CN114547288A - Customer service information display method, device, equipment and medium - Google Patents

Customer service information display method, device, equipment and medium Download PDF

Info

Publication number
CN114547288A
CN114547288A CN202210068344.0A CN202210068344A CN114547288A CN 114547288 A CN114547288 A CN 114547288A CN 202210068344 A CN202210068344 A CN 202210068344A CN 114547288 A CN114547288 A CN 114547288A
Authority
CN
China
Prior art keywords
customer service
text
conversation
user
audio
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210068344.0A
Other languages
Chinese (zh)
Inventor
张烜峰
李良斌
陈孝良
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing SoundAI Technology Co Ltd
Original Assignee
Beijing SoundAI Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing SoundAI Technology Co Ltd filed Critical Beijing SoundAI Technology Co Ltd
Priority to CN202210068344.0A priority Critical patent/CN114547288A/en
Publication of CN114547288A publication Critical patent/CN114547288A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/34—Browsing; Visualisation therefor
    • G06F16/345—Summarisation for human users
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/01—Customer relationship services

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Finance (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

The embodiment of the disclosure relates to a customer service information display method, a customer service information display device, customer service information display equipment and a customer service information display medium, wherein the method comprises the following steps: responding to manual customer service switching operation, and acquiring customer service conversation audio between a user and an AI customer service; converting the customer service dialogue audio into a customer service dialogue text; extracting a conversation abstract according to the customer service conversation text and/or the customer service conversation audio, wherein the conversation abstract comprises user attribute information, user problems and/or user emotion information; and displaying the conversation abstract and the customer service conversation text for the manual customer service. The conversation abstract and the conversation text can be displayed to the artificial customer service in the embodiment of the disclosure, and the conversation abstract comprises various types of information such as user problems and/or user emotions, so that the information displayed to the artificial customer service is more comprehensive, the artificial customer service can know the conversation condition between the user and the AI customer service through the displayed information, the user can be better served, and the accuracy and the service efficiency of the service are improved.

