine the initial point subset according to the maximum step range of the first number axis and the maximum step range of the second number axis.

5. The method according to claim 3, characterized in that Controlling the robotic head to enter each accessible point in the point subset to be positioned corresponding to the current step, and determining the accessible points as target points, includes: Repeatedly execute the following steps until there are no candidate points adjacent to the located area in the point subset to be positioned: Connect the target points that have been entered in the initial point subset corresponding to the current step to form a located area; Search for candidate points adjacent to the located area from the point subset to be positioned; Control the robotic head to enter the candidate point from the located area; If it can enter, mark the candidate point as a target point; If it cannot enter, mark the candidate point as an obstacle point.

6. The method according to claim 5, wherein Before repeatedly executing the following steps until there are no candidate points adjacent to the located area in the point subset to be positioned, it further includes: Obtain the point subset to be positioned corresponding to the previous step, and the obstacle points marked in the previous step; Remove the obstacle points marked in the previous step from the point subset to be positioned corresponding to the previous step to obtain the point subset to be positioned corresponding to the current step.

7. The method according to any one of claims 1 to 6, characterized in that, Obtaining the test result by performing a voice test at the target point by the robotic head, includes: Control the robotic head to rotate and reset to the starting angle at the target point; Control the robotic head to rotate and step from the starting angle with the fourth step length to enter multiple target angles; For each target angle, perform a voice test of the target angle by the robotic head to obtain the test result of the target angle.

8. The method according to claim 7, characterized in that, Performing the voice test of the target angle by the robotic head to obtain the test result of the target angle, includes: Obtain at least one test case and the preset number of times corresponding to different test cases; For each test case, perform a voice test corresponding to the preset number of times at the target angle by the robotic head to obtain the test result corresponding to the test case.

9. The method according to claim 7, wherein Recording the position information of the robotic head according to the test result to perform repeated voice tests based on the recorded position information, includes: If the test result is a test failure, record the position information of the robotic head under the current test to perform a reproduction test according to the position information; the position information includes the number of steps and step lengths corresponding to each number axis, and the number of steps of the rotational step corresponding to the current target angle and the fourth step length.

10. A voice test bracket for implementing the voice test method according to any one of claims 1-9, characterized in that, Includes: A support member, a plurality of moving members, a plurality of driving members, and a robotic head; The plurality of moving members are respectively connected to the plurality of driving members in one-to-one correspondence; Each moving member is configured to step relative to the support member along the corresponding number axis under the drive of the corresponding driving member; The robotic head is connected to each moving member, configured to be reset to the origin position under the drive of each moving member, further configured to step along each number axis in sequence from the origin position to enter multiple target points in sequence, and further configured to perform a voice test at each target point entered.

11. The voice test support according to claim 10, wherein The multiple moving members include a first moving member, a second moving member, and a third moving member; the multiple driving members include a first driving member, a second driving member, and a third driving member; The first moving member is connected to the first driving member and is configured to step relative to the support member along a first number axis under the drive of the first driving member; The second moving member is connected to the second driving member and is configured to step relative to the support member along a second number axis under the drive of the second driving member; The third moving member is connected to the first moving member, the second moving member, and the third driving member, and is configured to step relative to the support member along a third number axis under the drive of the third driving member, and is further configured to step relative to the support member along the first number axis under the drive of the first moving member, or step relative to the support member along the second number axis under the drive of the second moving member; The artificial head is connected to the third moving member and is configured to step following the stepping of the third moving member along each number axis.

12. An electronic device, characterized in that, Comprising: At least one processor and a memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the voice test method according to any one of claims 1 to 9.

13. A computer-readable storage medium, characterized in that, Computer-executable instructions are stored in the computer-readable storage medium, and when the processor executes the computer-executable instructions, the voice test method according to any one of claims 1 to 9 is implemented.

14. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the voice test method according to any one of claims 1 to 9 is implemented.

Images