CN110929005A - Emotion analysis-based task follow-up method, device, equipment and storage medium - Google Patents
Emotion analysis-based task follow-up method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110929005A CN110929005A CN201910990755.3A CN201910990755A CN110929005A CN 110929005 A CN110929005 A CN 110929005A CN 201910990755 A CN201910990755 A CN 201910990755A CN 110929005 A CN110929005 A CN 110929005A
- Authority
- CN
- China
- Prior art keywords
- follow
- task
- emotion
- urging
- customer service
- 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
Links
- 230000008451 emotion Effects 0.000 title claims abstract description 237
- 238000000034 method Methods 0.000 title claims abstract description 77
- 238000004458 analytical method Methods 0.000 title claims abstract description 69
- 230000008569 process Effects 0.000 claims abstract description 31
- 238000004891 communication Methods 0.000 claims description 28
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000013145 classification model Methods 0.000 claims description 11
- 230000008909 emotion recognition Effects 0.000 claims description 8
- 230000002996 emotional effect Effects 0.000 claims description 7
- 238000000611 regression analysis Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000003197 catalytic effect Effects 0.000 abstract 2
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000000977 initiatory effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006397 emotional response Effects 0.000 description 2
- 230000008450 motivation Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 208000027534 Emotional disease Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
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
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- G06F16/35—Clustering; Classification
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses a task follow-up method based on emotion analysis, which comprises the following steps: acquiring a follow-up task request initiated by a customer service terminal; extracting task information from the follow-up task request and generating a follow-up task list; extracting follow-up and urging tasks from the follow-up and urging task list and calling corresponding follow-up and urging task words templates; generating a corresponding follow-up and urging task text according to the follow-up and urging task utterance template and a preset follow-up and urging task strategy, and sending the follow-up and urging task text to a follow-up and urging object; recording follow-up traffic content between the customer service end and the follow-up traffic object end, and performing emotion analysis on the follow-up traffic content to obtain the current emotion of the customer service; and sending corresponding emotion management prompts to the customer service end according to the current emotion of the customer service, so that the customer service can adjust or keep the emotion in the follow-up task execution process. The invention also discloses a task follow-up and urging device, equipment and a computer readable storage medium based on emotion analysis. The invention realizes the monitoring and management of the follow-up catalytic process and improves the follow-up catalytic rate.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a task follow-up method, a device and equipment based on emotion analysis and a computer readable storage medium.
Background
With the steady development of national economy, financial credit technologies such as credit cards have already entered the large-scale development stage. In order to survive in intense market competition, credit institutions strive to improve quality of service and reduce overdue bad accounts while pursuing a large scale increase in customer size. At present, the domestic credit investigation system has more defects, which causes the bad account to be high.
The current account and urging modes are traditional ones, such as telephone, short message, mail, letter, etc., and the actual contact rate of the customer is lower. Although a more intelligent online collection prompting mode is generated at present, the function of the existing online collection prompting system is single, and much data still needs to be analyzed and judged manually, so that the analysis result has great subjectivity, and the tracking and prompting reaching rate of a credit agency is influenced.
Disclosure of Invention
The invention mainly aims to provide a task follow-up method, a task follow-up device, a task follow-up equipment and a computer readable storage medium based on emotion analysis, and aims to solve the technical problem that the follow-up and urge reach rate is not high due to weak data analysis capability of the existing on-line follow-up and urge mode.
In order to achieve the above object, the present invention provides a task follow-up method based on emotion analysis, which comprises the following steps:
acquiring a follow-up task request initiated by a customer service terminal;
extracting task information from the follow-up task request, and generating a follow-up task list according to the task information;
extracting follow-up and urging tasks from the follow-up and urging task list, and calling corresponding follow-up and urging task words templates according to task information of the follow-up and urging tasks;
generating a corresponding follow-up and urging task text according to the follow-up and urging task utterance template and a preset follow-up and urging task strategy, and sending the follow-up and urging task text to a follow-up and urging object terminal;
recording follow-up traffic content between the customer service end and the follow-up object end, and performing emotion analysis on the follow-up traffic content to obtain the current emotion of the customer service;
and sending a corresponding emotion management prompt to the customer service end according to the current emotion of the customer service, so that the customer service can adjust or keep the emotion in the follow-up task execution process.