Description

Customer service information display method, device, equipment and medium
Technical Field
The present disclosure relates to the field of information display technologies, and in particular, to a method, an apparatus, a device, and a medium for displaying customer service information.
Background
With the continuous development of Artificial Intelligence (AI) technology, more and more industries can apply AI technology to improve efficiency, and one of the customer service industries is.
In a scenario of providing customer service through voice, a user can be generally served through an AI customer service first, and then switched to serve a manual customer service when the service cannot be completed. However, in the voice customer service scene, when the AI customer service changes to the manual customer service, the manual customer service does not know the conversation situation between the current user and the AI customer service because the information displayed for the manual customer service is limited, and thus the accuracy and efficiency of the service are greatly affected.
Disclosure of Invention
In order to solve the technical problems or at least partially solve the technical problems, the present disclosure provides a customer service information display method, apparatus, device and medium.
The embodiment of the disclosure provides a customer service information display method, which comprises the following steps:
responding to manual customer service switching operation, and acquiring customer service conversation audio between a user and an AI customer service;
converting the customer service dialogue audio into a customer service dialogue text;
extracting a conversation abstract according to the customer service conversation text and/or the customer service conversation audio, wherein the conversation abstract comprises user attribute information, user problems and/or user emotion information;
and displaying the conversation abstract and the customer service conversation text to the manual customer service.
The embodiment of the present disclosure further provides a customer service information display device, the device includes:
the audio module is used for responding to manual customer service switching operation and acquiring customer service conversation audio between a user and an AI customer service;
the conversion module is used for converting the customer service conversation audio into a customer service conversation text;
the abstract module is used for extracting a conversation abstract according to the customer service conversation text and/or the customer service conversation audio, wherein the conversation abstract comprises user attribute information, user problems and/or user emotion information;
and the display module is used for displaying the conversation abstract and the customer service conversation text to the manual customer service.
An embodiment of the present disclosure further provides an electronic device, which includes: a processor; a memory for storing the processor-executable instructions; the processor is used for reading the executable instructions from the memory and executing the instructions to realize the customer service information display method provided by the embodiment of the disclosure.
The embodiment of the disclosure also provides a computer-readable storage medium, which stores a computer program for executing the customer service information display method provided by the embodiment of the disclosure.
Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages: the customer service information display scheme provided by the embodiment of the disclosure responds to manual customer service conversion operation, and acquires the customer service dialogue audio between a user and an AI customer service; converting the customer service conversation audio into a customer service conversation text; extracting a conversation abstract according to the customer service conversation text and/or the customer service conversation audio, wherein the conversation abstract comprises user attribute information, user problems and/or user emotion information; and displaying the conversation abstract and the customer service conversation text for the manual customer service. By adopting the technical scheme, when the AI customer service is converted into the artificial customer service, the conversation audio between the user and the AI customer service can be converted into the conversation text, the conversation abstract is extracted, and the conversation abstract and the conversation text are displayed to the artificial customer service.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present disclosure, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a customer service information display method according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of another customer service information display method according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a customer service information display provided by an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a customer service information display device according to an embodiment of the disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, aspects of the present disclosure will be further described below. It should be noted that the embodiments and features of the embodiments of the present disclosure may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced in other ways than those described herein; it is to be understood that the embodiments disclosed in the specification are only a few embodiments of the present disclosure, and not all embodiments.
In order to solve the problem that in the related art, the accuracy and efficiency of service are greatly affected because manual customer service does not know the conversation situation between the current user and the AI customer service, the embodiment of the disclosure provides a customer service information display method, and the method is introduced below by combining a specific embodiment.
Fig. 1 is a schematic flow chart of a customer service information display method according to an embodiment of the present disclosure, where the method may be executed by a customer service information display apparatus, where the apparatus may be implemented by software and/or hardware, and may be generally integrated in an electronic device. As shown in fig. 1, the method includes:
step 101, responding to manual customer service switching operation, and acquiring customer service conversation audio between a user and an AI customer service.
The AI customer service, also called intelligent customer service, can accurately analyze and predict the intention of the user by using technologies such as artificial intelligence technology and Natural Language Processing (NLP) technology, and automatically communicate with the user by voice, so as to solve the problem of complex scenes such as business consultation, business query and business handling of the user. The manual customer service switching operation may be understood as a selection operation of the manual customer service triggered by the user when the AI customer service cannot solve the user problem, and may include a gesture control operation (such as clicking, long pressing, double clicking, and the like), a voice control operation, and the like, which is not limited in this disclosure. The customer service conversation audio may be an audio file obtained by recording a voice conversation process between the user and the AI customer service, and the audio file is recorded after being authorized by the user.
In the embodiment of the disclosure, when the AI customer service cannot complete the service of the user, the user may trigger the manual customer service switching operation, and at this time, the customer service information display device may obtain the customer service dialogue audio between the user and the AI customer service in response to the manual customer service switching operation.
And 102, converting the customer service conversation audio into a customer service conversation text.
