Call risk processing method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a call risk processing method and device, electronic equipment and storage medium, and relates to the technical field of communication. The method comprises: acquiring real-time call voice between a customer terminal and a customer service terminal, and converting the real-time call voice into call text; performing risk detection on the call text, and determining a call risk processing mode matched with the risk detection result; and performing risk processing on the current call between the customer terminal and the customer service terminal according to the call risk processing mode. The method can detect the generated call risk in real time through risk detection on the current call state, determine the corresponding call risk processing mode according to the difference of the call risk, and timely intervene in the current call, thereby effectively improving the timeliness and efficiency of call risk processing.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and in particular relates to a call risk processing method and device, electronic equipment and storage medium. BACKGROUND

[0002] With the increasing communication services (such as online customer service communication services, information recommendation services, etc.) between various types of agents (such as customer service agents) and customers, the call risks generated in the communication services also gradually increase, such as agent communication violations, customer sensitive questions, etc. At present, the agent assistance system can only be used to pre-process the agent service rules, and cannot timely discover and process the call risks generated in the real-time call process. SUMMARY

[0003] The present disclosure provides a call risk processing method and device, electronic equipment and storage medium, which can solve the problem of not being able to timely discover and process call risks in real-time call processes.

[0004] In a first aspect, the present disclosure provides a call risk processing method applied to an agent assistance system, the method comprising the following steps:

[0005] Obtaining real-time call voice between an agent terminal and a customer terminal, and converting the real-time call voice into call text;

[0006] Detecting risks of the call text, and determining a call risk processing mode matched with the risk detection result;

[0007] Processing risks of the current call between the agent terminal and the customer terminal according to the call risk processing mode.

[0008] In a second aspect, the present disclosure provides a call risk processing device, the device comprising:

[0009] An obtaining module, configured to obtain real-time call voice between an agent terminal and a customer terminal, and convert the real-time call voice into call text;

[0010] A detecting module, configured to detect risks of the call text, and determine a call risk processing mode matched with the risk detection result;

[0011] A processing module, configured to process risks of the current call between the agent terminal and the customer terminal according to the call risk processing mode.

[0012] In a third aspect, the present disclosure provides an electronic device, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores one or more computer programs executable by the at least one processor, and the one or more computer programs are executed by the at least one processor to enable the at least one processor to perform the method described above.

[0013] In a fourth aspect, the present disclosure provides a computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor / processing core, implements the method described above.

[0014] The embodiments provided by the present disclosure can discover the call risk being generated in the current call in real time by performing risk detection on the real-time call voice of the agent terminal and the client terminal, determine the corresponding call risk processing manner according to the difference of the call risk, timely intervene in the current call by using the determined call risk processing manner, and thus effectively improve the timeliness and processing efficiency of the call risk processing.

[0015] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0016] The accompanying drawings are included to provide a further understanding of the present disclosure and constitute a part of the specification, which together with the embodiments of the present disclosure serve to explain the present disclosure, and do not constitute a limitation of the present disclosure. The above and other features and advantages will become more apparent from the detailed description of the specific example embodiments, with reference to the accompanying drawings, in which:

[0017] Figure 1 An application scenario architecture diagram of the call risk processing method provided by the embodiments of the present disclosure;

[0018] Figure 2 A flowchart of the call risk processing method provided by the embodiments of the present disclosure;

[0019] Figure 3 One of the signaling diagrams of the call risk processing method provided by the embodiments of the present disclosure;

[0020] Figure 4 The second signaling diagram of the call risk processing method provided by the embodiments of the present disclosure;

[0021] Figure 5 A block diagram of the call risk processing device provided by the embodiments of the present disclosure;

[0022] Figure 6 A block diagram of an electronic device according to an embodiment of the disclosure. DETAILED DESCRIPTION

[0023] For the better understanding of the technical solutions of the present disclosure, the exemplary embodiments of the present disclosure are described below in conjunction with the drawings, including various details of the embodiments of the present disclosure to help understanding, which should be considered only as exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, for the sake of clarity and conciseness, the description below omits the description of well-known functions and structures.

[0024] In the case of no conflict, each embodiment of the present disclosure and each feature in the embodiments can be combined with each other.

[0025] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0026] The terms used herein are only used to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. The terms "connected" and / or "coupled" and / or and like terms are not restricted to physical or mechanical connections or couplings, and can include electrical connections, whether direct or indirect.

[0027] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an overly literal or overly formal sense unless expressly so defined herein.

[0028] In the related art, as the communication services (for example, online customer service communication services, information recommendation services, and the like) between various types of agents (for example, customer service agents) and customers gradually increase, the service demand generated by the communication services also gradually increases. In order to meet these service demands, an agent assistance system is introduced, which is used to provide intelligent assistance information (for example, reply information, agent communication rule prompt information, and the like) for the agents. For example, the agent assistance system obtains the call voice of the agent and the customer during the call process, converts the call voice into call text, matches the reply information related to the question of the customer in the call text, and provides the reply information to the agent for reply prompt. For another example, the agent assistance system generates the agent service rule prompt information according to the pre-set agent service rule information, and provides the agent service rule prompt information to the agent for service rule prompt during the call process between the agent and the customer.

[0029] The inventors found the following problems in the research of the related art: The agent assistance system can usually only provide service rule prompt according to the pre-set agent service rule information to reduce the call risk caused by non-standard service, but cannot discover the real-time call risk generated during the call process in time and process it. In order to solve the problems in the related art, the inventors thought of detecting the real-time call voice during the call process between the agent and the customer, so as to discover the call risk being generated in the current call in time, and determined different call risk processing manners according to the different call risks, so as to determine the corresponding call risk processing manner according to the detected call risk, and timely intervene in the current call by using the determined call risk processing manner, thereby effectively improving the timeliness and processing efficiency of the call risk processing.

