CN114333766A - Voice performance testing method, device, system, equipment and storage medium - Google Patents

Abstract

The embodiment of the invention discloses a method, a device, a system, equipment and a storage medium for testing voice performance. The method comprises the following steps: test data are obtained through the test data uploading interface and sent to the data storage module; acquiring voice performance test task information through a test task configuration interface, and sending the voice performance test task information to a test execution module corresponding to the test execution module configuration information so that the test execution module performs voice performance test based on the voice performance test task information; the voice performance test task information comprises a task name, test data configuration information, test object configuration information, test interface configuration information and/or test execution module configuration information. The embodiment of the invention can complete the flows of uploading test data, configuring voice performance test task information, managing and displaying test results and the like in an interface interaction mode, is simple and convenient to operate, improves the test efficiency and reduces the test difficulty.

Description

Voice performance testing method, device, system, equipment and storage medium

technical field

Embodiments of the present invention relate to the field of computer technologies, and in particular, to a method, apparatus, system, device, and storage medium for testing voice performance.

Background technique

Smart terminals such as smart phones, smart speakers and other products are changing with each passing day. With the development of science and technology and the continuous improvement of user service demands, more and more smart terminals with speech recognition and semantic understanding functions have appeared on the market.

In the related art, the method of testing the speech recognition function and semantic understanding function of the intelligent terminal is usually: for each intelligent terminal, use the unified test audio or test text to call the speech recognition interface or semantic understanding interface of the intelligent terminal, and obtain the The speech recognition result or semantic recognition result of the smart terminal.

The test method of the related art can test the speech recognition function and semantic understanding function of the intelligent terminal in batches, but the test method is fixed and cannot be adjusted flexibly.

SUMMARY OF THE INVENTION

The embodiments of the present invention provide a voice performance testing method, device, system, equipment and storage medium, which can make the voice performance testing method more flexible and improve the efficiency and usability of the voice performance testing.

In a first aspect, an embodiment of the present invention also provides a voice performance testing method, including:

Obtain test data through the test data upload interface, and send the test data to the data storage module;

Obtain the voice performance test task information through the test task configuration interface, and send the voice performance test task information to the test execution module corresponding to the configuration information of the test execution module, so that the test execution module is based on the voice performance test task. Information for voice performance testing;

Wherein, the voice performance test task information includes task name, test data configuration information, test object configuration information, test interface configuration information and/or test execution module configuration information.

In a second aspect, an embodiment of the present invention also provides a voice performance testing method, including:

When receiving the voice performance test task information sent by the information interaction module, obtain target test data corresponding to the voice performance test task information from the data storage module according to the test data configuration information in the voice performance test task information;

According to the test object configuration information and the test interface configuration information in the voice performance test task information, call the to-be-tested interface of the terminal device to be tested corresponding to the voice performance test task information, and send the target test data to the The terminal device to be tested corresponding to the voice performance test task information, and the voice recognition result or semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information is obtained;

According to the speech recognition result or the semantic understanding result, and the task name, a speech recognition test result or a semantic understanding test result is generated and sent to the data storage module.

In a third aspect, an embodiment of the present invention also provides a voice performance testing device, including:

a test data sending unit, used to obtain test data through the test data upload interface, and send the test data to the data storage module;

The task information sending unit is used to obtain the voice performance test task information through the test task configuration interface, and send the voice performance test task information to the test execution module corresponding to the test execution module configuration information, so that the test execution module is based on the test execution module. The voice performance test task information is used for voice performance test;

Wherein, the voice performance test task information includes task name, test data configuration information, test object configuration information, test interface configuration information and/or test execution module configuration information.

In a fourth aspect, an embodiment of the present invention also provides a voice performance testing device, including:

The test data acquisition unit is used for, when receiving the voice performance test task information sent by the information interaction module, according to the test data configuration information in the voice performance test task information, from the data storage module and the voice performance test task. The target test data corresponding to the information;

The feedback result acquisition unit is configured to call the interface to be tested of the terminal device to be tested corresponding to the voice performance test task information according to the test object configuration information and the test interface configuration information in the voice performance test task information, and to The target test data is sent to the terminal device to be tested corresponding to the voice performance test task information, and the voice recognition result or semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information is obtained;

A test result sending unit, configured to generate a speech recognition test result or a semantic understanding test result according to the speech recognition result or the semantic understanding result and the task name and send the result to the data storage module.

In a fifth aspect, an embodiment of the present invention provides a voice performance testing system, including:

an information interaction module, a data storage module, at least two test execution modules, and at least two terminal devices to be tested;

Wherein, the information interaction module is used to obtain test data through the test data upload interface, and send the test data to the data storage module; obtain the voice performance test task information through the test task configuration interface, and store the voice The performance test task information is sent to the test execution module corresponding to the test execution module configuration information, where the voice performance test task information includes task name, test data configuration information, test object configuration information, test interface configuration information and/or test execution module configuration information; the data storage module is used to receive the test data and store the test data; store the speech recognition test results or the semantic understanding test results sent by each of the test execution modules;

Each of the test execution modules is configured to, when receiving the voice performance test task information sent by the information exchange module, according to the test data configuration information in the voice performance test task information, from the data storage module Obtain target test data corresponding to the voice performance test task information; call the terminal device to be tested corresponding to the voice performance test task information according to the test object configuration information and the test interface configuration information in the voice performance test task information the interface to be tested, send the target test data to the terminal device to be tested corresponding to the voice performance test task information, and obtain the voice recognition result or Semantic comprehension result; according to the speech recognition result or the semantic comprehension result, and the task name, generate the speech recognition test result or the semantic comprehension test result and send it to the data storage module;

Each terminal device to be tested is used to perform voice recognition or semantic understanding on the target test data when receiving the target test data corresponding to the voice performance test task information, and generate a voice recognition result or semantic understanding result and feed it back to the corresponding test execution module.

In a sixth aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and running on the processor, the processor implementing the computer program when executing the computer program. The voice performance testing method described in the embodiment of the invention.

In a seventh aspect, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the voice performance test according to the embodiment of the present invention is implemented method.

In the technical solution of the embodiment of the present invention, the test data is acquired through the test data upload interface, and the voice performance test task information is acquired through the test task configuration interface, and the procedures such as test data upload, voice performance test task information configuration, etc. Simple and convenient, it improves the efficiency of voice performance testing, reduces the difficulty of voice performance testing, and enables users without programming language foundation to perform automated voice performance testing with simple interface interaction based on the voice performance testing system.

Description of drawings

FIG. 1 is a schematic structural diagram of a voice performance testing system according to Embodiment 1 of the present invention.

FIG. 2 is a flowchart of a voice performance testing method according to Embodiment 2 of the present invention.

FIG. 3 is a flowchart of a voice performance testing method according to Embodiment 3 of the present invention.

FIG. 4 is a schematic structural diagram of a voice performance testing apparatus according to Embodiment 4 of the present invention.

FIG. 5 is a schematic structural diagram of a voice performance testing apparatus according to Embodiment 5 of the present invention.

FIG. 6 is a schematic structural diagram of a computer device according to Embodiment 6 of the present invention.

Detailed ways

The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

In addition, it should be noted that, for the convenience of description, the drawings only show some but not all of the contents related to the present invention. Before discussing the exemplary embodiments in greater detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts various operations (or steps) as a sequential process, many of the operations may be performed in parallel, concurrently, or concurrently. Additionally, the order of operations can be rearranged. The process may be terminated when its operation is complete, but may also have additional steps not included in the figures. The processes may correspond to methods, functions, procedures, subroutines, subroutines, and the like.

Example 1

FIG. 1 is a schematic structural diagram of a voice performance testing system according to Embodiment 1 of the present invention. The embodiments of the present invention are applicable to the case of testing the speech recognition function or the semantic understanding function of the terminal device. As shown in FIG. 1 , the voice performance testing system may specifically include: an information interaction module 101, a data storage module 102, at least two test execution modules 103, and at least two terminal devices to be tested 104. The structure and functions of the system are described below. illustrate.

Wherein, the information interaction module 101 is used to obtain test data through the test data upload interface, and send the test data to the data storage module 102; obtain the voice performance test task information through the test task configuration interface, and upload all the test data to the data storage module 102. The voice performance test task information is sent to the test execution module 103 corresponding to the test execution module configuration information, and the voice performance test task information includes task name, test data configuration information, test object configuration information, test interface configuration information and/or test Execute module configuration information.

The data storage module 102 is configured to receive the test data and store the test data; and store the speech recognition test results or semantic understanding test results sent by each of the test execution modules 103 .

