CN113628611A - Voice service test system, method, device and equipment - Google Patents
Voice service test system, method, device and equipment Download PDFInfo
- Publication number
- CN113628611A CN113628611A CN202010378808.9A CN202010378808A CN113628611A CN 113628611 A CN113628611 A CN 113628611A CN 202010378808 A CN202010378808 A CN 202010378808A CN 113628611 A CN113628611 A CN 113628611A
- Authority
- CN
- China
- Prior art keywords
- voice service
- voice
- tested
- sound box
- user
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 346
- 238000000034 method Methods 0.000 title claims abstract description 93
- 238000012545 processing Methods 0.000 claims abstract description 98
- 230000004044 response Effects 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 14
- 238000010998 test method Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 description 12
- 241000592183 Eidolon Species 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000012550 audit Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000001795 light effect Effects 0.000 description 3
- 230000036541 health Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003238 somatosensory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/01—Assessment or evaluation of speech recognition systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/50—Testing arrangements
Abstract
The application discloses a voice service test system, a method, a device and equipment. The system collects user voice data through an intelligent sound box, sends a voice service request aiming at the user voice data to a server and displays a voice service processing result returned by the server; the server side determines a user identification or an intelligent sound box identification and a corresponding relation set between the user identification or the intelligent sound box identification and the voice service to be tested, and loads the voice service to be tested and the published voice service; acquiring voice service information to be tested corresponding to the intelligent sound box according to the user identification information or the intelligent sound box identification information carried by the request; and if the voice service to be tested corresponding to the intelligent sound box comprises the voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested. By adopting the processing mode, the sound box equipment is used for carrying out real machine test on the voice service; therefore, the test accuracy can be effectively improved, and the test efficiency is improved.
Description
Technical Field
The application relates to the technical field of voice service testing of intelligent sound boxes, in particular to a voice service testing system, method and device, an intelligent sound box and electronic equipment.
Background
The intelligent sound box is a product of sound box upgrading, is a tool for household consumers to surf the internet by voice, such as song ordering, internet shopping or weather forecast knowing, and can also control intelligent household equipment, such as opening a curtain, setting the temperature of a refrigerator, heating a water heater in advance and the like.
The smart sound box can provide various voice services, namely, possess various voice skills. The voice skill refers to a function or service provided through voice, for example, "view weather" is a voice skill, and "listen to music" is also a skill. Voice services are typically developed by third party intelligent voice service vendors. Before a newly developed voice service is formally used, the voice service typically needs to be tested to ensure that the service is functioning properly in a predetermined manner. Currently, a typical voice service testing method is a non-real machine testing scheme, and a developer tests a voice service through a voice service development platform, which provides a voice service testing function based on a web page or a client simulation program. Specifically, a non-genuine testing scheme may be used in which a text command is a mandatory INPUT, and the scheme allows a tester to INPUT a dialog text into a testing device, and then the testing device feeds back an execution result to a user. In addition, the non-real machine testing scheme with audio information as the requisite INPUT is also available, and the scheme allows a tester to INPUT real audio information into the testing equipment, and the testing equipment feeds back the execution result to the user.
However, in the process of implementing the invention, the inventor finds that the technical scheme has at least the following problems: because the non-real machine test scheme only simulates a part of a real execution link and cannot simulate the effect of the real online integration of the voice service to the intelligent voice loudspeaker, only partial insufficient points and loophole points of the voice service can be exposed, and the effect of a preposed link before the voice service is accessed, such as time-consuming body feeling from the time when a user sends an instruction to the loudspeaker to the time when the loudspeaker feeds back the voice service, such as service execution feedback results, and the like, cannot be exposed. In addition, the test efficiency of the existing test scheme is low. In summary, how to improve the testing accuracy and the testing efficiency of the voice service so as to meet the testing requirements of the voice service developer and the auditing requirements of the voice service auditors of the voice service platform of the intelligent sound box becomes a technical problem which needs to be solved urgently by technical personnel in the field.
Disclosure of Invention
The application provides a voice service test system to solve the problem that the test accuracy and the test efficiency are lower in the prior art. The application additionally provides a voice service testing method and device, an intelligent sound box and electronic equipment.
The application provides a voice service test system, includes:
the intelligent sound box is used for acquiring user voice data and sending a voice service request aiming at the user voice data to a server; and displaying a voice service processing result returned by the server;
the server is used for determining a user identifier or an intelligent sound box identifier and a corresponding relation set between the user identifier or the intelligent sound box identifier and the voice service to be tested, and loading the voice service to be tested and the published voice service; acquiring to-be-tested voice service information corresponding to the intelligent sound box according to the user identification information or the intelligent sound box identification information carried by the request; and if the voice service to be tested corresponding to the intelligent sound box comprises the voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested, and sending a voice service processing result to the intelligent sound box.
The application also provides a voice service testing method, which comprises the following steps:
determining a user identifier or an intelligent sound box identifier and a corresponding relation set between the user identifier or the intelligent sound box identifier and the voice service to be tested, and loading the voice service to be tested and the published voice service;
acquiring voice service information to be tested corresponding to the intelligent sound box according to user identification information or intelligent sound box identification information carried by a voice service request aiming at user voice data sent by the intelligent sound box;
and if the voice service to be tested corresponding to the intelligent sound box comprises the voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested, and sending a voice service processing result to the intelligent sound box so that the intelligent sound box displays the voice service processing result.
Optionally, the method further includes:
receiving a voice service binding request to be tested, which is sent by a client and aims at a target user or a target intelligent sound box;
and storing the target user identification, the intelligent sound box identification corresponding to the target user, or the corresponding relation between the target intelligent sound box identification and the voice service to be tested.
Optionally, the voice service to be tested includes: an updated version of the published voice service;
if the voice service to be tested corresponding to the intelligent sound box comprises an updated version of the published voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested of the updated version;
and if the voice service to be tested corresponding to the intelligent sound box does not comprise the updated version of the published voice service corresponding to the user voice data, processing the user voice data through the published voice service.
Optionally, the method further includes:
using the voice service to be tested and the published voice service corresponding to the intelligent sound box as voice service decision objects of a conversation understanding and voice service decision model;
determining a text sequence corresponding to the user voice data through a voice recognition model;
and determining the voice service to be tested or the published voice service corresponding to the user voice data according to the text sequence through the decision model.
Optionally, the user includes: a voice service developer user;
the user voice data includes: voice data for detecting the validity of the service function.
Optionally, the user includes: a voice service of the intelligent sound box service platform is on-line for auditing a user;
the user voice data includes: voice data for detecting corpus conflicts, voice data for detecting voice recognition capabilities.
Optionally, the method further includes:
and sending real machine test result data to the client.
The application also provides a voice service testing method, which comprises the following steps:
collecting user voice data; the user voice data comprises test voice data aiming at the voice service to be tested;
sending a voice service request aiming at the user voice data to a server so that the server determines the voice service to be tested according to user identification information or intelligent sound box identification information carried by the request, and processing the test voice data through the voice service to be tested;
and displaying the voice service processing result returned by the server.
Optionally, the displaying of the voice service processing result returned by the server includes at least one of the following manners:
playing the reply voice data determined by the voice service;
adjusting the volume of the sound box according to the volume of the sound box determined by the voice service;
and adjusting the working mode of the Internet of things equipment according to the working mode of the Internet of things equipment controlled by the intelligent sound box determined through the voice service.
Optionally, the method further includes:
testing voice services through a real machine, and determining the voice services to be tested;
the collecting of the user voice data comprises the following steps:
playing the test voice data of the voice service to be tested;
and collecting the played test voice data.
