CN113836010A - Voice intelligent customer service automatic testing method, system and storage medium - Google Patents
Voice intelligent customer service automatic testing method, system and storage medium Download PDFInfo
- Publication number
- CN113836010A CN113836010A CN202111078981.8A CN202111078981A CN113836010A CN 113836010 A CN113836010 A CN 113836010A CN 202111078981 A CN202111078981 A CN 202111078981A CN 113836010 A CN113836010 A CN 113836010A
- Authority
- CN
- China
- Prior art keywords
- test
- voice
- customer service
- intelligent customer
- voice intelligent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Prevention of errors by analysis, debugging or testing of software
- G06F11/3604—Analysis of software for verifying properties of programs
- G06F11/3616—Analysis of software for verifying properties of programs using software metrics
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Prevention of errors by analysis, debugging or testing of software
- G06F11/3604—Analysis of software for verifying properties of programs
- G06F11/3612—Analysis of software for verifying properties of programs by runtime analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Prevention of errors by analysis, debugging or testing of software
- G06F11/3698—Environments for analysis, debugging or testing of software
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Telephonic Communication Services (AREA)
Abstract
本发明公开了一种语音智能客服自动化测试方法、系统及存储介质，该方法包括：接收对语音智能客服系统的测试指令；根据测试指令，对语音智能客服系统的人机交互流程和/或功能模块进行自动化测试。该方案针对语音智能客服的特点，结合智能语音技术和客服流程交互，模拟人机交互场景测试，解决了语音智能客服项目在机器人训练和调优测试阶段耗费大量测试人力的问题，提高测试效率，节省测试人工成本的同时，提升测试质量。
The invention discloses an automatic testing method, system and storage medium for voice intelligent customer service. The method includes: receiving a test instruction for the voice intelligent customer service system; Modules for automated testing. According to the characteristics of voice intelligent customer service, this solution combines intelligent voice technology and customer service process interaction, simulates human-computer interaction scenario testing, and solves the problem that the voice intelligent customer service project consumes a lot of test manpower in the robot training and tuning test stages, and improves the test efficiency. Improve test quality while saving test labor costs.
Description
Technical Field
The invention relates to the technical field of testing, in particular to a voice intelligent customer service automatic testing method, a system and a storage medium.
Background
With the rapid improvement of the artificial intelligence technology and the man-machine interaction mode, the voice intelligence technology is applied to various large scenes including real-time conference translation, recording quality inspection and the like, and is initially applied and successfully applied in an intelligent customer service scene, so that the business query and handling efficiency of customers is greatly improved, and the enterprise service quality is improved while the labor cost is saved.
At present, existing voice intelligent customer service robots in the industry adopt a mode of combining manual static testing and manual telephone dial testing to perform testing when training and tuning, when the robot is oriented to a complex knowledge base scene, the defects of low efficiency and high consumption of a manual testing mode are revealed, a large amount of testing manpower needs to be invested in simple and repeated work, and therefore the project is difficult to rapidly advance.
Disclosure of Invention
The invention mainly aims to provide a voice intelligent customer service automatic testing method, a system and a storage medium, and aims to solve the problem that a voice intelligent customer service project consumes a large amount of testing manpower in the robot training and tuning testing stage and improve the testing efficiency.
In order to achieve the above object, the present invention provides an automatic testing method for voice intelligent customer service, which is applied to a voice intelligent customer service system, and comprises the following steps:
receiving a test instruction of the voice intelligent customer service system;
and automatically testing the human-computer interaction flow and/or the functional module of the voice intelligent customer service system according to the test instruction.
Optionally, the type of the test instruction is end-to-end automated testing, and the step of performing automated testing on the human-computer interaction flow of the voice intelligent customer service system according to the test instruction includes:
and simulating a man-machine interaction scene according to the test instruction, and testing the correctness of the interaction flow by combining the functions of voice recognition, semantic recognition and voice synthesis.