Each of the test execution modules 103 is configured to, when receiving the voice performance test task information sent by the information exchange module 101, store data from the data storage according to the test data configuration information in the voice performance test task information. In module 102, the target test data corresponding to the voice performance test task information is obtained; according to the test object configuration information and the test interface configuration information in the voice performance test task information, the to-be-waited performance test task information corresponding to the voice performance test task information is called. Test the interface to be tested of the terminal device 104, send the target test data to the terminal device to be tested 104 corresponding to the voice performance test task information, and obtain the terminal device to be tested 104 corresponding to the voice performance test task information Feedback the speech recognition result or semantic understanding result; according to the speech recognition result or the semantic understanding result, and the task name, generate the speech recognition test result or the semantic understanding test result and send it to the data storage module 102 .

Each terminal device 104 to be tested is used to perform speech recognition or semantic understanding on the target test data when receiving the target test data corresponding to the voice performance test task information, and generate a speech recognition result or a semantic understanding result to feed back to the target test data. The corresponding test execution module 103 . Specifically, the information interaction module 101 acquires the test data through the test data uploading interface, and sends the test data to the data storage module 102 . The data storage module 102 receives the test data and stores the test data. The information interaction module 101 obtains voice performance test task information through the test task configuration interface, and sends the voice performance test task information to the test execution module 103 corresponding to the test execution module configuration information, where the voice performance test task information includes the task name , test data configuration information, test object configuration information, test interface configuration information and/or test execution module configuration information.

When the test execution module 103 corresponding to the test execution module configuration information receives the voice performance test task information sent by the information exchange module 101, according to the test data configuration information in the voice performance test task information, from the voice performance test task information. The target test data corresponding to the voice performance test task information is acquired in the data storage module 102 . Then, the test execution module 103 corresponding to the configuration information of the test execution module invokes the test object configuration information and the test interface configuration information in the voice performance test task information to call the terminal device 104 to be tested corresponding to the voice performance test task information. The interface to be tested sends the target test data to the terminal device to be tested 104 corresponding to the voice performance test task information, and obtains the voice recognition result fed back by the terminal device to be tested 104 corresponding to the voice performance test task information or semantic understanding results. When the terminal device 104 to be tested corresponding to the voice performance test task information receives the target test data corresponding to the voice performance test task information, the target test data is subjected to voice recognition or semantic understanding, and a voice recognition result is generated. Or the semantic understanding result is fed back to the corresponding test execution module 103 .

The test execution module 103 corresponding to the configuration information of the test execution module generates the speech recognition test result or the semantic understanding test result and sends it to the data storage module 102 according to the speech recognition result or the semantic understanding result and the task name. The data storage module 102 stores the speech recognition test result or the semantic understanding test result sent by the test execution module 103 corresponding to the configuration information of the test execution module.

Optionally, the information interaction module 101 is further configured to obtain a query request corresponding to the task name from the data storage module 102 when a test result query request carrying the task name is obtained through the test result display interface. The speech recognition test result or the semantic understanding test result, and the speech recognition test result or the semantic understanding test result corresponding to the task name is displayed through the test result display interface.

When the information interaction module 101 obtains the test result query request carrying the task name through the test result display interface, it obtains the speech recognition test result or the semantic understanding test corresponding to the task name from the data storage module 102. result, and display the speech recognition test result or the semantic understanding test result corresponding to the task name through the test result display interface.

Optionally, the information interaction module 101 is a server. The test data upload interface is an interface for uploading test data. The test data upload interface can be displayed in the form of a web page. The user can directly access the test data upload interface provided by the information interaction module 101, upload the test data through the test data upload interface, and upload the test data to the data storage module 102 of the voice performance test system.

Optionally, the test data upload interface includes a test data directory and an upload control; the acquiring test data through the test data upload interface and sending the test data to the data storage module 102 includes: acquiring the user's data in the test The test data identification information selected in the data directory; in the preset test database, obtain the test data corresponding to the test data identification information; The test data corresponding to the test data identification information is sent to the data storage module 102 .

Optionally, the test data directory includes test data identification information of multiple pieces of test data. Each item of test data has corresponding test data identification information. The test data identification information is used to distinguish each test data. A number of test data are stored in the preset test database. Each item of test data includes test audio, test text, expected speech recognition results corresponding to the test audio, and/or expected semantic understanding results corresponding to the test text. Test audio is the audio used to test the speech recognition function. The expected speech recognition result corresponding to the test audio is the text corresponding to the sentences in the test audio. The test text is the text used to test the semantic understanding function. The expected semantic understanding result corresponding to the test text is the action contained in the test text that the user wants to perform.

Optionally, the upload control is a control for inputting a test data upload instruction. The test data uploading instruction is an instruction for sending the test data corresponding to the test data identification information to the data storage module 102 .

Specifically, the user opens the test data upload interface provided by the information interaction module 101, selects the test data identification information of a certain test data to be uploaded in the test data directory, and then clicks the upload control. The information interaction module 101 obtains the test data identification information selected by the user in the test data directory, and then obtains the test data corresponding to the test data identification information in the preset test database, and when it is detected that the user has a After the click operation of the upload control is performed, the test data corresponding to the test data identification information is sent to the data storage module 102 .

Optionally, the data storage module 102 is a server. The data storage module 102 receives the test data and stores the test data in the database. The data storage module 102 receives the speech recognition test result or the semantic understanding test result sent by each test execution module 103, and stores the speech recognition test result or the semantic understanding test result in the database.

Optionally, the test task configuration interface is an interface for configuring voice performance test task information. The voice performance test task information is information for performing voice performance tests. One piece of voice performance test task information corresponds to one voice performance test task. The test execution module 103 can execute the voice performance test task according to the voice performance test task information, and test the voice recognition function or semantic understanding function of the designated terminal device 104 to be tested. The test task configuration interface can be displayed in the form of a web page. The user can directly access the test task configuration interface provided by the information interaction module 101, and configure the voice performance test task information through the test task configuration interface. The voice performance test task information includes task name, test data configuration information, test object configuration information, test interface configuration information and/or test execution module configuration information.

Optionally, the test task configuration interface includes: a task name configuration area, a test data configuration area, a test object configuration area, a test interface configuration area, a test execution module configuration area and/or a configuration completion control; The interface acquires voice performance test task information, and sends the voice performance test task information to the test execution module 103 corresponding to the test execution module configuration information, including: acquiring the task name input by the user in the task name configuration area, as the task name and/or, obtain the test data category information entered or selected by the user in the test data configuration area, as test data configuration information; and/or, obtain the test object input or selected by the user in the test object configuration area, As the test object configuration information; and/or, obtain the interface address and access parameters of the interface to be tested of the terminal device to be tested input by the user in the test interface configuration area, as the test interface configuration information; The test execution module identification information entered or selected in the test execution module configuration area is used as the test execution module configuration information; and/or, after detecting the click operation of the user on the configuration completion control, the task name, the The voice performance test task information formed by the test data configuration information, the test object configuration information, the test interface configuration information and/or the test execution module configuration information is sent to the test execution module corresponding to the test execution module configuration information 103.

Optionally, the task name configuration area is an interface area for entering the task name. The user can enter a custom task name in the task name configuration area. Usually, different voice performance test task information contains different task names. The task name can be used to distinguish different voice performance test task information.

Optionally, the test data configuration area is an interface area for inputting test data configuration information. The user can input or select test data category information in the test data configuration area. The test data category information is audio or text. The test data category information input or selected by the user is the test data configuration information input or selected by the user. If the test data category information entered or selected by the user in the test data configuration area is audio, it indicates that when performing the voice performance test task corresponding to the voice performance test task information, it is necessary to Corresponding to the expected speech recognition result, the speech recognition function of the designated terminal device 104 to be tested is tested. If the test data category information entered or selected by the user in the test data configuration area is text, it indicates that when performing the voice performance test task corresponding to the voice performance test task information, it is necessary to Corresponding to the expected semantic understanding result, the semantic understanding function of the designated terminal device 104 to be tested is tested.

Optionally, the test object configuration area is an interface area for inputting test object configuration information. The user can enter or select a test object in the test object configuration area. The test subjects are speech recognition or semantic understanding. The test object input or selected by the user is the configuration information of the test object input or selected by the user. If the test object input or selected by the user in the test object configuration area is speech recognition, it indicates that the speech performance test task corresponding to the speech performance test task information is to test the speech recognition function. If the test object input or selected by the user in the test object configuration area is semantic understanding, it indicates that the voice performance test task corresponding to the voice performance test task information is to test the semantic understanding function.

Optionally, the test interface configuration area is an interface area for inputting test interface configuration information. The user can input the interface address and access parameters of the interface to be tested of the terminal device 104 to be tested that needs to be tested for voice performance in the test interface configuration area. The interface address and access parameters of the interface to be tested of the terminal device 104 to be tested that need to be tested for voice performance input by the user are the test interface configuration information input by the user. The interface to be tested is a speech recognition interface or a semantic understanding interface. If the voice performance testing task is to test the voice recognition function, the user inputs the interface address and access parameters of the voice recognition interface of the terminal device 104 to be tested that needs to be tested for the voice recognition function in the test interface configuration area. If the voice performance test task is to test the semantic understanding function, the user inputs the interface address and access parameters of the semantic understanding interface of the terminal device 104 to be tested that needs to be tested for the semantic understanding function in the test interface configuration area.

