Voice dialogue testing method, device and storage medium

Abstract

The present application discloses a method, device and storage medium for testing voice dialogue. The method includes: in response to a trigger operation of a user dialing a test number on a call center's webpage, establishing a soft switch connection with the user; determining a first audio and first information related to the first audio to be broadcasted to the user; determining second information related to the second audio according to a second audio that the user responds to the first audio; and pushing the first information and the second information to the call center's webpage for display.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent voice dialogue testing, and in particular to a voice dialogue testing method, device and storage medium. Background Art

[0002] Intelligent chatbots are currently widely used in various fields, including intelligent customer service, smart speakers, entertainment products, etc., and intelligent voice robots, as their advanced form, are increasingly favored by the industry with a more natural and convenient interactive method (voice). At present, general intelligent voices will be connected to TTS (robot's mouth), ASR (robot's ears), and process engines (robot's brains), and will be delivered for use after being configured by operators according to needs (for example, the speech process of telemarketing and collection voice robots and the voice of TTS speakers may be different). Testing is required before use. Currently, testing is very inconvenient. It is necessary to upload the tester's call list (mobile phone number), create a task, call the tester's mobile phone, and then the tester interacts with the voice robot. After completion, check the backend phone records (including text-based chat records and recordings similar to the WeChat chat interface). If there is a problem, the above process must be repeated, which is time-consuming and labor-intensive, affecting the rapid delivery of products. In addition, the verification stage of the project implementation process has a strong dependence on the telephone line, and the line cannot be tested if it is not configured properly. If a new intelligent voice robot is configured for verification during project operation, it will occupy the telephone line and consume phone charges unnecessarily. Telephone lines are sometimes misconfigured, which can cause unnecessary interference in the verification of the intelligent voice process.

[0003] In view of the technical problem that the voice robots existing in the above-mentioned prior art are too dependent on telephone lines during the testing process, and problems arising during the testing process require repeated testing, thus causing time-consuming and labor-intensive technical problems that affect product delivery, no effective solution has been proposed so far. Summary of the invention

[0004] The embodiments of the present disclosure provide a voice conversation testing method, device and storage medium to at least solve the technical problems in the prior art that voice robots are overly dependent on telephone lines during testing, and that problems arising during the testing process require repeated testing, which is time-consuming and labor-intensive and affects product delivery.

[0005] According to one aspect of an embodiment of the present disclosure, a method for testing voice conversations is provided, including: in response to a trigger operation in which a user dials a test number on a call center's web page, establishing a soft switch connection with the user; determining a first audio to be broadcast to the user and first information related to the first audio; determining second information related to the second audio based on a second audio to which the user responds to the first audio; and pushing the first information and the second information to the call center's web page for display.

[0006] According to another aspect of an embodiment of the present disclosure, a storage medium is further provided, the storage medium including a stored program, wherein when the program is running, a processor executes any one of the methods described above.

[0007] According to another aspect of an embodiment of the present disclosure, a voice conversation testing device is also provided, including: a connection establishment module, used to establish a soft switch connection with the user in response to a trigger operation of the user dialing a test number on the call center's web page; a first information determination module, used to determine a first audio broadcast to the user and first information related to the first audio; a second information determination module, used to determine second information related to the second audio based on the second audio of the user's response to the first audio; and an information display module, used to push the first information and the second information to the call center's web page for display.

[0008] According to another aspect of an embodiment of the present disclosure, a voice conversation testing device is also provided, including: a processor; and a memory, connected to the processor, for providing the processor with instructions for processing the following processing steps: in response to a trigger operation of a user dialing a test number on a call center's web page, establishing a soft switch connection with the user; determining a first audio and first information related to the first audio to be broadcast to the user; determining second information related to the second audio based on a second audio in response to the first audio by the user; and pushing the first information and the second information to the call center's web page for display.

