WO2021143095A1 - Dialing test method and apparatus, and computer device and storage medium - Google Patents

Abstract

Disclosed in the present application are a dialing test method and apparatus, and a computer device and a storage medium. The method comprises: obtaining a sustained energy value fed back by a host to be tested; when the fed back sustained energy value is within a preset energy range, establishing a communication connection between a service interface to be tested and said host; monitoring, by means of an audio endpoint, whether said host issues first preset voice data in a communication connection process; when said host issues the first preset voice data, acquiring a first sampling frequency of the first preset voice data, and verifying whether the first sampling frequency reaches a standard; when the first sampling frequency reaches a standard, sending a voice reply to said host, and after obtaining second preset voice data fed back for the voice reply by said host, converting the second preset voice data into text data and then matching the text data with matching content; and when matching succeeds, completing the communication connection after determining that the second preset voice data is errorless. By means of the present application, the call service quality of the host to be tested can be effectively tested.

Description

Dial test method, device, computer equipment and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on January 14, 2020, the application number is 202010037782.1, and the invention title is "Dial test method, device, computer equipment and storage medium", the entire content of which is incorporated by reference In this application.

To

Technical field

This application relates to the field of voice processing in the field of artificial intelligence, and in particular to a dial test method, device, computer equipment, and storage medium.

To

Background technique

With the development of artificial intelligence, there are many intelligent voice robot products or systems on the market. The voice robot products or systems replace humans for customer service and marketing. However, the inventor realizes that whether the service quality of current intelligent voice robot products or systems is normal is to be dialed manually. This method wastes a lot of labor costs and is time-consuming, and in the process of manual dialing, it is necessary Manually aggregate the monitoring information of each component and formulate strategies based on the logic of the aggregated monitoring information, which will cause a serious delay in the final determination of the abnormal service quality of the voice robot, and even the abnormal service quality of the voice robot cannot be detected at all. Therefore, finding a technical solution to solve the above-mentioned problems has become an urgent problem to be solved by those skilled in the art.

To

Summary of the invention

Based on this, it is necessary to address the above technical problems and provide a dial test method, device, computer equipment and storage medium to solve the problem that the existing technology cannot effectively detect the call service quality of the voice robot (that is, the host under test). problem.

A dial test method, including:

Call the service interface to be tested of the host to be tested, obtain the unique identifier of the service interface to be tested, and send a communication connection instruction to the service interface to be tested through the unique identifier;

Monitor the host sound card of the host under test, and obtain the continuous energy value fed back by the host sound card of the host under test within a preset time threshold;

When the sustained energy value fed back by the host sound card within a preset time threshold is within the preset energy range, an answering instruction is sent to the service interface under test, so as to communicate with the service interface under test through the service interface under test. The host to be tested establishes a communication connection;

Monitor through the audio endpoint whether the host under test sends out the first preset voice data during the communication connection process;

When the host under test sends out the first preset voice data, collecting the first sampling frequency of the first preset voice data, and verifying whether the first sampling frequency meets the standard according to the preset background frequency range;

When the first sampling frequency reaches the standard, send a voice response corresponding to the first preset voice data to the host under test according to a preset template, and obtain the first feedback from the host under test for the voice response 2. preset voice data, converting the second preset voice data into text data, and matching the text data with matching content corresponding to the preset template;

When all the text data and the matching content corresponding to the preset template are successfully matched, it is determined that the second preset voice data fed back by the host to be tested is correct.

A dial test device, including:

A sending module, configured to call the service interface under test of the host under test, obtain the unique identifier of the service interface under test, and send a communication connection instruction to the service interface under test through the unique identifier;

An obtaining module, configured to monitor the host sound card of the host under test, and obtain the continuous energy value fed back by the host sound card of the host under test within a preset time threshold;

The trigger module is configured to send an answering instruction to the service interface to be tested when the sustained energy value fed back by the host sound card within a preset time threshold is within the preset energy range, so as to pass the test The service interface establishes a communication connection with the host to be tested;

The monitoring module is configured to monitor whether the host under test sends out the first preset voice data during the communication connection process through the audio endpoint;

The collection module is configured to collect the first sampling frequency of the first preset voice data when the host under test sends out the first preset voice data, and verify the first sampling frequency according to the preset background frequency range. Whether the sampling frequency meets the standard;

The matching module is configured to send a voice response corresponding to the first preset voice data to the host under test according to a preset template when the first sampling frequency reaches the standard, and obtain the host under test for the voice Replying to the second preset voice data fed back, converting the second preset voice data into text data, and matching the text data with matching content corresponding to the preset template;

The first determining module is configured to determine that the second preset voice data fed back by the host to be tested is correct when all the text data and the matching content corresponding to the preset template are successfully matched.

A computer device includes a memory, a processor, and a computer program that is stored in the memory and can run on the processor, and the processor implements the above dial test method when the computer program is executed.

A computer-readable storage medium that stores a computer program that implements the above dial test method when the computer program is executed by a processor.