Optionally, the test execution module configuration area is an interface area of the test execution module 103 for determining the execution of the voice performance test task corresponding to the voice performance test task information. The test execution module configuration area includes test execution module identification information and working status of each test execution module 103 . Each test execution module 103 has corresponding test execution module identification information. The test execution module identification information is used to distinguish each test execution module 103 . The working status includes idle and task execution. The test execution module 103 whose working status is idle does not execute the voice performance test task. The test execution module 103 whose working status is task execution is executing the voice performance test task according to the received voice performance test task information. The user can select the test execution module identification information of the test execution module 103 whose working status is idle in the test execution module configuration area. In this way, it can be avoided that the same test execution module 103 executes multiple voice performance testing tasks at the same time, resulting in abnormal test results, which can improve the efficiency of voice performance testing.

The test execution module 103 corresponding to the test execution module identification information selected by the user is the test execution module 103 corresponding to the test execution module configuration information, and is the test execution module 103 for executing the voice performance test task corresponding to the voice performance test task information.

Optionally, the configuration completion control is a control for inputting a configuration completion instruction. The configuration complete instruction is an instruction used to determine that the configuration of the voice performance test task information is complete.

Specifically, the user opens the test task configuration interface provided by the information interaction module 101, and inputs the task name in the task name configuration area; inputs or selects test data category information in the test data configuration area; inputs in the test object configuration area Or select a test object; input the interface address and access parameter of the interface to be tested of the terminal device to be tested that needs to be tested for voice performance testing in the test interface configuration area; in the test execution module configuration area, select a working state for the idle test execution The test execution module identification information of module 103, and then click the configuration complete control. The information interaction module 101 obtains the task name input by the user in the task name configuration area as the task name. The information interaction module 101 acquires the test data category information input or selected by the user in the test data configuration area, as the test data configuration information. The information interaction module 101 acquires the test object input or selected by the user in the test object configuration area, as the test object configuration information. The information interaction module 101 acquires the interface address and access parameters of the interface to be tested of the terminal device to be tested input by the user in the test interface configuration area, as test interface configuration information. The information interaction module 101 acquires the test execution module identification information input or selected by the user in the test execution module configuration area, as test execution module configuration information. After the information interaction module 101 detects the user's click operation on the configuration completion control, the task name, the test data configuration information, the test object configuration information, the test interface configuration information and/or the The voice performance test task information formed by the test execution module configuration information is sent to the test execution module 103 corresponding to the test execution module configuration information, thereby sending the voice performance test task information to the test execution module 103 selected by the user.

Optionally, the information interaction module 101 may further provide the user with information on a plurality of configured voice performance test tasks through the test task configuration interface. The user selects a piece of voice performance test task information on the test task configuration interface. The information interaction module 101 sends the voice performance test task information to the test execution module 103 corresponding to the test execution module configuration information in the voice performance test task information.

Optionally, each test execution module 103 is a server. The terminal device 104 to be tested is a terminal device with a speech recognition function and a semantic understanding function. If a certain test execution module 103 receives the voice performance test task information, it indicates that the test execution module 103 is the test execution module 103 selected by the user that needs to execute the voice performance test task corresponding to the voice performance test task information. When the test execution module 103 receives the voice performance test task information sent by the information exchange module 101, according to the test data configuration information in the voice performance test task information, it obtains the data from the data storage module 102. The target test data corresponding to the voice performance test task information. Then, according to the test object configuration information and the test interface configuration information in the voice performance test task information, call the test interface of the terminal device 104 to be tested corresponding to the voice performance test task information, and send the target test data to The terminal device to be tested 104 corresponding to the voice performance test task information, and acquires the speech recognition result or semantic understanding result fed back by the terminal device to be tested 104 corresponding to the voice performance test task information. Finally, according to the speech recognition result or the semantic understanding result, and the task name, a speech recognition test result or a semantic understanding test result is generated and sent to the data storage module 102 .

In a specific example, the test data configuration information received by the test execution module 103 in the voice performance test task information is audio, the test object configuration information is voice recognition, and the test interface configuration information includes the terminal to be tested corresponding to the voice performance test task information The interface address and access parameters of the speech recognition interface of the device 104. The interface address and access parameters of the speech recognition interface of the terminal device 104 to be tested corresponding to the voice performance test task information are the interface address and access parameters of the speech recognition interface of the terminal device to be tested 104 for which the speech recognition function test needs to be performed. The test execution module 103 obtains the test audio and the expected speech recognition result corresponding to the test audio from the data storage module 102 according to the audio, and determines the test audio as corresponding to the voice performance test task information target test data. Then the test execution module 103 calls the to-be-to-be-tested task information corresponding to the voice performance test task information according to the voice recognition and the interface address and access parameters of the voice recognition interface of the terminal device to be tested 104 corresponding to the voice performance test task information. Test the voice recognition interface of the terminal device, send the test audio to the terminal device to be tested 104 corresponding to the voice performance test task information, and obtain the feedback from the terminal device to be tested 104 corresponding to the voice performance test task information. Speech recognition results. When receiving the test audio, the terminal equipment to be tested 104 corresponding to the described voice performance test task information adopts automatic speech recognition (Automatic SpeechRecognition, ASR) technology to carry out speech recognition to the test audio, obtain the speech recognition result of the test audio, and The speech recognition result is fed back to the corresponding test execution module 103, that is, the speech recognition result is fed back to the test execution module 103 that sends the test audio. The speech recognition result is the text corresponding to the sentence in the test audio recognized by the terminal device 104 to be tested.

Optionally, the test execution module 103 obtains the voice recognition result fed back by the terminal device to be tested 104 corresponding to the voice performance test task information, and sends the voice recognition test result composed of the task name and the voice recognition result to the data storage module. 102.

Optionally, the test execution module 103 obtains the voice recognition result fed back by the terminal device to be tested 104 corresponding to the voice performance test task information, calculates the similarity between the voice recognition result and the expected voice recognition result, and then uses the task name, voice recognition The result and the speech recognition test result composed of the similarity between the speech recognition result and the expected speech recognition result are sent to the data storage module 102 .

In another specific example, the test data configuration information received by the test execution module 103 in the voice performance test task information is text, the test object configuration information is semantic understanding, and the test interface configuration information includes the corresponding voice performance test task information. The interface address and access parameters of the semantic understanding interface of the terminal device 104 to be tested. The interface address and access parameter of the semantic understanding interface of the terminal device 104 to be tested corresponding to the voice performance test task information are the interface address and access parameters of the semantic understanding interface of the terminal device 104 to be tested that need to perform the semantic understanding function test. The test execution module 103 obtains the test text and the expected semantic understanding result corresponding to the test text from the data storage module 102 according to the text, and determines the test text as corresponding to the voice performance test task information target test data. Then the test execution module 103 calls the to-be-to-be-tested task information corresponding to the voice performance test task information according to the semantic understanding and the interface address and access parameters of the semantic understanding interface of the terminal device 104 to be tested corresponding to the voice performance test task information. Test the semantic understanding interface of the terminal device 104, send the test text to the terminal device to be tested 104 corresponding to the voice performance test task information, and obtain feedback from the terminal device to be tested 104 corresponding to the voice performance test task information semantic understanding results.

When receiving the test text, the terminal device 104 to be tested corresponding to the voice performance test task information adopts a natural language understanding (Natural Language Understanding, NLU) technology to perform semantic understanding on the test text to obtain a semantic understanding result of the test text , and the semantic understanding result is fed back to the corresponding test execution module 103 , that is, the semantic understanding result is fed back to the test execution module 103 that sends the test text.

Optionally, the test execution module 103 obtains the semantic understanding result fed back by the terminal device to be tested 104 corresponding to the voice performance test task information, and sends the semantic understanding test result consisting of the task name and the semantic understanding result to the data storage module. 102.

Optionally, the test execution module 103 obtains the semantic understanding result fed back by the terminal device to be tested 104 corresponding to the voice performance test task information, calculates the similarity between the semantic understanding result and the expected semantic understanding result, and then uses the task name, semantic understanding The result and the semantic understanding test result composed of the similarity between the semantic understanding result and the expected semantic understanding result are sent to the data storage module 102 .

Optionally, the test result display interface includes a task name input area, a query control and/or a test result display area. The task name input area is an interface area for entering the task name. The query control is a control used to generate a test result query request carrying the task name according to the task name in the task name input area. The test result query request is used to request a query for the speech recognition test result or the semantic understanding test result containing the specified task name. The test result display area is an interface area for displaying the speech recognition test result or the semantic understanding test result.