Optionally, the recording of the follow-up transaction content between the customer service end and the follow-up transaction object end, and performing emotion analysis on the follow-up transaction content to obtain the current emotion of the customer service includes:
recording follow-up traffic content between the customer service end and the follow-up object end;
acquiring communication contents sent by the customer service to the follow-up object from the follow-up traffic contents;
if the communication content is text information, inputting the communication content into a preset emotion classification model for emotion recognition and classification to obtain an emotion classification result;
if the communication content is voice information, converting the voice information into text information through voice recognition, and inputting the text information into the emotion classification model for emotion recognition and classification to obtain an emotion classification result;
carrying out regression analysis on the emotion classification result to obtain a regression value of each emotion in the emotion classification result;
and calculating the score of each emotion according to the regression value of each emotion, and taking the emotion with the highest score as the current emotion of the customer service.
Optionally, the score for each emotion is calculated using the following formula:
wherein, TiScore, V, representing the ith emotioni,3、Vi,4And respectively representing a third layer regression value and a fourth layer regression value of the ith emotion obtained by adopting a hierarchical regression method, wherein i is a positive integer.
Optionally, the sending, according to the current emotion of the customer service, a corresponding emotion management prompt to the customer service end, so that the customer service adjusts or maintains the emotion in the process of executing the follow-up task, includes:
calling a preset comparison relation table between the emotion value and the emotion management prompt;
based on the current emotion of the customer service, searching the comparison relation table to obtain an emotion management prompt corresponding to the current emotion of the customer service;
and sending the emotion management prompt to the customer service end so as to be used by the customer service to adjust or maintain the emotion in the follow-up task execution process.
Optionally, after the step of sending a corresponding emotion management prompt to the customer service end according to the current emotion of the customer service, so that the customer service adjusts or maintains the emotion in the follow-up task execution process, the method further includes:
after the follow-up task is finished, extracting key data which are generated in the process of executing the follow-up task by the customer service and are related to the follow-up object;
drawing a task data curve according to the key data, wherein the task data curve takes time as an abscissa and the key data as an ordinate;
performing trend prediction on the task data curve through a preset trend prediction algorithm to obtain a trend prediction result;
and importing the trend prediction result into a follow-up task strategy of the follow-up object to be used as a judgment basis for executing the follow-up task on the follow-up object next time.
Optionally, the performing trend prediction on the task data curve through a preset trend prediction algorithm to obtain a trend prediction result includes:
sequentially acquiring adjacent key data pairs corresponding to each time point in the task data curve;
calculating the data average value of all key data pairs, and drawing a data average value curve according to the data average value, wherein the data average value curve takes time as an abscissa and the data average value as an ordinate;
and performing trend prediction on the data average value curve through a calculation formula corresponding to the following trend prediction algorithm to obtain a trend prediction result:
Yt＝m*xt+(1-m)*Yt-1；
wherein t represents time，YtIndicates the predicted value, x, corresponding to time ttRepresents the average value of data corresponding to time t, Yt-1The predicted value corresponding to the time t-1 is represented, and the value range of the m constant is [0.5, 1 ]]。
Optionally, the importing the trend prediction result into the follow-up task policy of the follow-up object to be used as a judgment basis for executing the follow-up task on the follow-up object next time includes:
importing the trend prediction result into the task data curve, and generating a trend line of the task data curve according to a least square method;
judging whether the slope of the trend line is greater than a preset threshold value or not;
if yes, performing trend prediction on the task data curve again;
if not, the trend prediction result is imported into a follow-up urging task strategy of the follow-up urging object to be used as a judgment basis for executing the follow-up urging task on the follow-up urging object next time.
Furthermore, the invention also provides a task follow-up and urging device based on emotion analysis, which comprises:
the acquisition module is used for acquiring a follow-up task request initiated by a customer service end;
the first generation module is used for extracting task information from the follow-up task request and generating a follow-up task list according to the task information;
the calling module is used for extracting follow-up task from the follow-up task list and calling a corresponding follow-up task utterance template according to the task information of the follow-up task;
the second generation module is used for generating a corresponding follow-up and urging task text according to the follow-up and urging task utterance template and a preset follow-up and urging task strategy and sending the follow-up and urging task text to a follow-up and urging object terminal;
the emotion analysis module is used for recording follow-up traffic content between the customer service end and the follow-up traffic object end, and performing emotion analysis on the follow-up traffic content to obtain the current emotion of the customer service;
and the prompt module is used for sending a corresponding emotion management prompt to the customer service end according to the current emotion of the customer service so as to adjust or keep the emotion of the customer service in the follow-up task execution process.
