Information processing method and device, electronic equipment and computer readable storage medium

Abstract

The application provides an information processing method and device, electronic equipment and a computer readable storage medium. The method comprises: obtaining dialogue information of a customer service providing consulting services, the dialogue information comprising at least one dialogue sentence; performing attribute prediction on each dialogue sentence in the at least one dialogue sentence by an attribute prediction model to obtain attribute information of each dialogue sentence, the attribute information representing a conversation stage in which the corresponding dialogue sentence is located; and determining a dialogue sentence in the dialogue information that meets a target promotion condition according to the attribute information of each dialogue sentence in the dialogue information.

Description

Technical Field

[0001] This application relates to computer technology, and more particularly to an information processing method, apparatus, electronic device, and computer-readable storage medium. Background Technology

[0002] When customer service representatives diagnose and resolve issues during consultations, their problem-solving abilities directly impact the final user experience. Currently, to improve service quality, the method involves collecting user reviews of customer service consultations over a period of time and using the average review rate to assess service capabilities. However, this approach has several drawbacks. Firstly, the user review rate is inherently low, meaning many users don't leave feedback after the service is completed. Secondly, data analysis reveals numerous discrepancies between reviews and the actual service experience. In other words, using a high positive review rate as the sole criterion cannot guarantee that users will provide thoughtful and objective feedback, thus failing to truly reflect the quality of the customer service consultations provided. Summary of the Invention

[0003] This application provides an information processing method, apparatus, electronic device, and computer-readable storage medium that can automatically determine dialogue statements in customer service consultation information that meet target driving conditions, thereby enabling further determination of the service quality of the consultation service provided by customer service.

[0004] The technical solution of this application embodiment is implemented as follows:

[0005] This application provides an information processing method, including:

[0006] Obtain dialogue information from customer service representatives who provide consultation services, wherein the dialogue information includes at least one dialogue statement;

[0007] The attribute prediction model is used to predict the attributes of each dialogue statement in the at least one dialogue statement to obtain the attribute information of each dialogue statement. The attribute information represents the conversation stage of the corresponding dialogue statement.

[0008] Based on the attribute information of each dialogue statement in the dialogue information, determine the dialogue statements in the dialogue information that satisfy the target driving conditions.

[0009] In the above solution, after obtaining the dialogue information from customer service regarding consultation services, the method further includes:

[0010] The dialogue information is classified using a classification model to determine the question type corresponding to the dialogue information.

[0011] In the above scheme, determining the dialogue statements in the dialogue information that satisfy the target driving conditions based on the attribute information of each dialogue statement in the dialogue information further includes:

[0012] Based on the attribute information of each dialogue statement in the dialogue information, determine the key dialogue statements whose attribute information type is the target type;

[0013] The key dialogue statements are identified as those that satisfy the target-driving conditions.

[0014] In the above scheme, the method further includes:

[0015] Based on the key dialogue statements, determine at least one indicator value for the service capability of the customer service representative;

[0016] The customer service capability is rated based on at least one of the aforementioned indicator values.

[0017] In the above scheme, the at least one indicator value includes at least one of the following:

[0018] The number of key dialogue statements, the dialogue time corresponding to the key dialogue statements, and the number of key statements whose attribute information type is the first type among the multiple key statements.

[0019] The target type includes at least two subtypes, and the first type is any one of the at least two subtypes.

[0020] In the above scheme, the step of rating the customer service capability based on the indicator value further includes:

[0021] Based on the at least one indicator value, determine the comprehensive capability value of the customer service representative;

[0022] Obtain the ability value range corresponding to multiple ability levels;

[0023] The customer service representative's capability level is determined based on the capability value range in which the comprehensive capability value falls.

[0024] In the above solution, before obtaining the dialogue information from customer service for consultation, the method further includes:

[0025] Obtain sample dialogue information of customer service representatives providing consultation services. The sample dialogue information includes at least one sample dialogue statement. Each of the at least one sample dialogue statement carries an attribute tag, which represents the conversation stage of the corresponding sample dialogue statement.

[0026] The attribute prediction model is used to predict the attributes of each sample dialogue statement in the at least one sample dialogue statement, thereby obtaining the predicted attribute information of each sample dialogue statement.

[0027] The model parameters of the attribute prediction model are updated based on the error between the predicted attribute information and the attribute label of each sample dialogue statement.

