Method and device for recommending speech skills

Abstract

The present application provides a speech recommendation method and device, which relates to the field of artificial intelligence technology. The method includes: obtaining batch collection business information groups, each collection business information group includes: outbound collection call information and customer repayment information; if there is a collection business information group whose customer repayment information is on-time repayment information, then marking the pending recording file corresponding to the outbound collection call information of the collection business information group as a positive pending recording file; applying a preset speech recommendation algorithm and the positive pending recording file to generate and output a positive speech recommendation list. The present application can effectively provide speech assistance to agents, thereby improving the efficiency and success rate of the collection business.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology and can also be used in the financial field, and in particular to a method and device for recommending speech skills. Background Art

[0002] With the continuous development of the financial field, in the outbound collection business, speech skills play a very important role in promoting customer repayment. Due to the uneven capabilities of outbound call agents and their high mobility, outbound call agents only conduct outbound collection based on communication experience, which is prone to low collection efficiency and low collection success rate. Summary of the invention

[0003] In response to the problems in the prior art, the present application proposes a method and device for recommending speech skills, which can effectively provide speech skills assistance to agents, thereby improving the efficiency and success rate of debt collection business.

[0004] In order to solve the above technical problems, this application provides the following technical solutions:

[0005] In a first aspect, the present application provides a method for recommending a speech technique, comprising:

[0006] Obtain batch collection business information groups, each collection business information group includes: outbound collection call information and customer repayment information;

[0007] If there is a collection business information group in which the customer repayment information is on-time repayment information, the pending recording file corresponding to the outbound collection call information of the collection business information group is marked as a positive pending recording file;

[0008] Apply the preset speech recommendation algorithm and the positive recording file to be processed to generate and output a positive speech recommendation list.

[0009] Furthermore, the application uses a preset speech recommendation algorithm and the positive recording file to be processed to generate and output a positive speech recommendation list, including:

[0010] Convert the forward recording file to be processed into a conversation list between the forward agent and the customer;

[0011] Apply the conversation list between the positive agent and the customer to obtain a positive keyword phrase set;

[0012] Apply the positive keyword phrase set and the preset speech recommendation algorithm to generate and output a positive speech recommendation list.

[0013] Furthermore, each collection business information group also includes: customer complaint information;

[0014] Correspondingly, after obtaining the batch collection business information group, it also includes:

[0015] If there is a collection business information group in which the customer complaint information is the complained information, the pending recording file corresponding to the outbound collection call information of the collection business information group is marked as a negative pending recording file;

[0016] Apply the preset speech recommendation algorithm and the positive recording file to be processed to generate and output a negative speech recommendation list.

[0017] Furthermore, the application uses a preset speech recommendation algorithm and the positive recording file to be processed to generate and output a negative speech recommendation list, including:

[0018] Convert the negative to-be-processed recording file into a conversation list between the negative agent and the customer;

[0019] Apply the conversation list between the negative agent and the customer to obtain a set of negative keyword phrases;

[0020] Apply the negative keyword phrase set and the preset speech recommendation algorithm to generate and output a negative speech recommendation list.

[0021] Furthermore, the preset speech recommendation algorithm is one of a correlation analysis algorithm, a frequency algorithm and a classification algorithm.

[0022] Furthermore, the application of the positive conversation list between the agent and the customer to obtain a positive keyword phrase set includes:

[0023] Obtaining positive agent statements from a list of conversations between the positive agent and the customer;

[0024] Extracting positive keyword phrases from the positive agent sentences;

[0025] Each positive keyword phrase constitutes the positive keyword phrase set.

[0026] Furthermore, the application of the positive keyword phrase set and the preset speech recommendation algorithm generates and outputs a positive speech recommendation list, including:

[0027] A positive keyword phrase set and a preset speech recommendation model are applied to generate and output a positive speech recommendation list, wherein the preset speech recommendation model is pre-trained using the XGBOOST algorithm.

[0028] In a second aspect, the present application provides a speech recommendation device, comprising:

[0029] The acquisition module is used to acquire batch collection business information groups, each collection business information group includes: outbound collection call information and customer repayment information;

[0030] A marking module, for marking a pending recording file corresponding to the outbound collection call information of the collection business information group as a positive pending recording file if there is a collection business information group in which the customer repayment information is on-time repayment information;

[0031] A generation module is used to apply a preset speech recommendation algorithm and the positive recording file to be processed to generate and output a positive speech recommendation list.

