CN116016779A - Speech call translation assistance method, system, computer equipment and storage medium - Google Patents

Abstract

The present application provides a voice call translation assistance method, system, computer equipment and storage medium. The method includes: acquiring the call audio of the target client; if the call audio is in the target language, cutting off the voice path between the target client and the target server ;Process the call audio, output the translation text of the preset language corresponding to the call audio, and display it on the display screen of the target server; obtain the reply information of the preset language corresponding to the translation text, and process the reply information to generate a corresponding Reply audio in the target language and transmit to the target client. The voice call translation assistance method provided by the embodiment of the present application can automate the entire process to realize the call interaction between the target client and the target server without introducing third-party personnel, and effectively improve the efficiency of the call center when receiving non-specific language calls. subsequent service efficiency.

Description

Speech call translation assistance method, system, computer equipment and storage medium

technical field

The present application relates to the technical field of call processing, in particular to a voice call translation assistance method, system, computer equipment and storage medium (computer-readable storage medium).

Background technique

The call center, also known as the customer service center, transfers the user's telephone call to a relatively centralized place, and a group of service personnel conduct telephone communication and service according to the user's needs.

At present, although various call centers can meet telephone service requests, they are limited by the language service capabilities of customer service personnel, and usually can only serve telephone requests for services in specific languages. After a call in a non-specific language is connected, the service personnel need to request translation demand, and then contact the third-party interpreter through the three-way call function, which will cause the waiting of the calling customer and affect the service efficiency.

Contents of the invention

Based on this, it is necessary to address the above technical problems and provide a voice call translation assistance method, system, computer equipment and storage media to solve the problem of low service efficiency in existing call centers after receiving service demands in non-specific languages. technical problem.

In the first aspect, the present application provides a voice call translation assistance method, including:

Obtain the call audio of the target client;

If the language type corresponding to the call audio is the target language, cut off the voice path between the target client and the target server;

Processing the call audio, outputting the translation text of the preset language corresponding to the call audio, and displaying it on the display screen of the target server;

Obtain reply information in a preset language corresponding to the translated text, process the reply information, generate reply audio corresponding to the target language, and transmit the reply to the target client.

As a feasible embodiment of the present application, the processing the call audio and outputting the translated text of the preset language corresponding to the call audio includes:

Querying a preset database according to the target language to obtain an audio processing model associated with the target language;

The call audio is input into the audio processing model for processing, and a translation text in a preset language corresponding to the call audio is output.

As a feasible embodiment of the present application, after outputting the translated text in the preset language corresponding to the call audio and displaying it on the display screen of the target server, the method further includes:

Processing the translated text to obtain semantic information corresponding to the translated text;

Querying a preset database according to the semantic information, obtaining associated text associated with the semantic information, and displaying the associated text on the display screen;

In response to a selection instruction for the associated text on the display screen, use text information corresponding to the selection instruction in the associated text as reply information corresponding to the translated text.

As a feasible embodiment of the present application, the obtaining the reply information corresponding to the translated text includes:

In response to a first operation instruction to a preset button on the display screen, start a preset recording device;

In response to a second operation instruction to the preset button on the display screen, turn off the preset recording device;

Generate answer information corresponding to the translated text according to the audio information collected by the preset recording device.

As a feasible embodiment of the present application, the generating the reply information corresponding to the translated text according to the audio information collected by the preset recording device includes:

Processing the audio information collected by the preset recording device, generating a reply text in a preset language corresponding to the audio information, and displaying it on the display screen;

In response to an operation instruction for modifying the reply text on the display screen, a revised reply text is generated, and the modified reply text is used as reply information corresponding to the translated text.

As a feasible embodiment of the present application, after obtaining the reply information in the preset language corresponding to the translated text, the method further includes:

Processing the reply information to generate a reply text in the target language, and transmitting the reply text in the target language to the target client.

As a feasible embodiment of the present application, after the acquisition of the call audio of the target client, the method further includes:

Obtain the call interval corresponding to the call audio, and the preset reminder voice information corresponding to the target language;

If the call interval is greater than a preset duration threshold, before the step of generating the reply audio corresponding to the target language, the preset reminder voice information is transmitted to the target client.

As a feasible embodiment of the present application, the cutting off the voice path between the target client and the target server refers to cutting off a one-way voice path sent from the target server to the target client.

In a second aspect, the present application provides a voice call translation assistance system, including:

The voice call subsystem is used to obtain the call audio of the target client; if the language type corresponding to the call audio is the target language, then cut off the voice path between the target client and the target server;

The speech translation subsystem is used to process the call audio, output the translation text of the preset language corresponding to the call audio, and display it on the display screen of the target server;

The speech synthesis subsystem is configured to obtain reply information in a preset language corresponding to the translated text, process the reply information, generate reply audio corresponding to the target language, and transmit the reply to the target client.