[0028] This application provides an information processing apparatus, including:

[0029] The acquisition module is used to acquire dialogue information provided by customer service for consultation services, the dialogue information including at least one dialogue statement;

[0030] The attribute prediction module is used to predict the attributes of each dialogue statement in the at least one dialogue statement through the attribute prediction model, so as to obtain the attribute information of each dialogue statement, wherein the attribute information represents the conversation stage of the corresponding dialogue statement.

[0031] The determination module is used to determine the dialogue statements in the dialogue information that satisfy the target driving conditions based on the attribute information of each dialogue statement in the dialogue information.

[0032] This application provides an electronic device, including:

[0033] Memory, used to store executable instructions;

[0034] The processor, when executing executable instructions stored in the memory, implements the information processing method provided in the embodiments of this application.

[0035] This application provides a computer-readable storage medium storing executable instructions for inducing a processor to execute and implement the information processing method provided in this application.

[0036] This application embodiment obtains dialogue information from customer service consultation services. The dialogue information includes at least one dialogue statement. Using an attribute prediction model, attributes are predicted for each dialogue statement in the at least one dialogue statement to obtain attribute information for each dialogue statement. The attribute information represents the conversation stage of the corresponding dialogue statement. Based on the attribute information of each dialogue statement in the dialogue information, the dialogue statements in the dialogue information that meet the target driving conditions are determined. This can automatically determine the dialogue statements in the customer service consultation service consultation information that meet the target driving conditions, thereby enabling further determination of the service quality of the consultation service provided by customer service. Attached Figure Description

[0037] Figure 1 This is an optional flowchart illustrating the information processing method provided in the embodiments of this application;

[0038] Figure 2 This is a schematic diagram of an optional model structure for the ELMo model;

[0039] Figure 3This is an optional flowchart illustrating the information processing method provided in the embodiments of this application;

[0040] Figure 4 This is an optional schematic diagram of the sample dialogue information in this application;

[0041] Figure 5 This is an optional model structure diagram of the attribute prediction model provided in the embodiments of this application;

[0042] Figure 6 This is a schematic diagram of an optional structure for a multi-layer attention network;

[0043] Figure 7 This is an optional detailed flowchart of the information processing method provided in the embodiments of this application;

[0044] Figure 8 This is an optional flowchart illustrating the information processing method provided in the embodiments of this application;

[0045] Figure 9 This is an optional structural schematic diagram of the electronic device 900 provided in the embodiments of this application. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0047] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0048] In the following description, the terms "first, second, third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0050] This application provides an information processing method, apparatus, electronic device, and computer-readable storage medium that can automatically determine dialogue statements in customer service consultation information that meet target driving conditions, thereby enabling further determination of the service quality of the consultation service provided by customer service.

[0051] The information processing method provided in this application will be described below with reference to exemplary applications and implementations of the terminal provided in the embodiments of this application.

[0052] See Figure 1 , Figure 1 This is an optional flowchart illustrating the information processing method provided in the embodiments of this application, which will be combined with... Figure 1 The steps shown are explained.

[0053] Step 201: Obtain the dialogue information provided by customer service for consultation services, wherein the dialogue information includes at least one dialogue statement;

[0054] Step 202: Using an attribute prediction model, perform attribute prediction on each dialogue statement in the at least one dialogue statement to obtain attribute information for each dialogue statement. The attribute information represents the conversation stage of the corresponding dialogue statement.

[0055] Step 203: Based on the attribute information of each dialogue statement in the dialogue information, determine the dialogue statements in the dialogue information that satisfy the target driving conditions.

[0056] Here, customer service can be either human or automated. Users can ask questions, and the customer service representative provides consultation services. In practice, the terminal obtains the dialogue information between the customer and the user during the consultation, which includes at least one dialogue statement. Specifically, the terminal can obtain the interaction data of this consultation service from the customer service dialogue system to obtain at least one dialogue statement for that consultation service. In this embodiment, the attribute prediction model is implemented using the ELMo (Embeddings from Language Models) model. See also... Figure 2 , Figure 2 This is a schematic diagram of an optional model architecture for the ELMo model. The ELMo model uses bidirectional Long Short-Term Memory (LSTM) to predict words based on context. ELMo first converts the input into character-level word embedding vectors, generates context-independent word embeddings based on the character-level word embeddings, and then uses a bidirectional language model (such as Bi-LSTM) to generate context-relevant embeddings.