A computer device includes a memory, a processor, and computer-readable instructions that are stored in the memory and can run on the processor, and the processor implements the following steps when the processor executes the computer-readable instructions:

Call the service interface to be tested of the host to be tested, obtain the unique identifier of the service interface to be tested, and send a communication connection instruction to the service interface to be tested through the unique identifier;

Monitor the host sound card of the host under test, and obtain the continuous energy value fed back by the host sound card of the host under test within a preset time threshold;

When the sustained energy value fed back by the host sound card within a preset time threshold is within the preset energy range, an answering instruction is sent to the service interface under test, so as to communicate with the service interface under test through the service interface under test. The host to be tested establishes a communication connection;

Monitor through the audio endpoint whether the host under test sends out the first preset voice data during the communication connection process;

When the host under test sends out the first preset voice data, collecting the first sampling frequency of the first preset voice data, and verifying whether the first sampling frequency meets the standard according to the preset background frequency range;

When the first sampling frequency reaches the standard, send a voice response corresponding to the first preset voice data to the host under test according to a preset template, and obtain the first feedback from the host under test for the voice response 2. preset voice data, converting the second preset voice data into text data, and matching the text data with matching content corresponding to the preset template;

When all the text data and the matching content corresponding to the preset template are successfully matched, it is determined that the second preset voice data fed back by the host to be tested is correct.

One or more readable storage media storing computer readable instructions, when the computer readable instructions are executed by one or more processors, the one or more processors execute the following steps:

Call the service interface to be tested of the host to be tested, obtain the unique identifier of the service interface to be tested, and send a communication connection instruction to the service interface to be tested through the unique identifier;

Monitor the host sound card of the host under test, and obtain the continuous energy value fed back by the host sound card of the host under test within a preset time threshold;

When the sustained energy value fed back by the host sound card within a preset time threshold is within the preset energy range, an answering instruction is sent to the service interface under test, so as to communicate with the service interface under test through the service interface under test. The host to be tested establishes a communication connection;

Monitor through the audio endpoint whether the host under test sends out the first preset voice data during the communication connection process;

When the host under test sends out the first preset voice data, collecting the first sampling frequency of the first preset voice data, and verifying whether the first sampling frequency meets the standard according to the preset background frequency range;

When the first sampling frequency reaches the standard, send a voice response corresponding to the first preset voice data to the host under test according to a preset template, and obtain the first feedback from the host under test for the voice response 2. preset voice data, converting the second preset voice data into text data, and matching the text data with matching content corresponding to the preset template;

When all the text data and the matching content corresponding to the preset template are successfully matched, it is determined that the second preset voice data fed back by the host to be tested is correct.

The above dial test method, device, computer equipment and storage medium use the audio endpoint to detect the continuous energy value to prove whether the host under test where the sound card of the host is located can be called successfully, so as to ensure the called function of the host under test; Whether the test host (can be understood as a virtual voice robot) can provide normal voice services during the communication connection process, so as to ensure that the host under test can perform normal conversation services; verify the first through the preset background frequency range Whether the sampling frequency is up to standard, so as to ensure that the first sampling frequency can be maintained in a frequency range that is acceptable to the human ear (the first sampling frequency that is too high or too low and the interference of the background frequency will affect the acceptance of the human ear ), which is convenient for the user to communicate with the host under test, which can improve the user experience. In general, the present invention can ensure the call service quality of the host to be tested.

The details of one or more embodiments of the present application are presented in the following drawings and description, and other features and advantages of the present application will become apparent from the description, drawings and claims.

To

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings that need to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative labor.

FIG. 1 is a schematic diagram of an application environment of the dial test method in an embodiment of the present application;

FIG. 2 is a flowchart of a dial test method in an embodiment of the present application;

3 is a schematic diagram of the structure of a dial test device in an embodiment of the present application;

Fig. 4 is a schematic diagram of a computer device in an embodiment of the present application.

To

Detailed ways

The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

The dial test method provided in this application can be applied in the application environment as shown in Fig. 1, in which the client communicates with the server through the network. Among them, the client can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented as an independent server or a server cluster composed of multiple servers.

In one embodiment, as shown in FIG. 2, a dial test method is provided. The method is applied to the server in FIG. 1 as an example for description, including the following steps S10-S70:

S10 Invoke the service interface under test of the host under test, obtain the unique identifier of the service interface under test, and send a communication connection instruction to the service interface under test through the unique identifier;

Understandably, the host under test has the function of providing an intelligent voice response to the outside world, and the host under test can be used as a customer service robot (that is, a virtual voice robot) to complete consultation responses, marketing, and surveys; The unique identifier is the identification code of the service interface to be tested, through which the communication connection instruction can be sent to the designated service interface to be tested. In this embodiment, the purpose of sending a communication connection instruction to the service interface under test is to perform a dial test task and test the intelligent voice reply function of the service interface under test of the host under test.

S20 , Monitor the host sound card of the host under test, and obtain the continuous energy value fed back by the host sound card of the host under test within a preset time threshold;

Understandably, the difference between the mute point and the sound point can be determined through audio endpoint technology. The mute point refers to the endpoint where the host sound card does not feedback sound, and the sound point refers to the endpoint where the sound feedback from the host sound card is located, regardless of whether it is The mute point or the sound point can be determined by the energy component associated with the audio endpoint technology (the energy value is determined by the energy amplitude) (that is, the energy value is determined). An endpoint can represent an energy value, and each The endpoint can be located in one of the voice frames, and each voice frame contains the same number of endpoints, so the energy value of a voice frame can be calculated). At this time, the continuous energy value of the host sound card feedback within the preset time threshold can be obtained (possibly The sustained energy value corresponding to at least one speech frame composed of multiple consecutive silent points may also be the sustained energy value corresponding to at least one speech frame composed of multiple consecutive sound points).