Specifically, the user can input the task name included in the speech recognition test result or the semantic understanding test result to be queried in the task name input area, and then click the query control. The information interaction module 101 obtains the query control according to the task name in the task name input area, and generates a test result query request carrying the task name, and obtains the speech recognition test result or semantics corresponding to the task name from the data storage module 102 Understand the test results. The speech recognition test result or the semantic understanding test result corresponding to the task name is the speech recognition test result or the semantic understanding test result including the specified task name. Then the information interaction module 101 displays the speech recognition test result or semantic understanding test result corresponding to the task name in the test result display area, so that the user can browse the speech recognition test result or the semantic understanding test result corresponding to the task name in the test result display area. Semantic comprehension test results.

Optionally, before acquiring the speech recognition test result or the semantic understanding test result corresponding to the task name from the data storage module, it also includes: according to the authentication information corresponding to the task name, performing a The result query request is authenticated.

Optionally, authentication information corresponding to each task name is preset. The authentication information is information used for authentication. The authentication information can be a key.

Specifically, the user inputs the task name and authentication information contained in the speech recognition test result or semantic understanding test result to be queried in the task name input area, and then clicks the query control. The information interaction module 101 obtains the query control according to the task name and the authentication information in the task name input area, and generates a query request for the test result carrying the task name and the authentication information. The test result query request is authenticated, and it is judged whether the authentication information in the test result query request is the authentication information corresponding to the task name. If the authentication information in the test result query request is the authentication information corresponding to the task name, then obtain the speech recognition test result or the semantic understanding test result corresponding to the task name from the data storage module 102, in the The test result display area displays the speech recognition test result or the semantic understanding test result corresponding to the task name. If the authentication information in the test result query request is not the authentication information corresponding to the task name, the query permission prompt information is displayed in the test result display area. The query permission prompt information is used to inform the user that the authentication fails, and there is no permission to query the speech recognition test result or the semantic understanding test result corresponding to the task name.

Optionally, the user configures a mailbox corresponding to the task name in the test task configuration interface provided by the information interaction module 101 . The data storage module 102 receives the speech recognition test results or the semantic understanding test results sent by the test execution module 103, and after storing the speech recognition test results or the semantic understanding test results in the database, sends the speech recognition test results or the semantic understanding test results to In the mailbox corresponding to the task name contained in the speech recognition test results or the semantic understanding test results.

The embodiment of the present invention provides a voice performance testing system. The information interaction module obtains test data through a test data upload interface, and sends the test data to a data storage module for storage; the information interaction module obtains the voice performance test through the test task configuration interface. task information, and send the voice performance test task information to the test execution module corresponding to the test execution module configuration information, so that the test execution module corresponding to the test execution module configuration information configures the information according to the test data in the voice performance test task information, Obtain the target test data corresponding to the voice performance test task information from the data storage module, and then call the terminal device to be tested corresponding to the voice performance test task information according to the test object configuration information and the test interface configuration information in the voice performance test task information the interface to be tested, the target test data is sent to the terminal device to be tested corresponding to the voice performance test task information, and the voice recognition result or semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information is obtained, According to the speech recognition result or semantic understanding result and the task name, the speech recognition test result or the semantic understanding test result is generated and sent to the data storage module for storage; the information interaction module obtains the test result carrying the task name through the test result display interface When querying a request, obtain the speech recognition test result or semantic understanding test result corresponding to the task name from the data storage module, and display the speech recognition test result or semantic understanding test result corresponding to the task name through the test result display interface. The performance test automation process is integrated, and the interface interaction is used to complete the process of test data upload, voice performance test task information configuration, etc. The operation is simple and convenient, which improves the efficiency of voice performance test, reduces the difficulty of voice performance test, and makes no programming language. Basic users can also perform automated voice performance testing with simple interface interaction based on the voice performance test system.

Embodiment 2

FIG. 2 is a flowchart of a voice performance testing method according to Embodiment 2 of the present invention. The embodiments of the present invention are applicable to the case of testing the speech recognition function or the semantic understanding function of the terminal device. The method can be applied to the information interaction module in the voice performance testing system provided by the above embodiments of the present invention. As shown in Figure 2, the method of this embodiment specifically includes:

Step 201: Acquire test data through a test data upload interface, and send the test data to a data storage module.

Optionally, the information interaction module is a server. The test data upload interface is an interface for uploading test data. The test data upload interface can be displayed in the form of a web page. Users can directly access the test data upload interface provided by the information interaction module, upload the test data through the test data upload interface, and upload the test data to the data storage module of the voice performance test system.

Optionally, the test data upload interface includes a test data directory and an upload control; the acquiring test data through the test data upload interface and sending the test data to the data storage module includes: acquiring the user's test data in the test data. The test data identification information selected in the catalog; in the preset test database, obtain the test data corresponding to the test data identification information; after detecting the click operation of the user on the upload control, the The test data corresponding to the test data identification information is sent to the data storage module.

Optionally, the test data directory includes test data identification information of multiple pieces of test data. Each item of test data has corresponding test data identification information. The test data identification information is used to distinguish each test data. A number of test data are stored in the preset test database. Each item of test data includes test audio, test text, expected speech recognition results corresponding to the test audio, and/or expected semantic understanding results corresponding to the test text. Test audio is the audio used to test the speech recognition function. The expected speech recognition result corresponding to the test audio is the text corresponding to the sentences in the test audio. The test text is the text used to test the semantic understanding function. The expected semantic understanding result corresponding to the test text is the action contained in the test text that the user wants to perform.

Optionally, the upload control is a control for inputting a test data upload instruction. The test data uploading instruction is an instruction for sending the test data corresponding to the test data identification information to the data storage module.

Specifically, the user opens the test data upload interface provided by the information interaction module, selects the test data identification information of a certain test data to be uploaded in the test data directory, and then clicks the upload control. The information interaction module obtains the test data identification information selected by the user in the test data directory, and then obtains the test data corresponding to the test data identification information in the preset test database, After uploading the click operation of the control, the test data corresponding to the test data identification information is sent to the data storage module.

Step 202, obtain voice performance test task information through the test task configuration interface, and send the voice performance test task information to the test execution module corresponding to the test execution module configuration information, so that the test execution module is based on the voice performance. Test task information for voice performance testing.

Wherein, the voice performance test task information includes task name, test data configuration information, test object configuration information, test interface configuration information and/or test execution module configuration information.

Optionally, the test task configuration interface is an interface for configuring voice performance test task information. The voice performance test task information is information for conducting voice performance tests. One piece of voice performance test task information corresponds to one voice performance test task. The test execution module can execute the voice performance test task according to the voice performance test task information, and test the voice recognition function or semantic understanding function of the designated terminal device to be tested. The test task configuration interface can be displayed in the form of a web page. The user can directly access the test task configuration interface provided by the information interaction module, and configure the voice performance test task information through the test task configuration interface. The voice performance test task information includes task name, test data configuration information, test object configuration information, test interface configuration information and/or test execution module configuration information.

Optionally, the test task configuration interface includes: a task name configuration area, a test data configuration area, a test object configuration area, a test interface configuration area, a test execution module configuration area and/or a configuration completion control; The interface acquires voice performance test task information, and sends the voice performance test task information to the test execution module corresponding to the test execution module configuration information, including: acquiring the task name input by the user in the task name configuration area as the task name and/or, obtain the test data category information that the user inputs or selects in the test data configuration area, as the test data configuration information; and/or, obtain the test object that the user inputs or selects in the test object configuration area, as the test data configuration information; Test object configuration information; and/or, obtain the interface address and access parameters of the interface to be tested of the terminal device to be tested input by the user in the test interface configuration area, as the test interface configuration information; The test execution module identification information input or selected in the test execution module configuration area is used as the test execution module configuration information; and/or, after detecting the click operation of the user on the configuration completion control, the task name, the test The voice performance test task information formed by the data configuration information, the test object configuration information, the test interface configuration information and/or the test execution module configuration information is sent to the test execution module corresponding to the test execution module configuration information.

Optionally, the task name configuration area is an interface area for entering the task name. The user can enter a custom task name in the task name configuration area. Usually, different voice performance test task information contains different task names. The task name can be used to distinguish different voice performance test task information.

Optionally, the test data configuration area is an interface area for inputting test data configuration information. The user can input or select test data category information in the test data configuration area. The test data category information is audio or text. The test data category information input or selected by the user is the test data configuration information input or selected by the user. If the test data category information entered or selected by the user in the test data configuration area is audio, it indicates that when performing the voice performance test task corresponding to the voice performance test task information, it is necessary to The corresponding expected speech recognition result is used to test the speech recognition function of the designated terminal device to be tested. If the test data category information entered or selected by the user in the test data configuration area is text, it indicates that when performing the voice performance test task corresponding to the voice performance test task information, it is necessary to The corresponding expected semantic understanding result is used to test the semantic understanding function of the specified terminal device to be tested.