Optionally, the step of simulating a human-computer interaction scene according to the test instruction, and testing the correctness of the human-computer interaction process of the intelligent voice customer service system by combining the functions of voice recognition, semantic recognition and voice synthesis includes:
in the voice input stage, analyzing a pre-established test case table according to the test instruction to obtain an RF case;
based on the RF case, generating TTS synthesis audio or obtaining historical audio as analog speech input audio, the types of analog speech input audio including: TTS synthesis standard questions, TTS synthesis extension questions and historical real user audio;
according to the simulated voice input audio, simulating a man-machine interaction scene, initiating a voice intelligent customer service system call through SIP, and playing voice;
in the interaction process, the correctness of the man-machine interaction process, the correctness of semantic recognition and the correctness of voice recognition are respectively tested.
Optionally, before playing the voice, the method further includes:
judging whether to simulate the response operation of the user;
if yes, inquiring a preset voice table and executing a voice playing step.
Optionally, the step of simulating a human-computer interaction scene according to the test instruction, and testing the correctness of the human-computer interaction process of the intelligent voice customer service system by combining the functions of voice recognition, semantic recognition and voice synthesis further includes:
in the stage of voice result transcription, obtaining result sound returned by the voice intelligent customer service system based on a man-machine interaction process;
recording the result sound to obtain recorded voice;
when the terminal service node is reached, the recorded voice is identified and transcribed to obtain a voice transcription result;
and comparing the voice transcription result with an expected test result to judge the interaction correctness of the man-machine interaction process of the voice intelligent customer service system.
Optionally, the type of the test instruction is a single-module automated test, and the step of automatically testing the function module of the voice intelligent customer service system according to the test instruction includes:
according to the test instruction, carrying out module capability test on the voice transcription module of the voice intelligent customer service system, and specifically comprising the following steps:
according to the test instruction, using a pre-labeled voice file and a labeling result, calling an ASR engine used by the voice intelligent customer service system, testing a new intention audio frequency of a current project of the voice transcription module, and outputting to obtain a transcription result;
and checking and comparing the transcription result and the labeling result to obtain a test result of the real-time voice transcription module.
Optionally, the type of the test instruction is a single-module automated test, and the step of automatically testing the function module of the voice intelligent customer service system according to the test instruction includes:
according to the test instruction, carrying out module capability test on a semantic understanding module of the voice intelligent customer service system, and specifically comprising the following steps:
according to the test instruction, using a pre-labeled real semantic result and an expansion question to call an ASR engine used by the voice intelligent customer service system, testing the new semantics of the current item of the semantic understanding module, and outputting to obtain a current semantic result;
and checking and comparing the current semantic result with the real semantic result to obtain a test result of the semantic understanding module.
Optionally, the method further comprises:
outputting a test result; the test instruction comprises a plurality of test tasks of voice intelligent customer service, and the plurality of test tasks are tested in a concurrent execution mode.
In addition, an embodiment of the present invention provides a voice intelligent customer service automation test system, where the system includes: the system comprises a memory, a processor and a voice intelligent customer service automatic test program which is stored on the memory and can run on the processor, wherein the voice intelligent customer service automatic test program realizes the steps of the voice intelligent customer service automatic test method when being executed by the processor.
In addition, an embodiment of the present invention provides a computer-readable storage medium, where a voice intelligent customer service automation test program is stored on the computer-readable storage medium, and when the voice intelligent customer service automation test program is executed by a processor, the steps of the voice intelligent customer service automation test method described above are implemented.
The voice intelligent customer service automatic testing method, the system and the storage medium provided by the embodiment of the invention receive a testing instruction of the voice intelligent customer service system; and automatically testing the human-computer interaction flow and/or the functional module of the voice intelligent customer service system according to the test instruction. The scheme aims at the characteristics of the voice intelligent customer service, combines the intelligent voice technology and the customer service flow interaction, simulates the human-computer interaction scene test, solves the problem that the voice intelligent customer service project consumes a large amount of test manpower in the robot training and tuning test stages, and improves the test efficiency; the scheme of the invention can support simultaneous parallel testing of multiple items. Compared with the prior art, the scheme of the embodiment of the invention can quickly and automatically complete the conventional interactive test of the voice customer service scene, thereby greatly improving the efficiency of project test; furthermore, the quick pertinence test can be carried out on the transcription module and the semantic module, so that the applicability of the voice engine in a new project scene is improved; in addition, the testing task of the voice intelligent customer service can be automatically and concurrently executed, the project testing efficiency is greatly improved, the testing labor cost is saved, and the testing quality is improved.