The service dialog text may be text content obtained after performing speech recognition and processing on the service dialog audio.
Specifically, after the customer service information presentation device obtains the customer service dialogue audio, A Speech Recognition (ASR) technology may be used for the customer service dialogue audio to recognize corresponding Speech information and convert the Speech information into text content, so as to obtain a customer service dialogue text. The speech recognition technology is a technology for converting human speech into text, and the specific speech recognition technology is not limited in the embodiment of the present disclosure, and for example, a random model method or an artificial neural network method may be used.
And 103, extracting a conversation abstract according to the customer service conversation text and/or the customer service conversation audio, wherein the conversation abstract comprises user attribute information, user problems and/or user emotion information.
The dialog summary may be a dialog summary extracted from the customer service dialog text and/or the customer service dialog audio, and may represent the main content of the dialog process between the user and the AI customer service. In the embodiment of the present disclosure, the dialog summary may include at least one of user attribute information, a user question, and/or user emotion information, and the user attribute information may be understood as related information of the current user, for example, the user attribute information may include information such as a user name, a user identifier, and a user gender, the user question may be a problem that needs to be solved and is presented by the current user to the AI customer service, and the user emotion information may be an emotion in a process of a dialog between the current user and the AI customer service, and may include happiness, anger, sadness, happiness, fear, and the like, which are not limited specifically.
In some embodiments, extracting the dialog summary from the customer service dialog text and/or the customer service dialog audio may include: and matching in the customer service dialog text according to the preset basic questions, and determining the successfully matched preset basic questions as the user questions in the dialog abstract. The preset basic problem may be understood as a problem that may occur in a service process of a preset AI customer service, and may be specifically set according to a service scenario, for example, in an operator scenario, the preset basic problem may be a problem of a call charge, a complaint, and the like.
Aiming at the user problem in the dialogue abstract, matching can be carried out in the customer service dialogue text according to the preset basic problem, and the preset basic problem with the matching degree larger than the matching degree threshold value is determined as the user problem.
In some embodiments, extracting the dialog summary from the customer service dialog text and/or the customer service dialog audio may include: analyzing the customer service conversation text by adopting an emotion analysis model to obtain user emotion information in the conversation abstract; and/or analyzing the customer service conversation audio by adopting a tone analysis model to obtain the user emotion information in the conversation abstract.
The emotion analysis model may be a deep learning model capable of performing emotion analysis on the text, and the specific model used is not limited, and for example, a supervised or unsupervised neural network may be used. The intonation can be understood as a cavity tone formed by the rapid, slow and heavy configuration during speaking, and also refers to tone and pause and the like during speaking, the intonation analysis model can be a deep learning model which can analyze the intonation of voice and determine emotion according to the intonation analysis result, and different intonations can correspond to different emotions.
In the above scheme, the dialogue summary of the user and the AI customer service can include user problems and user emotion information besides user attribute information, so that the information types are more various, and subsequent manual customer service can quickly know related contents.
And 104, displaying the conversation abstract and the customer service conversation text to serve the manual customer service.
Specifically, after extracting the conversation abstract according to the customer service conversation text and/or the customer service conversation audio, the customer service information display device can display the conversation abstract and the customer service conversation text on an information display page to provide manual customer service, and the manual customer service can acquire the condition of providing service for the AI customer service by browsing the conversation abstract and the customer service conversation text, so that targeted quick response and service are performed.
Optionally, a summary region for displaying the dialog summary and a text region for displaying the customer service dialog text may be set in the information display page, so as to display the dialog summary and the customer service dialog text in different regions.
Optionally, presenting the customer service dialog text may include: and displaying the customer service conversation text according to a mode of distinguishing roles, wherein the roles comprise user and AI customer service. When the customer service information display device displays the customer service dialogue text, marks can be made on the corresponding marks of the text paragraphs and/or text sentences of different roles, and each role has a unique mark, so that the text paragraphs and/or text sentences belonging to the user and/or the text paragraphs and/or text sentences belonging to the AI customer service can be quickly determined according to the marks. By displaying the roles in the customer service conversation text in a distinguishing manner, texts of different roles can be quickly determined by browsing the customer service conversation text, and the information acquisition efficiency is improved.
The customer service information display scheme provided by the embodiment of the disclosure responds to manual customer service conversion operation, and acquires the customer service dialogue audio between a user and an AI customer service; converting the customer service conversation audio into a customer service conversation text; extracting a conversation abstract according to the customer service conversation text and/or the customer service conversation audio, wherein the conversation abstract comprises user attribute information, user problems and/or user emotion information; and displaying the conversation abstract and the customer service conversation text for the manual customer service. By adopting the technical scheme, when the AI customer service is converted into the artificial customer service, the conversation audio between the user and the AI customer service can be converted into the conversation text, the conversation abstract is extracted, and the conversation abstract and the conversation text are displayed to the artificial customer service.
For example, fig. 2 is a schematic flow chart of another customer service information presentation method provided in an embodiment of the present disclosure, and in a possible implementation manner, after converting a customer service dialog audio into a customer service dialog text, the customer service information presentation method may further include:
step 201, identifying keywords in the customer service dialog text.
The keywords may be important words related to the current service scenario in the customer service dialog text, and the number of the keywords may be one or more, specifically, without limitation.
In some embodiments, identifying keywords in the customer service dialog text may include: and identifying in the customer service dialog text through a keyword identification model or a regular matching mode based on the preset basic keywords to obtain the keywords. The preset basic keyword may be understood as a preset keyword related to a service scenario, for example, in an operator scenario, the preset basic keyword may be a telephone fee, a package, and the like, which are only examples.