Optionally, the emotion analysis module includes:
the recording unit is used for recording the follow-up traffic content between the customer service end and the follow-up object end;
the acquisition unit is used for acquiring the communication content sent by the customer service to the follow-up urging object from the follow-up urging communication content;
the recognition unit is used for inputting the communication content into a preset emotion classification model for emotion recognition and classification if the communication content is text information, so as to obtain an emotion classification result;
the conversion unit is used for converting the voice information into text information through voice recognition if the communication content is the voice information;
the analysis unit is used for carrying out regression analysis on the emotion classification results to obtain a regression value of each emotion in the emotion classification results;
and the calculating unit is used for calculating the score of each emotion according to the regression value of each emotion and taking the emotion with the highest score as the current emotion of the customer service.
Optionally, the score for each emotion is calculated using the following formula:
wherein, TiScore, V, representing the ith emotioni,3、Vi,4And respectively representing a third layer regression value and a fourth layer regression value of the ith emotion obtained by adopting a hierarchical regression method, wherein i is a positive integer.
Optionally, the prompting module includes:
the calling unit is used for calling a comparison relation table between a preset emotion value and the emotion management prompt;
the searching unit is used for searching the comparison relation table based on the current emotion of the customer service to obtain an emotion management prompt corresponding to the current emotion of the customer service;
and the prompting unit is used for sending the emotion management prompt to the customer service end so as to be adjusted or kept by the customer service in the follow-up task execution process.
Optionally, the task follow-up and urging device based on emotion analysis further includes:
the extraction module is used for extracting key data which are generated in the process of executing the follow-up urging task by the customer service and are related to the follow-up urging object after the follow-up urging task is finished;
the drawing module is used for drawing a task data curve according to the key data, wherein the task data curve takes time as an abscissa and takes the key data as an ordinate;
the prediction module is used for carrying out trend prediction on the task data curve through a preset trend prediction algorithm to obtain a trend prediction result;
and the leading-in module is used for leading the trend prediction result into the follow-up urging task strategy of the follow-up urging object so as to be used as a judgment basis for executing the follow-up urging task on the follow-up urging object next time.
Optionally, the prediction module is specifically configured to:
sequentially acquiring adjacent key data pairs corresponding to each time point in the task data curve;
calculating the data average value of all key data pairs, and drawing a data average value curve according to the data average value, wherein the data average value curve takes time as an abscissa and the data average value as an ordinate;
and performing trend prediction on the data average value curve through a calculation formula corresponding to the following trend prediction algorithm to obtain a trend prediction result:
Yt＝m*xt+(1-m)*Yt-1；
wherein t represents time, YtIndicates the predicted value, x, corresponding to time ttRepresents the average value of data corresponding to time t, Yt-1Represents the predicted value corresponding to time t-1, m constant,the value range is [0.5, 1 ]]。
Optionally, the import module is specifically configured to:
importing the trend prediction result into the task data curve, and generating a trend line of the task data curve according to a least square method;
judging whether the slope of the trend line is greater than a preset threshold value or not;
if yes, performing trend prediction on the task data curve again;
if not, the trend prediction result is imported into a follow-up urging task strategy of the follow-up urging object to be used as a judgment basis for executing the follow-up urging task on the follow-up urging object next time.
Further, in order to achieve the above object, the present invention further provides a task follow-up and urging device based on emotion analysis, where the task follow-up and urging device based on emotion analysis includes a memory, a processor, and a task follow-up and urging program stored in the memory and capable of running on the processor, and when the task follow-up and urging program is executed by the processor, the steps of any one of the above task follow-up and urging methods based on emotion analysis are implemented.
Further, to achieve the above object, the present invention also provides a computer readable storage medium, wherein a task following and urging program is stored on the computer readable storage medium, and when being executed by a processor, the task following and urging program implements any one of the steps of the task following and urging method based on emotion analysis.
When initiating the follow-up task request, the invention can use the preset follow-up task words template and the follow-up task strategy to generate the corresponding follow-up task text and send the follow-up task text to the follow-up object, thereby standardizing the follow-up task and avoiding the follow-up object from generating the sense of incongruity. Meanwhile, in the follow-up urging process, follow-up urging traffic content between the customer service and the follow-up urging object is obtained in real time, emotion analysis is carried out on the follow-up urging traffic content to determine the current emotion of the customer service, the emotion of the customer service is adjusted in time, the follow-up urging object is prevented from generating a sense of opposition, monitoring and management can be carried out in the urging process, therefore, the effect of follow-up urging can be prevented from being influenced by bad emotion generated by the customer service, and the reaching rate of task follow-up urging is improved.