Drawings
Fig. 1 is a schematic diagram of functional modules of a terminal device to which a voice intelligent customer service automatic testing device according to an embodiment of the present invention belongs;
FIG. 2 is a schematic flow chart illustrating an embodiment of a voice intelligent customer service automated testing method according to the present invention;
FIG. 3 is a detailed flow diagram of an embodiment of the automated testing method for voice intelligent customer service according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The main solution of the embodiment of the invention is as follows: receiving a test instruction of the voice intelligent customer service system; and automatically testing the human-computer interaction flow and/or the functional module of the voice intelligent customer service system according to the test instruction. The scheme aims at the characteristics of the voice intelligent customer service, combines the intelligent voice technology and the customer service flow interaction, simulates the human-computer interaction scene test, solves the problem that the voice intelligent customer service project consumes a large amount of test manpower in the robot training and tuning test stages, and improves the test efficiency; the scheme of the invention can support simultaneous parallel testing of multiple items. Compared with the prior art, the scheme of the embodiment of the invention can quickly and automatically complete the conventional interactive test of the voice customer service scene, thereby greatly improving the efficiency of project test; furthermore, the quick pertinence test can be carried out on the transcription module and the semantic module, so that the applicability of the voice engine in a new project scene is improved; in addition, the testing task of the voice intelligent customer service can be automatically and concurrently executed, the project testing efficiency is greatly improved, the testing labor cost is saved, and the testing quality is improved.
The technical terms related to the embodiment of the invention are as follows:
SIP (session initiation protocol), the session initiation protocol, may enable interoperation of various products using the h.323 recommendation, but the h.323 recommendation is too complex, so the IETF has formulated another set of simpler standards, namely the session initiation protocol SIP, which uses many headers of HTTP, coding rules and some authentication mechanisms, and also combines with RTP and RTCP protocols to provide services similar to h.323 and have stronger scalability.
RF, called RobotFrameWork for short, is an open source automated testing framework, a visual testing framework, and RF tabular programming (keyword driving) realized based on Selenium, and because it has many compiled class libraries, it can make testers who do not know programming directly use development testing scripts.
TTS, the abbreviation of Text To Speech, Text-To-Speech, is a part of man-machine conversation, and TTS is a technology for converting Text information into voice signals according To voice processing rules and outputting the voice signals, so that a computer can read the Text information fluently, and people can understand the content of the information by listening To the Text information.
Asr (automatic Speech recognition), an automatic Speech recognition technology, is a technology that converts human Speech into text.
The embodiment of the invention considers that: at present, existing voice intelligent customer service robots in the industry adopt a mode of combining manual static testing and manual telephone dial testing to perform testing when training and tuning, when the robot is oriented to a complex knowledge base scene, the defects of low efficiency and high consumption of a manual testing mode are revealed, a large amount of testing manpower needs to be invested in simple and repeated work, and therefore the project is difficult to rapidly advance.
Based on the above, the embodiment of the invention provides a solution, which can simulate a human-computer interaction scene test by combining an intelligent voice technology and a customer service flow interaction according to the characteristics of voice intelligent customer service and through intelligent technologies such as voice recognition, semantic recognition, voice synthesis, voice transcription and the like, solve the problem that a voice intelligent customer service project consumes a large amount of test manpower in the robot training and tuning test stages, and improve the test efficiency.
Specifically, referring to fig. 1, fig. 1 is a schematic diagram of functional modules of a terminal device to which the voice intelligent customer service automation test device of the present invention belongs. The voice intelligent customer service automatic testing device can be a device independent of the terminal equipment, and can be borne on the terminal equipment or a system in a hardware or software mode. The terminal device can be an intelligent mobile terminal such as a mobile phone and a tablet personal computer, and can also be a network device such as a server.
In this embodiment, the terminal device of the voice intelligent customer service automation testing device at least includes an output module 110, a processor 120, a memory 130 and a communication module 140.
The memory 130 stores an operating system and a voice intelligent customer service automation test program; the output module 110 may be a display screen, a speaker, etc. The communication module 140 may include a WIFI module, a mobile communication module, a bluetooth module, and the like, and communicates with an external device or a server through the communication module 140.
As an embodiment, the voice intelligent customer service automation test program in the memory 130 implements the following steps when executed by the processor:
receiving a test instruction of the voice intelligent customer service system;
and automatically testing the human-computer interaction flow and/or the functional module of the voice intelligent customer service system according to the test instruction.