In a third aspect, the present application also provides a computer device, wherein the computer device includes:

processor; and

One or more application programs, wherein the one or more application programs are stored in the processor, and when the processor executes the one or more application programs, it is used to implement any of the above The voice call translation assistance method described above.

In the fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it is used to implement the voice call translation assistance method as described in any one of the above .

In the voice call translation assistance method provided by the embodiment of the present application, after obtaining the call audio of the target client, if it is detected that the language type corresponding to the call audio is the target language, the voice between the target client and the target server will be cut off channel, and output the translation text of the preset language corresponding to the call audio, and provide it on the display screen of the target server, so that after the service personnel feed back the reply information in the preset language according to the translated text, they can process the reply information and generate corresponding The reply audio in the target language is provided to the target client. The voice call translation assistance method provided by the embodiment of the present application can automate the entire process to realize the call interaction between the target client and the target server without introducing third-party personnel, effectively improving the call center's ability to receive non-specific language calls. subsequent service efficiency.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings that need to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, other drawings can also be obtained based on these drawings without any creative effort.

FIG. 1 is a schematic diagram of an application scenario of a voice call translation assistance method provided by an embodiment of the present application;

Fig. 2 provides a schematic flow chart of the steps of a voice call translation assistance method according to an embodiment of the present application;

FIG. 3 is a schematic flow diagram of steps for processing call audio by acquiring a corresponding audio processing model based on the language type provided by the embodiment of the present application;

FIG. 4 is an implementation scheme for synchronously displaying associated text on a display screen to assist customer service personnel in answering provided by an embodiment of the present application;

FIG. 5 is a schematic flow chart of steps for acquiring reply information based on voice provided in an embodiment of the present application;

Fig. 6 is a schematic flow chart of the steps of displaying the reply text to assist in modifying the reply information provided by the embodiment of the present application;

FIG. 7 is a schematic flow diagram of steps for providing reminder voice information to a target client according to an embodiment of the present application;

FIG. 8 is a schematic structural diagram of a voice call translation assistance system provided by an embodiment of the present application;

FIG. 9 is a schematic structural diagram of a computer device provided by an embodiment of the present application.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of this application.

In the description of the present application, the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of said features. In the description of the present application, "plurality" means two or more, unless otherwise specifically defined.

In the description of this application, the word "for example" is used to mean "serving as an example, illustration or illustration". Any embodiment described in this application as "such as" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is given to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for purposes of explanation. It should be understood that one of ordinary skill in the art would recognize that the present invention may be practiced without the use of these specific details. In other instances, well-known structures and procedures are not described in detail to avoid obscuring the description of the present invention with unnecessary detail. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed in this application.

In order to facilitate the understanding of the complete implementation solution of the voice call translation assistance method provided by the embodiment of the present application, the implementation scenario of the voice call translation assistance method is described first, and the details are as follows.

The voice call translation assistance method provided by the embodiment of the present application is mainly used in the business scenario of the call center, wherein the customer can communicate with the customer service personnel of the call center through the communication function between the client terminal on the terminal device and the corresponding server of the call center Make a call to obtain the corresponding service requirements. However, in most cases, customer service personnel can only provide services in a specific language. Therefore, when customer service personnel receive a call from a target customer in a non-specific language, they need to initiate a translation request first, and then use the three-way call function of the call center. Let a third-party interpreter join the call process, but the process is complicated, and the caller often needs to wait for a certain period of time, which affects the service efficiency of the call center.

Just to solve the above problems, the embodiments of the present application provide a voice call translation assistance method, system, computer equipment and storage medium. Wherein, the voice call translation auxiliary method is installed in the voice call translation auxiliary system in the form of a program, and the voice call translation auxiliary system is set in the computer equipment in the form of a processor, and the voice call translation auxiliary system in the computer equipment executes the voice call translation assistance system. The software program corresponding to the method for assisting call translation, thereby realizing the method for assisting speech call translation provided in the embodiment of the present application. Among them, the voice call translation auxiliary system can be provided by the call center, and has the function of data interaction with the server of the call center, of course, it can also be provided by the communication operator, and can communicate with the client and the server at the same time function. Specifically, as shown in FIG. 1, FIG. 1 is a schematic diagram of an application scenario of a voice call translation assistance method provided by the embodiment of the present application. In this schematic diagram, the target client 100 located on the user terminal device, the The provided voice call translation assistance system 200 and the target server 300 located in the call center, wherein the call audio entered by the user through the target client 100 will be transmitted to the voice call translation support system 200, and the call audio will be recognized After the corresponding language type is the target language that needs to be processed, the voice call translation assistance system 200 will process the call audio accordingly, convert the call audio into a translation text in a preset language, and transmit it to the target server 300 , to output to the customer service personnel through the display screen of the target server 300, so as to receive the reply information provided by the customer service personnel based on the displayed translated text, and then synthesize the response audio corresponding to the target language, and resend it to the target client 100.