The keyword recognition model may be a deep learning model trained in advance for performing keyword recognition, and the specific model is not limited. Specifically, after the customer service information presentation device converts the customer service dialogue audio into a customer service dialogue text, matching and recognition are performed in the customer service dialogue text based on preset basic keywords through a keyword recognition model or a regular matching mode, and words which are successfully matched are used as keywords.
Step 202, when the customer service dialog text is displayed, highlighting the keywords in a preset mode.
The preset manner may be any manner capable of distinguishing the keyword from other texts in the customer service dialog text, for example, the preset manner may be at least one of highlighting, bolding, underlining, and the like, and may be specifically set according to an actual situation.
Specifically, when the customer service information display device displays the customer service dialog text, the recognized keywords can be highlighted in a preset mode, so that the keywords can be quickly browsed by the manual customer service.
Optionally, the keyword may also be regarded as one of the above-mentioned dialog summaries, and is displayed in the dialog summary, so that when the customer service dialog text is long, the keyword can be obtained by the manual customer service without browsing the customer service dialog text.
Exemplarily, fig. 3 is a schematic diagram of customer service information display provided by an embodiment of the present disclosure, as shown in fig. 3, an information display page 300 displaying a dialog summary and a customer service dialog text is shown in the diagram, the information display page 300 includes a summary region 301 for displaying the dialog summary and a text region 302 for displaying the customer service dialog text, the dialog summary and the customer service dialog text are respectively displayed in two regions, which are only examples in the diagram, and the dialog summary and the customer service dialog text may also be displayed without dividing into regions. As shown in fig. 3, the dialog abstract may further include keywords, and the keywords may be highlighted in the customer service dialog text, and are highlighted by underlining in the figure. The text of the user in the service dialog text is displayed on the left side of the text area 302, and the text of the AI service is displayed on the right side of the text area 303, which is only an example in the figure, and the texts of the user and the AI service may be displayed on the same side, such as the center, the left side or the right side, and are not limited specifically. It is to be understood that fig. 3 is merely an example of customer service information presentation and is not limiting.
In the scheme, the customer service information display device can display the conversation abstract and the customer service conversation text, and can mark the keywords in the customer service conversation text or display the keywords in the conversation abstract, so that the manual customer service can quickly acquire the keywords, and the accuracy and efficiency of the manual customer service subsequent service user are further improved.
In some embodiments, after the service dialog text is displayed in a role-distinguishing manner, the service information display method may further include: aiming at a first text of a user in a customer service dialog text, displaying a plurality of audio playback controls in the first text by taking a sentence and/or a segment as a unit; and responding to the triggering operation of the manual customer service on the target audio playback control in the plurality of audio playback controls, and playing the audio segment of the text sentence and/or the text segment corresponding to the target audio playback control in the customer service dialogue audio.
Wherein, the first text can be understood as the text content corresponding to the voice spoken by the user in the customer service dialog text. The audio playback control can be understood as a control capable of playing audio corresponding to a text, and in the embodiment of the present disclosure, when the audio playback control is set, the audio playback control may be set in units of sentences and/or paragraphs, that is, one audio playback control may be set for each text sentence, and/or one audio playback control may be set for each text paragraph, which may be determined specifically according to actual situations.
Specifically, after the customer service information display device displays the customer service dialog text in a role distinguishing manner, the corresponding audio playback control can be displayed in a sentence and/or segment unit for the first text corresponding to the user, when the triggering operation of the manual customer service on one target audio playback control is received, the audio segment corresponding to the target audio playback control can be played, the audio segment is the audio segment corresponding to the text sentence and/or text segment corresponding to the target audio playback control in the customer service dialog audio, the manual customer service can conveniently perform proofreading when the customer service dialog text cannot be well understood, and the accuracy of obtaining the dialog condition is further improved.
In some embodiments, after the service dialog text is displayed in a role-distinguishing manner, the service information display method may further include: aiming at a second text of AI customer service in the customer service dialogue text, displaying a plurality of scoring controls in the second text by taking a sentence as a unit; and responding to the triggering operation of the manual customer service on the target scoring control in the plurality of scoring controls, and acquiring the score of the text sentence corresponding to the target scoring control.
The second text can be understood as the text content corresponding to the voice spoken by the AI customer service in the customer service dialog text. The scoring control can be understood as a judgment control for determining the accuracy of the text of the customer service conversation text conforming to the original audio expression meaning, and is used for providing the manual customer service, so that the manual customer service can score the customer service conversation text based on the scoring control. The scoring control can be set in sentence units when the scoring control is set, namely, one scoring control can be set for each text sentence.
Specifically, after the customer service information display device displays the customer service dialogue text in a role distinguishing mode, the corresponding scoring control can be set for the second text corresponding to the AI customer service in a sentence unit, and after the triggering operation of the artificial customer service on the target scoring control is received, the score marked by the artificial customer service can be obtained as the triggering operation can be the scoring operation of the artificial customer service through the target scoring control, and the score is the score of the text sentence corresponding to the target scoring control and represents the accuracy of the text sentence. The expression form of the above-mentioned trigger operation may include multiple forms, for example, the trigger operation may include an operation of clicking a target scoring control and inputting a score, or the trigger operation may also include an operation of selecting one score of multiple scores displayed by the target scoring control, and the like, which is specifically set according to an actual situation.