Further, the speech intelligent customer service automation test program in the memory 130 when executed by the processor further implements the following steps:
and simulating a man-machine interaction scene according to the test instruction, and testing the correctness of the interaction flow by combining the functions of voice recognition, semantic recognition and voice synthesis.
Further, the speech intelligent customer service automation test program in the memory 130 when executed by the processor further implements the following steps:
in the voice input stage, analyzing a pre-established test case table according to the test instruction to obtain an RF case;
based on the RF case, generating TTS synthesis audio or obtaining historical audio as analog speech input audio, the types of analog speech input audio including: TTS synthesis standard questions, TTS synthesis extension questions and historical real user audio;
according to the simulated voice input audio, simulating a man-machine interaction scene, initiating a voice intelligent customer service system call through SIP, and playing voice;
in the interaction process, the correctness of the man-machine interaction process, the correctness of semantic recognition and the correctness of voice recognition are respectively tested.
Further, the speech intelligent customer service automation test program in the memory 130 when executed by the processor further implements the following steps:
in the stage of voice result transcription, obtaining result sound returned by the voice intelligent customer service system based on a man-machine interaction process;
recording the result sound to obtain recorded voice;
when the terminal service node is reached, the recorded voice is identified and transcribed to obtain a voice transcription result;
and comparing the voice transcription result with an expected test result to judge the interaction correctness of the man-machine interaction process of the voice intelligent customer service system.
Further, the speech intelligent customer service automation test program in the memory 130 when executed by the processor further implements the following steps:
according to the test instruction, carrying out module capability test on the voice transcription module of the voice intelligent customer service system, and specifically comprising the following steps:
according to the test instruction, using a pre-labeled voice file and a labeling result, calling an ASR engine used by the voice intelligent customer service system, testing a new intention audio frequency of a current project of the voice transcription module, and outputting to obtain a transcription result;
and checking and comparing the transcription result and the labeling result to obtain a test result of the real-time voice transcription module.
Further, the speech intelligent customer service automation test program in the memory 130 when executed by the processor further implements the following steps:
according to the test instruction, carrying out module capability test on a semantic understanding module of the voice intelligent customer service system, and specifically comprising the following steps:
according to the test instruction, using a pre-labeled real semantic result and an expansion question to call an ASR engine used by the voice intelligent customer service system, testing the new semantics of the current item of the semantic understanding module, and outputting to obtain a current semantic result;
and checking and comparing the current semantic result with the real semantic result to obtain a test result of the semantic understanding module.
Further, the speech intelligent customer service automation test program in the memory 130 when executed by the processor further implements the following steps:
outputting a test result; the test instruction comprises a plurality of test tasks of voice intelligent customer service, and the plurality of test tasks are tested in a concurrent execution mode.
According to the scheme, the embodiment receives a test instruction of the voice intelligent customer service system; and automatically testing the human-computer interaction flow and/or the functional module of the voice intelligent customer service system according to the test instruction. The scheme aims at the characteristics of the voice intelligent customer service, combines the intelligent voice technology and the customer service flow interaction, simulates the human-computer interaction scene test, solves the problem that the voice intelligent customer service project consumes a large amount of test manpower in the robot training and tuning test stages, and improves the test efficiency; the scheme of the invention can support simultaneous parallel testing of multiple items. Compared with the prior art, the scheme of the embodiment of the invention can quickly and automatically complete the conventional interactive test of the voice customer service scene, thereby greatly improving the efficiency of project test; furthermore, the quick pertinence test can be carried out on the transcription module and the semantic module, so that the applicability of the voice engine in a new project scene is improved; in addition, the testing task of the voice intelligent customer service can be automatically and concurrently executed, the project testing efficiency is greatly improved, the testing labor cost is saved, and the testing quality is improved.
Based on the above terminal device architecture but not limited to the above architecture, embodiments of the method of the present invention are presented.
Referring to fig. 2, fig. 2 is a flow chart of an embodiment of the voice intelligent customer service automatic testing method of the present invention.