Optionally, the playing the test voice data of the voice service to be tested includes:
determining the playing time interval of the test voice of various operations of the voice service to be tested;
and playing the test voice data of various operations of the voice service to be tested according to the playing time interval.
Optionally, the method further includes:
testing the voice service through the real machine, and suspending testing the voice service to be tested;
recording the test voice at the pause moment;
and testing the voice service through the real machine, and continuously testing the voice service to be tested according to the testing voice at the pause moment.
Optionally, the method further includes:
testing voice service through the real machine, and collecting test voice data of the voice service to be tested;
and storing the test voice data of the voice service to be tested.
Determining the testing time of an automatic real machine of the voice service to be tested;
generating a test task according to the test time;
and executing a test task according to the test time.
Optionally, the method further includes:
and if the automatic testing condition of the voice service to be tested is established, performing real machine testing on the voice service to be tested.
Optionally, the method further includes:
determining actual test response information;
and if the actual test response information is different from the predicted test response information, displaying prompt information of operation execution errors.
Optionally, the method further includes:
recording error operation;
and automatically testing the error operation.
The application also provides a voice service testing method, which comprises the following steps:
and sending a voice service binding request to be tested aiming at the target user or the target intelligent sound box to the server so that the server can store the target user identification, the intelligent sound box identification corresponding to the target user or the corresponding relation between the target intelligent sound box identification and the voice service to be tested.
Optionally, the method further includes:
and receiving real machine test result data of the voice service to be tested, which is sent by the server.
Alternatively to this, the first and second parts may,
the real machine test result data comprises: the time length from the test voice sending to the sound box feedback result.
The present application further provides a voice service testing apparatus, including:
the voice service binding and loading unit to be tested is used for determining a user identifier or an intelligent sound box identifier and a corresponding relation set between the voice service to be tested and the voice service to be tested, and loading the voice service to be tested and the published voice service;
the voice service determining unit to be tested is used for acquiring voice service information to be tested corresponding to the intelligent sound box according to user identification information or intelligent sound box identification information carried by a voice service request aiming at user voice data sent by the intelligent sound box;
and the voice service execution unit to be tested is used for processing the user voice data through the voice service to be tested and sending a voice service processing result to the intelligent sound box if the voice service to be tested corresponding to the intelligent sound box comprises the voice service corresponding to the user voice data, so that the intelligent sound box displays the voice service processing result.
The present application further provides an electronic device, comprising:
a processor; and
a memory for storing a program for implementing the voice service test method, the device performing the following steps after being powered on and running the program of the method through the processor: determining a user identifier or an intelligent sound box identifier and a corresponding relation set between the user identifier or the intelligent sound box identifier and the voice service to be tested, and loading the voice service to be tested and the published voice service; acquiring voice service information to be tested corresponding to the intelligent sound box according to user identification information or intelligent sound box identification information carried by a voice service request aiming at user voice data sent by the intelligent sound box; and if the voice service to be tested corresponding to the intelligent sound box comprises the voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested, and sending a voice service processing result to the intelligent sound box so that the intelligent sound box displays the voice service processing result.
The present application further provides a voice service testing apparatus, including:
the voice acquisition unit is used for acquiring user voice data; the user voice data comprises test voice data aiming at the voice service to be tested;
a request sending unit, configured to send a voice service request for the user voice data to a server, so that the server determines the voice service to be tested according to user identification information or intelligent sound box identification information carried in the request, and processes the test voice data through the voice service to be tested;
and the result display unit is used for displaying the voice service processing result returned by the server.
The application further provides an intelligent sound box, include:
a processor; and
a memory for storing a program for implementing the voice service test method, the device performing the following steps after being powered on and running the program of the method through the processor: collecting user voice data; the user voice data comprises test voice data aiming at the voice service to be tested; sending a voice service request aiming at the user voice data to a server so that the server determines the voice service to be tested according to user identification information or intelligent sound box identification information carried by the request, and processing the test voice data through the voice service to be tested; and displaying the voice service processing result returned by the server.
The present application further provides a voice service testing apparatus, including:
and the request sending unit is used for sending a voice service binding request to be tested aiming at the target user or the target intelligent sound box to the server so as to facilitate the server to store the target user identification, the intelligent sound box identification corresponding to the target user or the corresponding relationship between the target intelligent sound box identification and the voice service to be tested.
The present application further provides an electronic device, comprising:
a processor; and
a memory for storing a program for implementing the voice service test method, the device performing the following steps after being powered on and running the program of the method through the processor: and sending a voice service binding request to be tested aiming at the target user or the target intelligent sound box to the server so that the server can store the target user identification, the intelligent sound box identification corresponding to the target user or the corresponding relation between the target intelligent sound box identification and the voice service to be tested.
The application also provides a method for generating the voice service test case, which comprises the following steps:
collecting test voice data of various operations of a voice service to be tested;
determining the playing time interval and the playing sequence of various operation test voices;
and generating a test case of the voice service to be tested according to the time interval and the playing sequence.
The present application also provides a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to perform the various methods described above.
The present application also provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the various methods described above.
Compared with the prior art, the method has the following advantages:
according to the voice service test system provided by the embodiment of the application, the voice data of a user is collected through the intelligent sound box, and a voice service request aiming at the voice data of the user is sent to the server; and displaying a voice service processing result returned by the server; the server side determines a user identification or an intelligent sound box identification and a corresponding relation set between the user identification or the intelligent sound box identification and the voice service to be tested, and loads the voice service to be tested and the published voice service; acquiring to-be-tested voice service information corresponding to the intelligent sound box according to the user identification information or the intelligent sound box identification information carried by the request; if the voice service to be tested corresponding to the intelligent sound box comprises the voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested, and sending a voice service processing result to the intelligent sound box; the processing mode allows a tester to initiate a test request from the sound box end and reuse the processing link of the normal request, namely, sound box equipment is used for carrying out real machine test on the voice service, the effect that the voice service is really integrated on the intelligent voice sound box on line is simulated, the problem that the test result is not real due to the fact that the end or part of the cloud end link is lost in the existing scheme is avoided, and therefore various problems of the voice service can be quickly found and modified; therefore, the test accuracy can be effectively improved, and the test efficiency is improved, so that the test requirements of a voice service developer and the audit requirements of voice service auditors of the intelligent sound box voice service platform are met.
Drawings
FIG. 1 is a schematic diagram of a voice service test system according to an embodiment of the present application;
FIG. 2 is a schematic diagram of an application scenario of an embodiment of a voice service testing system provided in the present application;
FIG. 3 is a schematic diagram of an interaction of devices in an embodiment of a voice service testing system provided by the present application;
FIG. 4 is a process flow diagram of an embodiment of a voice service test system provided herein;
fig. 5 is a schematic diagram illustrating a specific device interaction of an embodiment of a voice service testing system provided in the present application.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit of this application and is therefore not limited to the specific implementations disclosed below.
In the application, a voice service test system, a voice service test method and a voice service test device, a smart sound box and electronic equipment are provided. Each of the schemes is described in detail in the following examples.
First embodiment
Please refer to fig. 1, which is a block diagram of an embodiment of a voice service testing system according to the present application. The system comprises: the server side 1 and the intelligent sound box 2.
The server 1 may be a server deployed on a cloud server, or may be a server dedicated to implementing a voice service of an intelligent speaker, and may be deployed in a data center. The server may be a cluster server or a single server.
