Intelligent call forwarding method, device and equipment and readable storage medium

Abstract

The invention provides an intelligent call forwarding method, device and equipment and a readable storage medium, and relates to the technical field of call forwarding, and the method comprises the steps: sending a first response voice to a call object after a call is connected; receiving a first response voice of the calling object for the first response voice; analyzing the first reply voice to obtain a voice analysis result; if the voice analysis result meets the configured switching rule, respectively converting the first response voice and the first reply voice into a first response text and a first reply text; and transferring the call with the calling object to the artificial customer service, and sending the identity information, the historical call data, the to-be-mediated item data, the first response text and the first reply text to the artificial customer service. According to the invention, the intelligent and automatic degree of intelligent call forwarding is improved, and the mediation efficiency is also improved.

Description

Technical Field

[0001] The present application relates to the technical field of call forwarding, and in particular to an intelligent call forwarding method, device, equipment and readable storage medium. Background Art

[0002] Existing artificial intelligence call customer service technology can only reply with configured fixed words, but cannot generate targeted reply content based on the user's actual or historical situation, and is not flexible enough; and its voice is quite different from the human voice, resulting in a high probability that customers will hang up the phone after hearing the voice of the intelligent customer. Although there are platforms in the mediation industry where robots complete call actions, the calls are usually answered by human customer service as soon as they are connected. The human customer service staff will then convey general matters or fixed lines of dialogue to the customer before mediation communication is carried out. However, some customers will hang up the phone while conveying general matters or fixed lines of dialogue, which not only wastes the time of the human customer service staff, causing them to keep conveying repetitive matters, resulting in low mediation efficiency. In addition, the call forwarding is not intelligent enough and cannot automatically reply to the customer's voice, which leads to a poor user experience. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide an intelligent call forwarding method, device, equipment and readable storage medium to solve the above-mentioned problems existing in the prior art and improve the mediation efficiency.

[0004] In a first aspect, a smart call forwarding method is provided, which may include: When the call is connected, a first response voice is sent to the called party; wherein the first response voice is generated based on the identity information of the called party, data of items to be mediated, and historical call data; Receiving a first reply voice from the calling party to the first answer voice; Analyze the first reply speech to obtain a speech analysis result; If the speech analysis result satisfies the configured transfer rule, converting the first answer speech and the first reply speech into a first answer text and a first reply text respectively; The call with the calling party is transferred to the manual customer service, and the identity information, the historical call data, the data of the matters to be mediated, the first response text and the first reply text are sent to the manual customer service.

[0005] In an optional implementation, the method for generating the first response voice includes: Obtaining the identity information and data of matters to be mediated of the call object, as well as the historical call data of the call object; Generate a first response text based on the identity information, the data of the matter to be mediated, the historical call data, and the configured response template; Input the first response text into a pre-trained AI voice generation model to obtain a first response voice.

[0006] In an alternative implementation, the data of the matter to be mediated includes: the bank in arrears and the arrears status; The historical call data includes: the number of historical calls, the historical call time, and the call summary.

[0007] In an alternative implementation, inputting the first response text into a pre-trained AI voice generation model to obtain a first response voice includes: Input the first response text into a pre-trained AI voice generation model to obtain an initial response voice; wherein, the AI voice generation model is trained using historical mediation data; the historical mediation data is the historical call data of different human customer service representatives and different call objects; Perform voiceprint processing on the initial response voice to obtain a first response voice.

[0008] In an alternative implementation, analyzing the first response voice to obtain a voice analysis result includes: Convert the first response voice into text to obtain a first response text; Preprocess the first response text to obtain a preprocessed first response text; Perform semantic analysis on the preprocessed first response text to obtain a semantic analysis result; Input the preprocessed first response text and the semantic analysis result into a pre-trained text classification model to obtain a semantic classification result of the first response text; Determine the semantic analysis result and the semantic classification result as the voice analysis result of the first response voice.