Optionally, after the score of each text statement in the customer service dialog text is obtained based on the scoring control, the score may be determined as a label of each text statement, and the response model of the AI customer service is returned to perform update training, where the response model may be a deep learning model for the AI customer service to serve the user, so as to improve the service accuracy of the response model.
According to the scheme, the scoring control of the customer service conversation text is provided, so that the manual customer service can directly obtain the scoring processing result when browsing the customer service conversation text, the scoring processing result can be used as the label to update the model of the AI customer service, the labeling work of the model training sample is saved, and the model updating efficiency is improved.
According to the customer service information display scheme provided by the embodiment of the disclosure, when switching from the AI customer service to the manual customer service, the audio in the service process of the AI customer service can be converted into characters by using an ASR technology, and the characters are displayed separately on the left side of a user and the right side of the AI customer service in sequence; the transcribed text is subjected to three aspects of work of summarizing user problems, marking key words and analyzing user emotion by using a text summary generation technology in NLP, so that quick response is facilitated during manual customer service switching, the user can be better served during manual customer service switching, and the customer service satisfaction rate is improved; for the transcribed text, a recording playback button can be provided for each sentence, so that the manual customer service can conveniently correct the text when the text cannot be well understood; the transcribed text can be scored for each sentence, and manual customer service can directly score when previewing the preposed information, so that the work is saved for subsequent marking optimization.
Fig. 4 is a schematic structural diagram of a customer service information display device provided in an embodiment of the present disclosure, where the customer service information display device may be implemented by software and/or hardware, and may be generally integrated in an electronic device. As shown in fig. 4, the apparatus includes:
the audio module 401 is configured to respond to a manual customer service switching operation, and acquire a customer service conversation audio between a user and an AI customer service;
a conversion module 402, configured to convert the customer service dialog audio into a customer service dialog text;
a summarization module 403, configured to extract a dialog summary according to the customer service dialog text and/or the customer service dialog audio, where the dialog summary includes user attribute information, user questions, and/or user emotion information;
and the display module 404 is configured to display the dialog summary and the customer service dialog text to the manual customer service.
Optionally, the summarization module 403 is specifically configured to:
and matching in the customer service dialog text according to a preset basic question, and determining the successfully matched preset basic question as the user question in the dialog abstract.
Optionally, the summarization module 403 is specifically configured to:
analyzing the customer service conversation text by adopting an emotion analysis model to obtain user emotion information in the conversation abstract;
and/or analyzing the customer service dialogue audio by adopting a tone analysis model to obtain the user emotion information in the dialogue abstract.
Optionally, the apparatus further includes a keyword module, configured to: after converting the customer service dialog audio to customer service dialog text,
identifying keywords in the customer service dialog text;
and when the customer service dialog text is displayed, highlighting the keywords in a preset mode.
Optionally, the keyword module is specifically configured to:
and identifying in the customer service dialog text in a keyword identification model or a regular matching mode based on a preset basic keyword to obtain the keyword.
Optionally, the display module is configured to:
and displaying the customer service dialog text in a mode of distinguishing roles, wherein the roles comprise the user and the AI customer service.
Optionally, the apparatus further comprises a playback module, configured to: after the customer service dialog text is displayed according to a role distinguishing mode,
aiming at a first text of the user in the customer service dialog text, displaying a plurality of audio playback controls in the first text by taking a sentence and/or a segment as a unit;
and responding to the triggering operation of the manual customer service on a target audio playback control in the plurality of audio playback controls, and playing the audio segment of the text sentence and/or text paragraph corresponding to the target audio playback control in the customer service dialogue audio.
Optionally, the apparatus further includes a scoring module configured to: after the customer service dialog text is displayed according to a role distinguishing mode,
aiming at a second text of the AI customer service in the customer service dialogue text, displaying a plurality of scoring controls in the second text by taking a sentence as a unit;
and responding to the triggering operation of the manual customer service on a target scoring control in the plurality of scoring controls, and acquiring the score of the text sentence corresponding to the target scoring control.
The customer service information display device provided by the embodiment of the disclosure can execute the customer service information display method provided by any embodiment of the disclosure, and has the corresponding functional modules and beneficial effects of the execution method.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 5, the electronic device 500 includes one or more processors 501 and memory 502.
The processor 501 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 500 to perform desired functions.
Memory 502 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium and executed by the processor 501 to implement the customer service information presentation methods of the embodiments of the present disclosure described above and/or other desired functions. Various contents such as an input signal, a signal component, a noise component, etc. may also be stored in the computer-readable storage medium.
In one example, the electronic device 500 may further include: an input device 503 and an output device 504, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
The input device 503 may also include, for example, a keyboard, a mouse, and the like.
The output device 504 may output various information to the outside, including the determined distance information, direction information, and the like. The output devices 504 may include, for example, a display, speakers, printer, and the like, as well as a communication network and its connected remote output devices.
Of course, for simplicity, only some of the components of the electronic device 500 relevant to the present disclosure are shown in fig. 5, omitting components such as buses, input/output interfaces, and the like. In addition, the electronic device 500 may include any other suitable components depending on the particular application.
In addition to the above methods and apparatus, embodiments of the present disclosure may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the customer service information presentation methods provided by embodiments of the present disclosure.
The computer program product may write program code for carrying out operations for embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions, which, when executed by a processor, cause the processor to execute the customer service information presentation method provided by the embodiments of the present disclosure.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present disclosure, which enable those skilled in the art to understand or practice the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (11)