[0057] In this embodiment, attribute information represents the conversation stage of the corresponding dialogue statement. Specifically, the attribute prediction model outputs attribute information of at least two types, meaning there can be at least two conversation stages. For example, conversation stages can include the following four: greeting stage, problem identification stage, problem resolution stage, and ending stage. In some embodiments, in addition to the above four, conversation stages may also include, for example, a user reassurance stage or an information promotion stage.

[0058] In practice, the terminal determines the dialogue statements that satisfy the target promotion conditions based on the attribute information of each dialogue statement in the dialogue information. Here, the target promotion conditions are those that have a positive promoting effect on the consultation service. For example, in the four conversation stages mentioned above, the dialogue statements corresponding to the problem identification stage and the problem-solving stage are dialogue statements that satisfy the target promotion conditions. In this embodiment, the terminal determines the dialogue statements that satisfy the target promotion conditions from the dialogue information, thereby enabling the accurate extraction of useful information from the dialogue information of customer service providing consultation services, which is beneficial for evaluating the service quality of the consultation service.

[0059] In this embodiment, the attribute prediction model is pre-trained. Specifically, in some embodiments, see [link to relevant documentation]. Figure 3 , Figure 3 This is an optional flowchart illustrating the information processing method provided in this application embodiment. Before step 201, the following steps may also be performed:

[0060] Step 301: Obtain sample dialogue information of customer service representatives providing consultation services. The sample dialogue information includes at least one sample dialogue statement. Each of the at least one sample dialogue statement carries an attribute tag, which represents the conversation stage of the corresponding sample dialogue statement.

[0061] Step 302: Using the attribute prediction model, perform attribute prediction on each sample dialogue statement in the at least one sample dialogue statement to obtain the predicted attribute information of each sample dialogue statement.

[0062] Step 303: Update the model parameters of the attribute prediction model based on the error between the predicted attribute information and the attribute label of each sample dialogue statement.

[0063] In practice, the terminal obtains sample dialogue information, and each sample dialogue statement carries an attribute tag. Specifically, the attribute tags are sentence-level annotations, and the annotation system divides each stage of the dialogue information into a key stage, which may include four types: greeting stage, problem identification stage, problem-solving stage, and ending stage. For example, see [link to example]. Figure 4 , Figure 4This is an optional illustration of sample dialogue information from this application. Each sample dialogue statement carries an attribute label. For example, the attribute label for the sample dialogue statement "Hello" is the greeting stage; the attribute label for the sample dialogue statement "To verify, is this the machine? PF113SFB Legion R720-15IKBN" is the problem identification stage; the attribute label for the sample dialogue statement "This is a reply operation: Reset system operation: Left-click the Start menu, Settings, Update & Security, Recovery, Reset this PC, and the Start button below." is the problem-solving stage; and the attribute label for the sample dialogue statement "Okay, is there anything else I can help you with?" is the ending stage.

[0064] In practice, attribute prediction models are based on BERT, Bi-LSTM, and CRF. See also Figure 5 , Figure 5 This is an optional model structure diagram of the attribute prediction model provided in this application embodiment. By inputting sample dialogue information into the attribute prediction model, the attribute prediction model is used to predict the attributes of each sample dialogue statement in the dialogue information, thereby obtaining the predicted attribute information of each sample dialogue statement. Then, the model parameters are updated according to the error between the predicted attribute information and the corresponding attribute label, thereby realizing the training of the attribute prediction model.

[0065] In some embodiments, after obtaining the dialogue information provided by customer service, the method further includes: classifying the dialogue information using a classification model to obtain the question type corresponding to the dialogue information.

[0066] In this embodiment, after obtaining the dialogue information, it is input into a classification model to obtain the question type corresponding to the dialogue information. Here, the question type specifically refers to the question type corresponding to the question a user asks customer service in a consultation service. In real-world scenarios, the question type in the classification model can be labeled according to the types of faults involved in the product. Customer service can be used to provide after-sales service for the product. For example, the question type could be a computer startup problem or a monitor display problem. Here, the classification model can classify the dialogue information based on multi-turn dialogues to obtain the question type of the dialogue information.