As shown in fig. 2, the voice intelligent customer service automatic testing method provided by the embodiment of the present invention,
the voice intelligent customer service automatic testing method is applied to a voice intelligent customer service system, and comprises the following steps:
step S101, receiving a test instruction of the voice intelligent customer service system;
and S102, automatically testing the human-computer interaction flow and/or the functional module of the voice intelligent customer service system according to the test instruction.
The voice intelligent customer service system can be a voice intelligent customer service robot. The current industry is to pronunciation intelligence customer service scene, and pronunciation intelligence customer service robot adopts artifical static test to combine artifical telephone to dial the mode of surveying to test when training and tuning, when facing complicated knowledge base scene, shows out the shortcoming that artifical test mode inefficiency high-consumption promptly, and simple repeated work needs to invest in a large amount of test manpowers, leads to the project to be difficult to promote fast.
The embodiment of the invention can simulate the man-machine interaction scene test by combining the intelligent voice technology and the customer service flow interaction according to the characteristics of the voice intelligent customer service and through the intelligent technologies such as text retrieval, text matching, voice synthesis, voice transcription and the like, solves the problem that the voice intelligent customer service project consumes a large amount of test manpower in the robot training and tuning test stages, and improves the test efficiency.
The test of the voice intelligent customer service robot is divided into an end-to-end test mode and a single-module automatic test mode.
Specifically, a tester can trigger a test instruction for testing the voice intelligent customer service system through the application software operation interface, and can determine the type to be tested in the test instruction, that is, the type of the test instruction can be end-to-end automatic test, can also be single-module automatic test, and can also be end-to-end and single-module automatic test. In addition, the test instruction can comprise a plurality of test tasks of voice intelligent customer service, and the plurality of test tasks can be tested in a concurrent execution mode. That is, one or more tasks of the test item may be provided, and the embodiment may implement simultaneous and parallel execution of a plurality of test item tasks.
The method comprises the following steps that a voice intelligent customer service automatic test system where an application software operation interface is located receives a test instruction of the voice intelligent customer service system; and automatically testing the human-computer interaction flow and/or the functional module of the voice intelligent customer service system according to the test instruction.
More specifically, as an implementation manner, for a scenario where the type of the test instruction is an end-to-end automated test, the step of performing an automated test on the human-computer interaction flow of the voice intelligent customer service system according to the test instruction may include:
and simulating a man-machine interaction scene according to the test instruction, and testing the correctness of the interaction flow by combining the functions of voice recognition, semantic recognition and voice synthesis.
The specific implementation process comprises a voice input stage and a voice result transcription stage, and is specifically implemented as follows:
in the voice input stage, the process of automatically testing the human-computer interaction flow of the voice intelligent customer service system comprises the following steps:
firstly, analyzing a pre-established test case table according to the test instruction to obtain an RF case;
then, based on the RF case, TTS synthesis audio is generated or historical audio is obtained as analog speech input audio of the types including: TTS synthesis standard questions, TTS synthesis extension questions and historical real user audio;
then, according to the simulated voice input audio, simulating a man-machine interaction scene, initiating a voice intelligent customer service system call through SIP, and playing voice;
in the interaction process, the correctness of the man-machine interaction process, the correctness of semantic recognition and the correctness of voice recognition are respectively tested.
Wherein, before playing the voice, the method may further include:
judging whether to simulate the response operation of the user; if yes, inquiring a preset voice table and executing a voice playing step.
Therefore, by the scheme, the voice input stage is realized, and the correctness of the human-computer interaction process, the correctness of semantic recognition and the correctness of voice recognition are tested.
In addition, in the stage of transferring the voice result, the process of automatically testing the human-computer interaction flow of the voice intelligent customer service system comprises the following steps:
firstly, based on the testing process of the voice input stage, obtaining a result sound returned by the voice intelligent customer service system based on a man-machine interaction process;
recording the result sound to obtain recorded voice;
then, when the terminal service node is reached, the recorded voice is identified and transcribed to obtain a voice transcription result;
and comparing the voice transcription result with an expected test result to judge the interaction correctness of the man-machine interaction process of the voice intelligent customer service system.
The following describes in detail the process of implementing end-to-end automated testing according to the embodiment of the present invention with reference to fig. 3:
the end-to-end automatic test is a complete process for simulating man-machine interaction, the actual interaction flow is completely reproduced from incoming call to subsequent hang-up, and the whole process involves the combination of three modules of a voice intelligent customer service system, including speech recognition (ASR), semantic understanding (NLU) and speech synthesis (TTS).