Drawings
FIG. 1 is a schematic structural diagram of an operating environment of a task follow-up and urging device based on emotion analysis according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a task follow-up method based on emotion analysis according to the present invention;
FIG. 3 is a schematic diagram illustrating a detailed flow of step S50 in FIG. 2;
FIG. 4 is a flowchart illustrating a task following method based on emotion analysis according to a second embodiment of the present invention;
fig. 5 is a functional module diagram of an embodiment of the task follow-up and urging device based on emotion analysis.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides a task follow-up and urging device based on emotion analysis.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an operating environment of a task follow-up and urging device based on emotion analysis according to an embodiment of the present invention.
As shown in fig. 1, the task follow-up and urging device based on emotion analysis includes: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the hardware configuration of the emotion analysis based task follow-up device shown in fig. 1 does not constitute a limitation of the emotion analysis based task follow-up device, and may include more or less components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer-readable storage medium, may include therein an operating system, a network communication module, a user interface module, and a task following program. The operating system is a program for managing and controlling task follow-up and urging equipment and software resources based on emotion analysis, and supports the running of the task follow-up and urging program and other software and/or programs.
In the hardware structure of the task follow-up and urging device based on emotion analysis shown in fig. 1, the network interface 1004 is mainly used for accessing a network; the user interface 1003 is mainly used for detecting a confirmation instruction, an editing instruction, and the like, and the processor 1001 may be configured to call the task following program stored in the memory 1005 and perform the following operations of the embodiments of the task following method based on emotion analysis.
Based on the hardware structure of the task follow-up and urging equipment based on emotion analysis, the invention provides various embodiments of the task follow-up and urging method based on emotion analysis.
Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of a task follow-up method based on emotion analysis according to the present invention. In this embodiment, the task follow-up method based on emotion analysis includes the following steps:
step S10, acquiring a follow-up task request initiated by a customer service end;
the embodiment is not limited to the task content and the presentation form of the customer service need follow-up urging, and is specifically set according to actual needs. For example, a general affair is followed with urging, a loan is followed with urging, and the like. In addition, the follow-up task request initiated by the customer service end may include a plurality of follow-up tasks of the same or different types.
Step S20, extracting task information from the follow-up task request, and generating a follow-up task list according to the task information;
in this embodiment, in order to facilitate reasonable and effective follow-up urging for tasks of different types, different priority levels can be set for the follow-up urging tasks in advance. For example, the account follow-up and urging task can be divided into a plurality of task levels such as normal, urgent and the like, and according to the difference of the task levels, the customer service is generally preferentially arranged to execute the account follow-up and urging task with the task level of "urgent".
In this embodiment, the task information extracted from the follow-up task request is not limited, and may be, for example, a task name, task basic information, follow-up object basic information, a task level, and the like. It should be noted that the follow-up task list at least includes one follow-up task, and when there are a plurality of tasks in the follow-up task list, the follow-up tasks need to be sorted.
In one embodiment, the ranking rule is that follow-up tasks with the task level being "urgent" are preferably ranked in the front, and follow-up tasks with the same level are ranked according to other rules, such as the type of the tasks, the task generation time, and the like.
In this embodiment, after task information of each task in the follow-up task request is obtained, a corresponding follow-up task list is generated, and basic information of all follow-up tasks to be executed this time and an execution sequence of each follow-up task are recorded on the task list.
Step S30, extracting follow-up task from the follow-up task list, and calling a corresponding follow-up task utterance template according to the task information of the follow-up task;
in this embodiment, in order to further increase the reaching rate of the customer service executing the follow-up task, it is preferable that the customer service use a preset follow-up task speech target to communicate with the follow-up object. The follow-up task words template is set based on a specific follow-up task, different follow-up tasks correspond to different words templates, and standard and orderly professional words can be generated by using the words templates, so that the service specialty is embodied, the client touch rate is improved, and the phenomenon that the client is affected or is unfavorable due to the non-professional follow-up mode is avoided.
The embodiment is not limited to the specific content and the expression form of the follow-up task utterance template, for example, the follow-up task utterance template includes basic terms related to the follow-up task, question content and a response mode that are required to be used by the customer service, and the like.