[0030] The call risk processing method according to the embodiments of the present application can be executed by an electronic device such as a terminal device or a server. The terminal device can be a vehicle-mounted device, a user equipment (UE), a mobile device, a user terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, and the like. The server can be a standalone physical server, a server cluster, or a cloud server capable of cloud computing. The call risk processing method can be specifically realized by a processor calling computer readable program instructions stored in a memory of the electronic device.

[0031] Reference is made to Figure 1 , Figure 1A system architecture diagram showing an application scenario of a call risk processing method provided by an embodiment of the present disclosure is shown, and the system at least includes: a call exchange platform 1, a call center (Internet call center, ICC) 2 connected to the call exchange platform 1, an agent assistance system 3 connected to the call exchange platform 1 and the call center 2 respectively, and an agent terminal 4 connected to the call center 2 and the agent assistance system 3 respectively, and a customer terminal 5 connected to the call exchange platform 1. In addition, the system can further include an automatic speech recognition (ASR) system connected to the agent assistance system 3.

[0032] The call exchange platform 1 is a soft switching solution for communication, including a soft phone and a soft switch, to provide product driving of voice and chat. The call exchange platform is, for example, a Freeswitch platform, which can be used as a switch engine, a private branch exchange (PBX), an analog gateway, a multimedia server, etc. In the present disclosure, the call exchange platform 1 provides a communication switch service for the agent assistance system 3, the agent terminal 4, and the customer terminal 5.

[0033] The call center 2 is equivalent to an integrated "service window" of an integrated network. The call center 2 includes a computer telephony integration (CTI) module 21, which is a core technical module of the call center 2. Specifically, the call center 2 is based on an existing integrated information network of an enterprise or a group, and uses CTI technology to seamlessly integrate many parallel and vertical services provided by the integrated information network, to provide a horizontal service integrating multiple service functions. The CTI module 21 is used to automatically identify and process call signaling information in various information media by using computer technology, and to transmit predetermined communication information to users by establishing relevant call connections. The CTI module 21 can include the following sub-modules (not shown in the figure): a telephone line sub-module, an agent device sub-module, a CTI server sub-module, a CTI call center middleware sub-module, a call center application software sub-module, etc. Multiple agent terminals 4 are connected to the call center 2, and the call center 2 provides external communication services for the agent terminals 4. The agent assistance system 3 is connected to the call center 2, and calls the CTI module 21 through the call center 2, to realize the telephone communication function of the agent assistance system 3 and external terminals.

[0034] The agent support system 3 may include an agent manager terminal 31, which is used to monitor and manage agent terminals 4. The agent support system 3 provides various business support information to agent users of agent terminals 4 (e.g., customer service representatives, group employees, etc.) and agent manager users of agent manager terminal 31. This business support information may include at least one of the following: customer profile information, process status navigation information, call status information, agent map information, knowledge recommendation information, etc. In this disclosure, the agent support system 3 may also store information such as risk keywords, risk warning words, and call risk handling methods.

[0035] The ASR system 6 is used to receive real-time voice calls sent by the agent support system 3, convert the real-time voice calls into text calls, and then return the text calls to the agent support system 3.

[0036] See Figure 2 , Figure 2 A flowchart illustrating a method for handling call risks according to an embodiment of this disclosure is shown. The call risk handling method provided by this method can be applied to... Figure 1 In the seat assistance system 3, the method includes the following steps:

[0037] S1. Obtain the real-time voice call between the agent terminal and the client terminal, and convert the real-time voice call into text.

[0038] In practice, the agent terminal is transferred to the call exchange platform through the call center, enabling the agent terminal and the customer terminal to establish a call through the call exchange platform. The agent assistance system can obtain the real-time call voice between the agent terminal and the customer terminal from the call exchange platform, and then call the ASR system to perform text translation on the real-time call voice, thereby realizing the conversion of real-time call voice into call text.

[0039] In some examples, such as before S1, the method also includes:

[0040] Sub-step A: Pre-set multiple risk keywords and set a call risk handling method associated with each risk keyword.

[0041] The risk keywords are keywords for indicating possible call risks, and specifically, the risk keywords can be set according to call service rules, sensitive words, and the like. Different risk keywords can be associated with call risk processing manners in advance, and the risk keywords and the association between each risk keyword and the call risk processing manner can be stored in a storage medium of, for example, an agent assistance system. In S1, if a preset risk keyword is detected from the call text, the call risk processing manner for the current call can be quickly determined according to the association between the risk keyword and the call risk processing manner.

[0042] In some examples, a risk keyword library can be created in advance, and the preset risk keywords and the association between each risk keyword and the call risk processing manner can be stored in the risk keyword library. Subsequently, the risk keywords can be found and obtained from the risk keyword library by calling the risk keyword library. The risk keyword library can be stored in the agent assistance system or an external data storage server (for example, a database server), which is not limited herein.

[0043] S2, detecting the call text for risks and determining a call risk processing manner matched with the risk detection result.

[0044] Based on the above substep A, in the case where the plurality of risk keywords and the call risk processing manner associated with each risk keyword are preset, S2 can include the following substeps:

[0045] Substep one, detecting whether the call text contains any risk keyword in the plurality of risk keywords.

[0046] The call text is matched with the plurality of preset risk keywords. If any risk keyword in the plurality of preset risk keywords exists in the call text, it indicates that the current call between the client terminal and the agent terminal has a call risk.

[0047] In the embodiment where the risk keyword library is created and stored in the external data storage server, substep one includes:

[0048] Substep one a, generating a risk keyword obtaining command and sending the risk keyword obtaining command to the data storage server storing the risk keyword library.