[0067] In practice, classification models can be implemented using hierarchical attention networks. See also Figure 6 , Figure 6This is a schematic diagram of an optional structure for a multi-layer attention network, which includes a word embedding layer, a word encoder layer, a word attention layer, a sentence encoder layer, a sentence attention layer, and a fully connected layer. After dialogue information is input into a classification model based on a multi-layer attention network, the various layers of the classification model can output the question type involved in the dialogue information.

[0068] In practice, the classification model is pre-trained. Specifically, before step 301, the following steps can be performed: obtaining sample dialogue information, which carries question type labels; classifying the consultation questions involved in the sample dialogue information using the classification model to obtain corresponding predicted question types; and updating the model parameters of the classification model based on the error between the question type labels and the predicted question types. Here, the labeling system for question type labels is specifically a three-level fault classification system, which can have more than 300 labels for a single product. In practice, at least one sample dialogue information containing consultation text information can be extracted, and the question types of each sample dialogue information can be multi-level labeled according to this labeling system to obtain question type labels.

[0069] In some embodiments, see Figure 7 , Figure 7 This is an optional detailed flowchart of the information processing method provided in the embodiments of this application. Step 203 further includes:

[0070] Step 2031: Based on the attribute information of each dialogue statement in the dialogue information, determine the key dialogue statements whose attribute information type is the target type;

[0071] Step 2032: Determine the key dialogue statement as a dialogue statement that satisfies the target driving condition.

[0072] In practical implementation, the terminal identifies key dialogue statements in the dialogue information whose attribute information type corresponds to the target type. Here, the attribute information type can be one of the four types listed above, corresponding to the four conversation stages. The target type could be the problem identification stage or the problem-solving stage. In this embodiment, key dialogue statements are identified as those that meet the target-driving conditions. This embodiment allows for the convenient and rapid identification of dialogue statements in the dialogue information that promote consultation services, thereby facilitating further determination of customer service capabilities.

[0073] In some embodiments, see Figure 8 , Figure 8 This is an optional flowchart illustrating the information processing method provided in this application embodiment. After step 203, the following can also be executed:

[0074] Step 801: Determine at least one indicator value for the service capability of the customer service representative based on the key dialogue statement.

[0075] Step 802: Rate the service capability of the customer service representative based on the at least one indicator value.

[0076] In practice, the terminal determines at least one indicator value of the customer service representative's service capability based on key dialogue statements, and then rates the customer service representative's service capability based on the indicator value, thereby quantitatively determining the customer service representative's ability to resolve user inquiries when providing consultation services.

[0077] In some embodiments, the at least one indicator value includes at least one of the following: the number of statements in the key dialogue statement, the dialogue time corresponding to the key dialogue statement, and the number of statements corresponding to the key statements whose attribute information type is a first type among the multiple key statements; wherein, the target type includes at least two subtypes, and the first type is any one of the at least two subtypes.

[0078] In practical implementation, the terminal can count the number of key dialogue statements, using this number as an indicator to determine the number of dialogues a customer service representative spends answering user inquiries. A higher number of dialogues indicates weaker service capabilities. The terminal can also obtain the dialogue time for key dialogue statements; longer dialogue times indicate weaker service capabilities. Furthermore, the terminal can determine the dialogue time corresponding to each key dialogue statement and the number of statements whose attribute information is of a first type among the multiple key statements. Here, the target type can include, for example, the problem-finding stage and the problem-solving stage, with the first type being the problem-finding stage. By determining the number of statements in the problem-finding stage, the customer service representative's ability to locate problems can be determined. If the customer service representative repeatedly attempts to locate problems, it indicates weaker service capabilities. The weaker the customer service representative's service capability, the lower their service level. Specifically, the terminal obtains the attribute information corresponding to each key dialogue statement, identifies the attribute information indicating the conversation stage of the corresponding key dialogue statement as the problem-finding stage as the first type of attribute information, and further filters out the target dialogue statements whose attribute information indicates the conversation stage of the corresponding key dialogue statement, obtaining the number of target dialogue statements. It should be understood that the number of target dialogue statements can characterize the customer service's ability to determine and confirm product malfunctions based on user inquiries. In this application embodiment, the ability of the customer service to locate problems is determined by obtaining the number of statements in the key dialogue statements whose attribute information is of the first type.