[0009] In the disclosed embodiment, during the test of the intelligent voice robot, the tester can dial the short number (corresponding to the voice robot) on the FS in the form of a softphone, and can record the first information related to the robot broadcast audio and the second information related to the user answer audio generated during the interaction, and display the first information and the second information on the web page. Thus, compared with the prior art, this solution can complete the test of the voice robot in the form of a softphone, and can perform repeated tests many times, so it can save time and cost, thereby speeding up the delivery of products. In addition, this solution can also visualize the information generated during the test, so it is convenient to directly view the test results of each step. Therefore, the technical effect of saving time and cost and facilitating the viewing of test results is achieved. This solves the technical problem that the voice robot in the prior art is too dependent on the telephone line during the test, and problems in the test process require repeated testing, thus causing time-consuming and labor-intensive, affecting product delivery. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure. In the drawings:

[0011] Figure 1 is a hardware structure block diagram of a computing device for implementing the method according to Embodiment 1 of the present disclosure;

[0012] Figure 2 is a schematic diagram of a call center system according to Embodiment 1 of the present disclosure;

[0013] Figure 3 This is a schematic diagram of the front-end and back-end interaction process of the call center system according to Embodiment 1 of the present disclosure;

[0014] Figure 4 is a flowchart of a voice conversation testing method according to the first aspect of Embodiment 1 of the present disclosure;

[0015] Figure 5 is a test flow chart according to Embodiment 1 of the present disclosure;

[0016] Figure 6 is a schematic diagram of a voice dialogue testing device according to Embodiment 2 of the present disclosure;

[0017] Figure 7 It is a schematic diagram of a voice conversation testing device according to Embodiment 3 of the present disclosure. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0020] Example 1

[0021] According to this embodiment, a test method embodiment of a voice conversation is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0022] The method embodiment provided in this embodiment can be executed in a server or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computing device for implementing a voice dialogue test method. Figure 1 As shown, the computing device may include one or more processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, and a transmission device for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0023] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the computing device. As involved in the embodiments of the present disclosure, the data processing circuitry acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0024] The memory can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the voice dialogue test method in the embodiment of the present disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the voice dialogue test method of the above-mentioned application is realized. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computing device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0025] The transmission device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computing device. In one example, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

[0026] The display may be, for example, a touch screen liquid crystal display (LCD) that may enable a user to interact with a user interface of the computing device.

[0027] It should be noted that, in some optional embodiments, the above Figure 1 The computing device shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware elements and software elements. Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computing devices described above.

[0028] Figure 2Schematic diagram of the call center system according to this embodiment. Figure 2 As shown, the system includes: a front-end client 210 and a system backend 220 (Java backend), wherein the system backend 220 is deployed with, for example, an open source telephone soft switch platform software FreeSWITCH (hereinafter referred to as FS). Figure 3 As shown, the tester (user) can log in to the web page (front-end page) of the client 210 of the call center, which is connected to the FS through the SDK, and then can be connected to the voice robot through the FS. The user can call a specific short number on the web page (i.e., use a soft phone to call an intelligent voice), where the short number corresponds to the Lua script (voice robot) to be tested, and the Lua script corresponds to the process to be tested, that is, the process executed by the voice robot during the human-computer interaction process. Among them, during the test process, the Lua script can call the process engine module of the intelligent voice robot, where the process engine module can, for example, determine the speech technique based on the user's audio. In addition, the Lua script can also call the TTS and ASR functions of the intelligent voice robot and record relevant information. Then, the relevant information is sent to the call management component of the system background 220 (e.g., Java background), where the Lua script can, for example, pass the relevant information to the call management component of the call center java background through the ESL event. It should be noted that the front-end client 210 and the system background 220 in the system can both be applied to the hardware structure described above.