The smart speaker 2 may be a tool for a household consumer to surf the internet by voice, such as ordering songs, shopping online, or knowing weather forecast, and may also control smart home devices, such as opening curtains, setting the temperature of a refrigerator, raising the temperature of a water heater in advance, and the like.
Please refer to fig. 2, which is a schematic view illustrating a scenario of the voice service testing system of the present application. The server and the intelligent sound box can be connected through a network, for example, the intelligent sound box can be networked through a WIF I mode and the like, and the like. A developer user of the sound box voice service can deploy the developed voice service to be tested to a service end, and the service end can determine a user identifier or an intelligent sound box identifier and a corresponding relation set between the user identifier or the intelligent sound box identifier and the voice service to be tested; then, the developer user can carry out real machine test on the voice service to be tested through the intelligent sound box, specifically, a voice instruction related to the voice service to be tested is sent to the sound box, the instruction is locally processed by the sound box and then is transmitted to a network, and finally cloud processing is achieved; the server processes the instruction through a processing link when the service is actually online and put into use, and returns a processing result to the intelligent sound box, the sound box feeds the result back to the user, and the feedback result can comprise audio broadcasting, light effect, volume adjustment, household I OT equipment change triggering through a local communication protocol and other changes of a series of clients. By adopting the processing mode, the whole testing process is the same as the using process and the processing link of the normally published voice service, and the performance of the voice service to be tested under the real link is simulated as much as possible, so that a developer user can perceive the whole process from the voice instruction sending to the feedback given by the sound box. The developer user can find various problems possibly existing in each link of the whole processing process of the voice service to be tested through the real machine testing mode, and then can modify the service program.
Please refer to fig. 3, which is a schematic diagram of an apparatus interaction of an embodiment of the voice service system for smart speakers according to the present application. In this embodiment, the smart sound box collects user voice data and sends a voice service request for the user voice data to a server; and displaying a voice service processing result returned by the server; the server side determines a user identification or an intelligent sound box identification and a corresponding relation set between the user identification or the intelligent sound box identification and the voice service to be tested, and loads the voice service to be tested and the published voice service; acquiring to-be-tested voice service information corresponding to the intelligent sound box according to the user identification information or the intelligent sound box identification information carried by the request; and if the voice service to be tested corresponding to the intelligent sound box comprises the voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested, and sending a voice service processing result to the intelligent sound box.
The voice services, also known as speaker skills, include voice services provided to the user through a smart speaker. The voice services, including but not limited to: morning goodness, weather check, health check, shopping, etc.
The server records the user identification or the intelligent sound box identification and the corresponding relation set between the voice service to be tested. Table 1 shows a corresponding relationship set of the service-side record in this embodiment.
TABLE 1 set of correspondences
As can be seen from table 1, the voice service to be tested may be bound to a specific user, and may also be bound to a specific speaker device. One smart speaker may correspond to one or more voice services to be tested.
The server also needs to load the voice service to be tested and the published voice service. It should be noted that, in the prior art, the server only loads the published voice service, and the decision model can only decide the published voice service corresponding to the user voice data, but cannot decide the voice service to be tested. The system provided by the embodiment of the application not only loads the issued voice service through the server, but also loads the voice service to be tested. Loading a voice service to be tested and a published voice service to enable the voice service to be tested and the published voice service to become voice service decision objects of a conversation understanding and voice service decision model; and determining the voice service to be tested or the published voice service corresponding to the user voice data according to the text sequence corresponding to the user voice data through the decision model. By adopting the processing mode, a tester is allowed to initiate a test request from the sound box end, a processing link aiming at a normal request of the voice service to be tested is multiplexed, namely, sound box equipment is used for carrying out real machine test on the voice service, and the effect that the voice service is truly integrated on the intelligent voice sound box on line is simulated. Since the dialogue understanding and voice service decision model belongs to the mature prior art, the description is omitted here.
The request at least comprises user voice data, and can also comprise a user identification or a sound box device identification. And the server side can inquire the voice service information to be tested corresponding to the intelligent sound box sending the request from the table 1 according to the user identification information or the intelligent sound box identification information carried by the request.
In addition, the server can record published voice service information. Table 2 shows the published voice service information recorded by the service end in this embodiment.
| Voice service identification | Name of |
| 1 | |
| 2 | |
| 3 | Weather checking |
| 4 | Shopping |
| … |
Table 2 published voice service information table
As can be seen from table 2, the published voice service is not bound to a specific user or a speaker device, and can be used by any user.
In one example, the user includes: the system can meet the skill self-testing requirement of a skill developer. In this case, the user voice data includes, but is not limited to: voice data for detecting the validity of the service function. For example, a developer user may prepare test cases for testing whether a service can run correctly in a predetermined manner.
In another example, the user includes: a voice service on-line auditing user of the intelligent sound box service platform is responsible for testing whether the voice service to be issued on-line is audited to meet platform specifications. Points which are detected by the auditing mode provided by the existing platform and do not accord with the platform specification are not comprehensive enough, and the system provided by the embodiment of the application can meet the skill auditing requirement of platform skill auditors. The user voice data includes, but is not limited to: voice data for detecting corpus conflicts, voice data for detecting voice recognition capabilities. Under the condition, the tester is a platform auditor which is responsible for auditing the voice service before the voice service is released online to the intelligent sound box voice service platform, and the platform auditor can also utilize the system to test and audit whether the voice service to be online meets the platform specification in a real machine testing mode.
For example, the platform auditor sends some voice contents close to the starting words of other issued voice services to the sound box, and detects whether the text corpora of the voice service to be on-line conflicts with the starting words of other issued voice services, and whether the normal starting of other issued voice services is affected. For another example, the platform auditor sends some voice contents specific to the voice service to be on-line to the loudspeaker box, and detects whether the voice contents can be correctly recognized by a voice recognition model (ASR) of the platform.
In specific implementation, the server can be further used for using the voice service to be tested and the published voice service corresponding to the intelligent sound box as a voice service decision object of a conversation understanding and voice service decision model; determining a text sequence corresponding to the user voice data through a voice recognition model; and determining the voice service to be tested or the published voice service corresponding to the user voice data according to the text sequence through the decision model.
The speech recognition is a technology for converting a speech signal into a corresponding text or command through a recognition and understanding process by a machine, and mainly comprises three aspects of a feature extraction technology, a pattern matching criterion and a model training technology. The system provided by the embodiment of the application refers to a module for realizing the voice recognition technology as a voice recognition model. Since the speech recognition model belongs to the mature prior art, it is not described in detail here.
The voice service to be tested can be newly published voice service or updated version of the published voice service. The system supports real machine testing before new voice service is integrated into a formal effective voice service range on line, and also supports real machine testing in an effective voice service updating iteration process.
In one example, the voice service to be tested is an updated version of a published voice service; correspondingly, if the voice service to be tested corresponding to the intelligent sound box comprises an updated version of the published voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested of the updated version; and if the voice service to be tested corresponding to the intelligent sound box does not comprise the updated version of the published voice service corresponding to the user voice data, processing the user voice data through the published voice service. By adopting the processing mode, a tester can test the functions of the new version and provide voice service for the ordinary users through the released version.
In particular, the system may further include a user identity information table, as shown in table 3.
| User identification | |
| User | |
| 1 | Voice |
| User | |
| 2 | Auditor of voice |
| User | |
| 3 | Voice service developer |
| … |
TABLE 3 subscriber identity information Table
Through the user identity information shown in table 3, it is possible to determine that the genuine machine test result data of different indexes are displayed to users with different identities. For example, the duration from the test voice sending to the sound box feedback result is displayed for the developer, and the platform auditor is displayed which platform specifications are violated by the voice service to be tested.