In this embodiment, when the follow-up task is extracted from the follow-up task list and executed, task information of the follow-up task, such as basic task information, basic follow-up object information, task level, etc., is obtained first, and then the database is searched according to the obtained task information, and a follow-up task utterance template matched with the task information is determined and called.
Various follow-up task utterance templates need to be stored in a database in advance, and an association mapping relation between the templates and the tasks needs to be established.
Step S40, generating a corresponding follow-up and urging task text according to the follow-up and urging task utterance template and a preset follow-up and urging task strategy, and sending the follow-up and urging task text to a follow-up and urging object terminal;
in this embodiment, in order to make the follow-up urging task text sent by the customer service end easier to be accepted by the follow-up urging object, a corresponding follow-up urging task policy is preset, and the policy is specifically set according to the specific personal condition of the follow-up urging object, that is, different follow-up urging objects correspond to different follow-up urging task policies. For example, if the client likes chatting, the follow-up task strategy may start from chatting, and then some follow-up task texts related to chatting are generated. Or the client likes direct communication, the follow-up task strategy can be a direct cut-in theme, so that the client cover is avoided, and then follow-up task texts related to the follow-up task are generated.
The embodiment is not limited to the specific content and the expression mode of the follow-up task strategy, and is specifically set according to actual needs. The follow-up task strategy is a business rule and comprises a plurality of preset rules for generating follow-up task texts. And generating a follow-up and urging task text by using a follow-up and urging task utterance template according to a rule corresponding to the follow-up and urging task strategy, and then sending the generated follow-up and urging task text to a follow-up and urging object terminal, for example, if the follow-up and urging object terminal communicates by using a mail, chatting software and other modes, the follow-up and urging object terminal can be a mailbox, a micro signal and the like.
Step S50, recording follow-up traffic content between the customer service end and the follow-up object end, and performing emotion analysis on the follow-up traffic content to obtain the current emotion of the customer service;
in this embodiment, when the customer service communicates with the urging object, emotion is easily generated, so that the customer service emotion needs to be monitored and analyzed, and adverse effects on the urging object (i.e., the client) caused by the customer service emotion are avoided. In this embodiment, preferably, emotion analysis is performed on the follow-up traffic content between the customer service terminal and the follow-up object terminal, so as to obtain the current emotion of the customer service.
The embodiment is not limited to the implementation manner of the emotion analysis. For example, scores corresponding to various emotions are preset, various emotion keywords and scores corresponding to the emotion keywords are simultaneously set, then the obtained follow-up traffic content is retrieved to extract the emotion keywords, finally, the total scores of all the emotion keywords are counted, and then the corresponding emotions are determined according to the total scores of the emotion keywords.
And step S60, sending corresponding emotion management prompts to the customer service end according to the current emotion of the customer service end, so that the customer service can adjust or maintain the emotion in the follow-up task execution process.
In this embodiment, after the current emotion of the customer service is determined, the emotion management can be performed on the customer service, and specifically, the customer service is reminded to adjust or maintain the emotion in the process of executing the follow-up task by sending a prompt. For example, if the current emotion of the customer service is poor, the customer service is prompted to keep cool and calm, the emotion is adjusted, and the customer service is smiled; and if the current emotion of the customer service is stable and smiling is kept, prompting the customer service to keep the current emotion and executing the follow-up and urging task.
Optionally, in an embodiment, the emotion management is specifically performed on the customer service in the following manner:
firstly, a preset comparison relation table between emotion values and emotion management prompts is called;
secondly, based on the current emotion of the customer service, searching the comparison relation table to obtain an emotion management prompt corresponding to the current emotion of the customer service;
and finally, sending the emotion management prompt to the customer service end so as to be used by the customer service to adjust or maintain the emotion in the follow-up and urging task execution process.
In this optional embodiment, various emotions are quantized in advance, and then a comparison relation table between the emotion value and the emotion management prompt is set, that is, any one of different emotions is provided with the corresponding emotion management prompt. And (4) through table lookup, the emotion management prompt corresponding to the current emotion of the customer service can be obtained.