[0009] In an alternative implementation, after obtaining the voice analysis result, the method further includes: Match the semantic analysis result and the semantic classification result to a corresponding second response text from a configured look-up table of different semantic analysis results, different semantic classification results, and corresponding second response texts; Input the second response text into the AI voice generation model to obtain a second response voice, and send the second response voice to the call object.

[0010] In an alternative implementation, the method further includes: If the semantic analysis result, the semantic classification result, or the second response text is empty, then transfer the call with the called object to a human customer service, and send the identity information, the historical call data, the data of the matter to be mediated, the response text and the reply text during the current call to the human customer service.

[0011] In a second aspect, an intelligent call transfer device is provided, and the device may include: A sending unit, configured to send a first response voice to the called object after the call is connected; wherein, the first response voice is generated based on the identity information of the called object, the data of the matter to be mediated, and the historical call data; A receiving unit, configured to receive a first reply voice of the called object for the first response voice; An analysis unit, configured to analyze the first reply voice to obtain a voice analysis result; A conversion unit, configured to, if the voice analysis result meets the configured transfer rule, convert the first response voice and the first reply voice into a first response text and a first reply text respectively; A transfer unit, configured to transfer the call with the called object to a human customer service, and send the identity information, the historical call data, the data of the matter to be mediated, the first response text, and the first reply text to the human customer service.

[0012] In a third aspect, an electronic device is provided, and the electronic device includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is used for storing a computer program; The processor is configured to, when executing the program stored on the memory, implement any one of the method steps in the first aspect described above.

[0013] In a fourth aspect, a computer-readable storage medium is provided, and a computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, any one of the method steps in the first aspect described above is implemented.

[0014] This application not only completes batch outbound calls, but also does not transfer to a human customer service immediately after connection. Instead, a pre-trained model conveys general matters or fixed phrases to the called object; and intelligently makes a second reply according to the response of the customer to realize the dialogue between AI and the called object; and during the dialogue process, the pre-trained model is used to process the reply text to simulate human voices, thereby improving the user experience.

[0015] This application not only completes batch outbound calls, but also can replace manual labor to complete repetitive general tasks, thus liberating mediators and enabling them to focus their energy on the specific mediation process that most requires human effort. This not only reduces useless operations but also improves the mediation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the following will briefly introduce the drawings required for use in the embodiments of this application. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a flowchart of an intelligent call transfer method provided by an embodiment of this application; Figure 2 It is a schematic diagram of an intelligent call transfer method provided by an embodiment of this application; Figure 3 It is a schematic structural diagram of an intelligent call transfer device provided by an embodiment of this application; Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application.

[0019] The intelligent call transfer method provided by the embodiments of the present application can be applied in a server or in a terminal with strong computing power. The server can be a physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery network (CDN), and big data and artificial intelligence platforms. The terminal can be a user equipment (UE) such as a mobile phone, a smart phone, a laptop computer, a digital broadcast receiver, a personal digital assistant (PDA), a tablet computer (PAD), a handheld device, a vehicle-mounted device, a wearable device, a computing device or other processing devices connected to a wireless modem, a mobile station (MS), a mobile terminal, etc. The terminal and the server can be directly or indirectly connected through wired or wireless communication methods, which are not limited in this application.

[0020] The following describes the preferred embodiments of the present application with reference to the accompanying drawings of the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. And without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0021] Figure 1 It is a schematic flow chart of an intelligent call transfer method provided by an embodiment of the present application. As Figure 1 shown, the method may include: Step S110: After the call is connected, send a first response voice to the called party; receive the first reply voice of the called party for the first response voice; analyze the first reply voice to obtain a voice analysis result.

[0022] In the embodiments of the present application, the method for generating the first response voice includes: Obtain the identity information and the data of the matter to be mediated of the called party, as well as the historical call data of the called party; generate a first response text based on the identity information, the data of the matter to be mediated, the historical call data and the configured response template; input the first response text into a pre-trained AI voice generation model to obtain the first response voice.

[0023] In the embodiments of the present application, the data of matters to be mediated includes: the type of matters to be mediated; different response templates correspond to different types of matters to be mediated and different historical call data. From the configured different types of matters to be mediated, different historical call states, and the corresponding response templates, match the response templates corresponding to the matters to be mediated and historical call states of each call object; for example, if the type of matter to be mediated is mortgage overdue and none of the call objects answered the call in the historical call data of the call object, then it corresponds to the response template for mortgage overdue and failure to communicate before.

[0024] In the embodiments of the present application, the historical call state is obtained by analyzing the historical call data; it includes: not answered, answered but not replied, and answered and replied; among them, answered and replied can be refined into answered and replied with repayment date, answered but not replied with repayment date, and answered and replied with personal status.

[0025] In the embodiments of the present application, the AI voice generation model includes: A multimodal text preprocessing module, which is used to perform semantic parsing on the input first response text to obtain a text feature vector; An adaptive hybrid coding acoustic processing module, which is used to map the obtained text feature vector into the acoustic space: use a pre-trained conversion model based on Transformer-CNN to perform acoustic conversion on the text feature vector to obtain an initial acoustic feature; adopt a sparse attention mechanism to generate an acoustic feature vector according to the initial acoustic feature; An adjustment module, which is used to obtain the configured voice parameters; generate an adjusted acoustic feature vector according to the voice parameters and the acoustic feature vector; A voice conversion module, which is used to convert the adjusted acoustic feature vector into the first response voice.

[0026] In the embodiments of the present application, the multimodal text preprocessing module is specifically used for: Use regular expressions and the Natural Language Toolkit (such as NLTK) to perform standardization processing on the first response text; the standardization processing is used to remove irrelevant characters (punctuation marks, special symbols, etc.) from the first response text and perform case conversion on the first response text; Use BERT or other advanced NLP models to perform deep semantic analysis on the standardized first response text to generate a text feature vector containing semantic information.

[0027] In the embodiments of the present application, the voice parameters are obtained by analyzing the voice characteristics of the mediator in the target historical mediation call data in the mediation library; specifically, the target historical mediation call data is the historical call data of successful mediation.

[0028] In the embodiments of the present application, a response text is generated in advance according to the corresponding data of the call object, and the response text is sent to the AI voice generation model.

[0029] In the embodiments of the present application, the AI voice generation model is trained using the historical call data of different mediators.

[0030] In the embodiments of the present application, the data of the matter to be mediated includes: the bank in arrears, the arrears status, the amount in arrears, the mediation name of the current mediation project, the source of the mediation data, and data such as prohibited words and prohibited phrases; specifically, the arrears status is the overdue duration of the arrears and other data.

[0031] In the embodiments of the present application, the historical call data includes: the number of historical calls, the historical call time, and the call summary.

[0032] In the embodiments of the present application, the system predicts the concurrency volume, determines the number of call objects for batch outbound calls according to the concurrency volume, initiates batch outbound calls to the call objects; and sends the corresponding response voice to the connected call objects.

[0033] In the embodiments of the present application, inputting the first response text into the pre-trained AI voice generation model to obtain the first response voice includes: Inputting the first response text into the pre-trained AI voice generation model to obtain the initial response voice; performing voiceprint processing on the initial response voice to obtain the first response voice.

[0034] In the embodiments of the present application, the AI voice generation model is trained using historical mediation data; the historical mediation data is the historical call data of different artificial customer service representatives and different call objects.

[0035] In the embodiments of the present application, analyzing the first response voice to obtain the voice analysis result includes: Converting the first response voice into text to obtain the first response text; preprocessing the first response text to obtain the preprocessed first response text; performing semantic analysis on the preprocessed first response text to obtain the semantic analysis result; inputting the preprocessed first response text and the semantic analysis result into the pre-trained text classification model to obtain the semantic classification result of the first response text; determining the semantic analysis result and the semantic classification result as the voice analysis result of the first response voice.

[0036] In the embodiments of the present application, after obtaining the voice analysis result, the method further includes: Match the second response text corresponding to the semantic analysis result and semantic classification result from the configured different semantic analysis results, different semantic classification results, and the corresponding second response text comparison table; input the second response text into the AI voice generation model to obtain the second response voice, and send the second response voice to the called object.

[0037] In another embodiment of the present application, the second response text can be generated based on a pre-trained AI dialogue model.

[0038] For example, assume the called object is Mr. B, the mediation matter data is Bank A, the arrears is 100,000 yuan, and the mediation name is a third-party mediation agency entrusted by Bank A; the mediation data comes from Bank A; according to the identity information of the called object and the specific mediation matter data, generate the first response voice, including: Hello, Mr. B, I'm Staff Member C from the third-party mediation agency entrusted by Bank A. Now, on behalf of Bank A, I'm communicating with you about the matter of your 100,000 yuan arrears with Bank A and informing you of the following: Bank A has communicated with you about the overdue arrears on a certain date, but you haven't taken any action to repay the arrears. Now, Bank A has entrusted the court with this matter; we are now conducting pre-litigation mediation with you on this matter. Do you have any difficulties? In the above content, the statements such as "Now, Bank A has entrusted the court with this matter; we are now conducting pre-litigation mediation with you on this matter. Do you have any difficulties?" and "I'm Staff Member C from the third-party mediation agency entrusted by Bank A" come from the configured response templates; according to the different mediation matter data corresponding to the called object, the response templates are also different.

[0039] In the embodiment of the present application, if the voice analysis result obtained by analyzing the first response voice of the called object is that the called object is currently stating the current situation and reasons for being unable to repay the debt, then match the second response text, and combine the second response text and the configured response template to generate the second response voice.

[0040] In another embodiment of the present application, when analyzing the first response voice, keyword extraction technology will be combined to extract pre-configured keywords such as "unemployment" and "illness"; when the corresponding keywords exist in the first response voice, then according to the keywords, match the response template and preparation materials corresponding to the keyword from the configured different keywords, different response templates, and different preparation materials comparison table; generate the second response voice according to the response template, the second response text, and the preparation materials; for example, Okay, Mr. B, we have received your situation. Please submit the following preparation materials to a certain email address, and we will verify and contact you as soon as possible.

[0041] Step S120: If the voice analysis result meets the configured transfer rules, convert the first response voice and the first reply voice into a first response text and a first reply text respectively.

[0042] In the embodiments of the present application, the transfer rules are that the semantic analysis result, the semantic classification result, or the second response text is empty, or the semantic classification result is a transfer semantic classification result.

[0043] In the embodiments of the present application, if a matching response text can be obtained, it means that the AI voice generation model can continue to communicate with the called object. When it is impossible to communicate with the called object, for example, when the speech content of the called object cannot be recognized or the semantic analysis result cannot be obtained, a transfer is required.

[0044] For example, in the first reply voice, the called object does not speak, or there is no preset keyword, or the voice analysis result cannot extract valid information (such as dialect, etc.). At this time, it is determined that the transfer rules are met.

[0045] Step S130: Transfer the call with the called object to a human customer service, and send the identity information, historical call data, data of matters to be mediated, the first response text, and the first reply text to the human customer service.

[0046] In the embodiments of the present application, when the AI voice generation model cannot continue to communicate with the called object, a human customer service needs to intervene. However, when directly transferring, the human customer service is not aware of data such as the identity of the called object. Therefore, the corresponding data needs to be sent to the human customer service.

[0047] In another embodiment of the present application, the system makes outbound calls in batches, and the number of outbound calls is predicted based on the historical call connection situation: obtain historical call data, the corresponding historical call connection number, and the historical call call number within the configured time (i.e., connected and not hung up within a certain time), and obtain the number of mediators online at the same time during the historical time period corresponding to the historical call data; input the above data into a pre-constructed time series prediction model to obtain a trained time series prediction model; input the current number of mediators and the time data into the trained time series prediction model to obtain the target number of outbound calls; the system makes outbound calls for the target number of outbound calls.

[0048] In the embodiments of the present application, the time series prediction model can be ARIMA, SARIMA.

[0049] As Figure 2 shown, the intelligent call transfer method of the embodiments of the present application includes: 1. Mediators initiate AI intelligent outbound calls in batches, and the system automatically starts making batch calls.

[0050] 2. Once connected, the AI multi-round dialogue ability is invoked to start outputting audio, and the system begins a real-time dialogue with the party. During the dialogue, the AI selects and outputs appropriate dialogue content according to the context-limiting conditions.

[0051] 3. The system records the real-time voice-to-text dialogue between the AI and the party.

[0052] 4. When the system determines that the AI cannot continue the dialogue within 1 second, it automatically switches to the mediator's call line and synchronously sends the previous multi-round dialogue records between the AI and the party to the mediator.

[0053] 5. The mediator understands from the previous dialogue records where the AI left off in the dialogue and what was said before, ensuring that there are no obvious logical flaws in the language when the real person converses with the party, until the mediator completes the dialogue alone and hangs up.

[0054] Corresponding to the above method, an embodiment of the present application also provides an intelligent call transfer device, as Figure 3 shown. The intelligent call transfer device includes: A sending unit 310, configured to send a first response voice to the call object when the call is connected; wherein, the first response voice is generated based on the identity information of the call object, the data of the matter to be mediated, and the historical call data; A receiving unit 320, configured to receive a first reply voice from the call object in response to the first response voice; An analysis unit 330, configured to analyze the first reply voice to obtain a voice analysis result; A conversion unit 340, configured to convert the first response voice and the first reply voice into a first response text and a first reply text respectively if the voice analysis result meets the configured transfer rules; A transfer unit 350, configured to transfer the call with the call object to an artificial customer service, and send the identity information, historical call data, data of the matter to be mediated, the first response text, and the first reply text to the artificial customer service.

[0055] The functions of the functional units of the intelligent call transfer device provided in the above embodiments of the present application can be implemented by the above method steps. Therefore, the specific working processes and beneficial effects of each unit in the intelligent call transfer device provided in the embodiments of the present application will not be elaborated here.

[0056] An embodiment of the present application also provides an electronic device, as Figure 4 shown, including a processor 410, a communication interface 420, a memory 430, and a communication bus 440. Among them, the processor 410, the communication interface 420, and the memory 430 complete mutual communication through the communication bus 440.

[0057] A memory 430 for storing a computer program; A processor 410, when executing the program stored on the memory 430, implements the following steps: After the call is connected, send a first response voice to the called object; wherein, the first response voice is generated based on the identity information of the called object, the data of the matter to be mediated, and the historical call data; Receive a first reply voice from the called object in response to the first response voice; Analyze the first reply voice to obtain a voice analysis result; If the voice analysis result meets the configured transfer rule, convert the first response voice and the first reply voice into a first response text and a first reply text respectively; Transfer the call with the called object to a human customer service, and send the identity information, historical call data, data of the matter to be mediated, the first response text, and the first reply text to the human customer service.

[0058] The communication bus mentioned above may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0059] The communication interface is used for communication between the above-mentioned electronic device and other devices.

[0060] The memory may include a Random Access Memory (RAM), or may also include a Non-Volatile Memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0061] The above-mentioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0062] Since the implementation manners and beneficial effects of the devices of the electronic device in the above embodiments for solving problems can be realized by referring to the steps in the embodiments shown in Figure 1 Therefore, the specific working process and beneficial effects of the electronic device provided in the embodiments of the present application will not be repeated here.

[0063] In another embodiment provided by the present application, there is also provided a computer-readable storage medium storing instructions, which, when running on a computer, cause the computer to execute the intelligent call transfer method in any one of the above embodiments.

[0064] In another embodiment provided by the present application, there is also provided a computer program product containing instructions, which, when running on a computer, cause the computer to execute the intelligent call transfer method in any one of the above embodiments.

[0065] Those skilled in the art should understand that the embodiments in the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the embodiments in the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments in the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0066] Embodiments of the present application are described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0067] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0068] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0069] Although the preferred embodiments in the embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present application.