[0032] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the method for recommending speech is implemented when the processor executes the program.

[0033] In a fourth aspect, the present application provides a computer-readable storage medium having computer instructions stored thereon, which implement the method for recommending speech techniques when the instructions are executed.

[0034] It can be seen from the above technical solution that the present application provides a method and device for recommending speech. Among them, the method includes: obtaining batch collection business information groups, each collection business information group includes: outbound collection call information and customer repayment information; if there is a collection business information group in which the customer repayment information is on-time repayment information, then the pending recording file corresponding to the outbound collection call information of the collection business information group is marked as a positive pending recording file; applying the preset speech recommendation algorithm and the positive pending recording file to generate and output a positive speech recommendation list, which can effectively provide speech assistance to the seat personnel, thereby improving the efficiency and success rate of the collection business; specifically, it can improve the ability to accumulate positive and reverse speech knowledge, improve the business training efficiency, business development efficiency and service capabilities of the outbound call seat personnel, save costs, and thereby improve the level of communication with customers and enhance the corporate image. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 It is a flowchart of the method for recommending speech skills in an embodiment of the present application;

[0037] Figure 2 It is a flowchart of step 201 to step 203 of the speech recommendation method in an embodiment of the present application;

[0038] Figure 3It is a flowchart of a method for recommending speech in another embodiment of the present application;

[0039] Figure 4 It is a structural diagram of a speech technique recommendation device in an embodiment of the present application;

[0040] Figure 5 It is a structural diagram of a speech recommendation device in an application example of this application;

[0041] Figure 6 This is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] Based on this, in order to effectively provide salespersons with speech assistance, thereby improving the efficiency and success rate of debt collection services, the present application embodiment provides a speech recommendation device, which can be a server or client device, and the client device can include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, and a smart wearable device, etc. Among them, the smart wearable device can include smart glasses, smart watches, and smart bracelets, etc.

[0044] In practical applications, the part of the speech recommendation can be executed on the server side as described above, or all operations can be completed in the client device. The specific selection can be based on the processing capability of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device may also include a processor.

[0045] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0046] The server and the client device may communicate using any suitable network protocol, including network protocols that have not yet been developed on the date of filing this application. The network protocol may include, for example, TCP / IP protocol, UDP / IP protocol, HTTP protocol, HTTPS protocol, etc. Of course, the network protocol may also include, for example, RPC protocol (Remote Procedure Call Protocol) and REST protocol (Representational State Transfer) used on top of the above protocols.

[0047] It should be noted that the speech recommendation method and device disclosed in the present application can be used in the field of financial technology, and can also be used in any field other than the field of financial technology. The application field of the speech recommendation method and device disclosed in the present application is not limited.

[0048] The details are described through the following embodiments.

[0049] In order to effectively provide the agents with speech assistance, thereby improving the efficiency and success rate of the debt collection business, this embodiment provides a speech recommendation method in which the execution subject is a speech recommendation device, and the speech recommendation device includes but is not limited to a server, such as Figure 1 As shown, the method specifically includes the following contents:

[0050] Step 101: Acquire batch collection business information groups, each collection business information group including: outbound collection call information and customer repayment information.

[0051] Specifically, batch collection business information groups can be obtained at regular intervals; the outbound collection call information can include: outbound call time, outbound agent number and outbound customer information, etc.; the customer repayment information is used to indicate whether the customer repays within the scheduled time after being collected, and the customer repayment information can include: on-time repayment information or overdue repayment information; in one example, if the customer repayment information is "1", it indicates on-time repayment, and if the customer repayment information is "0", it indicates overdue repayment; each group of collection business information groups can correspond to one outbound collection call respectively.

[0052] Step 102: If there is a collection business information group in which the customer repayment information is on-time repayment information, the pending recording file corresponding to the outbound collection call information of the collection business information group is marked as a positive pending recording file.

[0053] Specifically, the to-be-processed recording file corresponding to the collection business information group can be locally obtained from the speech recommendation device.

[0054] Step 103: Apply the preset speech recommendation algorithm and the positive recording file to be processed to generate and output a positive speech recommendation list.

[0055] It can be understood that the positive speech recommendation list is a list of speech techniques recommended for outbound call agents to use during calls; the positive speech recommendation list can be output to the terminal device of the outbound call agent.