When initiating the follow-up task request, the embodiment can use the preset follow-up task utterance template and follow-up task strategy to generate a corresponding follow-up task text and send the follow-up task text to the follow-up object, thereby standardizing the follow-up task and avoiding the follow-up object from generating a sense of incongruity. Meanwhile, in the follow-up urging process, follow-up urging traffic content between the customer service and the follow-up urging object is obtained in real time, emotion analysis is carried out on the follow-up urging traffic content to determine the current emotion of the customer service, the emotion of the customer service is adjusted in time, the follow-up urging object is prevented from generating a sense of opposition, monitoring and management can be carried out in the urging process, therefore, the effect of follow-up urging can be prevented from being influenced by bad emotion generated by the customer service, and the reaching rate of task follow-up urging is improved.
Referring to fig. 3, fig. 3 is a schematic view of a detailed flow of the step S50 in fig. 2. In this embodiment, the step S50 further includes:
step S501, recording follow-up traffic content between the customer service end and the follow-up object end;
step S502, obtaining the communication content sent by the customer service to the follow-up urging object from the follow-up urging communication content;
in this embodiment, when the follow-up task is executed, the customer service end communicates with the follow-up object end (i.e., the client), that is, sends the communication information in a chat manner. For example, chat is performed by means of mail, WeChat, etc., and the chat content may be text or voice. The embodiment focuses on obtaining the communication content sent by the customer service to the follow-up urging object, so as to analyze and judge the current emotion of the customer service.
In this embodiment, the recording mode of the follow-up traffic content is not limited, for example, information is collected and sorted in a point burying mode, so as to obtain the follow-up traffic content.
Step S503, if the communication content is text information, inputting the communication content into a preset emotion classification model for emotion recognition and classification to obtain an emotion classification result;
step S504, if the communication content is voice information, the voice information is converted into text information through voice recognition and then is input into the emotion classification model for emotion recognition and classification, and an emotion classification result is obtained;
in this embodiment, if the communication content is text information, the communication content is directly input to a preset emotion classification model for emotion recognition and classification, and if the communication content is voice information, the voice information is converted into the text information through voice recognition, and then the text information obtained through conversion is input to the emotion classification model for processing.
In this embodiment, the training process of the emotion classification model is as follows: the method comprises the steps of collecting a plurality of chat records of a plurality of different customer services and a plurality of different task objects, segmenting words, determining the emotional characteristics of each word according to the part of speech of each word, and training an emotional classifier according to the emotional characteristics of each word, so that an emotional classification model is constructed.
In this embodiment, the emotion classification result includes multiple emotions corresponding to the same text message, for example, a sentence includes both positive emotion and negative emotion, so that it is necessary to further perform regression analysis on the multiple emotions in the classification result to determine the emotion most suitable for the current customer service.
Step S505, carrying out regression analysis on the emotion classification results to obtain a regression value of each emotion in the emotion classification results;
and step S506, calculating the score of each emotion according to the regression value of each emotion, and taking the emotion with the highest score as the current emotion of the customer service.
Regression analysis is a statistical analysis method for determining the quantitative relationship of interdependence between two or more variables. Namely, the causal relationship of the phenomena is determined by analyzing the specific form of the correlation between the phenomena, and the specific relationship is expressed by a mathematical model.
In this embodiment, a regression value of each emotion in the emotion classification result is obtained through regression analysis, and then a score of each emotion is calculated according to the regression value of each emotion. The specific calculation method is not limited. Such as counting the score of each emotion according to a preset weight value of emotions.
Optionally, in one embodiment, the score for each emotion is calculated using the following formula:
wherein, TiScore, V, representing the ith emotioni,3、Vi,4And respectively representing a third layer regression value and a fourth layer regression value of the ith emotion obtained by adopting a hierarchical regression method, wherein i is a positive integer.
In the optional embodiment, the score condition of each emotion is calculated, and then the emotion with the highest score is used as the current emotion of customer service.
Referring to fig. 4, fig. 4 is a flowchart illustrating a task following method based on emotion analysis according to a second embodiment of the present invention. In this embodiment, after step S60, the method further includes:
step S70, after the follow-up task is finished, extracting key data which are generated in the process of executing the follow-up task and are related to the follow-up object by the customer service;
step S80, drawing a task data curve according to the key data, wherein the task data curve takes time as an abscissa and takes the key data as an ordinate;
in this embodiment, the key data is specifically generated during the process of the customer service executing the follow-up task, and the specific content and the expression form of the key data are not limited in this embodiment. For example, the key data is data related to emotional changes in the customer service follow-up process, emotional reactions of follow-up subjects, and the like.