1. A customer service information display method is characterized by comprising the following steps:
responding to manual customer service switching operation, and acquiring customer service conversation audio between a user and an AI customer service;
converting the customer service dialogue audio into a customer service dialogue text;
extracting a conversation abstract according to the customer service conversation text and/or the customer service conversation audio, wherein the conversation abstract comprises user attribute information, user problems and/or user emotion information;
and displaying the conversation abstract and the customer service conversation text to the manual customer service.
2. The method of claim 1, wherein extracting a dialog summary from the customer service dialog text and/or the customer service dialog audio comprises:
and matching in the customer service dialog text according to a preset basic question, and determining the successfully matched preset basic question as the user question in the dialog abstract.
3. The method of claim 1, wherein extracting a dialog summary from the customer service dialog text and/or the customer service dialog audio comprises:
analyzing the customer service conversation text by adopting an emotion analysis model to obtain user emotion information in the conversation abstract;
and/or analyzing the customer service dialogue audio by adopting a tone analysis model to obtain the user emotion information in the dialogue abstract.
4. The method of claim 1, wherein after converting the customer service dialog audio to customer service dialog text, the method further comprises:
identifying keywords in the customer service dialog text;
and when the customer service dialog text is displayed, highlighting the keywords in a preset mode.
5. The method of claim 4, wherein identifying keywords in the customer service dialog text comprises:
and identifying in the customer service dialog text in a keyword identification model or a regular matching mode based on a preset basic keyword to obtain the keyword.
6. The method of claim 1, wherein presenting the customer service dialog text comprises:
and displaying the customer service dialog text in a mode of distinguishing roles, wherein the roles comprise the user and the AI customer service.
7. The method of claim 6, wherein after presenting the customer service dialog text in a role-differentiated manner, the method further comprises:
aiming at a first text of the user in the customer service dialog text, displaying a plurality of audio playback controls in the first text by taking a sentence and/or a segment as a unit;
and responding to the triggering operation of the manual customer service on a target audio playback control in the plurality of audio playback controls, and playing the audio segment of the text sentence and/or text paragraph corresponding to the target audio playback control in the customer service dialogue audio.
8. The method of claim 6, wherein after presenting the customer service dialog text in a role-differentiated manner, the method further comprises:
aiming at a second text of the AI customer service in the customer service dialogue text, displaying a plurality of scoring controls in the second text by taking a sentence as a unit;
and responding to the triggering operation of the manual customer service on a target scoring control in the plurality of scoring controls, and acquiring the score of the text sentence corresponding to the target scoring control.
9. A customer service information display device, comprising:
the audio module is used for responding to manual customer service switching operation and acquiring customer service conversation audio between a user and an AI customer service;
the conversion module is used for converting the customer service conversation audio into a customer service conversation text;
the abstract module is used for extracting a conversation abstract according to the customer service conversation text and/or the customer service conversation audio, wherein the conversation abstract comprises user attribute information, user problems and/or user emotion information;
and the display module is used for displaying the conversation abstract and the customer service conversation text to the manual customer service.
10. An electronic device, characterized in that the electronic device comprises:
a processor;
a memory for storing the processor-executable instructions;
the processor is used for reading the executable instructions from the memory and executing the instructions to realize the customer service information display method of any one of the claims 1-8.
11. A computer-readable storage medium, characterized in that the storage medium stores a computer program for executing the customer service information presentation method according to any one of claims 1 to 8.
CN202210068344.0A 2022-01-20 2022-01-20 Customer service information display method, device, equipment and medium Pending CN114547288A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210068344.0A CN114547288A (en) 2022-01-20 2022-01-20 Customer service information display method, device, equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210068344.0A CN114547288A (en) 2022-01-20 2022-01-20 Customer service information display method, device, equipment and medium