S30 , When the sustained energy value fed back by the host sound card within the preset time threshold is within the preset energy range, the answering instruction is sent to the service interface under test, so as to communicate with the service interface under test through the service interface under test. The host to be tested establishes a communication connection;

Understandably, a preset energy range is set by the average energy value of the sound feedback from the host sound card within the preset time threshold and the empirical data value (because the host sound card is muted, the host under test is The energy value determined in the energy component is significantly smaller than the energy value determined in the energy component associated with the audio endpoint when the host sound card is feeding back sound. Therefore, the preset energy range will be based on the above mentioned value. A comparison standard is set based on the sustained energy value corresponding to at least one speech frame composed of the received sound points). Understandably, the audio endpoint can determine the front-end point where the voice starts and the back-end point where the voice ends. However, in this embodiment, there is no need to determine the back-end point where the voice ends. You only need to determine the front-end point where the voice starts (the aforementioned sound Point) and setting a preset time threshold can realize the function of judging whether the host under test where the host sound card is located can be called.

In another embodiment, when the sustained energy value fed back by the host sound card within a preset time threshold is less than the preset energy range, a reminder message that the call cannot be made is sent to the preset person, and the communication connection is terminated. , The host under test where the host sound card is located cannot realize the called function.

S40 , Monitoring through the audio endpoint whether the host under test sends out the first preset voice data during the communication connection process;

Understandably, when the host under test sends out a sentence of first preset voice data, an instantaneous energy value corresponding to the first preset voice data can be monitored through the audio endpoint. The first preset voice data can be the host's A feedback polite phrase, when it is recognized that the instantaneous energy value of the first preset voice data corresponding to the polite phrase reaches the preset energy threshold, it can be determined that the host under test is normal in the communication connection process. In this embodiment, the audio endpoint is used to determine whether the host under test can perform normal conversation services during the communication connection process.

Further, the detecting and monitoring whether the host to be tested sends out the first preset voice data during the communication connection process through the audio endpoint detection includes:

Monitoring whether the instantaneous energy value fed back by the host under test reaches a preset energy threshold through audio endpoint detection;

When the feedback instantaneous energy value reaches the preset energy threshold, it is determined that the host under test emits the first preset voice data.

The specific method in this embodiment is the same as that of step S30, except that in this embodiment, only the instantaneous energy value corresponding to a speech frame formed by the first sound point needs to be determined.

S50 , When the host under test sends out the first preset voice data, collect the first sampling frequency of the first preset voice data, and verify whether the first sampling frequency meets the standard according to the preset background frequency range ；

Understandably, the first sampling frequency refers to the number of sound samples collected by the server per second, which describes the sound quality and tone of the sound file, and measures the quality standards of the sound card and the sound file.

In this embodiment, when the host under test sends out the first preset voice data, in order to monitor the first sampling frequency of the first preset voice data sent by the host under test, the first sampling frequency is verified through the preset background frequency range Whether it meets the standard, it can be determined whether the first sampling frequency can eliminate the interference of the background frequency under the preset background frequency range determined according to the background frequency (that is, the second sampling frequency of the background voice mentioned later), so that the current The first sampling frequency can be maintained in a frequency range that is acceptable to human ears (the first sampling frequency that is too high or too low and the interference of the background frequency will affect the acceptance of the human ear), which is convenient for subsequent users and waiting During the communication process of the test host, the user experience can be improved.

In another embodiment, when the host under test does not send out the first preset voice data, a silent warning prompt message is sent to the preset personnel, and the communication connection is terminated. This embodiment can explain that the host to be tested has a problem (for example, the host to be tested crashes, etc.), which causes the host to be unable to make a sound.

Further, when the host under test sends out the first preset voice data, the first sampling frequency of the first preset voice data is collected, and the first sampling frequency is verified according to the preset background frequency range. Whether the sampling frequency meets the standard, including:

Acquire a background sound when the host under test emits the first preset voice data, collect a second sampling frequency of the background voice, and determine the background frequency range by the second sampling frequency.

In this embodiment, because the background sound can affect the judgment of whether the first sampling frequency is up to the standard to a certain extent, and the second sampling frequency corresponding to the background sound is also in a state of being subject to interference from external factors at any time to change and fluctuate, Therefore, the background frequency range can be determined in real time through the second sampling frequency of the currently collected background sound. In this way, this background frequency range will be better suited for judging whether the first sampling frequency meets the standard.

S60 When the first sampling frequency reaches the standard, send a voice response corresponding to the first preset voice data to the host under test according to a preset template, and obtain feedback from the host under test for the voice response Second preset voice data, converting the second preset voice data into text data, and matching the text data with matching content corresponding to the preset template;

Understandably, the noise data can be background sounds or other noises; the server can select a set of specific application scenario templates from the preset templates according to preset selection rules (for example, a consultation for a problem), and each preset The templates have preset matching content (which can be understood as a standard answer); the host to be tested can recognize and understand the content of the voice response corresponding to the first preset voice data sent by the server, and the method for the host to be tested to identify The semantic recognition model can be used for recognition; the second preset voice data feedback by the host to be tested for the voice response must be for the matching content corresponding to the selected preset template (if the text data corresponding to the second preset voice data and the preset Assuming that the matching content corresponding to the template fails to match, it means that the host under test does not answer the question due to the existence of the problem or the host under test cannot send out specific and complete second preset voice data).

In this embodiment, when the first sampling frequency reaches the standard, in order to check whether the host under test can give correct responses to the external question and answer (feedback the second preset voice data), it ensures that the host under test can conduct normal conversations. service status.