It should be noted that the application scenario schematic diagram of the voice call translation assistance system provided above is only a feasible implementation solution, and does not constitute a limitation to the embodiment of the application. For example, the aforementioned FIG. 1 only takes a single target client 100 as an example It should be noted that, in fact, the voice call translation assistance system provided by the embodiment of the present application can be aimed at multiple different target clients 100 at the same time, so the embodiment of the present application will not repeat them here.

In addition, the target client 100 on the user terminal device can exist in different forms, for example, the target client can be a webpage, APP software, applet, etc., and the voice call translation assistance system 200 can be a server or a cloud Of course, the server may also be a server cluster composed of multiple servers, which will not be repeated in this embodiment of the present application.

In the above application scenario, the embodiment of the present application provides a schematic diagram of the steps of a voice call translation assistance method, specifically, steps 201-204 are included:

201. Acquire call audio of a target client.

In the embodiment of this application, when the target client initiates a communication request to the target server of the call center through the target client, if the target server receives the request and establishes a communication relationship with the The call information recorded by the target client will be sent to the voice call translation assistance system in the form of audio stream, and the audio stream is the call audio.

202. If the language type corresponding to the call audio is the target language, cut off the voice path between the target client and the target server.

In the embodiment of the present application, the call audio is obtained in the voice call translation assistance system, and the language type corresponding to the call audio can be detected through the trained language recognition model, wherein the trained language recognition model can be based on a supervised neural network The network algorithm is trained, for example, through deep learning to enable the language recognition model to learn the relationship between different language types and the acoustic spectrum features or phoneme features in the audio, which will not be described in this embodiment of the present application. Of course, in addition to the automatic detection of the call audio by the voice call translation assistance system, the target customer can also select the corresponding language type based on the language type options displayed by the target client during the process of initiating a communication request through the target client. , the selected language type will be sent to the voice call translation assistance system as the language type corresponding to the subsequently obtained call audio.

On the basis of determining the language type corresponding to the call audio, if the language type corresponding to the call audio is a pre-set target language, that is, a non-specific language other than the specific language service that the call center can provide, voice call translation The auxiliary system will cut off the voice channel between the target client and the target server, so as to prevent the call audio provided by the target client from being directly transmitted to the target server, and also to prevent the non-target language audio replied by the target server from being directly transmitted to the target customer end, resulting in unnecessary misunderstandings. Of course, as a feasible embodiment of the present application, cutting off the voice path between the target client and the target server here refers to cutting off the one-way voice path sent from the target server to the target client, that is, the call audio of the target client will be It is transmitted to the target server and played, thereby reducing the risk of errors in identifying and translating the call audio, but the non-target language audio replied by the target server will not be directly transmitted to the target client.

203. Process the call audio, output a translation text in a preset language corresponding to the call audio, and display it on a display screen of the target server.

In the embodiment of the present application, in order to enable the customer service personnel to understand the call audio in the target language, the voice call translation assistance system will first process the call audio to output the translation text in the preset language, and provide it to the target server. Specifically, the voice call translation assistance system processes the call audio mainly including the audio recognition process and the text translation process. The former is mainly used to recognize the call audio in the target language into the call text in the target language, while the latter is mainly used Translate the obtained call text in the target language into the translated text in the preset language. Among them, the recognition of audio and the translation of text can also be realized based on the trained neural network model. For example, the speech recognition process can use the existing speech recognition model, that is, determine the frequency spectrum feature information in a piece of audio. The information content contained in the audio. Specifically, as a feasible embodiment of the present application, the speech recognition model can be pre-trained based on training sample data, such as HMM (Hidden Markov Model, Hidden Markov Model), DNN (Deep NeuralNetworks, deep neural network ) model and so on. Among them, the training process of the speech recognition model generally includes the following steps: constructing a network model with parameter initialization; inputting sample audio with label text into the initial network model to obtain predicted text; Update the parameters in the initial network model so that the predicted text obtained by the updated network model processing the sample audio is closer to the label text; repeat the above process until the current network model is used to process the sample audio. When the difference between the predicted text and the labeled text is less than the preset difference threshold, the current network model is the trained speech recognition model, which has the function of accurately processing a piece of audio into corresponding text content. Similarly, for translated text, the translation process of the text can be realized by using the transformer model and RNN (Recurrent Neural Networks, cyclic neural network) model with text encoding and decoding functions to realize text translation, and the embodiments of the present application will not repeat them here. .

Of course, it should be noted that since the spectral features contained in audio in different languages are often different, it is often difficult for a single speech recognition model to complete audio recognition for different languages. Similarly, it is also difficult for a single text translation model to complete For text translation in different languages, therefore, in order to improve the applicability of the voice call translation assistance method provided by the embodiment of the present application, as a feasible implementation scheme of the embodiment of the application, the database of the voice call translation assistance system is deployed with different Language-related audio processing model, so that when processing the call audio, an appropriate audio processing model can be selected for processing, and the translation effect of the call audio can be improved. For the specific implementation plan, please refer to the following figure 3 and its explanation. .