In this embodiment, in order to facilitate prediction of the follow-up task in the next stage or later, a task data curve is drawn based on the key data, and the task data curve takes time as an abscissa and key data as an ordinate, and can reflect future key data change conditions, such as a trend of an emotional change in a follow-up process of customer service at a future time point, an emotional response of a follow-up object, and the like.
Step S90, performing trend prediction on the task data curve through a preset trend prediction algorithm to obtain a trend prediction result;
in this embodiment, after the task data curve is drawn, a preset trend prediction algorithm is used to perform trend prediction. It should be noted that the trend prediction is mainly used for predicting the emotional response of the follow-up motivation object, so as to facilitate the follow-up motivation task strategy to be adjusted.
Optionally, in an embodiment, the trend prediction is performed by:
A. sequentially acquiring adjacent key data pairs corresponding to each time point in the task data curve;
B. calculating the data average value of all key data pairs, and drawing a data average value curve according to the data average value, wherein the data average value curve takes time as an abscissa and the data average value as an ordinate;
C. and performing trend prediction on the data average value curve through a calculation formula corresponding to the following trend prediction algorithm to obtain a trend prediction result:
Yt＝m*xt+(1-m)*Yt-1；
wherein t represents time, YtIndicates the predicted value, x, corresponding to time ttRepresents the average value of data corresponding to time t, Yt-1The predicted value corresponding to the time t-1 is represented, and the value range of the m constant is [0.5, 1 ]]。
In this embodiment, to better fit the variation trend of the task data curve, before performing trend prediction, adjacent key data pairs corresponding to each time point in the task data curve are obtained, the data average value of all the key data pairs is calculated, then a data average value curve is drawn, and finally, the trend prediction is performed on the data average value curve.
And step S100, importing the trend prediction result into a follow-up urging task strategy of the follow-up urging object to be used as a judgment basis for executing a follow-up urging task on the follow-up urging object next time.
In this embodiment, after the trend prediction result is obtained, the trend prediction result is imported into the follow-up task policy for use in executing the follow-up task next time.
Optionally, in an embodiment, the importing of the trend prediction result is specifically implemented by the following method:
A. importing the trend prediction result into the task data curve, and generating a trend line of the task data curve according to a least square method;
B. judging whether the slope of the trend line is greater than a preset threshold value or not;
C. if yes, performing trend prediction on the task data curve again;
D. if not, the trend prediction result is imported into a follow-up urging task strategy of the follow-up urging object to be used as a judgment basis for executing the follow-up urging task on the follow-up urging object next time.
In this optional embodiment, in order to make the trend prediction result more referable, before the trend prediction result is introduced into the follow-up task policy, the trend prediction result is further screened, and the specific implementation manner is as follows: the method comprises the steps of firstly importing a trend prediction result into a task data curve, then generating a trend line of the task data curve according to a least square method, finally judging whether the slope of the trend line of the task data curve is larger than a preset threshold value, if so, judging that the trend prediction result does not have referability, so that the trend prediction result cannot be imported into a follow-up task strategy, otherwise, judging that the trend prediction result has referability, so that the trend prediction result can be imported into the follow-up task strategy to serve as a judgment basis for executing a follow-up task on a follow-up object next time.
The invention also provides a task follow-up and urging device based on emotion analysis.
Referring to fig. 5, fig. 5 is a functional module diagram of an embodiment of the task follow-up and urging device based on emotion analysis according to the present invention. In this embodiment, the task follow-up urging device based on emotion analysis includes:
the acquisition module 10 is configured to acquire a follow-up task request initiated by a client;
the first generation module 20 is configured to extract task information from the follow-up task request, and generate a follow-up task list according to the task information;
the calling module 30 is configured to extract the follow-up task from the follow-up task list, and call a corresponding follow-up task utterance template according to task information of the follow-up task;
the second generation module 40 is configured to generate a corresponding follow-up task text according to the follow-up task utterance template and a preset follow-up task policy, and send the follow-up task text to a follow-up object;
the emotion analysis module 50 is used for recording follow-up traffic content between the customer service and the follow-up traffic object, and performing emotion analysis on the follow-up traffic content to obtain the current emotion of the customer service;
and the prompt module 60 is configured to send a corresponding emotion management prompt to the customer service according to the current emotion of the customer service, so that the customer service can adjust or maintain the emotion in the follow-up task execution process.