Publications (1)

Publication Number Publication Date
CN114547288A true CN114547288A (en) 2022-05-27

Family

ID=81672061

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210068344.0A Pending CN114547288A (en) 2022-01-20 2022-01-20 Customer service information display method, device, equipment and medium

Country Status (1)

Country Link
CN (1) CN114547288A (en)

Similar Documents

Publication Publication Date Title
CN110444198B (en) Retrieval method, retrieval device, computer equipment and storage medium
CN107481720B (en) Explicit voiceprint recognition method and device
CN108536654B (en) Method and device for displaying identification text
WO2019153522A1 (en) Intelligent interaction method, electronic device, and storage medium
JP3848319B2 (en) Information processing method and information processing apparatus
US10770062B2 (en) Adjusting a ranking of information content of a software application based on feedback from a user
CN108984529A (en) Real-time court's trial speech recognition automatic error correction method, storage medium and computing device
CN110597952A (en) Information processing method, server, and computer storage medium
US20230069935A1 (en) Dialog system answering method based on sentence paraphrase recognition
WO2020233386A1 (en) Intelligent question-answering method and device employing aiml, computer apparatus, and storage medium
WO2020199600A1 (en) Sentiment polarity analysis method and related device
CN109508441B (en) Method and device for realizing data statistical analysis through natural language and electronic equipment
CN111639484A (en) Method for analyzing seat call content
CN109388705B (en) Text intention classification method
CN115292461B (en) Man-machine interaction learning method and system based on voice recognition
CN111145903A (en) Method and device for acquiring vertigo inquiry text, electronic equipment and inquiry system
CN111180025A (en) Method and device for representing medical record text vector and inquiry system
CN110852075A (en) Voice transcription method and device for automatically adding punctuation marks and readable storage medium
Wagner et al. Applying cooperative machine learning to speed up the annotation of social signals in large multi-modal corpora
CN114186041A (en) Answer output method
CN113901186A (en) Telephone recording marking method, device, equipment and storage medium
US20190088258A1 (en) Voice recognition device, voice recognition method, and computer program product
Jia et al. A deep learning system for sentiment analysis of service calls
CN117010907A (en) Multi-mode customer service method and system based on voice and image recognition
US20120197894A1 (en) Apparatus and method for processing documents to extract expressions and descriptions

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination