CN116167384A

CN116167384A - Information processing method, information processing device, electronic equipment and computer readable storage medium

Info

Publication number: CN116167384A
Application number: CN202211739523.9A
Authority: CN
Inventors: 杨晨光; 顾旭光; 王萌
Original assignee: Lenovo Beijing Ltd
Current assignee: Lenovo Beijing Ltd
Priority date: 2022-12-30
Filing date: 2022-12-30
Publication date: 2023-05-26

Abstract

The application provides an information processing method, an information processing device, electronic equipment and a computer readable storage medium; the method comprises the following steps: obtaining dialogue information for customer service to provide consultation service, wherein the dialogue information comprises at least one dialogue statement; carrying out attribute prediction on each dialogue sentence in the at least one dialogue sentence through an attribute prediction model to obtain attribute information of each dialogue sentence, wherein the attribute information characterizes a session stage where the corresponding dialogue sentence is located; and determining the dialogue sentences meeting the target pushing conditions in the dialogue information according to the attribute information of each dialogue sentence in the dialogue information.

Description

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

Technical Field

The present disclosure relates to computer technology, and in particular, to an information processing method, an information processing apparatus, an electronic device, and a computer readable storage medium.

Background

When customer service performs fault diagnosis problem solving in the process of providing consultation service, the problem solving capability directly influences the final user service experience. In order to provide service quality, the current method is to count the user evaluation of customer service providing consultation service in a period of time, and judge the developed service capability according to the average height of the user, but there is a problem that the user evaluation rate is very low, i.e. many users cannot evaluate after the service is finished, and then the actual data analysis finds that a great number of evaluation results are inconsistent with the service process, i.e. the user cannot be guaranteed to make serious and objective evaluation by using the evaluation rate as an evaluation standard, which cannot truly reflect the consultation service quality provided by the customer service.

Disclosure of Invention

The embodiment of the application provides an information processing method, an information processing device, electronic equipment and a computer readable storage medium, which can automatically determine dialogue sentences meeting target pushing conditions in dialogue information of customer service providing consultation services, so that the service quality of the consultation services provided by the customer service can be further determined based on the dialogue sentences.

The technical scheme of the embodiment of the application is realized as follows:

the embodiment of the application provides an information processing method, which comprises the following steps:

obtaining dialogue information for customer service to provide consultation service, wherein the dialogue information comprises at least one dialogue statement;

carrying out attribute prediction on each dialogue sentence in the at least one dialogue sentence through an attribute prediction model to obtain attribute information of each dialogue sentence, wherein the attribute information characterizes a session stage where the corresponding dialogue sentence is located;

and determining the dialogue sentences meeting the target pushing conditions in the dialogue information according to the attribute information of each dialogue sentence in the dialogue information.

In the above solution, after the session information for providing the consultation service by the customer service is obtained, the method further includes:

and classifying the dialogue information through a classification model to obtain the problem type corresponding to the dialogue information.

In the above solution, determining, according to attribute information of each dialogue sentence in the dialogue information, a dialogue sentence in the dialogue information that meets a target pushing condition, further includes:

determining a key dialogue sentence with the type of the attribute information as a target type according to the attribute information of each dialogue sentence in the dialogue information;

the key dialogue sentence is determined as a dialogue sentence satisfying a target pushing condition.

In the above scheme, the method further comprises:

determining at least one index value of service capability for the customer service according to the key dialogue statement;

and grading the service capacity of the customer service according to the at least one index value.

In the above aspect, the at least one index value includes at least one of the following:

the statement number of the key dialogue statement, dialogue time consumption corresponding to the key dialogue statement and statement number corresponding to the key statement with the type of attribute information of the plurality of key statements being the first type;

wherein the target type includes at least two sub-types, and the first type is any one of the at least two sub-types.

In the above solution, the rating the service capability of the customer service according to the index value further includes:

determining the comprehensive capacity value of the customer service according to the at least one index value; the method comprises the steps of carrying out a first treatment on the surface of the

Acquiring capability value intervals corresponding to a plurality of capability levels;

and determining the capability level of the customer service according to the capability value interval in which the comprehensive capability value is located.