The automatic testing system simulates a scene used by a real customer mainly in a voice input stage and a voice result transfer stage.
The voice input stage uses synthetic audio and historical audio to replace manual speaking, the types of the voice input audio are divided into three categories, namely TTS synthesis standard questions, TTS synthesis extension questions and historical real user audio, and the correctness of a man-machine interaction process, the correctness of semantic recognition and the correctness of voice recognition are respectively tested through the voice input audio.
In the voice result transferring stage, the voice frequency returned by the voice intelligent customer service system is transferred and compared with the expected test result to judge whether the interaction of the system is correct or not.
As shown in fig. 3, the specific process of the end-to-end automated test includes:
firstly, analyzing a test case table, acquiring an RF case, and generating needed TTS synthetic voice;
then, actively initiating an intelligent customer service system call through the SIP, and playing audio;
then, the voice intelligent customer service system returns result voice, records voice and carries out ASR voice transcription;
and finally, checking the result according to the expected test result and outputting the result.
The testing process of the end-to-end automated testing can be executed in parallel by a plurality of testing items.
Further, as another embodiment, for a scenario where the type of the test instruction is a single-module automated test, the step of performing an automated test on the functional module of the voice intelligent customer service system according to the test instruction may include:
according to the test instruction, carrying out module capability test on the voice transcription module of the voice intelligent customer service system, and specifically comprising the following steps:
according to the test instruction, using a pre-labeled voice file and a labeling result, calling an ASR engine used by the voice intelligent customer service system, testing a new intention audio frequency of a current project of the voice transcription module, and outputting to obtain a transcription result;
and checking and comparing the transcription result and the labeling result to obtain a test result of the real-time voice transcription module.
As another implementation, for another scenario in which the type of the test instruction is a single-module automated test, the step of automatically testing the function module of the speech intelligent customer service system according to the test instruction includes:
according to the test instruction, carrying out module capability test on a semantic understanding module of the voice intelligent customer service system, and specifically comprising the following steps:
according to the test instruction, using a pre-labeled real semantic result and an expansion question to call an ASR engine used by the voice intelligent customer service system, testing the new semantics of the current item of the semantic understanding module, and outputting to obtain a current semantic result;
and checking and comparing the current semantic result with the real semantic result to obtain a test result of the semantic understanding module.
More specifically, for the single-module automated testing, the single-module automated testing mainly performs module capability testing on a voice transcription module and a semantic understanding module of the intelligent voice customer service system. Wherein:
the voice transcription module automatically tests and uses pre-marked voice files and marking results, calls and tests an ASR engine used by the voice intelligent customer service, highlights new intention audios of the current project, and checks and compares the transcription results with the marking results.
The semantic understanding module automatically tests and uses a pre-labeled real semantic result and an expanded question, carries out calling test on an ASR engine used by the speech intelligent customer service, highlights new semantics of a test current item, and carries out result verification and comparison on a result output and an expected result.
The end-to-end automatic test and the single-module automatic test of the embodiment form a complete automatic test flow aiming at the voice intelligent customer service system robot.
Further, the automated test system may output the test results.
According to the scheme, the embodiment receives a test instruction of the voice intelligent customer service system; and automatically testing the human-computer interaction flow and/or the functional module of the voice intelligent customer service system according to the test instruction. The scheme aims at the characteristics of the voice intelligent customer service, combines the intelligent voice technology and the customer service flow interaction, simulates the human-computer interaction scene test, solves the problem that the voice intelligent customer service project consumes a large amount of test manpower in the robot training and tuning test stages, and improves the test efficiency; the scheme of the invention can support simultaneous parallel testing of multiple items. Compared with the prior art, the scheme of the embodiment of the invention can quickly and automatically complete the conventional interactive test of the voice customer service scene, thereby greatly improving the efficiency of project test; furthermore, the quick pertinence test can be carried out on the transcription module and the semantic module, so that the applicability of the voice engine in a new project scene is improved; in addition, the testing task of the voice intelligent customer service can be automatically and concurrently executed, the project testing efficiency is greatly improved, the testing labor cost is saved, and the testing quality is improved.