[0029] In the above operating environment, according to the first aspect of this embodiment, a method for testing a voice conversation is provided. The method comprises, for example, Figure 2 The system backend 220 of the call center shown in FIG. 1 is implemented, and specifically can be implemented by the Lua script. Figure 4 A schematic diagram showing the process of the method is shown in FIG. Figure 4 As shown, the method includes:

[0030] S402: In response to a trigger operation of a user dialing a test number on a webpage of a call center, establishing a softswitch connection with the user;

[0031] S404: Determine a first audio to be broadcasted to the user and first information related to the first audio;

[0032] S406: Determine second information related to the second audio according to the second audio in response to the first audio by the user; and

[0033] S408: Push the first information and the second information to the webpage of the call center for display.

[0034] As described in the background technology, the current testing is very inconvenient. It is necessary to upload the tester's call list (mobile phone number), create a task, call the tester's mobile phone, and then the tester interacts with the voice robot. After completion, check the background phone records (including text-based chat records and recordings similar to the WeChat chat interface). If there is a problem, the above process must be repeated, which is time-consuming and labor-intensive, affecting the rapid delivery of the product. In addition, the verification phase of the project implementation process has a strong dependence on telephone lines, and the line cannot be tested if it is not configured properly. Configuring a new intelligent voice robot for verification during project operation will unnecessarily occupy telephone lines and consume phone charges. Sometimes there are configuration issues with telephone lines, which will cause unnecessary interference to the verification of the intelligent voice process.

[0035] For the technical problems existing in the background technology, refer to Figure 4 and Figure 5 As shown, in the technical solution of this embodiment, in step S402, the system background 220 first responds to the trigger operation of the user dialing the test number on the web page of the call center, and establishes a connection with the user for soft switching. In actual operation, the user (tester) first logs in to the web page of the client 210 through the test account, wherein the account is, for example, an agent account with corresponding permissions, and then the page will display a dial pad, so that the user can use the dial pad to dial the short number (intelligent voice robot) on the FS in the form of a soft phone. In this case, the Lua script of the system background 220 can respond to the trigger operation of the user dialing and establish a connection with the user for soft switching, that is, the user can interact with the voice robot (Lua script) tested.

[0036] Furthermore, after the connection is established, the intelligent voice robot needs to interact with the user through audio, that is, to broadcast audio to the user. The audio broadcast can be determined according to the actual application scenario, for example, the audio broadcast includes: greetings, product introductions, product promotions, etc. In this case, the Lua script of the system background 220 can determine the first audio broadcast to the user, and determine the first information related to the first audio. (Corresponding to step S404)

[0037] Then, during the interaction, the user (tester) needs to respond or reply to the first audio. In this case, the Lua script of the system background 220 first determines the second audio (the audio answered by the user) to which the user responds to the first audio, and then determines the second information based on the second audio, which is related to the second audio answered by the user. (Corresponding to step S406). In addition, refer to Figure 5As shown, in actual applications, the tester and the intelligent voice robot may involve multiple broadcasts and responses in one interaction. The way in which multiple broadcasts and responses generate information is similar to the above-mentioned steps S404 and S406 and will not be repeated here until the user hangs up.

[0038] Finally, in step S408 , the first information, the second information (and multiple broadcast and response information) are pushed to the web page of the call center for display, that is, visually displayed by the web page of the client 210 .

[0039] Thus, in this way, during the testing of the intelligent voice robot, the tester can dial the short number (corresponding to the voice robot) on the FS in the form of a soft phone, and can record the first information related to the robot broadcast audio and the second information related to the user's answer audio generated during the interaction, and display the first information and the second information on the web page. Thus, compared with the prior art, this solution can complete the test of the voice robot in the form of a soft phone, and can perform repeated tests many times, so it can save time and cost, thereby speeding up the delivery of products. In addition, this solution can also visualize the information generated during the test, so it is convenient to directly view the test results of each step. Therefore, the technical effect of saving time and cost and facilitating viewing of test results is achieved. This solves the technical problem that the voice robot in the prior art is too dependent on the telephone line during the test, and problems occur during the test and need to be tested repeatedly, thus causing time-consuming and labor-intensive, affecting product delivery.