In the above solution, before the obtaining of the session information for providing the consultation service by the customer service, the method further includes:

obtaining sample dialogue information of a sample customer service providing consultation service, wherein the sample dialogue information comprises at least one sample dialogue statement, each dialogue statement in the at least one sample dialogue statement carries an attribute tag, and the attribute tag characterizes a dialogue stage in which the corresponding sample dialogue statement is located;

carrying out attribute prediction on the speech sentence by each sample in the at least one sample dialogue sentence through the attribute prediction model to obtain predicted attribute information of each sample on the speech sentence;

and updating model parameters of the attribute prediction model according to errors between the prediction attribute information and the attribute labels of each sample dialogue statement.

An embodiment of the present application provides an information processing apparatus including:

the system comprises an acquisition module, a query module and a query module, wherein the acquisition module is used for acquiring dialogue information for providing consultation services for customer service, and the dialogue information comprises at least one dialogue statement;

the attribute prediction module is used for carrying out attribute prediction on each dialogue sentence in the at least one dialogue sentence through an attribute prediction model to obtain attribute information of each dialogue sentence, and the attribute information characterizes a session stage where the corresponding dialogue sentence is located;

and the determining module is used for determining the dialogue sentences meeting the target pushing conditions in the dialogue information according to the attribute information of each dialogue sentence in the dialogue information.

An embodiment of the present application provides an electronic device, including:

a memory for storing executable instructions;

and the processor is used for realizing the information processing method provided by the embodiment of the application when executing the executable instructions stored in the memory.

The embodiment of the application provides a computer readable storage medium, which stores executable instructions for implementing the information processing method provided by the embodiment of the application when the executable instructions are executed by a processor.

According to the embodiment of the application, the dialogue information for providing the consultation service by the customer service is obtained, the dialogue information comprises at least one dialogue statement, attribute prediction is carried out on each dialogue statement in the at least one dialogue statement through an attribute prediction model, the attribute information of each dialogue statement is obtained, the attribute information characterizes the dialogue stage where the corresponding dialogue statement is located, the dialogue statement meeting the target pushing condition in the dialogue information is determined according to the attribute information of each dialogue statement in the dialogue information, and the dialogue statement meeting the target pushing condition in the dialogue information for providing the consultation service by the customer service can be automatically determined, so that the service quality of the consultation service provided by the customer service can be further determined based on the attribute information.

Drawings

FIG. 1 is a schematic flow chart of an alternative information processing method according to an embodiment of the present application;

FIG. 2 is a schematic diagram of an alternative model construction of an ELMo model;

FIG. 3 is a schematic flow chart of an alternative information processing method according to an embodiment of the present application;

FIG. 4 is an alternative schematic diagram of sample dialogue information of the present application;

FIG. 5 is an alternative model block diagram of an attribute prediction model provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of an alternative architecture of a multi-layer attention network;

FIG. 7 is a schematic diagram of an alternative refinement flow of the information processing method provided in an embodiment of the present application;

FIG. 8 is a schematic flow chart of an alternative information processing method according to an embodiment of the present application;

fig. 9 is a schematic diagram of an alternative structure of an electronic device 900 according to an embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.

In the following description, the terms "first", "second", "third" and the like are merely used to distinguish similar objects and do not represent a specific ordering of the objects, it being understood that the "first", "second", "third" may be interchanged with a specific order or sequence, as permitted, to enable embodiments of the application described herein to be practiced otherwise than as illustrated or described herein.

Unless defined otherwise, 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 the present application only and is not intended to be limiting of the present application.

The information processing method provided in the embodiment of the present application will be described below in connection with exemplary applications and implementations of the terminal provided in the embodiment of the present application.

Referring to fig. 1, fig. 1 is a schematic flowchart of an alternative information processing method according to an embodiment of the present application, and will be described with reference to the steps shown in fig. 1.