[0079] In some embodiments, step 902 can be implemented as follows: determining the comprehensive capability value of the customer service representative based on the at least one indicator value; obtaining capability value ranges corresponding to multiple capability levels; and determining the capability level of the customer service representative based on the capability value range in which the comprehensive capability value is located.

[0080] In practice, the terminal can unify various indicator values ​​to the same standard using unified rules, determine a comprehensive capability value based on these values, and obtain capability value ranges corresponding to multiple capability levels. It then determines the capability value statement into which the comprehensive capability value falls, and based on this range, determines the customer service capability level. For example, if capability levels are divided into three levels—Level 1, Level 2, and Level 3—each level corresponds to a different capability value range. If the comprehensive capability falls within one of these ranges, it indicates that the customer service representative's service capability corresponds to the capability level specified in that range.

[0081] In this embodiment, after determining the question type of the dialogue information through a classification model, the resulting customer service representative's capability level is the level at which they can resolve inquiries of that question type. In practical implementation, this embodiment allows us to obtain the customer service representative's capability level when resolving different question types, thereby identifying the question types where customer service representatives are relatively weak, and providing further training for those specific question types. If it is a human customer service representative, prompts can be sent to them, and relevant courses can be provided for their learning. Specifically, capability threshold standards can be set for each question type to filter out corresponding questions where their problem-solving ability is weak. Furthermore, target customer service representatives with relatively weak problem-solving abilities can be selected from among multiple human customer service representatives. This allows us to generate different training paths and push relevant training courses to each human customer service representative based on their varying problem-solving abilities for different question types. Simultaneously, real-world cases from human customer service representatives with strong problem-solving abilities can be pushed for reference and learning. We can also periodically and automatically determine changes in each human customer service representative's problem-solving ability for various question types, analyze the course learning effect, dynamically adjust the learning path based on capability improvement, and simultaneously refresh the capability threshold standards. If it is an intelligent customer service representative, further training can be provided for the intelligent customer service representative to improve their ability to resolve those question types.

[0082] This application embodiment obtains dialogue information from customer service consultation services. The dialogue information includes at least one dialogue statement. Using an attribute prediction model, attributes are predicted for each dialogue statement in the at least one dialogue statement to obtain attribute information for each dialogue statement. The attribute information represents the conversation stage of the corresponding dialogue statement. Based on the attribute information of each dialogue statement in the dialogue information, the dialogue statements in the dialogue information that meet the target driving conditions are determined. This can automatically determine the dialogue statements in the customer service consultation service consultation information that meet the target driving conditions, thereby enabling further determination of the service quality of the consultation service provided by customer service.

[0083] The electronic device for implementing the above-described information processing method, provided in the embodiments of this application, will now be described. See also Figure 9 , Figure 9 This is an optional structural diagram of the electronic device 900 provided in this application embodiment. In practical applications, the electronic device 900 can be implemented as a terminal or a server. The terminal can be a laptop, tablet, desktop computer, smartphone, dedicated messaging device, portable gaming device, smart speaker, smartwatch, etc., but is not limited to these. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery network (CDN) services, and big data and artificial intelligence platforms. Figure 1 The illustrated electronic device 900 includes at least one processor 901, a memory 905, at least one network interface 902, and a user interface 903. The various components in the electronic device 900 are coupled together via a bus system 904. It is understood that the bus system 904 is used to implement communication between these components. In addition to a data bus, the bus system 904 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 9 The general designated all buses as Bus System 904.

[0084] The processor 901 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0085] User interface 903 includes one or more output devices 9031 that enable the presentation of media content, including one or more speakers and / or one or more visual displays. User interface 903 also includes one or more input devices 9032, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0086] The memory 905 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state storage, hard disk drives, optical disk drives, etc. The memory 905 may optionally include one or more storage devices physically located away from the processor 901.

[0087] The memory 905 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), and the volatile memory may be random access memory (RAM). The memory 905 described in this application embodiment is intended to include any suitable type of memory.

[0088] In some embodiments, the memory 905 can store data to support various operations. Examples of such data include programs, modules, and data structures, or subsets or supersets thereof. In this embodiment, the memory 905 stores an operating system 9051, a network communication module 9052, a presentation module 9053, an input processing module 9054, and an information processing device 9055. Specifically...