Optionally, the test object configuration area is an interface area for inputting test object configuration information. The user can enter or select a test object in the test object configuration area. The test subjects are speech recognition or semantic understanding. The test object input or selected by the user is the configuration information of the test object input or selected by the user. If the test object input or selected by the user in the test object configuration area is speech recognition, it indicates that the speech performance test task corresponding to the speech performance test task information is to test the speech recognition function. If the test object input or selected by the user in the test object configuration area is semantic understanding, it indicates that the voice performance test task corresponding to the voice performance test task information is to test the semantic understanding function.

Optionally, the test interface configuration area is an interface area for inputting test interface configuration information. The user can input the interface address and access parameters of the to-be-tested interface of the to-be-tested terminal device that needs to be tested for voice performance in the test interface configuration area. The interface address and access parameters of the interface to be tested of the terminal device to be tested that need to be tested for voice performance input by the user are the test interface configuration information input by the user. The interface to be tested is a speech recognition interface or a semantic understanding interface. If the voice performance test task is to test the voice recognition function, the user enters the interface address and access parameters of the voice recognition interface of the terminal device to be tested that needs to be tested for the voice recognition function in the test interface configuration area. If the voice performance test task is to test the semantic understanding function, the user enters the interface address and access parameters of the semantic understanding interface of the terminal device to be tested that needs to be tested for the semantic understanding function in the test interface configuration area.

Optionally, the test execution module configuration area is an interface area for determining a test execution module that executes the voice performance test task corresponding to the voice performance test task information. The test execution module configuration area includes test execution module identification information and working status of each test execution module. Each test execution module has corresponding test execution module identification information. The test execution module identification information is used to distinguish each test execution module. The working status includes idle and task execution. The test execution module whose working status is idle does not execute the voice performance test task. The test execution module whose working status is task execution is executing the voice performance test task according to the received voice performance test task information. The user can select the test execution module identification information of a test execution module whose working status is idle in the test execution module configuration area. In this way, it can be avoided that the same test execution module executes multiple voice performance test tasks at the same time, resulting in abnormal test results, and the efficiency of voice performance test can be improved.

The test execution module corresponding to the test execution module identification information selected by the user is the test execution module corresponding to the test execution module configuration information, and is the test execution module for executing the voice performance test task corresponding to the voice performance test task information.

Optionally, the configuration completion control is a control for inputting a configuration completion instruction. The configuration complete instruction is an instruction used to determine that the configuration of the voice performance test task information is complete.

Specifically, the user opens the test task configuration interface provided by the information interaction module, and inputs the task name in the task name configuration area; inputs or selects test data category information in the test data configuration area; inputs or Select the test object; input the interface address and access parameters of the interface to be tested of the terminal device to be tested that needs to be tested for voice performance in the test interface configuration area; select a test execution module whose working state is idle in the test execution module configuration area the test execution module identification information, and then click Configure to complete the control. The information interaction module obtains the task name input by the user in the task name configuration area as the task name. The information interaction module acquires the test data category information input or selected by the user in the test data configuration area, as the test data configuration information. The information interaction module acquires the test object input or selected by the user in the test object configuration area, as the test object configuration information. The information interaction module acquires the interface address and access parameters of the interface to be tested of the terminal device to be tested input by the user in the test interface configuration area, as test interface configuration information. The information interaction module acquires the test execution module identification information input or selected by the user in the test execution module configuration area, as test execution module configuration information. After the information interaction module detects the user's click operation on the configuration completion control, the task name, the test data configuration information, the test object configuration information, the test interface configuration information and/or the test The voice performance test task information formed by the configuration information of the execution module is sent to the test execution module corresponding to the configuration information of the test execution module, so that the voice performance test task information is sent to the test execution module selected by the user.

Optionally, the information interaction module may also provide the user with information on a number of configured voice performance test tasks through the test task configuration interface. The user selects a piece of voice performance test task information on the test task configuration interface. The information interaction module sends the voice performance test task information to the test execution module corresponding to the test execution module configuration information in the voice performance test task information.

Optionally, the test execution module performs a voice performance test based on the voice performance test task information, including: when receiving the voice performance test task information sent by the information interaction module, configure according to the test data in the voice performance test task information. information, obtain the target test data corresponding to the voice performance test task information from the data storage module; according to the test object configuration information and test interface configuration information in the voice performance test task information, call the voice performance test task information. the interface to be tested of the terminal device to be tested corresponding to the information, send the target test data to the terminal device to be tested corresponding to the voice performance test task information, and obtain the terminal to be tested corresponding to the voice performance test task information The speech recognition result or semantic understanding result fed back by the device; according to the speech recognition result or the semantic understanding result, and the task name, the speech recognition test result or the semantic understanding test result is generated and sent to the data storage module.

Optionally, the voice performance testing method further includes: when a test result query request carrying the task name is obtained through a test result display interface, acquiring a voice recognition test corresponding to the task name from the data storage module result or semantic understanding test result, and display the speech recognition test result or semantic understanding test result corresponding to the task name through the test result display interface.

Optionally, the test result display interface includes a task name input area, a query control and/or a test result display area. The task name input area is an interface area for entering the task name. The query control is a control used to generate a test result query request carrying the task name according to the task name in the task name input area. The test result query request is used to request a query for the speech recognition test result or the semantic understanding test result containing the specified task name. The test result display area is an interface area for displaying the speech recognition test result or the semantic understanding test result.

Specifically, the user can input the task name included in the speech recognition test result or the semantic understanding test result to be queried in the task name input area, and then click the query control. The information interaction module obtains the query control according to the task name in the task name input area, generates a test result query request carrying the task name, and obtains the speech recognition test result or semantic understanding test corresponding to the task name from the data storage module result. The speech recognition test result or the semantic understanding test result corresponding to the task name is the speech recognition test result or the semantic understanding test result including the specified task name. Then the information interaction module displays the speech recognition test result or semantic understanding test result corresponding to the task name in the test result display area, so that the user can browse the speech recognition test result or semantic understanding corresponding to the task name in the test result display area Understand the test results.

Optionally, before acquiring the speech recognition test result or the semantic understanding test result corresponding to the task name from the data storage module, it also includes: according to the authentication information corresponding to the task name, performing a The result query request is authenticated.

Optionally, authentication information corresponding to each task name is preset. The authentication information is information used for authentication. The authentication information can be a key.

Specifically, the user inputs the task name and authentication information contained in the speech recognition test result or semantic understanding test result to be queried in the task name input area, and then clicks the query control. The information interaction module obtains the query control according to the task name and the authentication information in the task name input area, and generates a query request for the test result carrying the task name and the authentication information. The test result query request is authenticated, and it is judged whether the authentication information in the test result query request is the authentication information corresponding to the task name. If the authentication information in the test result query request is the authentication information corresponding to the task name, obtain the speech recognition test result or the semantic understanding test result corresponding to the task name from the data storage module, and in the test The result display area displays the speech recognition test result or the semantic understanding test result corresponding to the task name. If the authentication information in the test result query request is not the authentication information corresponding to the task name, the query permission prompt information is displayed in the test result display area. The query permission prompt information is used to inform the user that the authentication fails, and there is no permission to query the speech recognition test result or the semantic understanding test result corresponding to the task name.

The embodiment of the present invention provides a voice performance testing method. Test data is acquired through a test data upload interface, and voice performance test task information is acquired through a test task configuration interface. The interface interaction can be used to complete test data upload and voice performance test task information. The configuration and other processes are simple and convenient to operate, improve the efficiency of voice performance testing, and reduce the difficulty of voice performance testing, so that users without programming language foundation can also perform automatic voice performance testing based on the voice performance testing system with simple interface interaction.

Embodiment 3

FIG. 3 is a flowchart of a voice performance testing method according to Embodiment 3 of the present invention. The embodiments of the present invention are applicable to the case of testing the speech recognition function or the semantic understanding function of the terminal device. The method can be applied to the test execution module in the voice performance test system provided by the above embodiments of the present invention. As shown in Figure 3, the method of this embodiment specifically includes:

Step 301, when receiving the voice performance test task information sent by the information interaction module, according to the test data configuration information in the voice performance test task information, obtain the target corresponding to the voice performance test task information from the data storage module. Test Data.

Optionally, each test execution module is a server. The terminal device to be tested is a terminal device with speech recognition function and semantic understanding function. If a certain test execution module receives the voice performance test task information, it indicates that the test execution module is a test execution module selected by the user and needs to execute the voice performance test task corresponding to the voice performance test task information.

Optionally, the test data includes test audio, test text, expected speech recognition results corresponding to the test audio, and/or expected semantic understanding results corresponding to the test text.