[0040] Optionally, determining the first audio to be broadcast to the user includes: determining a speech text to be broadcast to the user through a preset test process engine; and performing speech synthesis on the speech text to determine the first audio.

[0041] Specifically, in the operation of determining the first audio to be broadcasted to the user, the Lua script first determines the speech text to be broadcasted to the user through a pre-set test flow engine, referring to Figure 5 That is, calling the process engine module preset by the intelligent voice robot, which contains the speech process for interacting with the user, such as the opening speech and the speech for the user's answer. Furthermore, the Lua script can call TTS (for example, it can be the speech synthesis technology in the prior art) to synthesize the speech text into the first audio. In this way, the effect of audio interaction with the user during the test can be achieved.

[0042] Optionally, determining the first information related to the first audio includes: determining the speech text corresponding to the first audio, start and end time information of the first audio, indication information of whether the first audio is successfully synthesized, and interruption information of whether the first audio is interrupted.

[0043] Specifically, in actual applications, the test includes, for example, testing of the process engine and testing of the TTS function, wherein the test of the process engine can be reflected by determining the speech text, and the test of the TTS function can be reflected by whether the first audio is successfully synthesized. Thus, in the operation of determining the first information related to the first audio, the speech text corresponding to the first audio, the start and end time information of the first audio, and the indication information of whether the first audio is successfully synthesized can be determined. In addition, the first audio may be interrupted by the user during the broadcast process, so the interruption information of whether the first audio is interrupted can also be determined. Thus, the speech text corresponding to the first audio, the start and end time information of the first audio, the indication information of whether the first audio is successfully synthesized, and the interruption information of whether the first audio is interrupted together constitute the first information. In addition, the first information can also include other relevant information, which will not be repeated here. Thus, in this way, the process engine and text-to-speech functions of the robot can be tested.

[0044] Optionally, determining the second information related to the second audio includes: determining a response text corresponding to the second audio, indication information of whether the second audio is successfully converted into text, start and end time information of the second audio, and user intention information contained in the second audio.

[0045] Specifically, the test may also include a test of the ASR (speech recognition) function, so in the operation of determining the second information related to the second audio, the ASR may also be called to convert the second audio into a corresponding response text, and determine whether the conversion is successful. In addition, the user's intention information in the second audio may also be determined by the execution engine. Therefore, the response text corresponding to the second audio, the indication information of whether the second audio is successfully converted into text, the start and end time information of the second audio, and the user intention information contained in the second audio constitute the second information.

[0046] Optionally, pushing the first information and the second information to the call center's webpage for display includes: sending the first information and the second information to the call center's system background; and pushing the first information and the second information to the call center's webpage for display via the system background.

[0047] Specifically, in the operation of pushing the first information and the second information to the webpage of the call center for display, since the Lua script cannot directly send the information to the front-end page for display, the Lua script first sends the first information and the second information to the system background 220 (Java background) of the call center. In a preferred embodiment, the Lua script is passed to the call center Java background call management component through the ESL event. Then, the first information and the second information are pushed to the webpage of the call center for display through the system background, for example, the call management component pushes the first information and the second information to the front-end page for display through the websocket connection.

[0048] Optionally, before pushing the first information and the second information to the call center's webpage for display, the method further includes: determining sequence numbers of the first information and the second information; and pushing the first information and the second information to the call center's webpage for display according to the sequence numbers.

[0049] Specifically, the present embodiment can also determine the sequence number of the first information and the second information, that is, the interactive information (first information, second information, etc.) generated during the interaction process is sequenced and numbered. Further, according to the sequence number, the first information and the second information are pushed to the webpage of the call center for display. Thus, the tester can intuitively view the process of the interaction.

[0050] Optionally, before pushing the first information and the second information to the call center's web page for display, it also includes: determining a first identifier corresponding to the first information, determining a second identifier corresponding to the second information; and pushing the first information and the second information to the call center's web page for display based on the first identifier and the second identifier.