After the client receives the voice service processing result returned by the server, the processing result can be displayed in at least one of the following ways: playing the reply voice data determined by the voice service; adjusting the volume of the sound box according to the volume of the sound box determined by the voice service; according to the work mode of the Internet of things equipment controlled by the intelligent sound box determined through the voice service, the work mode of the Internet of things equipment is adjusted, and in addition, the processing result can be displayed in other modes, such as a light effect and the like.
In this embodiment, a processing flow of the live testing at the cloud (server) is shown in fig. 4, and includes the following steps:
and S1, processing the user audio data reaching the cloud end by ASR to obtain a recognized text result and other audio characteristics.
And S2, according to the user id/equipment id carried by the current request, inquiring and pulling the voice service list set by the user/the equipment and to be debugged by the real machine. The binding policy for the standby test voice service and the requesting device may be two types:
1) a voice service developer serves as a tester, the tester starts a real machine testing function of developing the voice service through a voice service construction platform, and the voice service to be tested is bound with all the loudspeaker box devices bound with the tester account number in a default mode.
2) And the platform auditor is used as a tester, and all skills to be audited are bound with the specified loudspeaker box equipment bound with the account number of the tester.
A tester can bind the specified equipment and the specified skill to be tested through the platform page, and the method can be used for self-testing of a skill developer and can also be used for a platform-side skill auditor.
And S3, pulling the skill list integrated by the current loudspeaker box.
And S4, taking the results obtained in S1, S2 and S3 as the input of the dialogue understanding and skill decision module, and outputting the dialogue understanding result and hit skill:
1) when the real machine test skill list is empty, the current request is the same as the normal request.
2) And if the real machine test list is not empty, combining the real machine test list and the normal skill list to be used as the effective skill range of the request, and executing the dialogue understanding and skill decision in the skill range.
3) If the skill to be tested is a skill that has been released and integrated into the loudspeaker, the test objective is to test the effect of the skill function update iteration. The dialog understanding and skill decision module loads the on-line validated version of the skill and the version to be tested in the current iteration. When a normal request arrives, the on-line validated version is validated, and when a real machine test request arrives and the skill is contained in the test list, the version in the iteration is validated.
And S5, routing to the corresponding skill execution according to the hit skill result in the S4.
And S6, according to a series of contexts, the skill corresponds to the understanding result and the execution result generated in the S4, and the result is finally returned to the sound box equipment at the end.
By adopting the processing manner shown in fig. 4, a real execution link of the voice service to be tested is simulated, and the test effect may include: 1) entering a preposed link effect before skill, such as the effect that audio data obtained in the real sound box sound receiving process is influenced by the sound box cavity condition and various sound receiving equipment, and further such as the effect that user voice is converted into text through ASR; 2) a user sends an instruction to the sound box, and time consuming somatosensory is given to feedback by the sound box; 3) and (5) feedback results are executed by skills, wherein the feedback results comprise the effects of sound box broadcasting, light effect and the like.
As shown in fig. 5, in an example, the system may further include a client, through which a developer user of the speaker voice service may set a voice service to be tested bound to its user account or the speaker device; correspondingly, the server stores the target user identification, the intelligent sound box identification corresponding to the target user, or the corresponding relation between the target intelligent sound box identification and the voice service to be tested. For example, a developer user binds the user account with a voice service to be tested, so that the voice service to be tested can be subjected to real-machine test processing through all the intelligent sound boxes bound with the user.
The client, including but not limited to mobile communication device, is: the mobile phone or the smart phone also includes terminal devices such as a personal computer, a PAD, and an iPad.
In addition, the server can also be used for sending real machine test result data to the client, such as the time length from the test voice sending to the sound box feedback result; correspondingly, the developer user can also check the real machine test result data through the client.
In one example, the smart sound box may be further configured to determine a voice service to be tested through a live testing voice service; and can be used for broadcasting the test voice data of the voice service to be tested specifically; and collecting the played test voice data.
The intelligent sound box can be loaded with real machine testing voice service, and the service is the same as other voice services and is also a skill of the sound box. The user can manage a plurality of voice services to be tested which are authorized to be tested through the voice service for testing the real machine, such as starting the automatic voice service test for the voice service to be tested, collecting and storing the test voice data of the voice service to be tested, managing a test case of the real machine and the execution mode thereof, and the like.
For example, a user says in the speaker: "the tianmao eidolon, i want to test the skill of the sound box", the tianmao eidolon responds to the order, enter the real machine and test the voice service automatically, and can show the voice service to be tested that the user has the right to test through the display screen; the user accessible area screen audio amplifier selects the target voice service from a plurality of voice services that await measuring, then assigns the voice command to the audio amplifier: the sound box can automatically play test voice data aiming at various operations according to the test case of the tested service, and simultaneously collect the test voice data played by the sound box through the microphone.
A test case for a voice service may include: the voice data to be tested of various operations, if the voice service to be tested is 'song request', the user instruction may include: 1) the song requesting operation, the corresponding test voice can be 'I want to listen to the legend of Wangfenfei'; 2) the singer changing operation, the corresponding test voice can be 'changing singers'; 3) and (3) clicking the ranking list operation, wherein the corresponding test voice can be 'i want to listen to the song on the ranking list', and the like.
In specific implementation, the smart sound box may be specifically configured to determine a playing time interval of a test voice of various operations of the voice service to be tested; and playing the test voice data of various instructions included in the test case of the voice service to be tested according to the playing time interval.
In specific implementation, a user may set, in a voice manner, a playing time interval of test voice data of various operations, a playing sequence of the test voice data of various operations, and the like through a sound box, for example, "randomly playing test voices of various operations, playing every 30 seconds between the test voices of each operation" may be set, and "playing the test voices of various operations according to a sequence of various operations in a test case" may also be set.
In specific implementation, the response time of each operation may be determined first, and a fixed time duration (e.g., 10 seconds) is added to the response time, so as to play the test voice data of each operation at such time intervals; the processing mode can avoid that the test voice of the next instruction is played when the previous instruction does not respond, so that the real machine test effect of the previous instruction cannot be sensed; therefore, the test effectiveness can be effectively improved.
According to the system provided by the embodiment of the application, the intelligent sound box determines the voice service to be tested through the real-machine testing voice service, automatically plays the testing voice data of the voice service to be tested, collects the played testing voice data and realizes the automatic testing of sound playing and recording; the processing mode can automatically play the test voice, the test voice can be repeatedly used, and a test user does not need to send the test voice by himself; therefore, the testing efficiency can be effectively improved, and the testing precision is improved.
In one example, the smart sound box can be further used for testing the voice service through the real phone, pausing the testing of the voice service to be tested, and recording the testing voice at the pause moment; and testing the voice service through the real machine, and continuing to test the voice service to be tested according to the testing voice at the pause moment.
For example, a user says in the speaker: the Tianmao demon pauses the test of the voice service, responds to the instruction, automatically enters a state waiting for continuous test, records a test case execution point at the pause time, and can continuously play subsequent test voice in the test case from the execution point after subsequently receiving the continuous test voice initiated by the user. By adopting the processing mode, the automatic real-machine test can be interrupted at any time through the real-machine test voice service, and the real-machine test can be continuously executed subsequently; therefore, the flexibility of the automatic real machine test can be effectively improved, and the user experience is improved.
In one example, the smart sound box may be further configured to collect test voice data of the voice service to be tested through the live testing voice service; and storing the test voice data of the voice service to be tested.