Step 201, obtaining dialogue information for customer service to provide consultation service, wherein the dialogue information comprises at least one dialogue sentence;

step 202, carrying out attribute prediction on each dialogue sentence in the at least one dialogue sentence through an attribute prediction model to obtain attribute information of each dialogue sentence, wherein the attribute information characterizes a session stage where the corresponding dialogue sentence is located;

step 203, determining dialogue sentences meeting target pushing conditions in the dialogue information according to the attribute information of each dialogue sentence in the dialogue information.

Here, the customer service may be a manual customer service or an intelligent customer service, and the user may perform problem consultation with the customer service, and the customer may provide consultation service to the user. In actual implementation, the terminal obtains dialogue information with the user when the client provides the consultation service, and the dialogue information comprises at least one dialogue sentence. Specifically, the terminal may obtain the interaction data of the consulting service from the customer service dialogue system, to obtain at least one dialogue sentence of the consulting service. In the embodiment of the application, the attribute prediction model is realized through a ELMo (Embeddings from Language Models) model. Referring to fig. 2, fig. 2 is a schematic diagram of an alternative model structure of an ELMo model. The ELMo model uses a two-way short-term memory (LSTM) to predict words based on context. ELMo first converts an input into a character-level word-Embedding vector, generates a context-free word-Embedding (word-Embedding) from the character-level word-Embedding (Embedding), and then generates a context-dependent Embedding using a Bi-directional language model (e.g., bi-LSTM).

In the embodiment of the application, the attribute information characterizes the session stage where the corresponding dialogue sentence is located. Specifically, there are at least two types of attribute information output by the attribute prediction model, that is, there may be at least two types of session stages. By way of example, the session phases may have, for example, the following four types: a greeting stage, a positioning problem stage, a solving problem stage, an ending stage, etc. In some embodiments, the session stage may also have, for example, a pacifying user stage or an information promotion stage, etc., based on the above four.

In actual implementation, the terminal determines the dialogue sentences meeting the target pushing conditions in the dialogue information according to the attribute information of each dialogue sentence in the dialogue information. Here, the target pushing condition is a forward pushing effect on the advisory service, for example, among the above four session phases, the dialogue statement corresponding to the positioning problem phase and the solution problem phase is the dialogue statement satisfying the target pushing condition. In the embodiment of the application, the terminal determines the dialogue statement meeting the target pushing condition from the dialogue information, so that the useful information in the dialogue information for providing the consultation service by the customer service can be accurately extracted, and the evaluation of the service quality of the consultation service is facilitated.

In the embodiment of the present application, the attribute prediction model is obtained by training in advance. Specifically, in some embodiments, referring to fig. 3, fig. 3 is an optional flowchart of an information processing method provided in the embodiments of the present application, before step 201, further may be performed:

step 301, obtaining sample dialogue information of a sample customer service providing consultation service, wherein the sample dialogue information comprises at least one sample dialogue sentence, each dialogue sentence in the at least one sample dialogue sentence carries an attribute tag, and the attribute tag characterizes a session stage where the corresponding sample dialogue sentence is located;

step 302, predicting the attribute of the speech sentence for each sample in the at least one sample dialogue sentence through the attribute prediction model to obtain the predicted attribute information of each sample for the speech sentence;

and step 303, updating model parameters of the attribute prediction model according to the error between the predicted attribute information and the attribute labels of each sample dialogue statement.

In actual implementation, the terminal obtains sample dialogue information, and each sample dialogue statement in the sample dialogue information carries an attribute tag. Specifically, the attribute tag is a sentence-level label, and the labeling system of the attribute tag specifically divides each stage of the dialogue information into a key stage, which may include four types of greeting stage, positioning problem stage, solving problem stage and ending stage. Illustratively, referring to fig. 4, fig. 4 is an alternative schematic diagram of the sample dialogue information of the present application. Here, each sample dialogue sentence carries a attribute tag correspondingly, for example, the attribute tag corresponding to the sample pair dialogue sentence is a greeting stage; "check with you, is this machine mani? The attribute label corresponding to the speech sentence of the sample of the PF113SFB rescuer R720-15 IKBN' is a positioning problem stage; "this is a reply operation: resetting system operation: the left key starts the menu, sets, updates and security, resumes, resets the start button below the computer. The attribute label corresponding to the speech sentence of the sample is a problem solving stage; "good, please ask what can help you? The attribute label corresponding to the sample pair utterance is the ending stage.