[0089] The 9051 operating system includes system programs for handling various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, and driver layer, which are used to implement various basic business functions and handle hardware-based tasks.

[0090] The network communication module 9052 is used to reach other computing devices via one or more (wired or wireless) network interfaces 902, exemplary network interfaces 902 including: Bluetooth, WiFi, and Universal Serial Bus (USB), etc.

[0091] The presentation module 9053 is configured to enable the presentation of information (e.g., a user interface for operating peripheral devices and displaying content and information) via one or more output devices 9031 (e.g., a display screen, a speaker, etc.) associated with the user interface 903;

[0092] The input processing module 9054 is used to detect and translate one or more user inputs or interactions from one or more input devices 9032.

[0093] In some embodiments, the information processing apparatus provided in this application can be implemented in software. Figure 1 An information processing apparatus 9055 stored in memory 905 is shown. This apparatus can be software in the form of programs and plug-ins, and includes the following software modules: an acquisition module 90551, an attribute prediction module 90552, and a determination module 90553. These modules are logically linked and can therefore be arbitrarily combined or further separated according to their implemented functions. The functions of each module will be described below.

[0094] In other embodiments, the information processing apparatus provided in this application can be implemented in hardware. As an example, the information processing apparatus provided in this application can be a processor in the form of a hardware decoding processor, which is programmed to execute the information processing method provided in this application. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0095] The following description continues to illustrate the exemplary structure of the information processing device 9055 provided in the embodiments of this application as a software module. In some embodiments, such as Figure 9 As shown, the software modules stored in the information processing device 9055 in the memory 905 may include:

[0096] The module 90551 is used to obtain dialogue information provided by customer service for consultation services, and the dialogue information includes at least one dialogue statement.

[0097] The attribute prediction module 90552 is used to predict the attributes of each dialogue statement in the at least one dialogue statement through an attribute prediction model, so as to obtain the attribute information of each dialogue statement, wherein the attribute information represents the conversation stage of the corresponding dialogue statement.

[0098] The determination module 90553 is used to determine the dialogue statements in the dialogue information that satisfy the target driving conditions based on the attribute information of each dialogue statement in the dialogue information.

[0099] In some embodiments, the apparatus further includes a classification module, configured to classify the dialogue information using a classification model to obtain the question type corresponding to the dialogue information.

[0100] In some embodiments, the determining module 90553 is further configured to determine, based on the attribute information of each dialogue statement in the dialogue information, a key dialogue statement whose attribute information is of the target type; and to determine the key dialogue statement as a dialogue statement that satisfies the target driving condition.

[0101] In some embodiments, the apparatus further includes: a rating module, configured to determine at least one indicator value for the service capability of the customer service representative based on the key dialogue statement; and to rate the service capability of the customer service representative based on the at least one indicator value.

[0102] In some embodiments, the at least one indicator value includes at least one of the following: the number of statements in the key dialogue statement, the dialogue time corresponding to the key dialogue statement, and the number of statements corresponding to the key statements whose attribute information type is a first type among the multiple key statements; wherein, the target type includes at least two subtypes, and the first type is any one of the at least two subtypes.

[0103] In some embodiments, the rating module is further configured to determine the comprehensive capability value of the customer service representative based on the at least one indicator value; obtain capability value ranges corresponding to multiple capability levels; and determine the capability level of the customer service representative based on the capability value range in which the comprehensive capability value is located.

[0104] In some embodiments, the apparatus further includes: a model training module, configured to obtain sample dialogue information of sample customer service representatives providing consultation services, the sample dialogue information including at least one sample dialogue statement, each of the at least one sample dialogue statement carrying an attribute label, the attribute label representing the conversation stage of the corresponding sample dialogue statement; performing attribute prediction on each of the at least one sample dialogue statements using the attribute prediction model to obtain predicted attribute information for each sample dialogue statement; and updating the model parameters of the attribute prediction model based on the error between the predicted attribute information and the attribute label for each sample dialogue statement.

[0105] It should be noted that the description of the apparatus in this application embodiment is similar to the description of the method embodiment above, and has similar beneficial effects as the method embodiment, so it will not be repeated.

[0106] This application provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the information processing method described in this application.

[0107] This application provides a computer-readable storage medium storing executable instructions, wherein the executable instructions are stored and, when executed by a processor, will cause the processor to execute the information processing method provided in this application.