For example, a user says in the speaker: "the tianmao eidolon, i want to test a certain voice service", the tianmao eidolon responds to the order, enter the real machine and test the voice service automatically, and can show the multiple voice services to be tested that the user has the right to test through the display screen; the user accessible area screen audio amplifier selects the target voice service from a plurality of voice services that await measuring, then assigns the voice command to the audio amplifier: the sound box identifies the instruction through processing of voice identification, semantic understanding and the like, responds to the instruction to open the microphone and play a prompt sound to start recording, collects the test voice initiated by the user through the microphone and stores the test voice data so as to be used for subsequent automatic playing.
During specific implementation, the intelligent sound box can also determine the test time of the automatic real machine of the voice service to be tested, and generates a test task according to the test time; and executing a test task according to the test time.
For example, when the temperature of certain weather is very high, the tester predicts that a large number of users from 20 to 22 can open the air conditioner through the intelligent sound box, adjusts the working mode of the air conditioner, and then gives an instruction by the voice of the tester: 20: and (3) testing air conditioner control service, recognizing the instruction by the intelligent sound box, generating a corresponding test task, and reaching the following steps of 20: and the intelligent sound box automatically executes the test task at 30 hours.
During specific implementation, the intelligent sound box can be further used for executing a test case of the voice service to be tested and starting an automatic real machine test if the automatic test condition of the voice service to be tested is established. For example, the temperature may be determined by a temperature sensor; if the temperature is larger than the temperature threshold value, the test condition is established, the test case of the voice service to be tested is executed, and the automatic real machine test is started.
During specific implementation, the intelligent sound box can also be used for determining actual test response information, and if the actual test response information is different from the predicted test response information, prompt information of operation execution errors is displayed. For example, if the test voice is "bedroom light" turned on and "living room light" is actually turned on, a prompt message indicating that the operation is performed incorrectly is automatically generated. By adopting the processing mode, whether the operation is correct or not can be automatically determined, and incorrect prompt information can be given; therefore, the user experience can be effectively improved.
In addition, the intelligent sound box can also record incorrect operation, and subsequently, the incorrect operation can be specially tested automatically. By adopting the processing mode, the testing efficiency can be effectively improved.
During specific implementation, the intelligent sound box can acquire environment change information through a camera, a temperature sensor and other devices, and test response information is determined according to the environment change information. For example, if the test voice is "adjust the air conditioner to 22 degrees", and the indoor temperature is reduced to 22 degrees after the operation is performed, which is collected by the temperature sensor, the actual test response information is 22 degrees, and the expected response information is also 22 degrees, which indicates that the operation is correct.
As can be seen from the above embodiments, the voice service test system provided in the embodiments of the present application collects user voice data through the smart sound box, and sends a voice service request for the user voice data to the server; and displaying a voice service processing result returned by the server; the server side determines a user identification or an intelligent sound box identification and a corresponding relation set between the user identification or the intelligent sound box identification and the voice service to be tested, and loads the voice service to be tested and the published voice service; acquiring to-be-tested voice service information corresponding to the intelligent sound box according to the user identification information or the intelligent sound box identification information carried by the request; if the voice service to be tested corresponding to the intelligent sound box comprises the voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested, and sending a voice service processing result to the intelligent sound box; the processing mode allows a tester to initiate a test request from the sound box end and reuse the processing link of the normal request, namely, sound box equipment is used for carrying out real machine test on the voice service, the effect that the voice service is really integrated on the intelligent voice sound box on line is simulated, the problem that the test result is not real due to the fact that the end or part of the cloud end link is lost in the existing scheme is avoided, and therefore various problems of the voice service can be quickly found and modified; therefore, the test accuracy can be effectively improved, and the test efficiency is improved, so that the test requirements of a voice service developer and the audit requirements of voice service auditors of the intelligent sound box voice service platform are met.
Second embodiment
Corresponding to the voice service testing system, the application also provides a voice service testing method, and an execution main body of the method comprises but is not limited to a smart sound box. Parts of this embodiment that are the same as the first embodiment are not described again, please refer to corresponding parts in the first embodiment.
In this embodiment, the method includes the steps of:
step 1: collecting user voice data; the user voice data comprises test voice data aiming at the voice service to be tested;
step 2: sending a voice service request aiming at the user voice data to a server so that the server determines the voice service to be tested according to user identification information or intelligent sound box identification information carried by the request, and processing the test voice data through the voice service to be tested;
and step 3: and displaying the voice service processing result returned by the server.
In a specific implementation, step 3 may adopt at least one of the following ways: 1) playing the reply voice data determined by the voice service; 2) adjusting the volume of the sound box according to the volume of the sound box determined by the voice service; 3) and adjusting the working mode of the Internet of things equipment according to the working mode of the Internet of things equipment controlled by the intelligent sound box determined through the voice service.
In one example, the method may further comprise the steps of: testing voice services through a real machine, and determining the voice services to be tested; the collection of the user voice data can be realized by adopting the following modes: playing the test voice data of the voice service to be tested; and collecting the played test voice data.
In one example, the playing test voice data of the voice service to be tested may include the following sub-steps: determining the playing time interval of various instruction test voices of the voice service to be tested; and playing the test voice data of various instructions of the voice service to be tested according to the playing time interval.
In one example, the method may further comprise the steps of: testing the voice service through the real machine, and suspending testing the voice service to be tested; recording the test voice at the pause moment; and testing the voice service through the real machine, and continuously testing the voice service to be tested according to the testing voice at the pause moment.
In one example, the method may further comprise the steps of: testing voice service through the real machine, and collecting test voice data of the voice service to be tested; and storing the test voice data of the voice service to be tested.
In one example, the method may further comprise the steps of: determining the testing time of an automatic real machine of the voice service to be tested; generating a test task according to the test time; and executing a test task according to the test time.
In one example, the method may further comprise the steps of: and if the automatic testing condition of the voice service to be tested is established, performing real machine testing on the voice service to be tested.
In one example, the method may further comprise the steps of: determining actual test response information; and if the actual test response information is different from the predicted test response information, displaying prompt information of operation execution errors.
In one example, the method may further comprise the steps of: recording error operation; and automatically testing the error operation.
Third embodiment
In the foregoing embodiment, a voice service testing method is provided, and correspondingly, a voice service testing apparatus is also provided. The apparatus corresponds to an embodiment of the method described above.
Parts of this embodiment that are the same as the first embodiment are not described again, please refer to corresponding parts in the first embodiment. The application provides a voice service testing arrangement includes:
the voice acquisition unit is used for acquiring user voice data; the user voice data comprises test voice data aiming at the voice service to be tested;
a request sending unit, configured to send a voice service request for the user voice data to a server, so that the server determines the voice service to be tested according to user identification information or intelligent sound box identification information carried in the request, and processes the test voice data through the voice service to be tested;
and the result display unit is used for displaying the voice service processing result returned by the server.
Fourth embodiment
The application also provides an intelligent sound box. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
An intelligent audio amplifier of this embodiment, this intelligent audio amplifier includes: a processor and a memory; a memory for storing a program for implementing the voice service test method, the device performing the following steps after being powered on and running the program of the method through the processor: collecting user voice data; the user voice data comprises test voice data aiming at the voice service to be tested; sending a voice service request aiming at the user voice data to a server so that the server determines the voice service to be tested according to user identification information or intelligent sound box identification information carried by the request, and processing the test voice data through the voice service to be tested; and displaying the voice service processing result returned by the server.
Fifth embodiment
Corresponding to the voice service testing system, the application also provides a voice service testing method, and an execution subject of the method includes but is not limited to a server side, and the method can be any device capable of implementing the method. Parts of this embodiment that are the same as the first embodiment are not described again, please refer to corresponding parts in the first embodiment.