In actual implementation, the attribute prediction model is implemented based on BERT, bi-LSTM, and CRF. Referring to fig. 5, fig. 5 is an alternative model block diagram of an attribute prediction model provided in an embodiment of the present application. The method comprises the steps of inputting sample dialogue information into an attribute prediction model, predicting the attribute of each sample of dialogue information on an utterance by using the attribute prediction model to obtain predicted attribute information of each sample on the utterance, and updating model parameters according to errors between the predicted attribute information and corresponding attribute labels, so that training of the attribute prediction model is realized.

In some embodiments, after the obtaining of the session information for providing the consultation service by the customer service, the method further includes: and classifying the dialogue information through a classification model to obtain the problem type corresponding to the dialogue information.

In the embodiment of the application, after the dialogue information is obtained, the dialogue information is input into the classification model to obtain the problem type corresponding to the dialogue information. Here, the question type is specifically a question type corresponding to a question that a user consults with a customer service in the counseling service. In a practical scenario, the problem type of the classification model may be annotated according to the type of failure involved in the product. Customer service may be an after-market service for providing the product. By way of example, the question type may be, for example, a power-on question of a computer or a display question of a display, etc. Here, the classification model may classify the dialogue information based on a plurality of rounds of dialogue, thereby obtaining a question type of the dialogue information.

In actual implementation, the classification model may be implemented based on a multi-layer attention network (Hierarchical Attention Network). Referring to fig. 6, fig. 6 is an alternative structural schematic diagram of a multi-level attention network including a word embedding layer, a word encoder layer, a word attention layer, a sentence encoder layer, a sentence attention layer, and a full connection layer. After the dialogue information is input into the classification model implemented based on the multi-layer attention network, the problem types related to the dialogue information can be output through each layer of the classification model.

In actual implementation, the classification model is obtained through pre-training. Specifically, before step 301, it may also be performed that: obtaining sample dialogue information, wherein the sample dialogue information carries a question type label; classifying the consultation problems related to the sample dialogue information through the classification model to obtain corresponding predicted problem types; and updating model parameters of the classification model according to errors between the problem type labels and the predicted problem types. Here, the labeling system of the problem type label is specifically a three-level fault classification system, and for a product, for example, more than 300 types of labels can be provided. In actual implementation, at least one sample dialogue information with consultation text information can be extracted, and the question type of each sample dialogue information is marked in multiple stages according to the marking system, so that a question type label is obtained.

In some embodiments, referring to fig. 7, fig. 7 is an optional refinement flowchart of the information processing method provided in the embodiment of the present application, and step 203 further includes:

step 2031, determining, according to the attribute information of each dialogue sentence in the dialogue information, a key dialogue sentence with the type of the attribute information being the target type;

step 2032, determining the key dialogue sentence as a dialogue sentence satisfying a target pushing condition.

In actual implementation, the terminal determines a key dialogue sentence of which the type of the attribute information in the dialogue information is a target type. Here, the types of the attribute information may be the four types listed above, that is, the four corresponding session phases, and the target types herein may be the positioning problem phase and the solution problem phase. In the embodiment of the application, the key dialogue sentences are determined to be dialogue sentences meeting the target pushing conditions, and the dialogue sentences with pushing action on the consultation service in the dialogue information can be conveniently and rapidly determined through the embodiment of the application, so that the service capability of customer service can be conveniently and further determined.

In some embodiments, referring to fig. 8, fig. 8 is a schematic flow chart of an alternative information processing method provided in the embodiment of the present application, and after step 203, may further be executed:

step 801, determining at least one index value of service capability for the customer service according to the key dialogue statement;

step 802, the root ranks the service capability of the customer service according to the at least one index value.

In actual implementation, the terminal determines at least one index value of the service capability of the customer service according to the key dialogue statement, and then ranks the service capability of the customer service according to the index value, so that the capability of solving the problem of user consultation when the customer service provides the consultation service can be quantitatively determined.