Optionally, the test data configuration information is audio, the test object configuration information is voice recognition, and the test interface configuration information includes the interface of the voice recognition interface of the terminal device to be tested corresponding to the voice performance test task information. address and access parameters; the acquiring target test data corresponding to the voice performance test task information from the data storage module according to the test data configuration information in the voice performance test task information includes: according to the audio , obtain the test audio and the expected speech recognition result corresponding to the test audio from the data storage module; determine the test audio as the target test data corresponding to the voice performance test task information.

Optionally, the test data configuration information is text, the test object configuration information is semantic understanding, and the test interface configuration information includes the interface of the semantic understanding interface of the terminal device to be tested corresponding to the voice performance test task information. address and access parameters; the acquiring target test data corresponding to the voice performance test task information from the data storage module according to the test data configuration information in the voice performance test task information includes: according to the text , obtain the test text and the expected semantic understanding result corresponding to the test text from the data storage module; determine the test text as the target test data corresponding to the voice performance test task information.

Step 302: According to the test object configuration information and the test interface configuration information in the voice performance test task information, call the test interface of the terminal device to be tested corresponding to the voice performance test task information, and send the target test data. to the terminal device to be tested corresponding to the voice performance test task information, and obtain the speech recognition result or semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information.

Optionally, the test data configuration information is audio, the test object configuration information is voice recognition, and the test interface configuration information includes the interface of the voice recognition interface of the terminal device to be tested corresponding to the voice performance test task information. address and access parameters; according to the test object configuration information and the test interface configuration information in the voice performance test task information, call the to-be-tested interface of the terminal device to be tested corresponding to the voice performance test task information, and use the The target test data is sent to the terminal device to be tested corresponding to the voice performance test task information, and the voice recognition result or semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information is obtained, including: described voice recognition and the interface address and access parameter of the voice recognition interface of the terminal device to be tested corresponding to the voice performance test task information, call the voice recognition interface of the terminal device to be tested corresponding to the voice performance test task information, The test audio is sent to the terminal device to be tested corresponding to the voice performance test task information, and a voice recognition result fed back by the terminal device to be tested corresponding to the voice performance test task information is acquired.

Optionally, the test data configuration information is text, the test object configuration information is semantic understanding, and the test interface configuration information includes the interface of the semantic understanding interface of the terminal device to be tested corresponding to the voice performance test task information. address and access parameters; according to the test object configuration information and the test interface configuration information in the voice performance test task information, call the to-be-tested interface of the terminal device to be tested corresponding to the voice performance test task information, and use the The target test data is sent to the terminal device to be tested corresponding to the voice performance test task information, and the voice recognition result or semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information is obtained, including: Describe the semantic understanding and the interface address and access parameters of the semantic understanding interface of the terminal device to be tested corresponding to the voice performance test task information, and call the semantic understanding interface of the terminal device to be tested corresponding to the voice performance test task information, The test text is sent to the terminal device to be tested corresponding to the voice performance test task information, and the semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information is obtained.

Step 303 , according to the speech recognition result or the semantic understanding result, and the task name, generate a speech recognition test result or a semantic understanding test result and send it to the data storage module.

Optionally, the test execution module obtains the voice recognition result fed back by the terminal device to be tested corresponding to the voice performance test task information, and sends the voice recognition test result composed of the task name and the voice recognition result to the data storage module.

Optionally, the test execution module obtains the voice recognition result fed back by the terminal device to be tested corresponding to the voice performance test task information, calculates the similarity between the voice recognition result and the expected voice recognition result, and then uses the task name, voice recognition result, And the speech recognition test result composed of the similarity between the speech recognition result and the expected speech recognition result is sent to the data storage module.

Optionally, the test execution module obtains the semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information, and sends the semantic understanding test result composed of the task name and the semantic understanding result to the data storage module.

Optionally, the test execution module obtains the semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information, calculates the similarity between the semantic understanding result and the expected semantic understanding result, and then uses the task name, semantic understanding result, And the semantic understanding test result composed of the similarity between the semantic understanding result and the expected semantic understanding result is sent to the data storage module.

The embodiment of the present invention provides a voice performance testing method. The test execution module obtains target test data corresponding to the voice performance test task information from the data storage module according to the test data configuration information in the voice performance test task information, and then according to The test object configuration information and the test interface configuration information in the voice performance test task information, call the test interface of the terminal device to be tested corresponding to the voice performance test task information, and send the target test data to the voice performance test task information corresponding to The terminal device to be tested is obtained, and the voice recognition result or semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information is obtained, and the voice recognition test result or semantic understanding result is generated according to the voice recognition result or semantic understanding result and the task name. The comprehension test results are sent to the data storage module for storage. According to the test data obtained through the test data upload interface and the voice performance test task information obtained through the test task configuration interface, the speech recognition function or semantic understanding function of the terminal device to be tested can be tested. automated test.

Embodiment 4

FIG. 4 is a schematic structural diagram of a voice performance testing apparatus according to Embodiment 4 of the present invention. The device may be configured in the information interaction module in the voice performance testing system provided by the above embodiments of the present invention. As shown in FIG. 4 , the apparatus includes: a test data sending unit 401 and a task information sending unit 402 .

Wherein, the test data sending unit 401 is used to obtain test data through the test data upload interface, and send the test data to the data storage module; the task information sending unit 402 is used to obtain the voice performance test task information through the test task configuration interface , and send the voice performance test task information to the test execution module corresponding to the configuration information of the test execution module, so that the test execution module performs a voice performance test based on the voice performance test task information; The performance test task information includes task name, test data configuration information, test object configuration information, test interface configuration information and/or test execution module configuration information.

The embodiment of the present invention provides a voice performance testing device, which acquires test data through a test data upload interface, acquires voice performance test task information through a test task configuration interface, and can complete test data upload and voice performance test task information by using interface interaction. The configuration and other processes are simple and convenient to operate, improve the efficiency of voice performance testing, and reduce the difficulty of voice performance testing, so that users without programming language foundation can also perform automatic voice performance testing based on the voice performance testing system with simple interface interaction.

In an optional implementation manner of the embodiment of the present invention, optionally, the voice performance testing apparatus further includes: a test result query unit, configured to obtain a test result query request carrying the task name through the test result display interface , obtain the speech recognition test result or the semantic comprehension test result corresponding to the task name from the data storage module, and display the speech recognition test result or the semantic comprehension test corresponding to the task name through the test result display interface result.

In an optional implementation of the embodiment of the present invention, optionally, the test data uploading interface includes a test data directory and an upload control; the test data sending unit 401 includes: an identification information obtaining subunit for obtaining the user The test data identification information selected in the test data catalog; the test data acquisition subunit is used to obtain the test data corresponding to the test data identification information in the preset test database; the test data transmission subunit is used for After detecting the click operation on the upload control by the user, the test data corresponding to the test data identification information is sent to the data storage module.

In an optional implementation of the embodiment of the present invention, optionally, the test task configuration interface includes: a task name configuration area, a test data configuration area, a test object configuration area, a test interface configuration area, and a test execution module configuration area and/or a configuration completion control; the task information sending unit 402 includes: a first acquisition subunit, used for acquiring the task name input by the user in the task name configuration area, as the task name; and/or, a second acquisition subunit, for acquiring the test data category information input or selected by the user in the test data configuration area, as test data configuration information; and/or, a third acquisition subunit for acquiring the user input or selection in the test object configuration area The test object, as the test object configuration information; and/or, the fourth acquisition subunit, for acquiring the interface address and the access parameter of the interface to be tested of the terminal device to be tested input by the user in the test interface configuration area, as the test interface interface configuration information; and/or, a fifth acquisition subunit, configured to acquire the test execution module identification information input or selected by the user in the test execution module configuration area, as test execution module configuration information; and/or, sending task information The subunit is used for, after detecting the click operation of the user on the configuration completion control, the task name, the test data configuration information, the test object configuration information, the test interface configuration information and/or all The voice performance test task information composed of the configuration information of the test execution module is sent to the test execution module corresponding to the configuration information of the test execution module.

In an optional implementation manner of the embodiment of the present invention, optionally, the voice performance testing apparatus further includes: an authentication unit, configured to perform a query on the test result according to the authentication information corresponding to the task name. Authentication.

Regarding the apparatus in the foregoing embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the speech performance testing method, and will not be described in detail here.

Embodiment 5

FIG. 5 is a schematic structural diagram of a voice performance testing apparatus according to Embodiment 5 of the present invention. The apparatus may be configured in the test execution module in the voice performance test system provided by the above embodiments of the present invention. As shown in FIG. 5 , the apparatus includes: a test data acquisition unit 501 , a feedback result acquisition unit 502 and a test result transmission unit 503 .