In this embodiment, the method includes the steps of:
step 1: determining a user identifier or an intelligent sound box identifier and a corresponding relation set between the user identifier or the intelligent sound box identifier and the voice service to be tested, and loading the voice service to be tested and the published voice service;
step 2: acquiring voice service information to be tested corresponding to the intelligent sound box according to user identification information or intelligent sound box identification information carried by a voice service request aiming at user voice data sent by the intelligent sound box;
and step 3: and if the voice service to be tested corresponding to the intelligent sound box comprises the voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested, and sending a voice service processing result to the intelligent sound box so that the intelligent sound box displays the voice service processing result.
In one example, the method may further comprise the steps of: receiving a voice service binding request to be tested, which is sent by a client and aims at a target user or a target intelligent sound box; and storing the target user identification, the intelligent sound box identification corresponding to the target user, or the corresponding relation between the target intelligent sound box identification and the voice service to be tested.
In one example, the voice service to be tested includes: an updated version of the published voice service; if the voice service to be tested corresponding to the intelligent sound box comprises an updated version of the published voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested of the updated version; and if the voice service to be tested corresponding to the intelligent sound box does not comprise the updated version of the published voice service corresponding to the user voice data, processing the user voice data through the published voice service.
In one example, the method may further comprise the steps of: using the voice service to be tested and the published voice service corresponding to the intelligent sound box as voice service decision objects of a conversation understanding and voice service decision model; determining a text sequence corresponding to the user voice data through a voice recognition model; and determining the voice service to be tested or the published voice service corresponding to the user voice data according to the text sequence through the decision model.
In one example, the user includes: a voice service developer user; the user voice data includes: voice data for detecting the validity of the service function.
In one example, the user includes: a voice service of the intelligent sound box service platform is on-line for auditing a user; the user voice data includes: voice data for detecting corpus conflicts, voice data for detecting voice recognition capabilities.
In one example, the method may further comprise the steps of: and sending real machine test result data to the client.
Sixth embodiment
In the foregoing embodiment, a voice service testing method is provided, and correspondingly, a voice service testing apparatus is also provided. The apparatus corresponds to an embodiment of the method described above.
Parts of this embodiment that are the same as the first embodiment are not described again, please refer to corresponding parts in the first embodiment. The application provides a voice service testing arrangement includes:
the voice acquisition unit is used for acquiring user voice data; the user voice data comprises test voice data aiming at the voice service to be tested;
a request sending unit, configured to send a voice service request for the user voice data to a server, so that the server determines the voice service to be tested according to user identification information or intelligent sound box identification information carried in the request, and processes the test voice data through the voice service to be tested;
and the result display unit is used for displaying the voice service processing result returned by the server.
Seventh embodiment
The application also provides an electronic device embodiment. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
An electronic device of the present embodiment includes: a processor and a memory; a memory for storing a program for implementing the voice service test method, the device performing the following steps after being powered on and running the program of the method through the processor: collecting user voice data; the user voice data comprises test voice data aiming at the voice service to be tested; sending a voice service request aiming at the user voice data to a server so that the server determines the voice service to be tested according to user identification information or intelligent sound box identification information carried by the request, and processing the test voice data through the voice service to be tested; and displaying the voice service processing result returned by the server.
Eighth embodiment
Corresponding to the voice service testing system, the application also provides a voice service testing method, and the execution subject of the method includes but is not limited to a client. Parts of this embodiment that are the same as the first embodiment are not described again, please refer to corresponding parts in the first embodiment.
The voice service testing method provided by the application can comprise the following steps: and sending a voice service binding request to be tested aiming at the target user or the target intelligent sound box to the server so that the server can store the target user identification, the intelligent sound box identification corresponding to the target user or the corresponding relation between the target intelligent sound box identification and the voice service to be tested.
In one example, the method may further comprise the steps of: and receiving real machine test result data of the voice service to be tested, which is sent by the server.
The real machine test result data includes but is not limited to: the time length from the test voice sending to the sound box feedback result.
Ninth embodiment
In the foregoing embodiment, a voice service testing method is provided, and correspondingly, a voice service testing apparatus is also provided. The apparatus corresponds to an embodiment of the method described above. Parts of this embodiment that are the same as the first embodiment are not described again, please refer to corresponding parts in the first embodiment.
The application provides a voice service testing arrangement includes:
and the request sending unit is used for sending a voice service binding request to be tested aiming at the target user or the target intelligent sound box to the server so as to facilitate the server to store the target user identification, the intelligent sound box identification corresponding to the target user or the corresponding relationship between the target intelligent sound box identification and the voice service to be tested.
Tenth embodiment
The application also provides an electronic device. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
An electronic device of the present embodiment includes: a processor and a memory; a memory for storing a program for implementing the voice service test method, the device performing the following steps after being powered on and running the program of the method through the processor: and sending a voice service binding request to be tested aiming at the target user or the target intelligent sound box to the server so that the server can store the target user identification, the intelligent sound box identification corresponding to the target user or the corresponding relation between the target intelligent sound box identification and the voice service to be tested.
Eleventh embodiment
Corresponding to the voice service test system, the application also provides a voice service test case generation method, and an execution main body of the method comprises but is not limited to an intelligent sound box. Parts of this embodiment that are the same as the first embodiment are not described again, please refer to corresponding parts in the first embodiment.
In this embodiment, the method includes the steps of:
step 1: collecting test voice data of various operations of a voice service to be tested;
step 2: determining the playing time interval and the playing sequence of various operation test voices;
and step 3: and generating a test case of the voice service to be tested according to the time interval and the playing sequence.
For example, a user says in the speaker: "the tianmao eidolon, i want to prepare the test case of a certain voice service", the tianmao eidolon responds to the order, enter the real machine and test the voice service automatically, and can show the multiple voice services to be tested that the user has the right to test through the display screen; the user accessible area screen audio amplifier selects the target voice service from a plurality of voice services that await measuring, then assigns the voice command to the audio amplifier: the sound box identifies the instruction through processing of voice identification, semantic understanding and the like, responds to the instruction to open the microphone and play a prompt sound to start recording, collects test voice initiated by a user through the microphone and stores the test voice data. Then, the user can give a voice command to the sound box: the sound box identifies the instruction through processing of voice identification, semantic understanding and the like, responds to the instruction, automatically generates a test case of the voice service to be tested according to the time interval and the playing sequence, and stores the test case so as to be used in real machine testing.
For another example, the user says for the speaker: "the tianmao eidolon, i want to prepare the test case of a certain voice service", the tianmao eidolon responds to the order, enter the real machine and test the voice service automatically, and can show the multiple voice services to be tested that the user has the right to test through the display screen; the user accessible area screen audio amplifier selects the target voice service from a plurality of voice services that await measuring, then assigns the voice command to the audio amplifier: the sound box identifies the instruction through processing of voice identification, semantic understanding and the like, responds to the instruction to open the microphone and play a prompt sound to start recording, collects test voice initiated by a user through the microphone and stores the test voice data. Then, the user can give a voice command to the sound box: the sound box identifies the instruction through processing of voice identification, semantic understanding and the like, responds to the instruction, automatically generates a test case of the voice service to be tested according to the time interval and the playing sequence, and stores the test case so as to be used when a real machine is tested.
As can be seen from the foregoing embodiments, the method for generating a voice service test case provided in the embodiments of the present application collects test voice data of multiple operations of a voice service to be tested; determining the playing time interval and the playing sequence of various operation test voices; generating a test case of the voice service to be tested according to the time interval and the playing sequence; by the processing mode, the test case can be generated through the intelligent sound box; therefore, the generation efficiency of the test case can be effectively improved.