[0056] To further improve the efficiency and success rate of debt collection, see Figure 2 In one embodiment of the present application, step 103 includes:

[0057] Step 201: Convert the forward recording file to be processed into a conversation list between the forward agent and the customer.

[0058] Specifically, automatic speech recognition technology (ASR) can be used to convert the recording files to be processed into text, and each recording file to be processed can be converted into a conversation list between the agent and the customer, so as to separate the agent's sentences and the customer's sentences. The conversation list between the agent and the customer includes: the agent's sentences and the customer's sentences.

[0059] Step 202: Apply the conversation list between the positive agent and the customer to obtain a positive keyword phrase set.

[0060] Specifically, in order to improve the reliability of the positive keyword phrase set, positive agent statements can be obtained from the conversation list between the positive agent and the customer; natural language processing (NLP) technology can be applied to extract positive keyword phrases from the positive agent statements; and each positive keyword phrase constitutes the positive keyword phrase set.

[0061] Step 203: Apply the positive keyword phrase set and the preset speech recommendation algorithm to generate and output a positive speech recommendation list.

[0062] Specifically, the preset speech recommendation algorithm can be one of a correlation analysis algorithm, a frequency algorithm and a classification algorithm; for example, if the preset speech recommendation algorithm is a frequency algorithm, positive keyword phrases whose occurrence frequency is greater than a frequency screening threshold can be extracted from the positive keyword phrase set, and the positive keyword phrases can be combined into a positive speech recommendation list.

[0063] In order to further improve the accuracy and intelligence of generating a positive speech recommendation list, in one embodiment of the present application, step 203 includes:

[0064] A positive keyword phrase set and a preset speech recommendation model are applied to generate and output a positive speech recommendation list, wherein the preset speech recommendation model is pre-trained using the XGBOOST algorithm.

[0065] In order to avoid customer dissatisfaction during the outbound debt collection process and further improve the efficiency and success rate of debt collection, in one embodiment of the present application, each collection service information group also includes: customer complaint information; correspondingly, see Figure 3 , after step 101, further comprising:

[0066] Step 301: If there is a collection service information group in which the customer complaint information is the complained information, then the pending recording file corresponding to the outbound collection call information of the collection service information group is marked as a negative pending recording file.

[0067] Specifically, the customer complaint information is used to indicate whether the customer has complained about the outbound collection call after being collected. The customer complaint information may include: complaint information or non-complaint information. In one example, if the customer complaint information is "1", it indicates that a complaint has been made, and if the customer complaint information is "0", it indicates that no complaint has been made.

[0068] It can be understood that if there is a collection business information group in which the customer repayment information is on-time repayment information and the customer complaint information is complained information, then the pending recording files corresponding to the outbound collection call information of the collection business information group can be marked as positive pending recording files and negative pending recording files at the same time, both of which are used to generate positive speech recommendation lists and negative speech recommendation lists; if there is a collection business information group in which the customer repayment information is overdue repayment information and the customer complaint information is non-complained information, then the pending recording files corresponding to the outbound collection call information of the collection business information group can be treated as invalid recording files, and no further processing is performed.

[0069] Step 302: Apply the preset speech recommendation algorithm and the negative recording file to be processed to generate and output a negative speech recommendation list.

[0070] It can be understood that the negative speech recommendation list is a list of speech that outbound call agents are advised to avoid using during calls; the negative speech recommendation list can be output to the terminal device of the outbound call agent.

[0071] In order to further improve the efficiency and success rate of debt collection, in one embodiment of the present application, step 302 includes:

[0072] Step 401: convert the negative to-be-processed recording file into a conversation list between the negative agent and the customer.

[0073] Specifically, automatic speech recognition technology may be applied to convert the negative to-be-processed recording file into a list of conversations between the negative agent and the customer.

[0074] Step 402: Apply the conversation list between the negative agent and the customer to obtain a set of negative keyword phrases.

[0075] Specifically, negative agent statements can be obtained from the conversation list between the negative agent and the customer; natural language processing technology can be applied to extract negative keyword phrases from the negative agent statements; and each negative keyword phrase constitutes the negative keyword phrase set.

[0076] Step 403: Apply the negative keyword phrase set and the preset speech recommendation algorithm to generate and output a negative speech recommendation list.

[0077] For example, if the preset speech recommendation algorithm is a frequency algorithm, negative keyword phrases with an occurrence frequency greater than a frequency screening threshold can be extracted from the negative keyword phrase set, and the negative keyword phrases can be combined into a negative speech recommendation list.