Wherein, the test data acquisition unit 501 is configured to, when receiving the voice performance test task information sent by the information interaction module, acquire from the data storage module and the voice performance test task information according to the test data configuration information in the voice performance test task information The target test data corresponding to the performance test task information; the feedback result acquisition unit 502 is used for calling the waiting list corresponding to the voice performance test task information according to the test object configuration information and the test interface configuration information in the voice performance test task information. Test the interface to be tested of the terminal device, send the target test data to the terminal device to be tested corresponding to the voice performance test task information, and obtain the voice feedback from the terminal device to be tested corresponding to the voice performance test task information Recognition result or semantic understanding result; test result sending unit 503 is used for generating speech recognition test result or semantic understanding test result according to the speech recognition result or the semantic understanding result and the task name and sending the result to the data storage module.

The embodiment of the present invention provides a voice performance testing device. The test execution module obtains target test data corresponding to the voice performance test task information from the data storage module according to the test data configuration information in the voice performance test task information, and then according to The test object configuration information and the test interface configuration information in the voice performance test task information, call the test interface of the terminal device to be tested corresponding to the voice performance test task information, and send the target test data to the voice performance test task information corresponding to The terminal device to be tested is obtained, and the voice recognition result or semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information is obtained, and the voice recognition test result or semantic understanding result is generated according to the voice recognition result or semantic understanding result and the task name. The comprehension test results are sent to the data storage module for storage. According to the test data obtained through the test data upload interface and the voice performance test task information obtained through the test task configuration interface, the speech recognition function or semantic understanding function of the terminal device to be tested can be tested. automated test.

In an optional implementation of the embodiment of the present invention, optionally, the test data includes test audio, test text, expected speech recognition results corresponding to the test audio, and/or expected semantic understanding corresponding to the test text result.

In an optional implementation manner of the embodiment of the present invention, optionally, the test data configuration information is audio, the test object configuration information is voice recognition, and the test interface configuration information includes a task related to the voice performance test. The interface address and the access parameter of the speech recognition interface of the terminal device to be tested corresponding to the information; the test data acquisition unit 501 includes: an audio acquisition subunit for acquiring test audio from the data storage module according to the audio, and an expected speech recognition result corresponding to the test audio; an audio determination subunit, configured to determine the test audio as target test data corresponding to the speech performance test task information.

In an optional implementation of the embodiment of the present invention, optionally, the feedback result obtaining unit 502 includes: a speech recognition result obtaining subunit, configured to obtain a voice recognition result according to the voice recognition and the voice performance test task information corresponding to the The interface address and access parameters of the voice recognition interface of the terminal device to be tested, call the voice recognition interface of the terminal device to be tested corresponding to the voice performance test task information, and send the test audio to the voice performance test task information. corresponding terminal equipment to be tested, and acquire the voice recognition result fed back by the terminal equipment to be tested corresponding to the voice performance test task information.

In an optional implementation manner of the embodiment of the present invention, optionally, the test data configuration information is text, the test object configuration information is semantic understanding, and the test interface configuration information includes a task related to the voice performance test. The interface address and access parameter of the semantic understanding interface of the terminal device to be tested corresponding to the information; the test data acquisition unit 501 includes: a text acquisition subunit for acquiring the test text from the data storage module according to the text, and an expected semantic understanding result corresponding to the test text; a text determination subunit, configured to determine the test text as target test data corresponding to the voice performance test task information.

In an optional implementation manner of the embodiment of the present invention, optionally, the feedback result obtaining unit 502 includes: a subunit for obtaining the semantic understanding result, which is used for obtaining the semantic understanding and corresponding to the voice performance test task information according to the semantic understanding. The interface address and access parameters of the semantic understanding interface of the terminal device to be tested, call the semantic understanding interface of the terminal device to be tested corresponding to the voice performance test task information, and send the test text to the voice performance test task. The terminal device to be tested corresponding to the information, and the semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information is obtained.

Regarding the apparatus in the foregoing embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the speech performance testing method, and will not be described in detail here.

Embodiment 6

FIG. 6 is a schematic structural diagram of a computer device according to Embodiment 6 of the present invention. Figure 6 shows a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in FIG. 6 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present invention.

As shown in FIG. 6, computer device 12 takes the form of a general-purpose computing device. Components of computer device 12 may include, but are not limited to, one or more processors 16 , memory 28 , and bus 18 connecting various system components including memory 28 and processor 16 .

Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of a variety of bus structures. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect ( PCI) bus.

Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including both volatile and nonvolatile media, removable and non-removable media.

Memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and/or cache memory 32 . Computer device 12 may further include other removable/non-removable, volatile/non-volatile computer system storage media. For example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard drive"). Although not shown in Figure 6, disk drives for reading and writing to removable non-volatile magnetic disks (eg "floppy disks") and removable non-volatile optical disks (eg CD-ROM, DVD-ROM) may be provided or other optical media) to read and write optical drives. In these cases, each drive may be connected to bus 18 through one or more data media interfaces. Memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments of the present invention.

A program/utility 40 having a set (at least one) of program modules 42, which may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application clients, other program modules, and Program data, each or some combination of these examples may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the described embodiments of the present invention.

Computer device 12 may also communicate with one or more external devices 14 (eg, keyboard, pointing device, display 24, etc.), may also communicate with one or more devices that enable a user to interact with computer device 12, and/or communicate with Any device (eg, network card, modem, etc.) that enables the computer device 12 to communicate with one or more other computing devices. Such communication may take place through input/output (I/O) interface 22 . Also, the computer device 12 may communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN), and/or a public network such as the Internet) through a network adapter 20 . As shown in FIG. 6 , network adapter 20 communicates with other modules of computer device 12 via bus 18 . It should be understood that, although not shown in FIG. 6, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tapes drives and data backup storage systems, etc.

The processor 16 executes various functional applications and data processing by running the program stored in the memory 28, and realizes the voice performance testing method provided by the embodiment of the present invention: obtain the test data through the test data upload interface, and upload the test data to the test data. The data is sent to the data storage module; the voice performance test task information is obtained through the test task configuration interface, and the voice performance test task information is sent to the test execution module corresponding to the test execution module configuration information, so that the test execution module The voice performance test is performed based on the voice performance test task information; wherein the voice performance test task information includes task name, test data configuration information, test object configuration information, test interface configuration information and test execution module configuration information.

Or, implement the voice performance testing method provided by the embodiment of the present invention: when receiving voice performance test task information sent by the information interaction module, according to the test data configuration information in the voice performance test task information, from the data storage module Obtain target test data corresponding to the voice performance test task information; call the terminal device to be tested corresponding to the voice performance test task information according to the test object configuration information and the test interface configuration information in the voice performance test task information the interface to be tested, send the target test data to the terminal device to be tested corresponding to the voice performance test task information, and obtain the voice recognition result or Semantic understanding result; according to the speech recognition result or the semantic understanding result, and the task name, generate a speech recognition test result or a semantic understanding test result and send it to the data storage module.

Embodiment 7

Embodiment 7 of the present invention provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the voice performance testing method provided by the embodiment of the present invention: obtaining a test through a test data upload interface data, and send the test data to the data storage module; obtain voice performance test task information through the test task configuration interface, and send the voice performance test task information to the test execution module corresponding to the test execution module configuration information, to Make the test execution module perform a voice performance test based on the voice performance test task information; wherein the voice performance test task information includes a task name, test data configuration information, test object configuration information, test interface configuration information and a test execution module configuration information.

Or, implement the voice performance testing method provided by the embodiment of the present invention: when receiving voice performance test task information sent by the information interaction module, according to the test data configuration information in the voice performance test task information, from the data storage module Obtain target test data corresponding to the voice performance test task information; call the terminal device to be tested corresponding to the voice performance test task information according to the test object configuration information and the test interface configuration information in the voice performance test task information the interface to be tested, send the target test data to the terminal device to be tested corresponding to the voice performance test task information, and obtain the voice recognition result or Semantic understanding result; according to the speech recognition result or the semantic understanding result, and the task name, generate a speech recognition test result or a semantic understanding test result and send it to the data storage module.

Any combination of one or more computer-readable media may be employed. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples (a non-exhaustive list) of computer readable storage media include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable Programmable Read Only Memory (EPROM or Flash), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an information execution system, apparatus, or device.

A computer-readable signal medium may include a propagated data signal in baseband or as part of a carrier wave, with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transmit a program for use by or in connection with an information execution system, apparatus, or device .

Program code embodied on a computer readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations of the present invention may be written in one or more programming languages, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional Procedural programming language - such as the "C" language or similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or computer device. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or wide area network (WAN), or may be connected to an external computer (eg, through the Internet using an Internet service provider) connect).

Note that the above are only preferred embodiments of the present invention and applied technical principles. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the present invention. The scope is determined by the scope of the appended claims.

Claims (16)

1. A method for testing speech performance, the method comprising:

test data are obtained through a test data uploading interface and are sent to a data storage module;

acquiring voice performance test task information through a test task configuration interface, and sending the voice performance test task information to a test execution module corresponding to the test execution module configuration information so that the test execution module performs a voice performance test based on the voice performance test task information;

the voice performance test task information comprises a task name, test data configuration information, test object configuration information, test interface configuration information and/or test execution module configuration information.