[0051] Specifically, this embodiment can also determine a first identifier corresponding to the first information and a second identifier corresponding to the second information. The identifier can be, for example, a unique number or name, for example: 0 represents words spoken by a robot, and 1 represents words spoken by a person. Then, according to the first identifier and the second identifier, the first information and the second information are pushed to the webpage of the call center for display. Thus, the information generated by the robot and the information generated by the user can be clearly distinguished.

[0052] Optionally, before pushing the first information and the second information to the call center's webpage for display, the method further includes: determining display positions of the first information and the second information; and pushing the first information and the second information to the call center's webpage for display according to the display positions.

[0053] Specifically, the present embodiment can also determine the display positions of the first information and the second information, wherein the display positions can refer to the chat software in the prior art (such as WeChat chat interface), and the first information and the second information are displayed in two columns on the left and right. Then, the first information and the second information are pushed to the webpage of the call center for display according to the display positions.

[0054] Optionally, the method further includes: obtaining a trigger operation performed by the user during the answering process, and determining identification information corresponding to the trigger operation; and determining the second information according to the identification information corresponding to the trigger operation.

[0055] Specifically, the user can include multiple forms in the answering process, such as: the above-mentioned voice answering, in addition to key input (web page pop-up dial pad), hanging up and transferring to manual, etc. Therefore, this solution can also obtain the user's triggering operation in the answering process, and determine the identification information corresponding to the triggering operation, for example: 0 represents the next step receiving button (web page pop-up dial pad), 1 represents receiving voice (Lua starts ASR), 2 represents hanging up (Lua hanging up), 3 represents transferring skill group (Lua transfers to manual seat). Then, the second information is determined according to the identification information corresponding to the triggering operation.

[0056] In addition, the page can also display secondary text, such as the node name (displayed in small font) (query node, jump node) under the robot's speech text, and the intention of the sentence under the corresponding text of what the person said (displayed in small font).

[0057] In addition, reference Figure 1 As shown, according to the second aspect of this embodiment, a storage medium is provided, wherein the storage medium includes a stored program, wherein when the program is run, a processor executes any one of the above methods.

[0058] In a specific example, the process of this solution is as follows:

[0059] 1) The tester logs in to the call center agent page with a test account

[0060] 2) Use the web dialer to call a specific short number on fs (bridge connected to the voice robot) in the form of a soft phone (the short number corresponds to the Lua script to be tested, and the Lua script corresponds to the process to be tested; the web page is connected to fs through the SDK)

[0061] 3) In addition to the process response, the Lua script also records all necessary information (such as TTS playback status, ASR recognition status, start and end time points, etc.), and notifies the Java background call management component through ESL (send event). All the fields that need to be sent are as follows:

[0062] Text-Order: The order of text, the value range is [1,n]. When displayed in 4), it can be arranged in order.

[0063] Text-Type: 0 means the robot speaks, 1 means the human speaks, and it can be displayed in two columns, left and right.

[0064] Text-Main: The text corresponding to what the robot and the human say

[0065] Text-Sub: To display secondary text, such as the node name (displayed in small font) under the robot's speech text (query node, jump node), and the intention of the sentence under the corresponding text of the human speech (displayed in small font)

[0066] Next-Step: The next action. 0 means receiving the next button (a dial pad pops up on the web page), 1 means receiving voice (Lua starts ASR), 2 means hanging up (Lua hangs up), and 3 means transferring to a skill group (Lua transfers to a human agent)

[0067] Time-Start: The starting time of this sentence in the recording, in ms

[0068] Time-End: The ending time of this sentence in the recording, in ms

[0069] Break-Result: 0 means no interruption, 1 means interruption during broadcast

[0070] Login-Name: The seat login name, used to display the page corresponding to the seat

[0071] 4) The Java background call management component passes the above information to the front-end page for display through the websocket connection. For example, the texts of the robot and the human are arranged separately and in order (refer to the chat record layout of WeChat). You can listen to the recording of the entire conversation. Click on any text to listen to the recording of this text alone. If it is spoken by a robot, an icon will be used to indicate whether the TTS synthesis of the sentence is successful and whether it is interrupted. If it is spoken by a human, the intention of the sentence is displayed (the result comes from the intention recognition module connected to the process engine). If the node requires a button (such as entering an ID number), the front-end page will automatically pop up a dial pad for the tester to use during the verification process.