In some embodiments, the at least one index value comprises at least one of the following: the statement number of the key dialogue statement, dialogue time consumption corresponding to the key dialogue statement and statement number corresponding to the key statement with the type of attribute information of the plurality of key statements being the first type; wherein the target type includes at least two sub-types, and the first type is any one of the at least two sub-types.

In actual implementation, the terminal may count the number of sentences of the key dialogue sentences, and use the number of sentences as an index value to determine the number of dialogues spent by the customer service for answering the user consultation problem when providing the consultation service, where the larger the number of dialogues, the weaker the service capability of the customer service is represented. The terminal can also acquire the conversation time consumption of the key conversation statement, and the longer the conversation time consumption is, the weaker the service capability of the customer service is represented. In addition, the terminal may determine the conversation time consumption corresponding to the key conversation sentence and the number of sentences corresponding to the key sentence of which the type of the attribute information in the plurality of key sentences is the first type, where the target type may include, for example, a positioning problem stage and a solving problem stage, and the first type may be a positioning problem stage. The capacity of customer service to locate the problem can be determined by determining the statement number of the locating problem stage, and if the customer service is repeated for a plurality of times to locate the problem, the service capacity of representing the customer service is weaker. Here, the weaker the service capability of the customer service, the lower the level of service capability corresponding to the customer service. Specifically, the terminal acquires attribute information corresponding to each key dialogue sentence, determines attribute information representing that a dialogue stage where the corresponding key dialogue sentence is located is a positioning problem stage as first type attribute information, and further screens out target dialogue sentences of which the attribute information represents the dialogue stage where the corresponding key dialogue sentence is located from the key dialogue sentences to obtain the number of the target dialogue sentences. It should be understood that the number of target dialogue sentences can characterize the capability of customer service to confirm product faults according to the questioning judgment of the user, and the embodiment of the application determines the capability of customer service to locate the problems by obtaining the number of sentences with the type of attribute information in the key dialogue sentences as the first type.

In some embodiments, the step 902 may be implemented as follows: determining the comprehensive capacity value of the customer service according to the at least one index value; acquiring capability value intervals corresponding to a plurality of capability levels; and determining the capability level of the customer service according to the capability value interval in which the comprehensive capability value is located.

In practical implementation, the terminal may unify the index values to the same standard through a unifying rule, integrate the index values to determine a comprehensive capacity value, obtain capacity value intervals corresponding to a plurality of capacity levels, determine a capacity value statement in which the comprehensive capacity value falls, and determine the capacity level of the customer service based on the capacity value interval in which the comprehensive capacity is located. For example, if the capacity class is classified into three classes such as class 1, class 2 and class 3, the three classes respectively correspond to three capacity value intervals, and if the comprehensive capacity falls into one of the capacity value intervals, the service capacity representing the customer service corresponds to the capacity class corresponding to the capacity value interval.

In the embodiment of the present application, after the problem type of the dialogue information is determined by the classification model, the obtained capability level of the customer service is the capability level of the customer service for solving the consultation problem of the problem type. In practical implementation, the capacity level corresponding to the customer service in solving the problems of different problem types can be obtained through the embodiment of the application, so that the problem type of relatively weak customer service can be determined, and learning and training of the corresponding problem type can be further carried out on the customer service. If the user is the artificial customer service, a prompt can be sent to the artificial customer service, and corresponding courses are provided for learning. Specifically, the capability threshold standard under each problem type can be set, the corresponding problem with weak resolving capability can be screened out, and the target customer service with weak resolving capability in a plurality of manual customer services can be screened out, so that different training paths can be generated and relevant training courses can be pushed to the different training paths according to the resolving capability difference of each manual customer service for each problem type, and meanwhile, some real cases of the manual customer service with strong resolving capability can be pushed, so that the reference and the study are facilitated. The method can also automatically judge the solution capability change of various problem types of each manual customer service at regular intervals, analyze course learning effect, dynamically adjust learning paths according to capability lifting conditions and synchronously refresh capability threshold standards. If the intelligent customer service is provided, the intelligent customer service can be further trained on the corresponding problem types so as to improve the capability of the intelligent customer service to solve the problems of the corresponding problem types.

An electronic device for implementing the above information processing method provided in the embodiment of the present application is described below. Referring to fig. 9, fig. 9 is an optional schematic structural diagram of an electronic device 900 provided in an embodiment of the present application, where in practical application, the electronic device 900 may be implemented as a terminal or a server. The terminal may be, but is not limited to, a notebook computer, a tablet computer, a desktop computer, a smart phone, a dedicated messaging device, a portable game device, a smart speaker, a smart watch, etc. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing 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, content Delivery Network) services, basic cloud computing services such as big data and artificial intelligence platforms, and the like. The electronic device 900 shown in fig. 1 includes: at least one processor 901, memory 905, at least one network interface 902, and a user interface 903. The various components in the electronic device 900 are coupled together by a bus system 904. It is appreciated that the bus system 904 is used to facilitate connected communications between these components. The bus system 904 includes a power bus, a control bus, and a status signal bus in addition to a data bus. But for clarity of illustration, the various buses are labeled as bus system 904 in fig. 9.

The processor 901 may be an integrated circuit chip having signal processing capabilities such as a general purpose processor, such as a microprocessor or any conventional processor, digital signal processor (DSP, digital Signal Processor), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like.

The user interface 903 includes one or more output devices 9031 that enable presentation of media content, including one or more speakers and/or one or more visual displays. The 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.

The memory 905 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard drives, optical drives, and the like. Memory 905 optionally includes one or more storage devices physically remote from processor 901.

The memory 905 includes volatile memory or nonvolatile memory, and may also include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read Only Memory (ROM), and the volatile Memory may be a random access Memory (RAM, random Access Memory). The memory 905 described in embodiments of the present application is intended to comprise any suitable type of memory.

In some embodiments, the memory 905 is capable of storing data to support various operations, examples of which include programs, modules and data structures, or subsets or supersets thereof, in which embodiments 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; in particular, the method comprises the steps of,

an operating system 9051, including system programs, e.g., framework layer, core library layer, driver layer, etc., for handling various basic system services and hardware-related tasks, for implementing various basic services and handling hardware-based tasks;

network communication module 9052 for reaching other computing devices via one or more (wired or wireless) network interfaces 902, exemplary network interfaces 902 include: bluetooth, wireless compatibility authentication (WiFi), and universal serial bus (USB, universal Serial Bus), etc.;

a presentation module 9053 for enabling 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, speakers, etc.) associated with the user interface 903;

an input processing module 9054 for detecting one or more user inputs or interactions from one of the one or more input devices 9032 and translating the detected inputs or interactions.

In some embodiments, the information processing apparatus provided in the embodiments of the present application may be implemented in a software manner, and fig. 1 shows an information processing apparatus 9055 stored in a memory 905, which may be software in the form of a program, a plug-in, or the like, including the following software modules: the obtaining module 90551, the attribute prediction module 90552, and the determining module 90553 are logical, and thus may be arbitrarily combined or further split according to the implemented functions. The functions of the respective modules will be described hereinafter.

In other embodiments, the information processing apparatus provided in the embodiments of the present application may be implemented in hardware, and by way of example, the information processing apparatus provided in the embodiments of the present application may be a processor in the form of a hardware decoding processor that is programmed to perform the information processing method provided in the embodiments of the present application, for example, the processor in the form of a hardware decoding processor may employ one or more application specific integrated circuits (ASIC, application Specific Integrated Circuit), DSP, programmable logic device (PLD, programmable Logic Device), complex programmable logic device (CPLD, complex Programmable Logic Device), field programmable gate array (FPGA, field-Programmable Gate Array), or other electronic component.

Continuing with the description below of an exemplary structure of the information processing apparatus 9055 provided in the embodiments of the present application implemented as a software module, in some embodiments, as shown in fig. 9, the software module stored in the information processing apparatus 9055 of the memory 905 may include:

an obtaining module 90551, configured to obtain dialogue information for providing a consultation service by a customer service, where the dialogue information includes at least one dialogue sentence;

the attribute prediction module 90552 is configured to perform attribute prediction on each dialogue sentence in the at least one dialogue sentence through an attribute prediction model, so as to obtain attribute information of each dialogue sentence, where the attribute information characterizes a session stage where the corresponding dialogue sentence is located;

and the determining module 90553 is used for determining the dialogue sentences meeting the target pushing conditions in the dialogue information according to the attribute information of each dialogue sentence in the dialogue information.