In addition, the embodiment of the invention also provides a voice intelligent customer service automatic test system, which comprises: the system comprises a memory, a processor and a voice intelligent customer service automatic test program which is stored on the memory and can run on the processor, wherein when the voice intelligent customer service automatic test program is executed by the processor, the steps of the voice intelligent customer service automatic test method of the embodiment are realized.
The implementation principle of the voice intelligent customer service automatic test of the invention can refer to the above embodiments, and is not described herein again.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, where a voice intelligent customer service automation test program is stored on the computer-readable storage medium, and when the voice intelligent customer service automation test program is executed by a processor, the steps of the voice intelligent customer service automation test method according to the above embodiment are implemented
The implementation principle of the voice intelligent customer service automatic test of the invention can refer to the above embodiments, and is not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a recommendation effect evaluation system (e.g., a mobile phone, a computer, a server, a controlled terminal, or a network device) to execute the method of each embodiment of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111078981.8A CN113836010A (en) | 2021-09-14 | 2021-09-14 | Voice intelligent customer service automatic testing method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111078981.8A CN113836010A (en) | 2021-09-14 | 2021-09-14 | Voice intelligent customer service automatic testing method, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113836010A true CN113836010A (en) | 2021-12-24 |
Family
ID=78959275
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111078981.8A Pending CN113836010A (en) | 2021-09-14 | 2021-09-14 | Voice intelligent customer service automatic testing method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113836010A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114420092A (en) * | 2022-01-21 | 2022-04-29 | 中国第一汽车股份有限公司 | Voice test method, system, device, electronic equipment and storage medium |
| CN114840422A (en) * | 2022-04-29 | 2022-08-02 | 中国电信股份有限公司 | Test method, test device, electronic equipment and storage medium |
| CN114924951A (en) * | 2022-04-27 | 2022-08-19 | 平安国际智慧城市科技股份有限公司 | Automatic testing method, device, equipment and storage medium for intelligent training |
| CN115237785A (en) * | 2022-07-29 | 2022-10-25 | 平安科技（深圳）有限公司 | Test method, electronic device and storage medium for speech synthesis system |
| CN115473964A (en) * | 2022-09-14 | 2022-12-13 | 北京佳讯飞鸿电气股份有限公司 | Telephone traffic switching simulation method and device, electronic equipment and readable storage medium |
| CN116453655A (en) * | 2022-01-07 | 2023-07-18 | 腾讯科技（深圳）有限公司 | Interactive system testing method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101056216A (en) * | 2006-04-10 | 2007-10-17 | 华为技术有限公司 | A test system and test method |
| CN106228986A (en) * | 2016-07-26 | 2016-12-14 | 北京奇虎科技有限公司 | The automated testing method of a kind of speech recognition engine, device and system |
| CN109360550A (en) * | 2018-12-07 | 2019-02-19 | 上海智臻智能网络科技股份有限公司 | Test method, device, equipment and storage medium for voice interactive system |
| CN109448701A (en) * | 2018-09-19 | 2019-03-08 | 易诚博睿(南京)科技有限公司 | A kind of intelligent sound recognizes the result statistical system and method for semantic understanding |
| CN110010121A (en) * | 2019-03-08 | 2019-07-12 | 平安科技（深圳）有限公司 | Verify method, apparatus, computer equipment and the storage medium of the art that should answer |
| WO2020204256A1 (en) * | 2019-04-04 | 2020-10-08 | 미디어젠 주식회사 | Automatic multimedia speech recognition evaluation system using speech synthesis engine |
| CN113110997A (en) * | 2021-04-23 | 2021-07-13 | 中国工商银行股份有限公司 | Test method, device and equipment |
-
2021
- 2021-09-14 CN CN202111078981.8A patent/CN113836010A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101056216A (en) * | 2006-04-10 | 2007-10-17 | 华为技术有限公司 | A test system and test method |
| CN106228986A (en) * | 2016-07-26 | 2016-12-14 | 北京奇虎科技有限公司 | The automated testing method of a kind of speech recognition engine, device and system |