[0072] 5) After this round of interaction is completed, the tester can start the next round of interaction in this conversation, or choose to hang up.

[0073] Thus, according to this embodiment, in the process of testing the intelligent voice robot, the tester can dial the short number (corresponding to the voice robot) on the FS in the form of a soft phone, and can record the first information related to the robot broadcast audio and the second information related to the user's answer audio generated during the interaction, and display the first information and the second information on the web page. Thus, compared with the prior art, this solution can complete the test of the voice robot in the form of a soft phone, and can perform repeated tests many times, so it can save time and cost, and thus speed up the delivery of the product. In addition, this solution can also visualize the information generated during the test, so it is convenient to directly view the test results of each step. Therefore, the technical effect of saving time and cost and facilitating viewing of the test results is achieved. Then, the existing voice robot in the prior art is overly dependent on the telephone line during the test, and problems in the test process need to be repeatedly tested, thus causing time-consuming and labor-intensive technical problems that affect product delivery.

[0074] In addition, this solution does not require real outbound calls in the production system. You only need to log in to the call center page and call the soft phone to quickly verify the intelligent voice robot process, which is fast, accurate, and convenient for repeated verification. In addition, this embodiment uses a call directly on the web page to interact with the intelligent voice robot, and displays various interactive information on the page (including text information corresponding to the voice, whether TTS is successfully synthesized, whether the TTS broadcast is interrupted, the intention recognition result information of the person's words, and recording information) to verify various aspects of the intelligent voice process. It is simple to use, accurate and comprehensive, and can be easily verified repeatedly; while the existing method of using real phone verification is cumbersome to operate, not conducive to repeated verification, and will waste line and telephone fee resources. When there is a problem with the phone line, it will also interfere with the verification of the intelligent voice process. In addition, using pure Internet interaction to verify the intelligent voice process can eliminate the dependence on the telephone line in the verification stage of the project landing process, which can speed up the landing process; secondly, it can eliminate the interference of the telephone line; thirdly, the information required for verification is concentrated on the page, easy to operate, and easy to repeat, avoiding the cumbersome operations such as uploading lists and creating outbound call tasks brought by the real telephone line (these operations are actually irrelevant to the verification of the intelligent voice process). Freeing testers from irrelevant pre-operations allows them to focus on intelligent voice process verification, improving work efficiency and accuracy and further ensuring project quality.

[0075] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0076] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0077] Example 2

[0078] Figure 6 A voice dialogue testing device 600 according to this embodiment is shown, and the device 600 corresponds to the method according to the first aspect of embodiment 1. Figure 6 As shown, the device 600 includes: a connection establishment module 610, which is used to establish a soft switch connection with the user in response to a trigger operation of the user dialing a test number on the call center's web page; a first information determination module 620, which is used to determine a first audio to be broadcast to the user and first information related to the first audio; a second information determination module 630, which is used to determine second information related to the second audio based on the second audio of the user's response to the first audio; and an information display module 640, which is used to push the first information and the second information to the call center's web page for display.

[0079] Optionally, the first information determination module 620 includes: a speech determination submodule, which is used to determine the speech text to be broadcast to the user through a pre-set test process engine; and an audio synthesis submodule, which is used to perform speech synthesis on the speech text to determine the first audio.

[0080] Optionally, the first information determination module 620 includes: a first information determination sub-module, used to determine the speech text corresponding to the first audio, the start and end time information of the first audio, the indication information of whether the first audio is successfully synthesized, and the interruption information of whether the first audio is interrupted.