[0108] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a variety of devices including one or any combination of the above-mentioned memories.

[0109] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0110] As an example, executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple collaborating files (e.g., a file that stores one or more modules, subroutines, or code sections).

[0111] As an example, executable instructions can be deployed to execute on a single computing device, or on multiple computing devices located in one location, or on multiple computing devices distributed across multiple locations and interconnected via a communication network.

[0112] In summary, the embodiments of this application can automatically identify dialogue statements in customer service consultation information that meet the target driving conditions, thereby enabling further determination of the service quality of the consultation services provided by customer service.

[0113] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. An information processing method, characterized in that, include: Obtain dialogue information from customer service providing consultation services, wherein the dialogue information includes at least one dialogue statement; the consultation service is after-sales service for the product. The dialogue information is classified using a classification model to obtain the question type corresponding to the dialogue information; the question type is the fault type of the product. The attribute prediction model is used to predict the attributes of each dialogue statement in the at least one dialogue statement to obtain the attribute information of each dialogue statement. The attribute information represents the conversation stage of the corresponding dialogue statement. Based on the attribute information of each dialogue statement in the dialogue information, determine the dialogue statements in the dialogue information that satisfy the target driving conditions; The dialogue statement that meets the target driving condition is used to determine the capability level of the customer service representative's service capability for the fault type.

2. The method according to claim 1, further comprising determining, based on the attribute information of each dialogue statement in the dialogue information, the dialogue statements in the dialogue information that satisfy the target driving condition, and the following: Based on the attribute information of each dialogue statement in the dialogue information, determine the key dialogue statements whose attribute information type is the target type; The key dialogue statements are identified as those that satisfy the target-driving conditions.

3. The method according to claim 2, wherein the method further comprises: Based on the key dialogue statements, determine at least one indicator value for the service capability of the customer service representative; The customer service capability is rated based on at least one of the aforementioned indicator values.

4. The method according to claim 3, wherein the at least one indicator value includes at least one of the following: The number of key dialogue statements, the dialogue time corresponding to the key dialogue statements, and the number of key dialogue statements whose attribute information type is the first type among multiple key dialogue statements. in, The target type includes at least two subtypes, and the first type is any one of the at least two subtypes.

5. The method according to claim 3, wherein rating the customer service capability based on the indicator value further includes: The overall capability value of the customer service representative is determined based on at least one of the aforementioned indicator values. Obtain the ability value range corresponding to multiple ability levels; The customer service representative's capability level is determined based on the capability value range in which the comprehensive capability value falls.

6. The method according to claim 1, wherein before obtaining the dialogue information of customer service providing consultation services, the method further comprises: Obtain sample dialogue information of customer service representatives providing consultation services. The sample dialogue information includes at least one sample dialogue statement. Each of the at least one sample dialogue statement carries an attribute tag, which represents the conversation stage of the corresponding sample dialogue statement. The attribute prediction model is used to predict the attributes of each sample dialogue statement in the at least one sample dialogue statement, thereby obtaining the predicted attribute information of each sample dialogue statement. The model parameters of the attribute prediction model are updated based on the error between the predicted attribute information and the attribute label of each sample dialogue statement.

7. An information processing apparatus, comprising: The acquisition module is used to acquire dialogue information provided by customer service for consultation services, the dialogue information including at least one dialogue statement; The consulting service mentioned is the after-sales service for the product; The classification module is used to classify the dialogue information using a classification model to obtain the question type corresponding to the dialogue information; the question type is the fault type of the product. The attribute prediction module is used to predict the attributes of each dialogue statement in the at least one dialogue statement through the attribute prediction model, so as to obtain the attribute information of each dialogue statement, wherein the attribute information represents the conversation stage of the corresponding dialogue statement. The determining module is used to determine the dialogue statements in the dialogue information that satisfy the target driving conditions based on the attribute information of each dialogue statement in the dialogue information; The dialogue statement that meets the target driving condition is used to determine the capability level of the customer service representative's service capability for the fault type.

8. An electronic device, comprising: Memory, used to store executable instructions; A processor, when executing executable instructions stored in the memory, implements the information processing method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing executable instructions for implementing the information processing method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that, The device contains a computer program that, when executed by a processor, implements the information processing method according to any one of claims 1 to 6.

Images