2. The method of claim 1, further comprising:

and when a test result query request carrying the task name is acquired through a test result display interface, acquiring a voice recognition test result or a semantic understanding test result corresponding to the task name from the data storage module, and displaying the voice recognition test result or the semantic understanding test result corresponding to the task name through the test result display interface.

3. The method of claim 1, wherein the test data upload interface comprises a test data directory and/or an upload control;

the test data is obtained through the test data uploading interface and is sent to the data storage module, and the method comprises the following steps:

acquiring test data identification information selected by a user in the test data directory;

acquiring test data corresponding to the test data identification information in a preset test database;

and after the clicking operation of the user on the uploading control is detected, sending the test data corresponding to the test data identification information to a data storage module.

4. The method of claim 1, wherein the test task configuration interface comprises: a task name configuration area, a test data configuration area, a test object configuration area, a test interface configuration area, a test execution module configuration area and/or a configuration completion control;

the method for acquiring the voice performance test task information through the test task configuration interface and sending the voice performance test task information to the test execution module corresponding to the test execution module configuration information comprises the following steps:

acquiring a task name input by a user in the task name configuration area as a task name;

and/or acquiring test data category information input or selected by a user in the test data configuration area as test data configuration information;

and/or acquiring a test object input or selected by a user in the test object configuration area as test object configuration information;

and/or acquiring an interface address and an access parameter of a to-be-tested interface of the to-be-tested terminal equipment, which are input by a user in the test interface configuration area, as test interface configuration information;

and/or acquiring the identification information of the test execution module input or selected by the user in the test execution module configuration area as the configuration information of the test execution module;

and/or after the clicking operation of the configuration completion control by the user is detected, sending the voice performance test task information formed by the task name, the test data configuration information, the test object configuration information, the test interface configuration information and/or the test execution module configuration information to the test execution module corresponding to the test execution module configuration information.

5. The method of claim 2, further comprising, prior to retrieving the speech recognition test result or semantic understanding test result corresponding to the task name from the data storage module:

and authenticating the test result query request according to the authentication information corresponding to the task name.

6. A method for testing speech performance, the method comprising:

when receiving voice performance test task information sent by an information interaction module, acquiring target test data corresponding to the voice performance test task information from a data storage module according to test data configuration information in the voice performance test task information;

calling a to-be-tested interface of a to-be-tested terminal device corresponding to the voice performance test task information according to test object configuration information and test interface configuration information in the voice performance test task information, sending the target test data to the to-be-tested terminal device corresponding to the voice performance test task information, and acquiring a voice recognition result or a semantic understanding result fed back by the to-be-tested terminal device corresponding to the voice performance test task information;

and generating a voice recognition test result or a semantic understanding test result according to the voice recognition result or the semantic understanding result and the task name, and sending the voice recognition test result or the semantic understanding test result to the data storage module.

7. The method of claim 6, wherein test data comprises test audio, test text, expected speech recognition results corresponding to the test audio, and/or expected semantic understanding results corresponding to the test text.

8. The method according to claim 7, wherein the test data configuration information is audio, the test object configuration information is voice recognition, and the test interface configuration information includes an interface address and an access parameter of a voice recognition interface of the terminal device to be tested corresponding to the voice performance test task information;

the acquiring, from the data storage module, target test data corresponding to the voice performance test task information according to the test data configuration information in the voice performance test task information includes:

according to the audio, acquiring a test audio and an expected voice recognition result corresponding to the test audio from the data storage module;

and determining the test audio as target test data corresponding to the voice performance test task information.

9. The method according to claim 8, wherein the calling an interface to be tested of a terminal device to be tested corresponding to the voice performance test task information according to test object configuration information and test interface configuration information in the voice performance test task information, sending the target test data to the terminal device to be tested corresponding to the voice performance test task information, and obtaining a voice recognition result or a semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information comprises:

calling a voice recognition interface of the terminal equipment to be tested corresponding to the voice performance test task information according to the voice recognition and the interface address and the access parameter of the voice recognition interface of the terminal equipment to be tested corresponding to the voice performance test task information, sending the test audio to the terminal equipment to be tested corresponding to the voice performance test task information, and acquiring a voice recognition result fed back by the terminal equipment to be tested corresponding to the voice performance test task information.

10. The method according to claim 7, wherein the test data configuration information is a text, the test object configuration information is semantic understanding, and the test interface configuration information includes an interface address and an access parameter of a semantic understanding interface of the terminal device to be tested corresponding to the voice performance test task information;

the acquiring, from the data storage module, target test data corresponding to the voice performance test task information according to the test data configuration information in the voice performance test task information includes:

according to the text, obtaining a test text and an expected semantic understanding result corresponding to the test text from the data storage module;

and determining the test text as target test data corresponding to the voice performance test task information.

11. The method according to claim 10, wherein the calling an interface to be tested of a terminal device to be tested corresponding to the voice performance test task information according to test object configuration information and test interface configuration information in the voice performance test task information, sending the target test data to the terminal device to be tested corresponding to the voice performance test task information, and obtaining a voice recognition result or a semantic understanding result fed back by the terminal device to be tested corresponding to the voice performance test task information, comprises:

calling a semantic understanding interface of the terminal equipment to be tested corresponding to the voice performance test task information according to the semantic understanding and the interface address and the access parameter of the semantic understanding interface of the terminal equipment to be tested corresponding to the voice performance test task information, sending the test text to the terminal equipment to be tested corresponding to the voice performance test task information, and acquiring a semantic understanding result fed back by the terminal equipment to be tested corresponding to the voice performance test task information.

12. A speech performance testing apparatus, the apparatus comprising:

the test data transmitting unit is used for acquiring test data through a test data uploading interface and transmitting the test data to the data storage module;

the task information sending unit is used for obtaining voice performance test task information through a test task configuration interface and sending the voice performance test task information to a test execution module corresponding to the test execution module configuration information so that the test execution module performs voice performance test based on the voice performance test task information;

the voice performance test task information comprises a task name, test data configuration information, test object configuration information, test interface configuration information and/or test execution module configuration information.

13. A speech performance testing apparatus, the apparatus comprising:

the test data acquisition unit is used for acquiring target test data corresponding to the voice performance test task information from the data storage module according to test data configuration information in the voice performance test task information when receiving the voice performance test task information sent by the information interaction module;

a feedback result obtaining unit, configured to call a to-be-tested interface of a to-be-tested terminal device corresponding to the voice performance test task information according to test object configuration information and test interface configuration information in the voice performance test task information, send the target test data to the to-be-tested terminal device corresponding to the voice performance test task information, and obtain a voice recognition result or a semantic understanding result fed back by the to-be-tested terminal device corresponding to the voice performance test task information;

and the test result sending unit is used for generating a voice recognition test result or a semantic understanding test result according to the voice recognition result or the semantic understanding result and the task name and sending the voice recognition test result or the semantic understanding test result to the data storage module.

14. A speech performance testing system, comprising:

the system comprises an information interaction module, a data storage module, at least two test execution modules and at least two terminal devices to be tested;

the information interaction module is used for acquiring test data through a test data uploading interface and sending the test data to the data storage module; acquiring voice performance test task information through a test task configuration interface, and sending the voice performance test task information to a test execution module corresponding to the test execution module configuration information, wherein the voice performance test task information comprises a task name, test data configuration information, test object configuration information, test interface configuration information and/or test execution module configuration information;

the data storage module is used for receiving the test data and storing the test data; storing the voice recognition test result or the semantic understanding test result sent by each test execution module;

each test execution module is used for acquiring target test data corresponding to the voice performance test task information from the data storage module according to test data configuration information in the voice performance test task information when the voice performance test task information sent by the information interaction module is received; calling a to-be-tested interface of a to-be-tested terminal device corresponding to the voice performance test task information according to test object configuration information and test interface configuration information in the voice performance test task information, sending the target test data to the to-be-tested terminal device corresponding to the voice performance test task information, and acquiring a voice recognition result or a semantic understanding result fed back by the to-be-tested terminal device corresponding to the voice performance test task information; generating a voice recognition test result or a semantic understanding test result according to the voice recognition result or the semantic understanding result and/or the task name, and sending the voice recognition test result or the semantic understanding test result to the data storage module;

and each terminal device to be tested is used for carrying out voice recognition or semantic understanding on the target test data when receiving the target test data corresponding to the voice performance test task information, and generating a voice recognition result or a semantic understanding result to feed back to the corresponding test execution module.

15. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the speech performance testing method according to any of claims 1-5 or the speech performance testing method according to any of claims 6-11 when executing the computer program.

16. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method for speech performance testing according to any one of claims 1-5, or the method for speech performance testing according to any one of claims 6-11.

Images