| CN109448701A (en) * | 2018-09-19 | 2019-03-08 | 易诚博睿(南京)科技有限公司 | A kind of intelligent sound recognizes the result statistical system and method for semantic understanding |
| CN109360550A (en) * | 2018-12-07 | 2019-02-19 | 上海智臻智能网络科技股份有限公司 | Test method, device, equipment and storage medium for voice interactive system |
| CN110010121A (en) * | 2019-03-08 | 2019-07-12 | 平安科技（深圳）有限公司 | Verify method, apparatus, computer equipment and the storage medium of the art that should answer |
| WO2020204256A1 (en) * | 2019-04-04 | 2020-10-08 | 미디어젠 주식회사 | Automatic multimedia speech recognition evaluation system using speech synthesis engine |
| CN113110997A (en) * | 2021-04-23 | 2021-07-13 | 中国工商银行股份有限公司 | Test method, device and equipment |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116453655A (en) * | 2022-01-07 | 2023-07-18 | 腾讯科技（深圳）有限公司 | Interactive system testing method and device, electronic equipment and storage medium |
| CN114420092A (en) * | 2022-01-21 | 2022-04-29 | 中国第一汽车股份有限公司 | Voice test method, system, device, electronic equipment and storage medium |
| CN114924951A (en) * | 2022-04-27 | 2022-08-19 | 平安国际智慧城市科技股份有限公司 | Automatic testing method, device, equipment and storage medium for intelligent training |
| CN114840422A (en) * | 2022-04-29 | 2022-08-02 | 中国电信股份有限公司 | Test method, test device, electronic equipment and storage medium |
| CN114840422B (en) * | 2022-04-29 | 2025-04-18 | 中国电信股份有限公司 | Test method, device, electronic device and storage medium |
| CN115237785A (en) * | 2022-07-29 | 2022-10-25 | 平安科技（深圳）有限公司 | Test method, electronic device and storage medium for speech synthesis system |
| CN115237785B (en) * | 2022-07-29 | 2025-05-30 | 平安科技（深圳）有限公司 | Test method, electronic device and storage medium of speech synthesis system |
| CN115473964A (en) * | 2022-09-14 | 2022-12-13 | 北京佳讯飞鸿电气股份有限公司 | Telephone traffic switching simulation method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12412050B2 (en) | Multi-platform voice analysis and translation | |
| JP5124573B2 (en) | Detect answering machine using voice recognition | |
| US7995732B2 (en) | Managing audio in a multi-source audio environment | |
| US8798255B2 (en) | Methods and apparatus for deep interaction analysis | |
| US20110099011A1 (en) | Detecting And Communicating Biometrics Of Recorded Voice During Transcription Process | |
| CN106228986A (en) | The automated testing method of a kind of speech recognition engine, device and system | |
| CN110265032A (en) | Conferencing data analysis and processing method, device, computer equipment and storage medium | |
| WO2005046195A1 (en) | Apparatus and method for event-driven content analysis | |
| CN109360550A (en) | Test method, device, equipment and storage medium for voice interactive system | |
| CN107465816A (en) | A kind of call terminal and method of instant original voice translation of conversing | |
| CN107886951B (en) | Voice detection method, device and equipment | |
| CN110738981A (en) | interaction method based on intelligent voice call answering | |
| CN111445906A (en) | Big data-based voice generation method, device, equipment and medium | |
| Ramanarayanan et al. | Bootstrapping Development of a Cloud‐Based Spoken Dialog System in the Educational Domain From Scratch Using Crowdsourced Data | |
| CN119150814A (en) | Conference summary generation method, device, terminal and computer readable storage medium | |
| US7787598B2 (en) | Method and system for automatic generation and testing of voice applications | |
| US20250022471A1 (en) | Conference content display method, conference system and conference device | |
| CN112532794B (en) | Voice outbound method, system, equipment and storage medium | |
| KR102610360B1 (en) | Method for providing labeling for spoken voices, and apparatus implementing the same method | |
| US8478588B2 (en) | Run-time simulation environment for voiceXML applications that simulates and automates user interaction | |
| CN115579024A (en) | Speech quality inspection method, device, electronic equipment and storage medium | |
| CN115602172A (en) | Intelligent outbound method and system | |
| CN116156057A (en) | Call practice method, device, electronic equipment and storage medium | |
| CN115440188A (en) | Splicing method and device for audio data, electronic equipment and storage medium | |
| CN114664305B (en) | Information push method, device, storage medium and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211224 |
|
| WD01 | Invention patent application deemed withdrawn after publication |