Further, the acquiring the second preset voice data fed back by the host under test for the voice response includes:

Obtain a simulated manual component, and use the time point when the simulated manual component completes a voice response to the first preset voice data of the host under test as the start time point of the unprocessed voice data fed back by the host under test, Taking the time point when the simulated manual component starts the next voice response to the unprocessed voice data as the end time point of the unprocessed voice data fed back by the host to be tested, it is acquired at the start time point and the time point. The unprocessed voice data between the end time points; the unprocessed voice data includes a noise data segment;

Determine the spectrum of all voice segments in the unprocessed voice data, clear the noise data segment in the unprocessed voice data according to the spectrum of the voice segment, and send the host under test to the voice response The feedback unprocessed voice data that does not include the noise data segment is recorded as second preset voice data.

Understandably, the simulated manual component can be called by the server, and the server can make the server complete the voice response to the first preset voice data of the host under test through the simulated manual component, and the simulated manual component is the voice response according to the preset template .

Specifically, the start time point and the end time point of a piece of unprocessed voice data are first determined by the time point, and the segment of unprocessed voice data containing the noise data segment between the start time point and the end time point is obtained ; Then the noise data segment is determined by a similar method to the endpoint (the noise data segment in the unprocessed voice data is determined by a voice data that only contains the noise data segment), and the frequency spectrum and inclusion of the noise data segment are determined by Fourier transform After the spectrum of the unprocessed voice data in the noise data segment, the spectrum of the unprocessed voice data containing the noise data segment is subtracted from the spectrum of the noise data segment in the spectrum to realize the removal of the noise data segment, and the first voice after noise reduction is obtained. 2. The frequency spectrum of the preset voice data; finally, the frequency domain where the second preset voice data is located is converted back to the time domain through an inverse Fourier transform to obtain the second preset voice data after voice noise reduction.

In this embodiment, the second preset voice data that does not contain the noise data segment can be determined, which can facilitate the server to better recognize the second preset voice data and completely convert the second preset voice data into text data.

Further, after obtaining the second preset voice data fed back by the host under test for the voice response, the method further includes:

Collecting the third sampling frequency of the second preset voice data in real time, and detecting whether the third sampling frequency falls within the background frequency range;

When the third sampling frequency corresponding to the second preset voice data does not fall within the background frequency range, a frequency modulation component is called and the communication connection is frequency modulated through the frequency modulation component.

In this embodiment, when the third sampling frequency does not fall within the background frequency range, the frequency modulation component can be used to frequency modulate the communication connection. When the third sampling frequency corresponding to the second preset voice data does not fall within the background frequency range , The third sampling frequency corresponding to the second preset voice data can be maintained in the background frequency range to maintain good call quality. In another embodiment, when the third sampling frequency corresponding to the second preset voice data falls within the background frequency range, there is no need to call a frequency modulation component and use the frequency modulation component to frequency the communication connection. modulation.

S70 When all the text data and the matching content corresponding to the preset template are successfully matched, it is determined that the second preset voice data fed back by the host to be tested is correct.

In this embodiment, when all the text data and the matching content corresponding to the preset template are successfully matched, it is possible to determine that there is no problem with the host under test through the current dial test task of the host under test.

Further, after the matching the text data with the matching content corresponding to the preset template, the method further includes:

When the text data fails to match the matching content corresponding to the preset template, a preset prompting manner is used to send a prompt message indicating that the second preset voice data is incorrect to the preset personnel terminal.

Understandably, the preset prompt methods include, but are not limited to, email and short message prompts. In this embodiment, it is to give the preset personnel a vigilant function.

Further, after the text data fails to match the matching content corresponding to the preset template, the method further includes:

Determining, according to the text data, whether the second preset voice data of the host to be tested has a packet loss phenomenon corresponding to a preset packet loss cause;

When a packet loss phenomenon corresponding to a preset packet loss cause occurs, decode the second preset voice data fed back by the host to be tested, and determine the second preset voice based on the decoded information obtained by decoding Packet loss voice frames with packet loss in the data;

Determine a replacement voice frame according to the state information of the previous voice frame of the packet loss voice frame, and replace the packet loss voice frame in the second preset voice data with the replacement voice frame.

Specifically, firstly, analyze the second preset voice data fed back by the host under test for voice responses during the communication connection process, and when the second preset voice data is not specific and complete voice data, it can be determined that the host under test is A preset cause of packet loss occurs in the communication connection (part or all of the voice frames in the second preset voice data cause packet loss due to the interference of the external environment. The interference of the above external environment includes physical line failure, equipment failure, virus attack, Routing information error and other interference); then decode the second preset voice data (decoding is the reverse process of encoding, and at the same time remove the noise data mixed in the bit stream during the propagation process, and use the decoding table to translate the text into a group of groups The process of translating a series of signals representing a certain item of information into text by digital or using a decoding table is called decoding, and decoding is usually a process in which less input becomes more output), and it can be used in the decoding process. Acquire the state information of each voice frame of the second preset voice data (state information includes LPC information and decoded incomplete signal, etc., where LPC information is linear predictive coding information), and determine the voice by calculating the bit rate of each voice frame Whether the frame is lost, the speech frame with the bit rate loss is regarded as the lost speech frame with packet loss; finally the packet loss compensation unit is made to reconstruct the lost speech frame according to the state information of the previous speech frame of the lost packet speech frame Then, the packet loss compensation unit reconstructs the replacement voice frame through the LPC information and the torn signal. At this time, the server replaces the lost voice frame with the replacement voice frame.