Although the present application has been described with reference to the preferred embodiments, it is not intended to limit the present application, and those skilled in the art can make variations and modifications without departing from the spirit and scope of the present application, therefore, the scope of the present application should be determined by the claims that follow.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
1. Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory computer readable media (transient media), such as modulated data signals and carrier waves.
2. As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Claims (28)
1. A voice service testing system, comprising:
the intelligent sound box is used for acquiring user voice data and sending a voice service request aiming at the user voice data to a server; and displaying a voice service processing result returned by the server;
the server is used for determining a user identifier or an intelligent sound box identifier and a corresponding relation set between the user identifier or the intelligent sound box identifier and the voice service to be tested, and loading the voice service to be tested and the published voice service; acquiring to-be-tested voice service information corresponding to the intelligent sound box according to the user identification information or the intelligent sound box identification information carried by the request; and if the voice service to be tested corresponding to the intelligent sound box comprises the voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested, and sending a voice service processing result to the intelligent sound box.
2. A voice service testing method, comprising:
determining a user identifier or an intelligent sound box identifier and a corresponding relation set between the user identifier or the intelligent sound box identifier and the voice service to be tested, and loading the voice service to be tested and the published voice service;
acquiring voice service information to be tested corresponding to the intelligent sound box according to user identification information or intelligent sound box identification information carried by a voice service request aiming at user voice data sent by the intelligent sound box;
and if the voice service to be tested corresponding to the intelligent sound box comprises the voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested, and sending a voice service processing result to the intelligent sound box so that the intelligent sound box displays the voice service processing result.
3. The method of claim 2, further comprising:
receiving a voice service binding request to be tested, which is sent by a client and aims at a target user or a target intelligent sound box;
and storing the target user identification, the intelligent sound box identification corresponding to the target user, or the corresponding relation between the target intelligent sound box identification and the voice service to be tested.
4. The method of claim 2,
the voice service to be tested comprises: an updated version of the published voice service;
if the voice service to be tested corresponding to the intelligent sound box comprises an updated version of the published voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested of the updated version;
and if the voice service to be tested corresponding to the intelligent sound box does not comprise the updated version of the published voice service corresponding to the user voice data, processing the user voice data through the published voice service.
5. The method of claim 2, further comprising:
using the voice service to be tested and the published voice service corresponding to the intelligent sound box as voice service decision objects of a conversation understanding and voice service decision model;
determining a text sequence corresponding to the user voice data through a voice recognition model;
and determining the voice service to be tested or the published voice service corresponding to the user voice data according to the text sequence through the decision model.
6. The method of claim 2,
the user includes: a voice service developer user;
the user voice data includes: voice data for detecting the validity of the service function.
7. The method of claim 2,
the user includes: a voice service of the intelligent sound box service platform is on-line for auditing a user;
the user voice data includes: voice data for detecting corpus conflicts, voice data for detecting voice recognition capabilities.
8. The method of claim 2, further comprising:
and sending real machine test result data to the client.
9. A voice service testing method, comprising:
collecting user voice data; the user voice data comprises test voice data aiming at the voice service to be tested;
sending a voice service request aiming at the user voice data to a server so that the server determines the voice service to be tested according to user identification information or intelligent sound box identification information carried by the request, and processing the test voice data through the voice service to be tested;
and displaying the voice service processing result returned by the server.
10. The method of claim 9, wherein the presenting the processing result of the voice service returned by the service end comprises at least one of the following manners:
playing the reply voice data determined by the voice service;
adjusting the volume of the sound box according to the volume of the sound box determined by the voice service;
and adjusting the working mode of the Internet of things equipment according to the working mode of the Internet of things equipment controlled by the intelligent sound box determined through the voice service.
11. The method of claim 9, further comprising:
testing voice services through a real machine, and determining the voice services to be tested;
the collecting of the user voice data comprises the following steps:
playing the test voice data of the voice service to be tested;
and collecting the played test voice data.
12. The method of claim 11,
the playing the test voice data of the voice service to be tested comprises:
determining the playing time interval of the test voice of various operations of the voice service to be tested;
and playing the test voice data of various operations of the voice service to be tested according to the playing time interval.
13. The method of claim 11, further comprising:
testing the voice service through the real machine, and suspending testing the voice service to be tested;
recording the test voice at the pause moment;
and testing the voice service through the real machine, and continuously testing the voice service to be tested according to the testing voice at the pause moment.
14. The method of claim 11, further comprising:
testing voice service through the real machine, and collecting test voice data of the voice service to be tested;
and storing the test voice data of the voice service to be tested.
15. The method of claim 9, further comprising:
determining the testing time of an automatic real machine of the voice service to be tested;
generating a test task according to the test time;
and executing a test task according to the test time.
16. The method of claim 9, further comprising:
and if the automatic testing condition of the voice service to be tested is established, performing real machine testing on the voice service to be tested.
17. The method of claim 9, further comprising:
determining actual test response information;
and if the actual test response information is different from the predicted test response information, displaying prompt information of operation execution errors.
18. The method of claim 17, further comprising:
recording error operation;
and automatically testing the error operation.
19. A voice service testing method, comprising:
and sending a voice service binding request to be tested aiming at the target user or the target intelligent sound box to the server so that the server can store the target user identification, the intelligent sound box identification corresponding to the target user or the corresponding relation between the target intelligent sound box identification and the voice service to be tested.
20. The method of claim 19, further comprising:
and receiving real machine test result data of the voice service to be tested, which is sent by the server.
21. The method of claim 20,
the real machine test result data comprises: the time length from the test voice sending to the sound box feedback result.
22. A voice service testing apparatus, comprising:
the voice service binding and loading unit to be tested is used for determining a user identifier or an intelligent sound box identifier and a corresponding relation set between the voice service to be tested and the voice service to be tested, and loading the voice service to be tested and the published voice service;
the voice service determining unit to be tested is used for acquiring voice service information to be tested corresponding to the intelligent sound box according to user identification information or intelligent sound box identification information carried by a voice service request aiming at user voice data sent by the intelligent sound box;
and the voice service execution unit to be tested is used for processing the user voice data through the voice service to be tested and sending a voice service processing result to the intelligent sound box if the voice service to be tested corresponding to the intelligent sound box comprises the voice service corresponding to the user voice data, so that the intelligent sound box displays the voice service processing result.
23. An electronic device, comprising:
a processor; and
a memory for storing a program for implementing the voice service test method, the device performing the following steps after being powered on and running the program of the method through the processor: determining a user identifier or an intelligent sound box identifier and a corresponding relation set between the user identifier or the intelligent sound box identifier and the voice service to be tested, and loading the voice service to be tested and the published voice service; acquiring voice service information to be tested corresponding to the intelligent sound box according to user identification information or intelligent sound box identification information carried by a voice service request aiming at user voice data sent by the intelligent sound box; and if the voice service to be tested corresponding to the intelligent sound box comprises the voice service corresponding to the user voice data, processing the user voice data through the voice service to be tested, and sending a voice service processing result to the intelligent sound box so that the intelligent sound box displays the voice service processing result.
24. A voice service testing apparatus, comprising:
the voice acquisition unit is used for acquiring user voice data; the user voice data comprises test voice data aiming at the voice service to be tested;
a request sending unit, configured to send a voice service request for the user voice data to a server, so that the server determines the voice service to be tested according to user identification information or intelligent sound box identification information carried in the request, and processes the test voice data through the voice service to be tested;
and the result display unit is used for displaying the voice service processing result returned by the server.