[0070] Obviously, those skilled in the art can make various changes and variations to the embodiments in the embodiments of the present application without departing from the spirit and scope of the embodiments in the embodiments of the present application. Thus, if these modifications and variations of the embodiments in the embodiments of the present application fall within the scope of the claims of the embodiments of the present application and their equivalent technologies, the embodiments in the embodiments of the present application are also intended to include these changes and variations.

Claims

1. An intelligent call forwarding method, characterized in that: The method comprises: When the call is connected, a first response voice is sent to the called party; wherein the first response voice is generated based on the identity information of the called party, data of items to be mediated, and historical call data; Receiving a first reply voice from the calling party to the first answer voice; Analyze the first reply speech to obtain a speech analysis result; If the speech analysis result satisfies the configured transfer rule, converting the first answer speech and the first reply speech into a first answer text and a first reply text respectively; The call with the calling party is transferred to the manual customer service, and the identity information, the historical call data, the data of the matters to be mediated, the first response text and the first reply text are sent to the manual customer service.

2. The method according to claim 1, characterized in that The method for generating the first response voice includes: Obtaining the identity information and data of matters to be mediated of the call object, as well as the historical call data of the call object; Generate a first response text based on the identity information, the data of the matters to be mediated, the historical call data and the configured response template; The first response text is input into a pre-trained AI speech generation model to obtain a first response speech.

3. The method according to claim 2, characterized in that The data on items to be mediated include: the bank where the debt is owed and the status of the debt; The historical call data includes: the number of historical calls, the historical call time and the call summary.

4. The method according to claim 3, characterized in that Inputting the first response text into a pre-trained AI voice generation model to obtain a first response voice includes: Inputting the first response text into a pre-trained AI voice generation model to obtain an initial response voice; wherein the AI ​​voice generation model is trained using historical mediation data; the historical mediation data is historical call data between different manual customer service representatives and different call objects; The initial response voice is subjected to voiceprint processing to obtain a first response voice.

5. The method according to claim 1, characterized in that Analyze the first reply voice to obtain a voice analysis result, including: Converting the first reply voice into text to obtain a first answer text; Preprocessing the first response text to obtain a preprocessed first response text; Performing semantic analysis on the preprocessed first response text to obtain a semantic analysis result; Inputting the preprocessed first response text and the semantic analysis result into a pre-trained text classification model to obtain a semantic classification result of the first response text; The semantic analysis result and the semantic classification result are determined as the speech analysis result of the first reply speech.

6. The method according to claim 4, characterized in that After obtaining the speech analysis result, the method further includes: Matching the second response text corresponding to the semantic analysis result and the semantic classification result from the configured comparison table of different semantic analysis results, different semantic classification results and corresponding second response texts; The second response text is input into the AI ​​voice generation model to obtain a second response voice, and the second response voice is sent to the calling party.

7. The method according to claim 6, characterized in that The method further comprises: If the semantic analysis result, the semantic classification result or the second response text is empty, the call with the calling party will be transferred to the manual customer service, and the identity information, the historical call data, the data of matters to be mediated, the response text and the reply text during this call will be sent to the manual customer service.

8. An intelligent call forwarding device, characterized in that: The device comprises: A sending unit, configured to send a first response voice to the calling party after the call is connected; wherein the first response voice is generated based on the identity information of the calling party, data of items to be mediated, and historical call data; A receiving unit, configured to receive a first reply voice from the calling party in response to the first answer voice; An analysis unit, configured to analyze the first reply speech to obtain a speech analysis result; a conversion unit, configured to convert the first answer voice and the first reply voice into a first answer text and a first reply text, respectively, if the voice analysis result satisfies the configured transfer rule; The transfer unit is used to transfer the call with the calling party to the manual customer service, and send the identity information, the historical call data, the data of the matters to be mediated, the first response text and the first reply text to the manual customer service.

9. An electronic device, characterized in that: The electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; A processor, for implementing any of the methods described in claims 1-7 when executing a program stored in a memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images