[0081] Optionally, the second information determination module 630 includes: a second information determination submodule, used to determine the response text corresponding to the second audio, indication information of whether the second audio is successfully converted into text, start and end time information of the second audio, and user intention information contained in the second audio.

[0082] Optionally, the information display module 640 includes: an information sending submodule, used to send the first information and the second information to the system background of the call center; and an information display submodule, used to push the first information and the second information to the webpage of the call center for display through the system background.

[0083] Optionally, the device 600 further includes: a number determination module, used to determine the sequence numbers of the first information and the second information; and a number display module, used to push the first information and the second information to a webpage of a call center for display according to the sequence numbers.

[0084] Optionally, the device 600 also includes: an identification determination module, used to determine a first identification corresponding to the first information, and determine a second identification corresponding to the second information; and an identification display module, used to push the first information and the second information to the call center's web page for display based on the first identification and the second identification.

[0085] Optionally, the device 600 further includes: a display position determination module, used to determine the display positions of the first information and the second information; and a position display module, used to push the first information and the second information to a webpage of a call center for display according to the display positions.

[0086] Optionally, the device 600 also includes: a trigger module, used to obtain a trigger operation of the user during the answering process and determine identification information corresponding to the trigger operation; and an identification determination information module, used to determine the second information according to the identification information corresponding to the trigger operation.

[0087] Thus, according to this embodiment, in the process of testing the intelligent voice robot, the tester can dial the short number (corresponding to the voice robot) on the FS in the form of a soft phone, and can record the first information related to the robot broadcast audio and the second information related to the user answer audio generated during the interaction, and display the first information and the second information on the web page. Thus, compared with the prior art, this solution can complete the test of the voice robot in the form of a soft phone, and can perform repeated tests many times, so it can save time and cost, and thus speed up the delivery of the product. In addition, this solution can also visualize the information generated during the test, so it is convenient to directly view the test results of each step. Therefore, the technical effect of saving time and cost and facilitating viewing of the test results is achieved. Then, the existing voice robot in the prior art is overly dependent on the telephone line during the test, and problems in the test process need to be repeatedly tested, thus causing time-consuming and labor-intensive technical problems that affect product delivery.

[0088] Example 3

[0089] Figure 7 A voice dialogue testing device 700 according to this embodiment is shown, and the device 700 corresponds to the method according to the first aspect of embodiment 1. Figure 7 As shown, the device 700 includes: a processor 710; and a memory 720, which is connected to the processor 710 and is used to provide instructions for the processor 710 to process the following processing steps: in response to a trigger operation of a user dialing a test number on a call center's web page, establishing a soft switch connection with the user; determining a first audio and first information related to the first audio to be broadcast to the user; determining second information related to the second audio based on a second audio in response to the first audio by the user; and pushing the first information and the second information to the call center's web page for display.

[0090] Optionally, determining the first audio to be broadcast to the user includes: determining a speech text to be broadcast to the user through a preset test process engine; and performing speech synthesis on the speech text to determine the first audio.

[0091] Optionally, determining the first information related to the first audio includes: determining the speech text corresponding to the first audio, start and end time information of the first audio, indication information of whether the first audio is successfully synthesized, and interruption information of whether the first audio is interrupted.

[0092] Optionally, determining the second information related to the second audio includes: determining a response text corresponding to the second audio, indication information of whether the second audio is successfully converted into text, start and end time information of the second audio, and user intention information contained in the second audio.

[0093] Optionally, pushing the first information and the second information to the call center's webpage for display includes: sending the first information and the second information to the call center's system background; and pushing the first information and the second information to the call center's webpage for display via the system background.

[0094] Optionally, the memory 720 is also used to provide instructions for the processor 710 to process the following processing steps: before pushing the first information and the second information to the call center's web page for display, determine the sequence numbers of the first information and the second information; and according to the sequence numbers, push the first information and the second information to the call center's web page for display.