[0049] Substep one b, receiving the plurality of risk keywords (and the association between the risk keywords and the call risk processing manner) contained in the risk keyword library returned by the data storage server in response to the risk keyword obtaining command.

[0050] The sub-step 1c detects whether the call text contains any of the plurality of risk keywords according to the plurality of risk keywords obtained.

[0051] The sub-step 2 determines the call risk processing mode associated with the detected risk keyword in the case that the risk detection result is that the call text contains any of the plurality of risk keywords, and determines the determined call risk processing mode as the call risk processing mode matched with the risk detection result.

[0052] The risk detection result is a detection result of detecting whether the call text contains the risk keyword. In the case that it is detected that the call text contains the preset plurality of risk keywords, it indicates that the current call between the client terminal and the agent terminal has a call risk. According to the association relationship between the risk keyword and the call risk processing mode, the call risk processing mode corresponding to the current call risk can be quickly determined, thereby improving the efficiency of risk processing and the accuracy of determining the processing mode.

[0053] In some examples, each risk keyword in the plurality of risk keywords is provided with a corresponding risk level. In the case that the call text contains a plurality of risk keywords under different call risk processing modes, the sub-step 2 includes:

[0054] The sub-step 2a determines the risk level of each risk keyword in the plurality of risk keywords contained in the call text.

[0055] It should be noted that in the embodiment in which each risk keyword is provided with a risk level, correspondingly, the information returned by the data storage server in response to the risk keyword acquisition command in the above-mentioned sub-step 1b at least includes: the plurality of risk keywords, the association relationship between each risk keyword in the plurality of risk keywords and the call risk processing mode, and the risk level of each risk keyword in the plurality of risk keywords.

[0056] The sub-step 2b determines the call risk processing mode associated with the risk keyword with the highest risk level as the call risk processing mode matched with the risk detection result.

[0057] Specifically, when setting the risk keywords, a risk level can be set for each risk keyword according to the risk importance or risk danger degree of the risk keyword. In some cases, multiple risk keywords can be detected in the call text of the current call, and the call risk processing manners corresponding to the multiple risk keywords are different. In this case, the call risk processing manner corresponding to the risk keyword with the highest risk level is determined as the call risk processing manner for the call risk of the current call, so as to ensure that the call risk corresponding to the risk keyword with the highest risk danger degree or importance is processed preferentially, thereby effectively improving the reliability and flexibility of the call risk intervention.

[0058] S3, processing the current call between the agent terminal and the customer terminal according to the call risk processing manner.

[0059] By detecting different call risks, different risk processing manners are determined for different call risks, and the current call is processed according to the determined risk processing manner. In this way, different call risks can be intelligently processed, and the call risk processing is more flexible and accurate.

[0060] Further, the agent assistance system needs to call the call exchange platform through the CTI module of the call center to implement risk processing, or directly interacts with the agent terminal to implement risk processing. Therefore, S3 includes:

[0061] Substep one, generating risk processing instruction information corresponding to the call risk processing manner, and sending the risk processing instruction information to an instruction information receiving end, so that the instruction information receiving end processes the current call between the agent terminal and the customer terminal according to the risk processing instruction information.

[0062] The instruction information receiving end includes the agent terminal and / or a call center providing external communication services for the agent terminal.

[0063] Specifically, the call risk processing manner has multiple implementation manners, and the following will take three different call risk processing manners as examples to illustrate the specific process of substep one of S3.

[0064] For one of the call risk processing manners, the call risk processing manner is a call disconnection and reconstruction processing manner, in other words, the current call between the agent terminal and the customer terminal is disconnected, and a call between the agent manager terminal in the agent assistance system and the customer terminal is established. Correspondingly, the risk processing instruction information in substep one of S3 is call disconnection and reconstruction instruction information, and the instruction information receiving end is a call center. In this case, substep one of S3 specifically includes:

[0065] The sub-step la generates the call disconnection and reconstruction instruction information based on the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent manager terminal, and sends the call disconnection and reconstruction instruction information to the call center, so that the call center generates the call disconnection and reconstruction instruction containing the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent manager terminal based on the call disconnection and reconstruction instruction information, and sends the call disconnection and reconstruction instruction to the call switching platform connected to the call center.

[0066] The call disconnection and reconstruction instruction is used to instruct the call switching platform to generate and call the call creation instruction containing the identification code of the agent terminal and the identification code of the agent manager terminal to establish the call between the agent terminal and the agent manager terminal, and generate and call the call disconnection instruction containing the identification code of the agent terminal and the identification code of the customer terminal to disconnect the call between the agent terminal and the customer terminal.

[0067] Specifically, referring to Figure 3 , Figure 3 The system signaling diagram of the sub-step la is shown. As Figure 3 shown, the sub-step la is applied in the application scenario shown in Figure 1 and will be described in detail as follows:

[0068] S1a, the agent assistance system generates the call disconnection and reconstruction instruction information, and sends the call disconnection and reconstruction instruction information to the call center.

[0069] The call disconnection and reconstruction instruction information contains the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent manager terminal, wherein the identification code is a universally unique identifier (UUID), and the call switching platform adopts the UUID of the communication terminal to establish communication in the standard of the call switching platform (such as Freeswitch).

[0070] The agent assistance system calls the call disconnection interface provided by the CTI module of the call center to send the call disconnection and reconstruction instruction information to the CTI module.

[0071] S2a, the CTI module of the call center generates the call disconnection and reconstruction instruction based on the call disconnection and reconstruction instruction information in response to the call disconnection and reconstruction instruction information, and sends the call disconnection and reconstruction instruction to the call switching platform.