In this embodiment, when the packet loss phenomenon corresponding to the preset packet loss reason occurs, the lost packet voice frame in the second preset voice data can be repaired, so as to ensure the integrity of the second preset voice data sex.

Further, the replacement voice frame is determined according to the state information of the previous voice frame of the packet loss voice frame, and the packet loss voice frame in the second preset voice data is replaced with the After replacing the voice frame, it also includes:

The second preset voice data including the replacement voice frame is converted back into new text data, and the new text data is matched with the matching content corresponding to the preset template.

In this embodiment, referring to step S60, the new text data can be further matched with the matching content corresponding to the preset template. After that, it can be ensured whether the repaired second preset voice data still has a preset Set the packet loss phenomenon corresponding to the packet loss reason. When the packet loss phenomenon corresponding to the preset packet loss reason does not occur, the communication process can continue to run; when the packet loss phenomenon corresponding to the preset packet loss reason occurs again, The preset prompt method is used to prompt the preset personnel that the second preset voice data is incorrect, so as to prompt the preset personnel to perform the next step of processing the problem (such as manual processing).

Further, after the step S70, it further includes:

Call a preset number of outbound call components, and send a communication connection instruction to the service interface under test of the host under test through the outbound call component, and determine the current communication load information of the service interface under test The maximum number of outbound calls currently loadable by the service interface to be tested, and the number of outbound call components established with the host under test through all the service interfaces to be tested is determined according to the maximum number of outbound calls.

Understandably, the communication load information of the host to be tested refers to how many outbound components can be simultaneously loaded by all the service interfaces of the host to be tested. The maximum number of outbound calls determined in this embodiment can maintain the host under test in an optimal operating state, avoid affecting the operating efficiency of the host under test, and can also serve as the largest number of consulting users at the same time (one outbound component can be On behalf of a customer) for better communication connection services.

In summary, the above provides a dial test method, which uses the audio endpoint to detect the continuous energy value to prove whether the host under test where the host sound card is located can be called successfully, so as to ensure the called function of the host under test; monitor through the audio endpoint Whether the host under test (can be understood as a virtual voice robot) can perform normal voice services during the communication connection process, so as to ensure that the host under test can perform normal conversation services; verify the first through the preset background frequency range A sampling frequency is up to the standard, so as to ensure that the first sampling frequency can be maintained in a frequency range that is acceptable to human ears (too high or low first sampling frequency and interference from background frequencies will affect the acceptance of human ears Degree), to facilitate the communication between the user and the host under test, which can improve the user experience. In general, this application can ensure the call service quality of the host under test.

It should be understood that the size of the sequence number of each step in the foregoing embodiment does not mean the order of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

To

In one embodiment, a dial test device is provided, and the dial test device corresponds to the dial test method in the above-mentioned embodiment one-to-one. As shown in FIG. 3, the dial test device includes a sending module 11, an acquisition module 12, a trigger module 13, a monitoring module 14, an acquisition module 15, a matching module 16 and a first determination module 17. The detailed description of each functional module is as follows:

The sending module 11 is configured to call the service interface under test of the host under test, obtain the unique identifier of the service interface under test, and send a communication connection instruction to the service interface under test through the unique identifier;

The obtaining module 12 is configured to monitor the host sound card of the host under test, and obtain the continuous energy value fed back by the host sound card of the host under test within a preset time threshold;

The trigger module 13 is configured to send an answering instruction to the service interface to be tested when the sustained energy value fed back by the host sound card within a preset time threshold is within the preset energy range, so as to pass the waiting The test service interface establishes a communication connection with the host to be tested;

The monitoring module 14 is configured to monitor whether the host to be tested sends out the first preset voice data during the communication connection process through the audio endpoint;

The collection module 15 is configured to collect the first sampling frequency of the first preset voice data when the host to be tested emits the first preset voice data, and verify the first sampling frequency according to the preset background frequency range 1. Whether the sampling frequency meets the standard;

The matching module 16 is configured to send a voice response corresponding to the first preset voice data to the host under test according to a preset template when the first sampling frequency meets the standard, and obtain that the host under test responds to the Voice reply to the second preset voice data fed back, convert the second preset voice data into text data, and match the text data with matching content corresponding to the preset template;

The first determining module 17 is configured to determine that the second preset voice data fed back by the host to be tested is correct when all the text data and the matching content corresponding to the preset template are successfully matched.

Further, the dial test device further includes:

The verification module is configured to obtain the background sound when the host under test emits the first preset voice data, collect the second sampling frequency of the background voice, and determine the background frequency range by the second sampling frequency.

Further, the matching module includes:

The matching sub-module is used to obtain an analog manual component, and use the time point when the analog manual component completes a voice response to the first preset voice data of the host under test as the unprocessed voice feedback from the host under test The start time point of the data, the time point at which the simulated manual component starts the next voice response for the unprocessed voice data is the end time point of the unprocessed voice data fed back by the host under test, and the location is acquired The unprocessed voice data between the start time point and the end time point; the unprocessed voice data includes a noise data segment;

The recording sub-module is used to determine the frequency spectrum of all voice segments in the unprocessed voice data, clear the noise data segment in the unprocessed voice data according to the frequency spectrum of the voice segment, and remove the to-be-tested The unprocessed voice data that does not include the noise data segment that is fed back by the host for the voice response is recorded as second preset voice data.

Further, the dial test device further includes:

The detection module is configured to collect the third sampling frequency of the second preset voice data in real time, and detect whether the third sampling frequency falls within the background frequency range;

The modulation module is configured to call a frequency modulation component and perform frequency modulation on the communication connection through the frequency modulation component when the third sampling frequency corresponding to the second preset voice data does not fall within the background frequency range.

Further, the dial test device further includes:

The prompt module is configured to send a prompt message indicating that the second preset voice data is incorrect in a preset prompt manner to a preset personnel terminal when the text data fails to match the matching content corresponding to the preset template.

Further, the dial test device further includes:

The second determining module is configured to determine, according to the text data, whether the second preset voice data of the host to be tested has a packet loss phenomenon corresponding to a preset packet loss cause;

The third determining module is configured to decode the second preset voice data fed back by the host to be tested when a packet loss phenomenon corresponding to a preset packet loss cause occurs, and determine the result from the decoding information obtained by the decoding Packet loss voice frames in the second preset voice data where packet loss occurs;

The replacement module is configured to determine a replacement voice frame according to the state information of the voice frame before the packet loss voice frame, and replace the packet loss voice frame in the second preset voice data with the Replace speech frame.

Further, the dial test device further includes:

The fourth determining module is configured to call a preset number of outbound call components, and send a communication connection instruction to the service interface under test of the host under test through the outbound call component, and according to the service interface under test The current communication load information determines the maximum number of outbound calls that the service interface under test can currently load, and determines, according to the maximum number of outbound calls, to establish the outbound call component with the host under test through all the service interfaces under test quantity.

For the specific definition of the dial test device, please refer to the above definition of the dial test method, which will not be repeated here. Each module in the above dial test device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

To

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 4. The computer equipment includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes computer readable instructions and internal memory. The computer readable instructions are stored with an operating system, computer readable instructions and a database. The internal memory provides an environment for the operation of the operating system and the computer-readable instructions in the computer-readable instructions. The database of the computer equipment is used to store multiple pieces of historical test data, and each piece of historical test data corresponds to a test problem record. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer readable instruction is executed by the processor to realize a dial test method.理method. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored on the memory and capable of running on the processor. The processor executes the computer-readable instructions to implement the above-mentioned embodiments. State the dial test method.

In one embodiment, one or more readable storage media storing computer readable instructions are provided. The readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage. Medium; the readable storage medium stores computer readable instructions, and when the computer readable instructions are executed by one or more processors, the one or more processors implement the dial test method described in the above embodiments.

A person of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by computer-readable instructions to instruct relevant hardware. The computer-readable instructions can be stored in a non-volatile computer. In a readable storage medium or a volatile readable storage medium, when the computer readable instruction is executed, it may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not a limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the division of the above functional units and modules is used as an example. In practical applications, the above functions can be allocated to different functional units and modules as needed. Module completion, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still implement the foregoing The technical solutions recorded in the examples are modified, or some of the technical features are equivalently replaced; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the application, and should be included in Within the scope of protection of this application .

Claims (20)

1. A dial test method, which includes:

   Call the service interface to be tested of the host to be tested, obtain the unique identifier of the service interface to be tested, and send a communication connection instruction to the service interface to be tested through the unique identifier;

   Monitor the host sound card of the host under test, and obtain the continuous energy value fed back by the host sound card of the host under test within a preset time threshold;

   When the sustained energy value fed back by the host sound card within a preset time threshold is within the preset energy range, an answering instruction is sent to the service interface under test, so as to communicate with the service interface under test through the service interface under test. The host to be tested establishes a communication connection;

   Monitor through the audio endpoint whether the host under test sends out the first preset voice data during the communication connection process;

   When the host under test sends out the first preset voice data, collecting the first sampling frequency of the first preset voice data, and verifying whether the first sampling frequency meets the standard according to the preset background frequency range;

   When the first sampling frequency reaches the standard, send a voice response corresponding to the first preset voice data to the host under test according to a preset template, and obtain the first feedback from the host under test for the voice response 2. preset voice data, converting the second preset voice data into text data, and matching the text data with matching content corresponding to the preset template;

   When all the text data and the matching content corresponding to the preset template are successfully matched, it is determined that the second preset voice data fed back by the host to be tested is correct.
2. The dial test method according to claim 1, wherein, after the host under test sends out the first preset voice data, the method further comprises:

   Acquire a background sound when the host under test emits the first preset voice data, collect a second sampling frequency of the background voice, and determine the background frequency range by the second sampling frequency.
3. The dial test method according to claim 1, wherein the obtaining the second preset voice data fed back by the host under test for the voice response comprises:

   Obtain a simulated manual component, and use the time point when the simulated manual component completes a voice response to the first preset voice data of the host under test as the start time point of the unprocessed voice data fed back by the host under test, Taking the time point when the simulated manual component starts the next voice response to the unprocessed voice data as the end time point of the unprocessed voice data fed back by the host to be tested, it is acquired at the start time point and the time point. The unprocessed voice data between the end time points; the unprocessed voice data includes a noise data segment;

   Determine the spectrum of all voice segments in the unprocessed voice data, clear the noise data segment in the unprocessed voice data according to the spectrum of the voice segment, and send the host under test to the voice response The feedback unprocessed voice data that does not include the noise data segment is recorded as second preset voice data.
4. The dial test method according to claim 1, wherein after obtaining the second preset voice data fed back by the host under test for the voice response, the method further comprises:

   Collecting the third sampling frequency of the second preset voice data in real time, and detecting whether the third sampling frequency falls within the background frequency range;

   When the third sampling frequency corresponding to the second preset voice data does not fall within the background frequency range, a frequency modulation component is called and the communication connection is frequency modulated through the frequency modulation component.
5. The dial test method according to claim 1, wherein after the matching the text data with the matching content corresponding to the preset template, the method further comprises:

   When the text data fails to match the matching content corresponding to the preset template, a preset prompt manner is used to send a prompt message indicating that the second preset voice data is incorrect to the preset personnel terminal.
6. The dial test method according to claim 5, wherein after the matching content corresponding to the text data and the preset template fails to match, the method further comprises:

   Determining, according to the text data, whether the second preset voice data of the host to be tested has a packet loss phenomenon corresponding to a preset packet loss cause;

   When a packet loss phenomenon corresponding to a preset packet loss cause occurs, decode the second preset voice data fed back by the host to be tested, and determine the second preset voice based on the decoded information obtained by decoding Packet loss voice frames with packet loss in the data;

   Determine a replacement voice frame according to the state information of the previous voice frame of the packet loss voice frame, and replace the packet loss voice frame in the second preset voice data with the replacement voice frame.
7. The dial test method according to claim 1, wherein after determining that the second preset voice data fed back by the host to be tested is correct, the method further comprises:

   Call a preset number of outbound call components, and send a communication connection instruction to the service interface under test of the host under test through the outbound call component, and determine the current communication load information of the service interface under test The maximum number of outbound calls currently loadable by the service interface to be tested, and the number of outbound call components established with the host under test through all the service interfaces to be tested is determined according to the maximum number of outbound calls.
8. A dial test device, which includes:

   A sending module, configured to call the service interface under test of the host under test, obtain the unique identifier of the service interface under test, and send a communication connection instruction to the service interface under test through the unique identifier;

   An obtaining module, configured to monitor the host sound card of the host under test, and obtain the continuous energy value fed back by the host sound card of the host under test within a preset time threshold;

   The trigger module is configured to send an answering instruction to the service interface under test when the sustained energy value fed back by the host sound card within a preset time threshold remains within the preset energy range, so as to pass the test The service interface establishes a communication connection with the host to be tested;

   The monitoring module is configured to monitor whether the host under test sends out the first preset voice data during the communication connection process through the audio endpoint;

   The collection module is configured to collect the first sampling frequency of the first preset voice data when the host under test sends out the first preset voice data, and verify the first sampling frequency according to the preset background frequency range. Whether the sampling frequency meets the standard;

   The matching module is configured to send a voice response corresponding to the first preset voice data to the host under test according to a preset template when the first sampling frequency reaches the standard, and obtain the host under test for the voice Replying to the second preset voice data fed back, converting the second preset voice data into text data, and matching the text data with matching content corresponding to the preset template;

   The first determining module is configured to determine that the second preset voice data fed back by the host to be tested is correct when all the text data and the matching content corresponding to the preset template are successfully matched.
9. A computer device includes a memory, a processor, and computer-readable instructions that are stored in the memory and can run on the processor, wherein the processor implements the following steps when the processor executes the computer-readable instructions:

   Call the service interface to be tested of the host to be tested, obtain the unique identifier of the service interface to be tested, and send a communication connection instruction to the service interface to be tested through the unique identifier;

   Monitor the host sound card of the host under test, and obtain the continuous energy value fed back by the host sound card of the host under test within a preset time threshold;

   When the sustained energy value fed back by the host sound card within a preset time threshold is within the preset energy range, an answering instruction is sent to the service interface under test, so as to communicate with the service interface under test through the service interface under test. The host to be tested establishes a communication connection;

   Monitor through the audio endpoint whether the host under test sends out the first preset voice data during the communication connection process;

   When the host under test sends out the first preset voice data, collecting the first sampling frequency of the first preset voice data, and verifying whether the first sampling frequency meets the standard according to the preset background frequency range;

   When the first sampling frequency reaches the standard, send a voice response corresponding to the first preset voice data to the host under test according to a preset template, and obtain the first feedback from the host under test for the voice response 2. preset voice data, converting the second preset voice data into text data, and matching the text data with matching content corresponding to the preset template;

   When all the text data and the matching content corresponding to the preset template are successfully matched, it is determined that the second preset voice data fed back by the host to be tested is correct.
10. 9. The computer device according to claim 9, wherein the following steps are further implemented when the processor executes the computer-readable instruction after the host under test sends out the first preset voice data:

    Acquire a background sound when the host under test emits the first preset voice data, collect a second sampling frequency of the background voice, and determine the background frequency range by the second sampling frequency.
11. 9. The computer device according to claim 9, wherein said acquiring the second preset voice data fed back by said host under test for said voice response comprises:

    Obtain a simulated manual component, and use the time point when the simulated manual component completes a voice response to the first preset voice data of the host under test as the start time point of the unprocessed voice data fed back by the host under test, Taking the time point when the simulated manual component starts the next voice response to the unprocessed voice data as the end time point of the unprocessed voice data fed back by the host to be tested, it is acquired at the start time point and the time point. The unprocessed voice data between the end time points; the unprocessed voice data includes a noise data segment;

    Determine the spectrum of all voice segments in the unprocessed voice data, clear the noise data segment in the unprocessed voice data according to the spectrum of the voice segment, and send the host under test to the voice response The feedback unprocessed voice data that does not include the noise data segment is recorded as second preset voice data.
12. The computer device according to claim 9, wherein, after the acquisition of the second preset voice data fed back by the host under test for the voice response, when the processor executes the computer-readable instruction, it also implements The following steps:

    Collecting the third sampling frequency of the second preset voice data in real time, and detecting whether the third sampling frequency falls within the background frequency range;

    When the third sampling frequency corresponding to the second preset voice data does not fall within the background frequency range, a frequency modulation component is called and the communication connection is frequency modulated through the frequency modulation component.
13. 9. The computer device according to claim 9, wherein, after the matching content corresponding to the preset template is matched between the text data, the processor further implements the following steps when executing the computer-readable instruction:

    When the text data fails to match the matching content corresponding to the preset template, a preset prompt manner is used to send a prompt message indicating that the second preset voice data is incorrect to the preset personnel terminal.
14. 15. The computer device according to claim 13, wherein, after the text data fails to match the matching content corresponding to the preset template, the processor further implements the following steps when executing the computer readable instruction:

    Determining, according to the text data, whether the second preset voice data of the host to be tested has a packet loss phenomenon corresponding to a preset packet loss cause;

    When a packet loss phenomenon corresponding to a preset packet loss cause occurs, decode the second preset voice data fed back by the host to be tested, and determine the second preset voice based on the decoded information obtained by decoding Packet loss voice frames with packet loss in the data;

    Determine a replacement voice frame according to the state information of the previous voice frame of the packet loss voice frame, and replace the packet loss voice frame in the second preset voice data with the replacement voice frame.
15. One or more readable storage media storing computer readable instructions, where when the computer readable instructions are executed by one or more processors, the one or more processors execute the following steps:

    Call the service interface to be tested of the host to be tested, obtain the unique identifier of the service interface to be tested, and send a communication connection instruction to the service interface to be tested through the unique identifier;

    Monitor the host sound card of the host under test, and obtain the continuous energy value fed back by the host sound card of the host under test within a preset time threshold;

    When the sustained energy value fed back by the host sound card within a preset time threshold is within the preset energy range, an answering instruction is sent to the service interface under test, so as to communicate with the service interface under test through the service interface under test. The host to be tested establishes a communication connection;

    Monitor through the audio endpoint whether the host under test sends out the first preset voice data during the communication connection process;

    When the host under test sends out the first preset voice data, collecting the first sampling frequency of the first preset voice data, and verifying whether the first sampling frequency meets the standard according to the preset background frequency range;

    When the first sampling frequency reaches the standard, send a voice response corresponding to the first preset voice data to the host under test according to a preset template, and obtain the first feedback from the host under test for the voice response 2. preset voice data, converting the second preset voice data into text data, and matching the text data with matching content corresponding to the preset template;

    When all the text data and the matching content corresponding to the preset template are successfully matched, it is determined that the second preset voice data fed back by the host to be tested is correct.
16. The readable storage medium according to claim 15, wherein, after the computer-readable instruction is executed by one or more processors after the host under test sends out the first preset voice data, So that the one or more processors further execute the following steps:

    Acquire a background sound when the host under test emits the first preset voice data, collect a second sampling frequency of the background voice, and determine the background frequency range by the second sampling frequency.
17. 15. The readable storage medium according to claim 15, wherein said acquiring the second preset voice data fed back by said host under test for said voice response comprises:

    Obtain a simulated manual component, and use the time point when the simulated manual component completes a voice response to the first preset voice data of the host under test as the start time point of the unprocessed voice data fed back by the host under test, Taking the time point when the simulated manual component starts the next voice response to the unprocessed voice data as the end time point of the unprocessed voice data fed back by the host to be tested, it is acquired at the start time point and the time point. The unprocessed voice data between the end time points; the unprocessed voice data includes a noise data segment;

    Determine the spectrum of all voice segments in the unprocessed voice data, clear the noise data segment in the unprocessed voice data according to the spectrum of the voice segment, and send the host under test to the voice response The feedback unprocessed voice data that does not include the noise data segment is recorded as second preset voice data.
18. The readable storage medium according to claim 15, wherein, after obtaining the second preset voice data fed back by the host under test for the voice response, the computer-readable instruction is processed by one or more When the processor executes, the one or more processors further execute the following steps:

    Collecting the third sampling frequency of the second preset voice data in real time, and detecting whether the third sampling frequency falls within the background frequency range;

    When the third sampling frequency corresponding to the second preset voice data does not fall within the background frequency range, a frequency modulation component is called and the communication connection is frequency modulated through the frequency modulation component.
19. The readable storage medium according to claim 15, wherein, after the matching content corresponding to the preset template is matched with the text data, when the computer-readable instructions are executed by one or more processors , So that the one or more processors further execute the following steps:

    When the text data fails to match the matching content corresponding to the preset template, a preset prompt manner is used to send a prompt message indicating that the second preset voice data is incorrect to the preset personnel terminal.
20. The readable storage medium according to claim 19, wherein the computer-readable instructions are executed by one or more processors after the text data fails to match the matching content corresponding to the preset template. , So that the one or more processors further execute the following steps:

    Determining, according to the text data, whether the second preset voice data of the host to be tested has a packet loss phenomenon corresponding to a preset packet loss cause;

    When a packet loss phenomenon corresponding to a preset packet loss cause occurs, decode the second preset voice data fed back by the host to be tested, and determine the second preset voice based on the decoded information obtained by decoding Packet loss voice frames with packet loss in the data;

    Determine a replacement voice frame according to the state information of the previous voice frame of the packet loss voice frame, and replace the packet loss voice frame in the second preset voice data with the replacement voice frame.