In some embodiments, the apparatus further comprises: and the classification module is used for classifying the dialogue information through a classification model to obtain the problem type corresponding to the dialogue information.

In some embodiments, the determining module 90553 is further configured to determine, according to the attribute information of each dialogue sentence in the dialogue information, a key dialogue sentence whose attribute information is of a target type; the key dialogue sentence is determined as a dialogue sentence satisfying a target pushing condition.

In some embodiments, the apparatus further comprises: a rating module for determining at least one index value of service capability for the customer service according to the key dialogue statement; and grading the service capacity of the customer service according to the at least one index value.

In some embodiments, the rating module is further configured to determine a comprehensive capability value of the customer service according to the at least one index value; acquiring capability value intervals corresponding to a plurality of capability levels; and determining the capability level of the customer service according to the capability value interval in which the comprehensive capability value is located.

In some embodiments, the apparatus further comprises: the model training module is used for obtaining sample dialogue information for providing consultation services by the sample customer service, the sample dialogue information comprises at least one sample dialogue statement, each dialogue statement in the at least one sample dialogue statement carries an attribute tag, and the attribute tag characterizes a dialogue stage where the corresponding sample dialogue statement is located; carrying out attribute prediction on the speech sentence by each sample in the at least one sample dialogue sentence through the attribute prediction model to obtain predicted attribute information of each sample on the speech sentence; and updating model parameters of the attribute prediction model according to errors between the prediction attribute information and the attribute labels of each sample dialogue statement.

It should be noted that, the description of the apparatus in the embodiment of the present application is similar to the description of the embodiment of the method described above, and has similar beneficial effects as the embodiment of the method, so that a detailed description is omitted.

Embodiments of the present application provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the information processing method according to the embodiment of the present application.

The present embodiments provide a computer-readable storage medium storing executable instructions that, when executed by a processor, cause the processor to perform the information processing method provided by the embodiments of the present application.

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

In some embodiments, the executable instructions may be in the form of programs, software modules, scripts, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and they may be deployed in any form, including as stand-alone programs or as modules, components, subroutines, or other units suitable for use in a computing environment.

As an example, the executable instructions may, but need not, correspond to files in a file system, 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, hyperTextMarkupLanguage) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).

As an example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices located at one site or, alternatively, distributed across multiple sites and interconnected by a communication network.

In summary, according to the embodiment of the present application, a dialogue sentence satisfying a target pushing condition in dialogue information of providing a consultation service by a customer service can be automatically determined, so that the service quality of the consultation service provided by the customer service can be further determined based on the dialogue sentence.

The foregoing is merely exemplary embodiments of the present application and is not intended to limit the scope of the present application. Any modifications, equivalent substitutions, improvements, etc. that are within the spirit and scope of the present application are intended to be included within the scope of the present application.

Claims

1. An information processing method, characterized by comprising:

2. The method of claim 1, after the session information providing the counseling service is obtained, the method further comprising:

3. The method according to claim 1 or 2, determining a dialogue sentence in the dialogue information that satisfies a target pushing condition according to attribute information of each dialogue sentence in the dialogue information, further comprising:

4. A method according to claim 3, the method further comprising:

5. The method of claim 4, the at least one indicator value comprising at least one of:

6. The method of claim 4, the rating the service capability of the customer service according to the indicator value, further comprising:

determining the comprehensive capacity value of the customer service according to the at least one index value;

7. The method of claim 1, prior to obtaining session information for providing advisory services, the method further comprising:

8. An information processing apparatus comprising:

9. An electronic device, comprising:

a memory for storing executable instructions;

a processor for implementing the information processing method of any one of claims 1 to 7 when executing executable instructions stored in said memory.

10. A computer readable storage medium storing executable instructions for implementing the information processing method of any one of claims 1 to 7 when executed by a processor.