[0072] The call disconnection and reconstruction instruction contains the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent manager terminal. The CTI module can interact with the call switching center by using the CTI technology, and call various instructions of the call switching center to realize various call functions.

[0073] S3a, the call switching platform generates and invokes a call teardown instruction (for example, a UUID_kill instruction) containing the identification code of the agent terminal and the identification code of the customer terminal to teardown the call between the agent terminal and the customer terminal, that is, to terminate the communication channel between the agent terminal and the customer terminal.

[0074] S24a, the call switching platform generates and invokes a call creation instruction containing the identification code of the agent terminal and the identification code of the agent supervisor terminal to establish a call between the agent terminal and the agent supervisor terminal.

[0075] Specifically, the call creation instruction includes a call initiation instruction (for example, an originate instruction) to instruct the call switching platform to initiate a call instruction with the agent supervisor terminal as the called party and the customer terminal as the calling party; the call creation instruction also includes a call transfer instruction (for example, a UUID_transfer instruction) carrying the UUID of the agent supervisor terminal to instruct the call switching platform to transfer the initiated call instruction to the agent supervisor terminal to establish a call between the agent supervisor and the customer terminal.

[0076] According to this way, in the case that the call risk level of the current call between the customer and the agent is high, the call between the customer and the agent can be terminated directly, and a call between the agent supervisor and the customer is established to realize a higher level of call intervention.

[0077] For another call risk processing mode, the call risk processing mode is a call insertion processing mode, in other words, the current call between the agent terminal and the customer terminal is maintained, and the agent supervisor terminal in the agent assistance system is inserted into the current call to establish a three-party call among the agent terminal, the customer terminal and the agent supervisor terminal. Correspondingly, the risk processing instruction information in sub-step one of S3 is call insertion instruction information, and the instruction information receiving end is the call center. In this case, sub-step one specifically includes:

[0078] Sub-step one b, based on the identification code of the agent terminal and the identification code of the agent supervisor terminal, generate call insertion instruction information, and send the call insertion instruction information to the call center, so that the call center generates call insertion instruction containing the identification code of the agent terminal and the identification code of the agent supervisor terminal based on the call insertion instruction information, and sends the call insertion instruction to the call switching platform connected with the call center.

[0079] The call insertion instruction is used to instruct the call switching platform to determine the identification code of the customer terminal currently in conversation with the agent terminal through the identification code of the agent terminal, generate and call a three-party call instruction containing the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent manager terminal, and create a three-party call among the customer terminal, the agent terminal and the agent manager terminal.

[0080] Specifically, referring to Figure 4 , Figure 4 The system signaling diagram of sub-step 1b is shown. As Figure 4 indicated, sub-step 1b is applied in the application scenario shown in Figure 1 and is described in detail as follows.

[0081] S1b, the agent assistance system generates call insertion instruction information and sends the call insertion instruction information to the call center.

[0082] The call insertion instruction information contains the identification code of the agent terminal and the identification code of the agent manager terminal, wherein the identification code is UUID, and in the standard of the call switching platform (such as Freeswitch), the call switching platform uses the UUID of the communication terminal to establish communication.

[0083] The agent assistance system calls the call insertion interface provided by the CTI module of the call center to send the call insertion instruction information to the CTI module.

[0084] S2b, the CTI module of the call center generates a call insertion instruction based on the call insertion instruction information in response to the call insertion instruction information, and sends the call insertion instruction to the call switching platform.

[0085] The call insertion instruction contains the identification code of the agent terminal and the identification code of the agent manager terminal. The CTI module can interact with the call switching center by using the CTI technology, and call various instructions of the call switching center to realize various call functions.

[0086] S3b, the call switching platform determines the identification code of the customer terminal currently in conversation with the agent terminal through the identification code of the agent terminal in the call insertion instruction.

[0087] S4b, the call switching platform generates and calls a three-party call instruction to create a three-party call among the customer terminal, the agent terminal and the agent manager terminal.

[0088] Specifically, the three-way call instruction contains the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent supervisor terminal. The three-way call instruction includes a call initiation instruction (for example, an originate instruction) to instruct the call switching platform to initiate a call instruction; the three-way call instruction also includes a three-way call creation instruction (for example, a three_way(UUID) instruction) carrying the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent supervisor terminal, and the three-way call creation instruction is implemented by calling the Freeswitch mod_dptools module (which can provide a three-way call function). After calling the three-way call creation instruction, the Freeswitch mod_dptools module creates a three-way call among the customer terminal, the agent terminal and the agent supervisor terminal according to the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent supervisor terminal.

[0089] According to this manner, in the case that the risk degree of the current call between the customer and the agent is high, the call between the customer and the agent can be directly joined for communication without terminating the call between the customer and the agent, so as to realize efficient call intervention

[0090] For another call risk processing manner, the call risk processing manner is a risk prompt processing manner, in other words, the current call between the agent terminal and the customer terminal is maintained, and the agent supervisor terminal in the agent assistance system directly communicates with the agent terminal to send risk prompt information to the agent terminal for business indication. Correspondingly, the risk processing indication information in substep one of S3 is the risk prompt information, and the indication information receiving end is the agent terminal. In this case, substep one specifically includes:

[0091] Substep one c, generating risk prompt information based on the risk prompt word and the corresponding risk processing scheme, and sending the risk prompt information to the agent terminal to prompt the agent terminal to perform risk processing on the current call between the agent terminal and the customer terminal according to the risk prompt information.

[0092] In this case, the agent assistance system directly communicates with the agent terminal and has no communication connection with the customer terminal, and the agent assistance system directly sends the risk prompt information to the agent terminal to prompt the agent user of the agent terminal to pay attention to the call risk and prompt the agent user to perform risk processing.

[0093] Wherein, the risk prompt word is generated in the following manner:

[0094] Manner one, sending the call text to the fuzzy matching system for risk prompt word fuzzy matching, and generating the risk prompt word according to the matching result.

[0095] The fuzzy matching system can be a system specially provided for risk semantic recognition by a third party. The fuzzy matching system forms fuzzy matching rules through model training. The call text converted from the call voice between the client terminal and the agent terminal in the method is sent to the fuzzy matching system for fuzzy matching to detect whether there is a risk prompt word trained by the fuzzy matching system in the call text. If there is, the matched risk prompt word trained by the fuzzy matching system is determined as the risk prompt word in substep 1c.

[0096] In mode two, the preset risk prompt word set is used to match the risk prompt word against the call text, and the risk prompt word is generated according to the matching result.

[0097] The risk prompt word set containing the risk prompt word can be generated in advance according to the call service rule, sensitive word, etc. It is detected whether there is a risk prompt word set in the call text converted from the call voice between the client terminal and the agent terminal. If there is, the risk prompt word matched in the risk prompt word set is determined as the risk prompt word in substep 1c. It should be noted that in the method, in some examples, the risk prompt word can be the above-mentioned risk keyword. Accordingly, in this case, the risk prompt word is determined in the following manner: the risk keyword associated with the risk prompt processing mode detected from the call text in S2 is determined as the risk prompt word. Of course, the risk prompt word can also be a different word from the risk keyword. The specific difference is that the risk keyword is used to determine the corresponding call risk processing mode, and the risk prompt word is used to provide the agent user of the agent terminal for risk prompt, which needs to consider the relevance of the business and the readability of human language. In some examples, the risk prompt word can be generated according to the risk keyword.

[0098] Further, before S1, the method can further include: setting a matching risk processing scheme for each risk prompt word. Then in substep 1c, the risk processing scheme can be determined in the following manner: according to the matching relationship between the risk prompt word and the risk processing scheme, the risk processing scheme matched with the risk prompt word is determined.

[0099] Here, the risk processing scheme can be the textual prompt information of the risk processing flow set according to the risk prompt word, which is sent and displayed to the agent terminal to provide auxiliary information to the agent terminal and prompt the agent user of the agent terminal to perform risk processing according to the risk processing scheme.

[0100] The method for processing a call risk provided by the embodiments of the present disclosure can discover a call risk generated in a current call in real time by performing risk detection on call voice between an agent terminal and a customer terminal, and determine a corresponding call risk processing manner according to different call risks, and timely intervene in the current call by using the determined call risk processing manner, thereby effectively improving the timeliness and processing efficiency of the call risk processing.

[0101] It can be understood that the above-mentioned various method embodiments mentioned in the present disclosure can be combined with each other to form combined embodiments without deviating from the principle logic. Limited by the length, the present disclosure will not be repeated. Those skilled in the art can understand that the specific execution order of each step in the above-mentioned method should be determined according to its function and possible internal logic.

[0102] In addition, the present disclosure also provides a call risk processing apparatus, an electronic device, and a computer readable storage medium, which can be used to implement any one of the dynamic report generation methods provided by the present disclosure. The corresponding technical solutions and descriptions are described in the method part and are not repeated.

[0103] Figure 5 The system architecture diagram of a call risk processing apparatus provided by the embodiments of the present disclosure.

[0104] With reference to Figure 5 The present disclosure provides a call risk processing apparatus, which comprises:

[0105] The acquisition module 101 is configured to acquire real-time call voice between an agent terminal and a customer terminal, and convert the real-time call voice into call text.

[0106] The detection module 102 is configured to perform risk detection on the call text, and determine a call risk processing manner matched with the risk detection result.

[0107] The processing module 103 is configured to perform risk processing on a current call between the agent terminal and the customer terminal according to the call risk processing manner.

[0108] In some examples, the processing module 103 is specifically configured to:

[0109] generate risk processing instruction information corresponding to the call risk processing manner, and send the risk processing instruction information to an instruction information receiving end, so that the instruction information receiving end performs risk processing on the current call between the agent terminal and the customer terminal according to the risk processing instruction information.

[0110] The instruction information receiving end comprises the agent terminal, and / or a call center providing external communication services for the agent terminal.

[0111] In some examples, the call risk processing manner is a call disconnection and reconstruction processing manner, the risk processing indication information is call disconnection and reconstruction indication information, and the indication information receiving end is a call center; the agent assistance system comprises an agent manager terminal; and the processing module 103 is specifically configured to:

[0112] generate the call disconnection and reconstruction indication information based on the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent manager terminal, and send the call disconnection and reconstruction indication information to the call center, so that the call center generates a call disconnection and reconstruction instruction containing the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent manager terminal based on the call disconnection and reconstruction indication information, and sends the call disconnection and reconstruction instruction to a call switching platform connected to the call center;

[0113] The call disconnection and reconstruction instruction is used to instruct the call switching platform to generate and invoke a call creation instruction containing the identification code of the agent terminal and the identification code of the agent manager terminal to establish a call between the agent terminal and the agent manager terminal, and generate and invoke a call disconnection instruction containing the identification code of the agent terminal and the identification code of the customer terminal to disconnect the call between the agent terminal and the customer terminal.

[0114] In some examples, the call risk processing manner is a call disconnection and reconstruction processing manner, the risk processing indication information is call disconnection and reconstruction indication information, and the indication information receiving end is a call center; the agent assistance system comprises an agent manager terminal; and the processing module 103 is specifically configured to:

[0115] generate the call disconnection and reconstruction indication information based on the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent manager terminal, and send the call disconnection and reconstruction indication information to the call center, so that the call center generates a call disconnection and reconstruction instruction containing the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent manager terminal based on the call disconnection and reconstruction indication information, and sends the call disconnection and reconstruction instruction to a call switching platform connected to the call center;

[0116] The call disconnection and reconstruction instruction is used to instruct the call switching platform to generate and invoke a call creation instruction containing the identification code of the agent terminal and the identification code of the agent manager terminal to establish a call between the agent terminal and the agent manager terminal, and generate and invoke a call disconnection instruction containing the identification code of the agent terminal and the identification code of the customer terminal to disconnect the call between the agent terminal and the customer terminal.

[0117] In some examples, the call risk processing manner is a risk prompt processing manner, the risk processing indication information is risk prompt information, and the indication information receiving end is the agent terminal; and the processing module 103 is specifically configured to:

[0118] generate the risk prompt information based on the risk prompt word and the corresponding risk processing scheme, and send the risk prompt information to the agent terminal to prompt the agent terminal to perform risk processing on the current call between the agent terminal and the client terminal according to the risk prompt information;

[0119] The risk prompt word is generated in the following manner:

[0120] The call text is sent to the fuzzy matching system for risk prompt word fuzzy matching, and the risk prompt word is generated according to the matching result;

[0121] In some examples, the risk prompt word is matched with the call text by using a preset word set of risk prompt words, and the risk prompt word is generated according to the matching result.

[0122] In some examples, the apparatus further comprises:

[0123] The risk keyword module is configured to pre-set a plurality of risk keywords, and set, for each risk keyword, a call risk processing manner associated with the risk keyword;

[0124] The detection module 102 is specifically configured to:

[0125] detect whether the call text contains any of the plurality of risk keywords;

[0126] In a case where the risk detection result is that the call text contains any of the plurality of risk keywords, determine the call risk processing manner associated with the detected risk keyword, and determine the determined call risk processing manner as the call risk processing manner matched with the risk detection result.

[0127] In some examples, each risk keyword of the plurality of risk keywords is provided with a corresponding risk level; in a case where the call text contains a plurality of risk keywords under different call risk processing manners, the detection module 102 is specifically configured to:

[0128] determine the risk level of each risk keyword of the plurality of risk keywords contained in the call text;

[0129] determine the call risk processing manner associated with the risk keyword with the highest risk level as the call risk processing manner matched with the risk detection result.

[0130] Figure 6 A block diagram of an electronic device according to an embodiment of the present disclosure is provided.

[0131] Reference is made to Figure 6The embodiment of the present disclosure provides an electronic device, which comprises: at least one processor 501; at least one memory 502, and one or more I / O interfaces 503 connected between the processor 501 and the memory 502; wherein the memory 502 stores one or more computer programs executable by the at least one processor 501, and the one or more computer programs are executed by the at least one processor 501 to execute the above-mentioned call risk processing method, which comprises the following steps:

[0132] obtaining real-time call voice between the agent terminal and the customer terminal, and converting the real-time call voice into call text;

[0133] detecting the call text for risk, and determining a call risk processing mode matched with the risk detection result;

[0134] processing the current call between the agent terminal and the customer terminal according to the call risk processing mode.

[0135] In some examples, processing the current call between the agent terminal and the customer terminal according to the call risk processing mode comprises the following steps:

[0136] generating risk processing instruction information corresponding to the call risk processing mode, and sending the risk processing instruction information to an instruction information receiving end, so that the instruction information receiving end processes the current call between the agent terminal and the customer terminal according to the risk processing instruction information;

[0137] The instruction information receiving end comprises: an agent terminal, and / or a call center providing external communication services for the agent terminal.

[0138] In some examples, the call risk processing mode is a call disconnection and reconstruction processing mode, the risk processing instruction information is call disconnection and reconstruction instruction information, and the instruction information receiving end is a call center; the agent assistance system comprises an agent manager terminal; generating risk processing instruction information corresponding to the call risk processing mode, and sending the risk processing instruction information to the instruction information receiving end, so that the instruction information receiving end processes the current call between the agent terminal and the customer terminal according to the risk processing instruction information, comprises:

[0139] generating the call disconnection and reconstruction instruction information based on the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent manager terminal, and sending the call disconnection and reconstruction instruction information to the call center, so that the call center generates the call disconnection and reconstruction instruction containing the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent manager terminal based on the call disconnection and reconstruction instruction information, and sends the call disconnection and reconstruction instruction to a call switching platform connected with the call center;

[0140] The call teardown reconstruction instruction is used to instruct the call switching platform to generate and invoke a call creation instruction containing the identification code of the agent terminal and the identification code of the agent supervisor terminal to establish a call between the agent terminal and the agent supervisor terminal, and generate and invoke a call teardown instruction containing the identification code of the agent terminal and the identification code of the customer terminal to teardown the call between the agent terminal and the customer terminal.

[0141] In some examples, the call risk processing mode is a call insertion processing mode, the risk processing indication information is call insertion indication information, and the indication information receiving end is a call center; the agent assistance system includes an agent supervisor terminal; risk processing indication information corresponding to the call risk processing mode is generated, and the risk processing indication information is sent to the indication information receiving end, so that the indication information receiving end performs risk processing on a current call between the agent terminal and the customer terminal according to the risk processing indication information, including:

[0142] The call insertion indication information is generated based on the identification code of the agent terminal and the identification code of the agent supervisor terminal, and is sent to the call center, so that the call center generates a call insertion instruction containing the identification code of the agent terminal and the identification code of the agent supervisor terminal based on the call insertion indication information, and sends the call insertion instruction to a call switching platform connected to the call center;

[0143] The call insertion instruction is used to instruct the call switching platform to determine the identification code of the customer terminal currently having a call with the agent terminal through the identification code of the agent terminal, generate and invoke a three-party call instruction containing the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent supervisor terminal, and create a three-party call among the customer terminal, the agent terminal and the agent supervisor terminal.

[0144] In some examples, the call risk processing mode is a risk prompt processing mode, the risk processing indication information is risk prompt information, and the indication information receiving end is an agent terminal; risk processing indication information corresponding to the call risk processing mode is generated, and the risk processing indication information is sent to the indication information receiving end, so that the indication information receiving end performs risk processing on a current call between the agent terminal and the customer terminal according to the risk processing indication information, including:

[0145] The risk prompt information is generated based on the risk prompt word and the corresponding risk processing scheme, and is sent to the agent terminal to prompt the agent terminal to perform risk processing on a current call between the agent terminal and the customer terminal according to the risk prompt information;

[0146] The risk prompt word is generated in the following way:

[0147] The call text is sent to a fuzzy matching system for risk prompt word fuzzy matching, and a risk prompt word is generated according to the matching result.

[0148] And / or, a preset risk prompt word set is used for risk prompt word matching on the call text, and a risk prompt word is generated according to a matching result.

[0149] In some examples, real-time call voice between the agent terminal and the customer terminal is acquired, and before the real-time call voice is converted into call text, the method further includes:

[0150] A plurality of risk keywords are preset, and a call risk processing manner associated with each risk keyword is set for each risk keyword;

[0151] Risk detection is performed on the call text, and a call risk processing manner matched with a risk detection result is determined, including:

[0152] It is detected whether the call text contains any of the plurality of risk keywords;

[0153] In a case where the risk detection result is that the call text contains any of the plurality of risk keywords, a call risk processing manner associated with the detected risk keyword is determined, and the determined call risk processing manner is determined as the call risk processing manner matched with the risk detection result.

[0154] In some examples, each risk keyword of the plurality of risk keywords is provided with a corresponding risk level; in a case where the call text contains a plurality of risk keywords under different call risk processing manners, a call risk processing manner associated with the detected risk keyword is determined, and the determined call risk processing manner is determined as the call risk processing manner matched with the risk detection result, including:

[0155] The risk level of each risk keyword of the plurality of risk keywords contained in the call text is determined;

[0156] The call risk processing manner associated with the risk keyword with the highest risk level is determined as the call risk processing manner matched with the risk detection result.

[0157] The disclosure embodiments also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor / processing core, implements the call risk processing method described above. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0158] The disclosure embodiments also provide a computer program product including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, when the computer-readable code is run in a processor of an electronic device, the processor in the electronic device executes the call risk processing method described above.

[0159] Those skilled in the art can understand that all or some of the steps in the methods disclosed above and the functional modules / units in the systems and devices can be implemented by software, firmware, hardware, or a combination thereof. In hardware implementation, the split between the functional modules / units referred to in the above description does not necessarily correspond to the split between physical components; for example, one physical component can have multiple functions, or one function or step can be performed by several physical components working together. Certain physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on computer-readable storage media, which can include computer storage media (or non-transitory media) and communication media (or transitory media).

[0160] As is well known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable program instructions, data structures, program modules or other data. Computer storage media include, but are not limited to, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM), static random access memory (SRAM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by a computer. Further, as is well known to those skilled in the art, communication media typically embodies computer readable program instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. Accordingly, the disclosure is considered to include any

[0161] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0162] Computer readable program instructions for carrying out operations of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state setting data, or any combination of one or more of the above in any combination of one or more programming languages including an object oriented programming language such as Smalltalk, C++ or the like and conventional procedural programming languages such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0163] The computer program product described herein can be embodied in a specific manner by hardware, software, or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium. In another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK), and the like.

[0164] The various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer readable program instructions.

[0165] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include a non-transitory computer readable storage medium that can be a computer- readable storage medium having no data storage cycles that change state. The instructions can be executed by one or more processors of a computer, other programmable data processing apparatus, or other devices to produce a computer-implemented process such that the instructions which execute via the one or more processors of the computer or other programmable data processing devices create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0166] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0167] The flow and block diagrams in the drawings show architectural, functional, and operational aspects of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow and block diagrams can represent a module, a segment, or a portion of instructions which comprise one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may

[0168] Example embodiments have been disclosed and, although a specific terminology is employed, it is merely for the convenience of the reader and is not intended to be limiting. In some instances, specific details have been included for the purpose of providing a thorough understanding of the embodiments presented, but it will be apparent to those skilled in the art that embodiments of the application can be practiced without these specific details. In some instances, features, characteristics and / or elements described in connection with a particular embodiment can be used in conjunction with, or switched to, features, characteristics and / or elements described in connection with other embodiments, unless otherwise explicitly stated. Accordingly, it will be understood that various changes in form and details can be made without departing from the scope of the disclosure as set forth in the appended claims.

Claims

1. A method for handling call risk, characterized by, The application is applied to a seat assistant system, wherein a risk keyword library is preset in the seat assistant system, the risk keyword library comprises a plurality of risk keywords and a call risk processing mode associated with each risk keyword, and the method comprises the following steps: Obtaining real-time call voice between a seat terminal and a customer terminal, and converting the real-time call voice into call text; Performing risk detection on the call text based on the risk keyword library, and determining a call risk processing mode matched with the risk detection result, the call risk processing mode comprising a call dismantling and reconstruction processing mode, a call insertion processing mode and a risk prompt processing mode; Performing risk processing on the current call between the seat terminal and the customer terminal according to the call risk processing mode.

2. The method of claim 1, wherein, The risk processing on the current call between the seat terminal and the customer terminal according to the call risk processing mode comprises: Generating risk processing indication information corresponding to the call risk processing mode, and sending the risk processing indication information to an indication information receiving end, so that the indication information receiving end performs risk processing on the current call between the seat terminal and the customer terminal according to the risk processing indication information; The indication information receiving end comprises the seat terminal and / or a call center providing external communication services for the seat terminal.

3. The method of claim 2, wherein, The call risk processing mode is a call dismantling and reconstruction processing mode, the risk processing indication information is call dismantling and reconstruction indication information, and the indication information receiving end is the call center; the seat assistant system comprises a seat manager terminal; The risk processing on the current call between the seat terminal and the customer terminal according to the call risk processing mode comprises: Generating call dismantling and reconstruction indication information based on the identification code of the seat terminal, the identification code of the customer terminal and the identification code of the seat manager terminal, and sending the call dismantling and reconstruction indication information to the call center, so that the call center generates call dismantling and reconstruction instructions containing the identification code of the seat terminal, the identification code of the customer terminal and the identification code of the seat manager terminal based on the call dismantling and reconstruction indication information, and sends the call dismantling and reconstruction instructions to a call switching platform connected with the call center; The call dismantling and reconstruction instructions are used to instruct the call switching platform to generate and call call creation instructions containing the identification code of the seat terminal and the identification code of the seat manager terminal to establish a call between the seat terminal and the seat manager terminal, and to generate and call call dismantling instructions containing the identification code of the seat terminal and the identification code of the customer terminal to dismantle the call between the seat terminal and the customer terminal.

4. The method of claim 2, wherein, The call risk processing mode is a call insertion processing mode, the risk processing instruction information is call insertion instruction information, and the instruction information receiving end is the call center. The agent assistance system comprises an agent manager terminal. The risk processing instruction information corresponding to the call risk processing mode is generated, and the risk processing instruction information is sent to the instruction information receiving end, so that the instruction information receiving end performs risk processing on the current call between the agent terminal and the customer terminal according to the risk processing instruction information, comprising: Call insertion instruction information is generated based on the identification code of the agent terminal and the identification code of the agent manager terminal, and the call insertion instruction information is sent to the call center, so that the call center generates a call insertion instruction containing the identification code of the agent terminal and the identification code of the agent manager terminal based on the call insertion instruction information, and sends the call insertion instruction to the call switching platform connected to the call center; Wherein, the call insertion instruction is used to instruct the call switching platform to determine the identification code of the customer terminal performing the current call with the agent terminal through the identification code of the agent terminal, generate and call a three-party call instruction containing the identification code of the agent terminal, the identification code of the customer terminal and the identification code of the agent manager terminal, and create a three-party call between the customer terminal, the agent terminal and the agent manager terminal.

5. The method of claim 2, wherein, The call risk processing mode is a risk prompt processing mode, the risk processing instruction information is risk prompt information, and the instruction information receiving end is the agent terminal. The risk processing instruction information corresponding to the call risk processing mode is generated, and the risk processing instruction information is sent to the instruction information receiving end, so that the instruction information receiving end performs risk processing on the current call between the agent terminal and the customer terminal according to the risk processing instruction information, comprising: Risk prompt information is generated based on risk prompt words and corresponding risk processing schemes, and the risk prompt information is sent to the agent terminal to prompt the agent terminal to perform risk processing on the current call between the agent terminal and the customer terminal according to the risk prompt information; Wherein, the risk prompt words are generated in the following way: The call text is sent to a fuzzy matching system for risk prompt word fuzzy matching, and the risk prompt words are generated according to the matching result; And / or, a preset risk prompt word set is used to match the risk prompt words for the call text, and the risk prompt words are generated according to the matching result.

6. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: A plurality of risk keywords are set in advance, and a call risk processing mode associated with each risk keyword is set for each risk keyword; The risk detection of the call text based on the risk keyword library and the determination of the call risk processing mode matched with the risk detection result, comprising: Detecting whether the call text contains any of the plurality of risk keywords; In a case where the risk detection result is that the call text contains any of the plurality of risk keywords, a call risk processing mode associated with the detected risk keyword is determined, and the determined call risk processing mode is determined as the call risk processing mode matched with the risk detection result.

7. The method of claim 6, wherein, Each of the plurality of risk keywords is provided with a corresponding risk level. In a case where the call text contains a plurality of risk keywords under different call risk processing modes, the call risk processing mode associated with the detected risk keyword is determined, and the determined call risk processing mode is determined as the call risk processing mode matched with the risk detection result, including: Determining the risk level of each risk keyword in the plurality of risk keywords contained in the call text; The call risk processing mode associated with the risk keyword with the highest risk level is determined as the call risk processing mode matched with the risk detection result.

8. A call risk handling apparatus, characterized by comprising: The device is pre-stored with a risk keyword library, the risk keyword library includes a plurality of risk keywords and a call risk processing mode associated with each risk keyword, and the device includes: An acquisition module is configured to acquire real-time call voice between a client terminal and a customer terminal, and convert the real-time call voice into a call text; A detection module is configured to perform risk detection on the call text based on the risk keyword library, and determine a call risk processing mode matched with the risk detection result, the call risk processing mode including a call dismantling and reconstruction processing mode, a call insertion processing mode, and a risk prompt processing mode; A processing module is configured to perform risk processing on a current call between the client terminal and the customer terminal according to the call risk processing mode.

9. An electronic device, comprising: including: At least one processor; and A memory connected to the at least one processor; wherein The memory stores one or more computer programs executable by the at least one processor, and the one or more computer programs are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the method of any one of claims 1-7.

Images