[0078] From the software level, in order to effectively provide the agents with speech assistance, thereby improving the efficiency and success rate of the collection business, the present application provides an embodiment of a speech recommendation device for implementing all or part of the content of the speech recommendation method, see Figure 4 The speech recommendation device specifically includes the following contents:

[0079] The acquisition module 10 is used to acquire batch collection business information groups, each collection business information group includes: outbound collection call information and customer repayment information.

[0080] The marking module 20 is used to mark the pending recording file corresponding to the outbound collection call information of the collection business information group as a positive pending recording file if there is a collection business information group whose customer repayment information is on-time repayment information.

[0081] The generation module 30 is used to apply a preset speech recommendation algorithm and the positive recording file to be processed to generate and output a positive speech recommendation list.

[0082] The embodiment of the speech recommendation device provided in this specification can be specifically used to execute the processing flow of the embodiment of the above-mentioned speech recommendation method. Its functions will not be repeated here, and reference can be made to the detailed description of the embodiment of the above-mentioned speech recommendation method.

[0083] To further illustrate this solution, this application provides an application example of a speech recommendation method. Figure 5The device includes: a call information acquisition module 11, a customer complaint information acquisition module 12, a customer repayment information collection module 13, a call marking module 14, a call recording acquisition module 15, a recording file to text module 16, a sentence analysis module 17 and a data analysis module 18; the functions implemented by the call information acquisition module 11, the customer complaint information acquisition module 12 and the customer repayment information collection module 13 in combination can be equivalent to the functions implemented by the acquisition module 10, the functions implemented by the call marking module 14 and the call recording acquisition module 15 in combination can be equivalent to the functions implemented by the marking module 20, and the functions implemented by the recording file to text module 16, the sentence analysis module 17 and the data analysis module 18 in combination can be equivalent to the functions implemented by the generation module 30; the specific description of the speech recommendation device is as follows:

[0084] The call information acquisition module 11 is used to collect outbound collection call information and obtain the development status of the outbound collection business, including: outbound call time, outbound call seat number and outbound call customer information.

[0085] The customer complaint information acquisition module 12 is used to collect customer complaint records regarding the outbound collection service, including customer information and the seat number of the complained agent.

[0086] The customer repayment information collection module 13 is used to collect the repayment status of the customer within 7 days after the collection action is taken for the customer who has been subject to outbound collection calls.

[0087] The call marking module 14 is used to mark the associated outbound calls according to the customer complaint records and customer repayment actions, and identify them as positive or negative calls.

[0088] The call recording acquisition module 15 is used to analyze the marked outbound collection calls, trace back to the call recording files corresponding to the calls, form a list of recording files to be processed, and inherit the output of the call marking module to form positive and negative marks for the recording files.

[0089] The recording file conversion module 16 uses automatic speech recognition technology (ASR) to convert the recording file to be processed into text, converts each recording into a conversation list between the agent and the customer, and separates the agent's sentences from the customer's sentences.

[0090] The sentence analysis module 17 uses natural language processing (NLP) technology to process the agent's sentences in each recording and extract key words and phrases; it combines the positive and negative tags of the recording file to form a positive word and phrase set and a negative word and phrase set.

[0091] The data analysis module 18 is used to analyze the positive word and phrase set and the negative word and phrase set respectively to form a positive and negative speech recommendation list.

[0092] To further illustrate the present case, in combination with the above-mentioned speech recommendation device, the present application provides an application example of a speech recommendation method, including:

[0093] Obtain call record information for outbound collection services; obtain customer complaint records due to outbound collection and customer repayment information after the collection action occurs based on customer information in the call record information; form positive and negative call tags based on customer complaint records and customer repayment information; obtain recording files and mark them; transcribe recordings and separate agent statements and customer statements; analyze agent statements and extract key words and phrases to form a collection; analyze and form a positive and negative speech recommendation list.

[0094] From the above description, it can be seen that the speech recommendation method and device provided by the present application can effectively provide speech assistance to the agents, thereby improving the efficiency and success rate of the collection business; specifically, it can improve the ability to accumulate positive and reverse speech knowledge, and can improve the business training efficiency, business development efficiency and service capabilities of outbound call agents, save costs, and thereby improve the level of communication with customers and enhance the corporate image.