25. An intelligent sound box, comprising:
a processor; and
a memory for storing a program for implementing the voice service test method, the device performing the following steps after being powered on and running the program of the method through the processor: collecting user voice data; the user voice data comprises test voice data aiming at the voice service to be tested; sending a voice service request aiming at the user voice data to a server so that the server determines the voice service to be tested according to user identification information or intelligent sound box identification information carried by the request, and processing the test voice data through the voice service to be tested; and displaying the voice service processing result returned by the server.
26. A voice service testing apparatus, comprising:
and the request sending unit is used for sending a voice service binding request to be tested aiming at the target user or the target intelligent sound box to the server so as to facilitate the server to store the target user identification, the intelligent sound box identification corresponding to the target user or the corresponding relationship between the target intelligent sound box identification and the voice service to be tested.
27. An electronic device, comprising:
a processor; and
a memory for storing a program for implementing the voice service test method, the device performing the following steps after being powered on and running the program of the method through the processor: and sending a voice service binding request to be tested aiming at the target user or the target intelligent sound box to the server so that the server can store the target user identification, the intelligent sound box identification corresponding to the target user or the corresponding relation between the target intelligent sound box identification and the voice service to be tested.
28. A method for generating a voice service test case is characterized by comprising the following steps:
collecting test voice data of various operations of a voice service to be tested;
determining the playing time interval and the playing sequence of various operation test voices;
and generating a test case of the voice service to be tested according to the time interval and the playing sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010378808.9A CN113628611A (en) | 2020-05-07 | 2020-05-07 | Voice service test system, method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010378808.9A CN113628611A (en) | 2020-05-07 | 2020-05-07 | Voice service test system, method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113628611A true CN113628611A (en) | 2021-11-09 |
Family
ID=78376976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010378808.9A Pending CN113628611A (en) | 2020-05-07 | 2020-05-07 | Voice service test system, method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113628611A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000115362A (en) * | 1998-10-05 | 2000-04-21 | Fujitsu Ltd | Acoustic equipment test system for exchange |
| US20060224392A1 (en) * | 2005-03-31 | 2006-10-05 | Microsoft Corporation | Test harness for a speech server |
| CN105357408A (en) * | 2015-10-16 | 2016-02-24 | 国家电网公司 | Communication detection method and device for power grid voice system |
| US20160134752A1 (en) * | 2014-11-12 | 2016-05-12 | 24/7 Customer, Inc. | Method and apparatus for facilitating speech application testing |
| CN107516510A (en) * | 2017-07-05 | 2017-12-26 | 百度在线网络技术（北京）有限公司 | A kind of smart machine automated voice method of testing and device |
| CN108228468A (en) * | 2018-02-12 | 2018-06-29 | 腾讯科技（深圳）有限公司 | A kind of test method, device, test equipment and storage medium |
| KR20180078746A (en) * | 2016-12-30 | 2018-07-10 | (주) 블루테크솔루션 | Method for providing automated test for application to developer, thereby registering said application to market portal server, servers and terminal using the same |
| CN108959087A (en) * | 2018-06-29 | 2018-12-07 | 百度在线网络技术（北京）有限公司 | test method and device |
| CN109062779A (en) * | 2018-06-07 | 2018-12-21 | 优视科技有限公司 | Test control method, main control device, controlled device and test macro |
| CN109976995A (en) * | 2017-12-28 | 2019-07-05 | 百度在线网络技术（北京）有限公司 | Method and apparatus for test |
| CN110221983A (en) * | 2019-06-19 | 2019-09-10 | 深圳市腾讯网域计算机网络有限公司 | Test method, device, computer readable storage medium and computer equipment |
-
2020
- 2020-05-07 CN CN202010378808.9A patent/CN113628611A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000115362A (en) * | 1998-10-05 | 2000-04-21 | Fujitsu Ltd | Acoustic equipment test system for exchange |
| US20060224392A1 (en) * | 2005-03-31 | 2006-10-05 | Microsoft Corporation | Test harness for a speech server |
| US20160134752A1 (en) * | 2014-11-12 | 2016-05-12 | 24/7 Customer, Inc. | Method and apparatus for facilitating speech application testing |
| CN105357408A (en) * | 2015-10-16 | 2016-02-24 | 国家电网公司 | Communication detection method and device for power grid voice system |
| KR20180078746A (en) * | 2016-12-30 | 2018-07-10 | (주) 블루테크솔루션 | Method for providing automated test for application to developer, thereby registering said application to market portal server, servers and terminal using the same |
| CN107516510A (en) * | 2017-07-05 | 2017-12-26 | 百度在线网络技术（北京）有限公司 | A kind of smart machine automated voice method of testing and device |
| CN109976995A (en) * | 2017-12-28 | 2019-07-05 | 百度在线网络技术（北京）有限公司 | Method and apparatus for test |
| CN108228468A (en) * | 2018-02-12 | 2018-06-29 | 腾讯科技（深圳）有限公司 | A kind of test method, device, test equipment and storage medium |
| CN109062779A (en) * | 2018-06-07 | 2018-12-21 | 优视科技有限公司 | Test control method, main control device, controlled device and test macro |
| CN108959087A (en) * | 2018-06-29 | 2018-12-07 | 百度在线网络技术（北京）有限公司 | test method and device |
| CN110221983A (en) * | 2019-06-19 | 2019-09-10 | 深圳市腾讯网域计算机网络有限公司 | Test method, device, computer readable storage medium and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107516510B (en) | Automatic voice testing method and device for intelligent equipment | |
| CN110175012B (en) | Skill recommendation method, skill recommendation device, skill recommendation equipment and computer readable storage medium | |
| US8126716B2 (en) | Method and system for collecting audio prompts in a dynamically generated voice application | |
| US10861480B2 (en) | Method and device for generating far-field speech data, computer device and computer readable storage medium | |
| CN109817219A (en) | Voice wake-up test method and system | |
| US20200151212A1 (en) | Music recommending method, device, terminal, and storage medium | |
| CN107403627B (en) | Sound source calibration system and method | |
| CN109192193A (en) | A kind of speech recognition product test method and test device | |
| US20200320975A1 (en) | Automated voice processing testing system and method | |
| CN108469966A (en) | Voice broadcast control method and device, intelligent device and medium | |
| CN108744521A (en) | The method and device of game speech production, electronic equipment, storage medium | |
| US20200135156A1 (en) | Method and apparatus for correcting delay between accompaniment audio and unaccompanied audio, and storage medium | |
| CN102881309A (en) | Lyric file generating and correcting method and device | |
| CN108899011B (en) | Voice function testing method, device and system of air conditioner | |
| CN111627460B (en) | Ambient reverberation detection method, device, equipment and computer readable storage medium | |
| CN107403629B (en) | Far-field pickup performance evaluation method and system, and electronic device | |
| CN106653054B (en) | Method and device for generating voice animation | |
| CN113628611A (en) | Voice service test system, method, device and equipment | |
| CN109197674B (en) | Bird training method and device | |
| CN109271480B (en) | Voice question searching method and electronic equipment | |
| CN109121068A (en) | Sound effect control method, apparatus and electronic equipment | |
| CN113241056B (en) | Training and speech synthesis method, device, system and medium for speech synthesis model | |
| CN113241057A (en) | Interactive method, apparatus, system and medium for speech synthesis model training | |
| CN113257247A (en) | Test method and system | |
| CN110782874B (en) | Voice library management method, voice recognition test method and 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 |