[0095] Optionally, the memory 720 is also used to provide instructions for the processor 710 to process the following processing steps: before pushing the first information and the second information to the call center's web page for display, determining a first identifier corresponding to the first information and determining a second identifier corresponding to the second information; and pushing the first information and the second information to the call center's web page for display based on the first identifier and the second identifier.

[0096] Optionally, the memory 720 is also used to provide instructions for the processor 710 to process the following processing steps: before pushing the first information and the second information to the call center's web page for display, determining the display position of the first information and the second information; and pushing the first information and the second information to the call center's web page for display according to the display position.

[0097] Optionally, the memory 720 is also used to provide the processor 710 with instructions for processing the following processing steps: obtaining a trigger operation of the user during the answering process, and determining identification information corresponding to the trigger operation; and determining the second information according to the identification information corresponding to the trigger operation.

[0098] Thus, according to this embodiment, in the process of testing the intelligent voice robot, the tester can dial the short number (corresponding to the voice robot) on the FS in the form of a soft phone, and can record the first information related to the robot broadcast audio and the second information related to the user answer audio generated during the interaction, and display the first information and the second information on the web page. Thus, compared with the prior art, this solution can complete the test of the voice robot in the form of a soft phone, and can perform repeated tests many times, so it can save time and cost, and thus speed up the delivery of the product. In addition, this solution can also visualize the information generated during the test, so it is convenient to directly view the test results of each step. Therefore, the technical effect of saving time and cost and facilitating viewing of the test results is achieved. Then, the existing voice robot in the prior art is overly dependent on the telephone line during the test, and problems in the test process need to be repeatedly tested, thus causing time-consuming and labor-intensive technical problems that affect product delivery.

[0099] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0100] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0101] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0102] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0104] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0105] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for testing voice dialogue, It is characterized in that include: In response to a trigger operation of a user dialing a test number on a webpage of a call center, establishing a soft-switch connection with the user; Determine a first audio to be broadcasted to the user and first information related to the first audio; Determining second information related to the second audio according to the second audio responded by the user to the first audio; as well as Pushing the first information and the second information to the webpage of the call center for display; Determining a first audio to be broadcasted to the user includes: Determining the speech text to be broadcasted to the user through a pre-set test process engine; and Performing speech synthesis on the speech text to determine the first audio; Determining first information related to the first audio includes: Determine the speech text corresponding to the first audio, start and end time information of the first audio, indication information of whether the first audio is successfully synthesized, and interruption information of whether the first audio is interrupted; Determining second information related to the second audio includes: Determine a response text corresponding to the second audio, indication information of whether the second audio is successfully converted into text, start and end time information of the second audio, and user intent information contained in the second audio; Pushing the first information and the second information to a webpage of the call center for display includes: Sending the first information and the second information to the system backend of the call center; and Pushing the first information and the second information to the webpage of the call center for display through the system background; Before pushing the first information and the second information to the webpage of the call center for display, the method further includes: Determine the sequence numbers of the first information and the second information; and According to the sequence number, the first information and the second information are pushed to the webpage of the call center for display; Before pushing the first information and the second information to the webpage of the call center for display, the method further includes: Determine a first identifier corresponding to the first information, and determine a second identifier corresponding to the second information; and Pushing the first information and the second information to a webpage of the call center for display according to the first identifier and the second identifier; Before pushing the first information and the second information to the webpage of the call center for display, the method further includes: determining display positions of the first information and the second information; and Pushing the first information and the second information to the webpage of the call center for display according to the display position; Also includes: Acquiring a trigger operation performed by the user during the answering process, and determining identification information corresponding to the trigger operation; and The second information is determined according to identification information corresponding to the trigger operation.

2. A storage medium, It is characterized in that The storage medium includes a stored program, wherein when the program is executed, the method of claim 1 is executed by a processor.

Images