[0095] From the hardware level, in order to effectively provide speech assistance to the seat personnel, thereby improving the efficiency and success rate of the collection business, the present application provides an embodiment of an electronic device for implementing all or part of the content of the speech recommendation method. The electronic device specifically includes the following content:

[0096] A processor, a memory, a communications interface and a bus; wherein the processor, the memory and the communications interface communicate with each other through the bus; the communications interface is used to realize information transmission between the speech recommendation device and related devices such as user terminals; the electronic device can be a desktop computer, a tablet computer and a mobile terminal, etc., but the present embodiment is not limited thereto. In the present embodiment, the electronic device can be implemented with reference to the embodiments for realizing the speech recommendation method and the embodiments for realizing the speech recommendation device, and the contents thereof are incorporated herein and the repeated parts are not repeated.

[0097] Figure 6 FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Figure 6 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Figure 6 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0098] In one or more embodiments of the present application, the speech recommendation function may be integrated into the central processor 9100. The central processor 9100 may be configured to perform the following control:

[0099] Step 101: Acquire batch collection business information groups, each collection business information group including: outbound collection call information and customer repayment information.

[0100] Step 102: If there is a collection business information group in which the customer repayment information is on-time repayment information, the pending recording file corresponding to the outbound collection call information of the collection business information group is marked as a positive pending recording file.

[0101] Step 103: Apply a preset speech recommendation algorithm and the positive recording file to be processed to generate and output a positive speech recommendation list.

[0102] From the above description, it can be seen that the electronic device provided in the embodiments of the present application can effectively provide speech assistance to the seat personnel, thereby improving the efficiency and success rate of the collection business.

[0103] In another embodiment, the speech recommendation device can be configured separately from the central processor 9100. For example, the speech recommendation device can be configured as a chip connected to the central processor 9100, and the speech recommendation function is implemented through the control of the central processor.

[0104] like Figure 6 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Figure 6 In addition, the electronic device 9600 may also include Figure 6 For components not shown, reference may be made to the prior art.

[0105] like Figure 6 As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device, which receives input and controls the operation of various components of the electronic device 9600.

[0106] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0107] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0108] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.

[0109] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0110] The communication module 9110 is a transmitter / receiver 9110 that sends and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0111] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module, etc. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.

[0112] It can be seen from the above description that the electronic device provided in the embodiments of the present application can effectively provide speech assistance to the agents, thereby improving the efficiency and success rate of the collection business.

[0113] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the speech recommendation method in the above embodiments. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all the steps of the speech recommendation method in the above embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0114] Step 101: Acquire batch collection business information groups, each collection business information group including: outbound collection call information and customer repayment information.

[0115] Step 102: If there is a collection business information group in which the customer repayment information is on-time repayment information, the pending recording file corresponding to the outbound collection call information of the collection business information group is marked as a positive pending recording file.

[0116] Step 103: Apply the preset speech recommendation algorithm and the positive recording file to be processed to generate and output a positive speech recommendation list.

[0117] From the above description, it can be seen that the computer-readable storage medium provided in the embodiment of the present application can effectively provide speech assistance to the seat personnel, thereby improving the efficiency and success rate of the collection business.

[0118] In this application, each embodiment of the above method is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. For relevant parts, refer to the partial description of the method embodiment.

[0119] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0120] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0123] Specific embodiments are used in this application to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core idea of ​​this application. At the same time, for those skilled in the art, according to the idea of ​​this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on this application.