In addition, as another feasible solution of this application, in order to further improve the service efficiency of customer service personnel, in addition to displaying the translated text, the display screen of the target server will also simultaneously display associated text related to the translated text for customer service personnel. Answer, for the specific implementation plan, please refer to the subsequent Figure 4 and its explanation.

204. Obtain reply information in a preset language corresponding to the translated text, process the reply information, generate reply audio corresponding to the target language, and transmit the reply to the target client.

In the embodiment of the present application, since the voice channel between the target client and the target server has been cut off, the customer service personnel will not directly transmit the reply information in the preset language based on the translated text feedback on the display screen of the target server to the target client, it will first be transmitted to the voice call translation assistance system for processing. After the voice call translation assistance system completes the processing of the reply information, it translates it into the reply text in the target language, and then synthesizes it into the reply audio in the target language Only then will it be transmitted to the target client.

Specifically, the reply information of the preset language corresponding to the translated text can be entered into the target server in various ways. For example, after displaying the associated text, the customer service personnel can select the text corresponding to the instruction on the display screen The information is used as the reply information, but as another simple and feasible implementation plan, the voice information answered by the customer service personnel can be obtained by starting and stopping the recording device through different operation instructions to the buttons on the display screen. For a specific implementation solution, refer to the subsequent FIG. 5 and its explanations.

Further, as another optional embodiment of this application, it is considered that during the processing of the reply information by the voice call translation assistance system, the reply text in the target language will be generated first, and then the reply audio in the target language will be synthesized and provided to the target Client, in this process, in order to further improve the service effect of the call center, the voice call translation assistance system can also transmit the reply text in the target language to the target client.

In addition, considering that in this embodiment of the application, due to the addition of speech recognition, text translation, and speech synthesis processes, it is easy to cause target customers to wait. Therefore, in order to eliminate the adverse effects of target customers waiting, in the embodiment of this application , after obtaining the call audio of the target client, the voice call translation assistance system will record the call interval corresponding to the call audio, that is, record the time from the target client to complete the call audio, and when the call interval is greater than the preset duration threshold , if the reply audio in the target language is still not generated, at this time, the voice call translation assistance system will play the preset reminder information to the target client. For a specific implementation solution, refer to the subsequent FIG. 7 and its explanations.

In the voice call translation assistance method provided by the embodiment of the present application, after obtaining the call audio of the target client, if it is detected that the language type corresponding to the call audio is the target language, the voice between the target client and the target server will be cut off channel, and output the translation text of the preset language corresponding to the call audio, and provide it on the display screen of the target server, so that after the service personnel feed back the reply information in the preset language according to the translated text, they can process the reply information and generate corresponding The reply audio in the target language is provided to the target client. The voice call translation assistance method provided by the embodiment of the present application can automate the entire process to realize the call interaction between the target client and the target server without introducing third-party personnel, effectively improving the call center's ability to receive non-specific language calls. subsequent service efficiency.

As shown in FIG. 3 , FIG. 3 is a schematic flow chart of steps for processing call audio by acquiring a corresponding audio processing model based on the language type provided by the embodiment of the present application. Specifically, steps 301-302 are included:

301. Query a preset database according to the target language to obtain an audio processing model associated with the target language.

In the embodiment of the present application, audio processing models associated with different languages are pre-stored in the database of the voice call translation assistance system, including audio recognition models and text translation models, wherein the audio processing models associated with different languages are respectively associated with The training text of the language is trained. For example, the audio processing model associated with language A is trained using the training text of language A, and the audio processing model associated with language B is trained using the training text of language B. This The application embodiments will not be repeated here.

Further, in addition to the speech recognition model and text translation model provided above, combined with the relevant description of step 204 above, the voice call translation assistance system can also synthesize the reply text in the target language into the reply audio in the target language through the speech synthesis model , therefore, the audio processing model may also include a speech synthesis model, and of course the training of the model is also implemented based on the training text of the corresponding language.

302. Input the call audio into the audio processing model for processing, and output a translation text in a preset language corresponding to the call audio.

In the embodiment of the present application, the call audio is input into the audio processing model for processing. Since the audio processing model is implemented based on the training text of the target language, it can effectively complete the recognition and translation of the call audio, ensuring the output accuracy of the translated text.

As shown in Figure 4, Figure 4 is an implementation scheme for synchronously displaying associated text on the display screen to assist customer service personnel in answering provided by the embodiment of the present application, specifically, steps 401-403 are included:

401. Process the translated text to obtain semantic information corresponding to the translated text.

In the embodiment of the present application, in order to improve the service effect of customer service personnel, the voice call translation assistance system will further perform semantic recognition processing on the obtained translated text, that is, determine the semantic information of the translated text by extracting keywords in the text. Specifically, this process can usually be realized by a semantic recognition model based on training. For example, a semantic recognition model based on NLP (Natural Language Processing, Natural Language Processing) technology is more common, and the embodiments of the present application are not described here. Let me repeat.

In the embodiment of the present application, the aforementioned voice information obtained by processing the translated text generally describes what type of problems the target customer seeks for help or feedback based on, for example, life problems or work problems.

402. Query a preset database according to the semantic information, obtain associated text associated with the semantic information, and display the associated text on the display screen.

In the embodiment of the present application, after identifying the semantic information corresponding to the translated text, the voice call translation assistance system will also query the corresponding database based on the semantic information, so as to directly obtain the associated text associated with the semantic information from the database and pass The aforementioned display screen is provided to customer service personnel. For example, the associated text may be some policies, regulatory documents, etc. associated with the semantic information of the translated text.

Of course, while displaying the translated text and associated text, in order to facilitate the customer service personnel to distinguish, the translated text and associated text displayed on the display screen may be different, for example, they may be displayed in different positions, such as in the upper area of the display screen The translated text is displayed, and the associated text is displayed in the lower area of the display screen. Of course, different colors can also be used to distinguish them, which will not be repeated in this embodiment of the present application.

403. In response to a selection instruction for the associated text on the display screen, use text information corresponding to the selection instruction in the associated text as answer information corresponding to the translated text.

In the embodiment of the present application, after the associated text of the translated text is displayed on the display screen, if some of the text information in it is information that can be used to answer the call audio, at this time, the customer service personnel of the call center can directly display the text on the display screen. Input the selection command by means of selection, such as box selection or click selection. At this time, the voice call translation assistance system will automatically use this part of the text information as the response information corresponding to the translated text for subsequent processing, thereby generating The corresponding reply audio.

Of course, another simplified implementation solution for replying to translated texts provided above, in fact, in addition to directly selecting related texts to reply, customer service personnel can also further reply based on their own business experience. At this time, in order to facilitate customer service For the personnel’s reply, the target server can also include a recording device to record the user’s voice and reply as the reply information. Specifically, as shown in Figure 5, it is a voice-based method provided by the embodiment of the present application Schematic flow chart of steps for obtaining reply information, specifically, steps 501-503 are included:

501. Start a preset recording device in response to a first operation instruction to a preset button on the display screen.

502. In response to a second operation instruction to the preset button on the display screen, close the preset recording device.

In the embodiment of the present application, there may be a single preset button on the display screen, and of course there may be multiple preset buttons, for example, there may also be two preset buttons. Specifically, when only one preset button is provided on the display screen, the first operation instruction at this time may be the first click, and at this time, the recording device of the target server will be started to record the currently input voice information. Further, the second operation instruction of the preset button is usually clickable again. In order to distinguish between two different clicks, the preset button can be displayed in different styles. For example, before the first click, the preset button A triangular pattern pattern will be displayed on the button, and after receiving the first operation instruction of the button, a circular pattern pattern will be displayed on the preset button, and the recording device will be started, and when the second operation instruction of the button is received again After the command, the triangle pattern will reappear on the preset button and the recording device will be turned off.

Of course, the above is just an example of the preset button including a single button. In fact, the preset button can also include two or more. For example, take the preset button including two buttons as an example. At this time, the preset The first operation instruction of the button may be a click operation on the first button among the preset buttons, and the second operation instruction on the preset button may be a click operation on the second button among the preset buttons. Of course, the preset button More may be included, corresponding to different functions of the recording device, such as noise reduction, waveform enhancement, echo cancellation, etc., which will not be described in this embodiment of the present application.

503. Generate reply information corresponding to the translated text according to the audio information collected by the preset recording device,

In the embodiment of the present application, during the start-up process of the aforementioned recording device, that is, between the first operation instruction and the second operation instruction to the preset button on the display screen, the voice information recorded by the recording device is the corresponding translation text. Reply message in default language.

On the basis of the above scheme, in order to further improve the reply effect of customer service personnel, the audio information will be converted into text information in the preset language first, and displayed on the display screen, so as to facilitate modification by customer service personnel. Specifically, as shown in the figure 6, FIG. 6 is a schematic flow chart of the steps of displaying the reply text to assist in modifying the reply information provided by the embodiment of the present application. Specifically, it includes steps 601-602:

601. Process the audio information collected by the preset recording device, generate a reply text in a preset language corresponding to the audio information, and display it on the display screen.

In the embodiment of the present application, the voice call translation assistance system will first process the audio information collected by the recording device for speech recognition processing, process it into a reply text in a preset language, and display it on the display screen. Specifically, the speech recognition process here may be similar to the aforementioned steps, obtained by using a speech recognition model, but it should be noted that the speech recognition model here is obtained by using the training text of the preset language. No longer.

602. Generate a modified reply text in response to an operation instruction for modifying the reply text on the display screen, and use the modified reply text as reply information corresponding to the translated text.

In the embodiment of this application, in addition to displaying the initial reply text of the customer service personnel through the display screen, if the customer service personnel want to modify part of the content, the modification can also be completed by modifying the reply text on the display screen. Specifically Yes, the modified reply text will be used as the final reply information for subsequent generation of reply audio and provided to the target client.

As shown in FIG. 7, FIG. 7 is a schematic flow diagram of the steps for providing reminder voice information to the target client provided by the embodiment of the present application. Specifically, it includes steps 701-702:

701. Acquire a call interval corresponding to the call audio and preset reminder voice information corresponding to the target language.

In the embodiment of the present application, when the voice call translation assistance system acquires the call audio of the target client, it will record the call interval of the call audio through a timing device, and then obtain the preset reminder information in the target language information, for example, "Ongoing Inquiry, please wait later", of course, other reminder information is also possible, which will not be repeated here in this embodiment of the application.

702. If the call interval is greater than a preset duration threshold, before the step of generating the reply audio corresponding to the target language, transmit the preset reminder voice information to the target client.

In the embodiment of the present application, when the call interval is greater than the preset duration threshold, for example, after more than 2 minutes, the voice call translation assistance system has not yet generated a reply audio in the target language. At this time, the voice call translation assistance system will use the preset The reminder voice information is transmitted to the target client to remind the customer to wait until the reply audio corresponding to the target language is generated, and the playback of the reminder voice information is turned off, and the reply audio is transmitted to the target client.

Specifically, in order to more clearly understand the voice call translation assistance method provided by the embodiment of the present application, on the basis of the above-mentioned voice call translation assistance method, the embodiment of the present application also provides a voice call translation assistance system, specifically, as shown in the figure As shown in 8, it is a schematic structural diagram of a voice call translation assistance system provided in the embodiment of this application, specifically, it includes 810-830:

The voice call subsystem 810 is used to obtain the call audio of the target client; if the language type corresponding to the call audio is the target language, then cut off the voice path between the target client and the target server;

The speech translation subsystem 820 is configured to process the call audio, output the translated text in the preset language corresponding to the call audio, and display it on the display screen of the target server;

The speech synthesis subsystem 830 is configured to obtain reply information in a preset language corresponding to the translated text, process the reply information, generate reply audio corresponding to the target language, and transmit the reply to the target client.

In the embodiment of the present application, the speech translation subsystem is also used to query the preset database according to the target language to obtain an audio processing model associated with the target language; input the call audio into the audio processing model for processing to output the translated text in the preset language corresponding to the call audio.

In the embodiment of the present application, after the speech translation subsystem outputs the translation text in the preset language corresponding to the call audio and displays it on the display screen of the target server, it is also used to process the translation text to obtain the Semantic information corresponding to the translated text; query a preset database according to the semantic information, obtain associated text associated with the semantic information, and display the associated text on the display screen; respond to the query on the display screen The selection instruction of the associated text uses the text information corresponding to the selection instruction in the associated text as the reply information corresponding to the translated text.

In the embodiment of the present application, the speech synthesis subsystem is also used to start the preset recording device in response to the first operation instruction to the preset button on the display screen; The operation instruction is to close the preset recording device; generate the reply information corresponding to the translated text according to the audio information collected by the preset recording device.

In the embodiment of the present application, the speech synthesis subsystem is also used to process the audio information collected by the preset recording device, generate the reply text in the preset language corresponding to the audio information, and perform the reply on the display screen. displaying; in response to an operation instruction for modifying the reply text on the display screen, generate a revised reply text, and use the modified reply text as reply information corresponding to the translated text.

In the embodiment of the present application, after obtaining the reply information in the preset language corresponding to the translated text, the speech synthesis subsystem is also used to process the reply information, generate a reply text in the target language, and convert the text in the target language The reply text is transmitted to the target client.

In the embodiment of the present application, after the voice call subsystem acquires the call audio of the target client, it is also used to acquire the call interval corresponding to the call audio and the preset reminder voice information corresponding to the target language; at this time, the speech synthesis The subsystem is configured to transmit the preset reminder voice information to the target client before the step of generating the reply audio corresponding to the target language if the call interval is greater than a preset duration threshold.

For the specific limitations of the voice call translation assistance system, refer to the above description of the voice call translation assistance method, which will not be repeated here. Each step in the above voice call translation assistance method can be fully or partially realized by software, hardware and combinations thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.

In some embodiments of the present application, the voice call translation assistance system 200 may be implemented in the form of a computer program, and the computer program may run on a computer device as shown in FIG. 9 . Each program module constituting the voice call translation assistance system 200 can be stored in the memory of the computer device, and the computer program constituted by each program module enables the processor to execute the steps in the voice call translation assistance method of each embodiment of the application described in this specification. .

For example, the computer device shown in FIG. 9 includes a processor, memory, and network interface connected by a system bus. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used to communicate with external computer devices via a network connection. When the computer program is executed by the processor, a voice call translation assistance method is realized.

Those skilled in the art can understand that the structure shown in FIG. 9 is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation on the computer equipment on which the solution of this application is applied. The specific computer equipment can be More or fewer components than shown in the figures may be included, or some components may be combined, or have a different arrangement of components.

In some embodiments of the present application, a computer device is provided, including one or more processors; memory; and one or more application programs, wherein one or more application programs are stored in the memory and configured to be used by The processor executes to achieve the following steps:

Obtain the call audio of the target client;

If the language type corresponding to the call audio is the target language, cut off the voice path between the target client and the target server;

Processing the call audio, outputting the translation text of the preset language corresponding to the call audio, and displaying it on the display screen of the target server;

Obtain reply information in a preset language corresponding to the translated text, process the reply information, generate reply audio corresponding to the target language, and transmit the reply to the target client.

In some embodiments of the present application, when the processor executes the computer program, the following steps are also implemented: querying the preset database according to the target language to obtain an audio processing model associated with the target language; inputting the call audio into the Processing is performed in the audio processing model, and the translation text in the preset language corresponding to the call audio is output.

In some embodiments of the present application, when the processor executes the computer program, the following steps are also implemented: processing the translated text to obtain semantic information corresponding to the translated text; querying a preset database according to the semantic information, and obtaining information related to the translated text associated text associated with the semantic information, and display the associated text on the display screen; in response to a selection instruction for the associated text on the display screen, select the text corresponding to the selection instruction in the associated text information as the reply information corresponding to the translated text.

In some embodiments of the present application, when the processor executes the computer program, the following steps are also implemented: in response to the first operation instruction to the preset button on the display screen, start the preset recording device; The second operation command of the preset button is to turn off the preset recording device; generate the reply information corresponding to the translated text according to the audio information collected by the preset recording device.

In some embodiments of the present application, when the processor executes the computer program, the following steps are also implemented: processing the audio information collected by the preset recording device, generating a reply text in a preset language corresponding to the audio information, and displaying on the display screen; in response to an operation instruction to modify the reply text on the display screen, generate a revised reply text, and use the modified reply text as reply information corresponding to the translated text.

In some embodiments of the present application, when the processor executes the computer program, the following steps are also implemented: processing the reply information, generating a reply text in the target language, and transmitting the reply text in the target language to the target client .

In some embodiments of the present application, when the processor executes the computer program, the following steps are also implemented: obtaining the call interval corresponding to the call audio and the preset reminder voice information corresponding to the target language; if the call interval is greater than the preset before the step of generating the reply audio corresponding to the target language, transmit the preset reminder voice information to the target client.

In some embodiments of the present application, a computer-readable storage medium is provided, which stores a computer program, and the computer program is loaded by a processor, so that the processor performs the following steps:

Obtain the call audio of the target client;

If the language type corresponding to the call audio is the target language, cut off the voice path between the target client and the target server;

Processing the call audio, outputting the translation text of the preset language corresponding to the call audio, and displaying it on the display screen of the target server;

Obtain reply information in a preset language corresponding to the translated text, process the reply information, generate reply audio corresponding to the target language, and transmit the reply to the target client.

In some embodiments of the present application, when the processor executes the computer program, the following steps are also implemented: querying the preset database according to the target language to obtain an audio processing model associated with the target language; inputting the call audio into the Processing is performed in the audio processing model, and the translation text in the preset language corresponding to the call audio is output.

In some embodiments of the present application, when the processor executes the computer program, the following steps are also implemented: processing the translated text to obtain semantic information corresponding to the translated text; querying a preset database according to the semantic information, and obtaining information related to the translated text associated text associated with the semantic information, and display the associated text on the display screen; in response to a selection instruction for the associated text on the display screen, select the text corresponding to the selection instruction in the associated text information as the reply information corresponding to the translated text.

In some embodiments of the present application, when the processor executes the computer program, the following steps are also implemented: in response to the first operation instruction to the preset button on the display screen, start the preset recording device; The second operation command of the preset button is to turn off the preset recording device; generate the reply information corresponding to the translated text according to the audio information collected by the preset recording device.

In some embodiments of the present application, when the processor executes the computer program, the following steps are also implemented: processing the audio information collected by the preset recording device, generating a reply text in a preset language corresponding to the audio information, and displaying on the display screen; in response to an operation instruction to modify the reply text on the display screen, generate a revised reply text, and use the modified reply text as reply information corresponding to the translated text.

In some embodiments of the present application, when the processor executes the computer program, the following steps are also implemented: processing the reply information, generating a reply text in the target language, and transmitting the reply text in the target language to the target client .

In some embodiments of the present application, when the processor executes the computer program, the following steps are also implemented: obtaining the call interval corresponding to the call audio and the preset reminder voice information corresponding to the target language; if the call interval is greater than the preset before the step of generating the reply audio corresponding to the target language, transmit the preset reminder voice information to the target client.

Those of ordinary skill in the art can understand that realizing all or part of the processes in the methods of the above embodiments can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium In this case, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Any reference to memory, storage, database or other media used in the various embodiments provided in this application may include at least one of non-volatile and volatile memory. The non-volatile memory may include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory or optical memory, and the like. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM).

The technical features of the above embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered to be within the range described in this specification.

A voice call translation assistance method, system, computer equipment, and storage medium provided by the embodiments of the present application have been described above in detail. In this paper, specific examples are used to illustrate the principle and implementation of the present invention. The above embodiments The explanation is only used to help understand the method and core idea of the present invention; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation and scope of application. In summary, The contents of this specification should not be construed as limiting the present invention.

Claims (11)

1. A voice call translation assistance method, characterized in that, comprising: Obtain the call audio of the target client; If the language type corresponding to the call audio is the target language, cut off the voice path between the target client and the target server; Processing the call audio, outputting the translation text of the preset language corresponding to the call audio, and displaying it on the display screen of the target server; Obtain reply information in a preset language corresponding to the translated text, process the reply information, generate reply audio corresponding to the target language, and transmit the reply to the target client. 2. The voice call translation assistance method according to claim 1, wherein the processing of the call audio and outputting the translation text of the preset language corresponding to the call audio includes: Querying a preset database according to the target language to obtain an audio processing model associated with the target language; The call audio is input into the audio processing model for processing, and a translation text in a preset language corresponding to the call audio is output. 3. The voice call translation assistance method according to claim 1, characterized in that, after outputting the translated text of the preset language corresponding to the call audio and displaying it on the display screen of the target server, the method Also includes: Processing the translated text to obtain semantic information corresponding to the translated text; Querying a preset database according to the semantic information, obtaining associated text associated with the semantic information, and displaying the associated text on the display screen; In response to a selection instruction for the associated text on the display screen, use text information corresponding to the selection instruction in the associated text as reply information corresponding to the translated text. 4. The voice call translation assistance method according to claim 1, wherein said obtaining the reply information corresponding to said translated text comprises: In response to a first operation instruction to a preset button on the display screen, start a preset recording device; In response to a second operation instruction to the preset button on the display screen, turn off the preset recording device; Generate answer information corresponding to the translated text according to the audio information collected by the preset recording device. 5. The voice call translation assistance method according to claim 4, characterized in that, generating the reply information corresponding to the translated text according to the audio information collected by the preset recording device includes: Processing the audio information collected by the preset recording device, generating a reply text in a preset language corresponding to the audio information, and displaying it on the display screen; In response to an operation instruction for modifying the reply text on the display screen, a revised reply text is generated, and the modified reply text is used as reply information corresponding to the translated text. 6. The voice call translation assistance method according to claim 1, characterized in that, after obtaining the reply information in the preset language corresponding to the translated text, the method further comprises: Processing the reply information to generate a reply text in the target language, and transmitting the reply text in the target language to the target client. 7. The voice call translation assistance method according to claim 1, wherein, after the acquisition of the call audio of the target client, the method further comprises: Obtain the call interval corresponding to the call audio, and the preset reminder voice information corresponding to the target language; If the call interval is greater than a preset duration threshold, before the step of generating the reply audio corresponding to the target language, the preset reminder voice information is transmitted to the target client. 8. The voice call translation assistance method according to any one of claims 1 to 7, wherein the cutting off the voice path between the target client and the target server refers to cutting off the voice channel provided by the target server. A one-way voice path to the target client. 9. A voice call translation assistance system, characterized in that, comprising: The voice call subsystem is used to obtain the call audio of the target client; if the language type corresponding to the call audio is the target language, then cut off the voice path between the target client and the target server; The speech translation subsystem is used to process the call audio, output the translation text of the preset language corresponding to the call audio, and display it on the display screen of the target server; The speech synthesis subsystem is configured to obtain reply information in a preset language corresponding to the translated text, process the reply information, generate reply audio corresponding to the target language, and transmit the reply to the target client. 10. A computer device, characterized in that the computer device comprises: processor; and One or more application programs, wherein the one or more application programs are stored in the processor, and when the processor executes the one or more application programs, it is used to implement claims 1-8 Any one of the voice call translation assistance methods. 11. A computer-readable storage medium, characterized in that a computer program is stored thereon, and when the computer program is executed by a processor, it is used to realize the voice call translation according to any one of claims 1-8 helper method.

Images