Claims

1. A method for recommending speech skills, characterized in that: include: Obtain batch collection business information groups, each collection business information group includes: outbound collection call information and customer repayment information; If there is a collection business information group in which the customer repayment information is on-time repayment information, the pending recording file corresponding to the outbound collection call information of the collection business information group is marked as a positive pending recording file; Applying a preset speech recommendation algorithm and the positive recording file to be processed, generating a positive speech recommendation list and outputting it; The application of the preset speech recommendation algorithm and the positive recording file to be processed generates and outputs a positive speech recommendation list, including: Convert the forward recording file to be processed into a conversation list between the forward agent and the customer; Apply the conversation list between the positive agent and the customer to obtain a positive keyword phrase set; Apply the positive keyword phrase set and the preset speech recommendation algorithm to generate and output a positive speech recommendation list; Each collection business information group also includes: customer complaint information; Correspondingly, after obtaining the batch collection business information group, it also includes: If there is a collection business information group in which the customer complaint information is the complained information, the pending recording file corresponding to the outbound collection call information of the collection business information group is marked as a negative pending recording file; Applying a preset speech recommendation algorithm and the negative recording file to be processed, generating and outputting a negative speech recommendation list; The application of the preset speech recommendation algorithm and the negative recording file to be processed generates and outputs a negative speech recommendation list, including: Convert the negative to-be-processed recording file into a conversation list between the negative agent and the customer; Apply the conversation list between the negative agent and the customer to obtain a set of negative keyword phrases; Apply the negative keyword phrase set and the preset speech recommendation algorithm to generate and output a negative speech recommendation list; The preset word recommendation algorithm is one of a correlation analysis algorithm, a frequency algorithm and a classification algorithm; The method for recommending speech techniques further includes: If there is a collection business information group in which the customer repayment information is on-time repayment information and the customer complaint information is complained information, the pending recording files corresponding to the outbound collection call information of the collection business information group will be marked as positive pending recording files and negative pending recording files, both of which are used to generate positive speech recommendation lists and negative speech recommendation lists; if there is a collection business information group in which the customer repayment information is overdue repayment information and the customer complaint information is non-complained information, the pending recording files corresponding to the outbound collection call information of the collection business information group will be treated as invalid recording files, and no further processing will be performed.

2. The method for recommending words according to claim 1, characterized in that: The application of the positive conversation list between the agent and the customer obtains a positive keyword phrase set, including: Obtaining positive agent statements from a list of conversations between the positive agent and the customer; Extracting positive keyword phrases from the positive agent sentences; Each positive keyword phrase constitutes the positive keyword phrase set.

3. The method for recommending words according to claim 1, characterized in that: The positive keyword phrase set and the preset speech recommendation algorithm are applied to generate and output a positive speech recommendation list, including: A positive keyword phrase set and a preset speech recommendation model are applied to generate and output a positive speech recommendation list, wherein the preset speech recommendation model is pre-trained using the XGBOOST algorithm.

4. A speech recommendation device, characterized in that: include: The acquisition module is used to acquire batch collection business information groups, each collection business information group includes: outbound collection call information and customer repayment information; A marking module, for marking a pending recording file corresponding to the outbound collection call information of the collection business information group as a positive pending recording file if there is a collection business information group in which the customer repayment information is on-time repayment information; A generation module, used to apply a preset speech recommendation algorithm and the positive recording file to be processed to generate and output a positive speech recommendation list; The application of the preset speech recommendation algorithm and the positive recording file to be processed generates and outputs a positive speech recommendation list, including: Convert the forward recording file to be processed into a conversation list between the forward agent and the customer; Apply the conversation list between the positive agent and the customer to obtain a positive keyword phrase set; Apply the positive keyword phrase set and the preset speech recommendation algorithm to generate and output a positive speech recommendation list; Each collection business information group also includes: customer complaint information; Correspondingly, the speech recommendation device is also used for: If there is a collection business information group in which the customer complaint information is the complained information, the pending recording file corresponding to the outbound collection call information of the collection business information group is marked as a negative pending recording file; Applying a preset speech recommendation algorithm and the negative recording file to be processed, generating and outputting a negative speech recommendation list; The application of the preset speech recommendation algorithm and the negative recording file to be processed generates and outputs a negative speech recommendation list, including: Convert the negative to-be-processed recording file into a conversation list between the negative agent and the customer; Apply the conversation list between the negative agent and the customer to obtain a set of negative keyword phrases; Apply the negative keyword phrase set and the preset speech recommendation algorithm to generate and output a negative speech recommendation list; The preset word recommendation algorithm is one of a correlation analysis algorithm, a frequency algorithm and a classification algorithm; The speech recommendation device is also used for: If there is a collection business information group in which the customer repayment information is on-time repayment information and the customer complaint information is complained information, the pending recording files corresponding to the outbound collection call information of the collection business information group will be marked as positive pending recording files and negative pending recording files, both of which are used to generate positive speech recommendation lists and negative speech recommendation lists; if there is a collection business information group in which the customer repayment information is overdue repayment information and the customer complaint information is non-complained information, the pending recording files corresponding to the outbound collection call information of the collection business information group will be treated as invalid recording files, and no further processing will be performed.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the speech recommendation method described in any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instructions are executed, the speech recommendation method described in any one of claims 1 to 3 is implemented.

Images