Based on the same embodiment as the method for task follow-up and urging based on emotion analysis in the present invention, the contents of the embodiment of the task follow-up and urging device based on emotion analysis are not described in detail in this embodiment.
In this embodiment, the task is with urging the device when initiating with urging the task request, can use the task words template of urging with of presetting and with urging the task strategy, generate corresponding with urge the task text and send to with urging the object to make with urge the task standardized, avoid with urging the object to produce the reaction. Meanwhile, further in the follow-up urging process, the task follow-up urging device acquires follow-up urging traffic content between the customer service and the follow-up urging object in real time, emotion analysis is carried out on the follow-up urging traffic content, the current emotion of the customer service is determined, then the emotion of the customer service is adjusted in time, the emotion is prevented from being followed by urging, so that the follow-up urging object is prevented from generating counter feeling, monitoring and management can be carried out in the urging process, therefore, the effect of the follow-up urging can be prevented from being influenced by the bad emotion generated by the customer service, and the contact rate of the task follow-up urging is improved.
The invention also provides a computer readable storage medium.
In this embodiment, a task follow-up program is stored on a computer-readable storage medium, and when being executed by a processor, the task follow-up program implements the steps of the method for task follow-up based on emotion analysis described in any of the above embodiments. The method implemented when the task follow-up program is executed by the processor may refer to each embodiment of the task follow-up method based on emotion analysis of the present invention, and thus, redundant description is not repeated.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM), and includes instructions for causing a terminal (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The present invention is described in connection with the accompanying drawings, but the present invention is not limited to the above embodiments, which are only illustrative and not restrictive, and those skilled in the art can make various changes without departing from the spirit and scope of the invention as defined by the appended claims, and all changes that come within the meaning and range of equivalency of the specification and drawings that are obvious from the description and the attached claims are intended to be embraced therein.
Claims (10)
1. A task follow-up method based on emotion analysis is characterized by comprising the following steps:
acquiring a follow-up task request initiated by a customer service terminal;
extracting task information from the follow-up task request, and generating a follow-up task list according to the task information;
extracting follow-up and urging tasks from the follow-up and urging task list, and calling corresponding follow-up and urging task words templates according to task information of the follow-up and urging tasks;
generating a corresponding follow-up and urging task text according to the follow-up and urging task utterance template and a preset follow-up and urging task strategy, and sending the follow-up and urging task text to a follow-up and urging object terminal;
recording follow-up traffic content between the customer service end and the follow-up object end, and performing emotion analysis on the follow-up traffic content to obtain the current emotion of the customer service;
and sending a corresponding emotion management prompt to the customer service end according to the current emotion of the customer service, so that the customer service can adjust or keep the emotion in the follow-up task execution process.
2. The task follow-up method based on emotion analysis as recited in claim 1, wherein said recording follow-up traffic content between said customer service terminal and said follow-up object terminal, and performing emotion analysis on said follow-up traffic content to obtain current emotion of customer service comprises:
recording follow-up traffic content between the customer service end and the follow-up object end;
acquiring communication contents sent by the customer service to the follow-up object from the follow-up traffic contents;
if the communication content is text information, inputting the communication content into a preset emotion classification model for emotion recognition and classification to obtain an emotion classification result;
if the communication content is voice information, converting the voice information into text information through voice recognition, and inputting the text information into the emotion classification model for emotion recognition and classification to obtain an emotion classification result;
carrying out regression analysis on the emotion classification result to obtain a regression value of each emotion in the emotion classification result;
and calculating the score of each emotion according to the regression value of each emotion, and taking the emotion with the highest score as the current emotion of the customer service.
3. A method for emotion-analysis-based task follow-up as claimed in claim 2, wherein the score for each emotion is calculated using the formula:
wherein, TiScore, V, representing the ith emotioni,3、Vi,4And respectively representing a third layer regression value and a fourth layer regression value of the ith emotion obtained by adopting a hierarchical regression method, wherein i is a positive integer.
4. The task follow-up method based on emotion analysis as claimed in claim 1, wherein said sending a corresponding emotion management prompt to the customer service end according to the current emotion of the customer service end, so that the customer service can adjust or maintain the emotion in the process of executing the follow-up task, comprises:
calling a preset comparison relation table between the emotion value and the emotion management prompt;
based on the current emotion of the customer service, searching the comparison relation table to obtain an emotion management prompt corresponding to the current emotion of the customer service;
and sending the emotion management prompt to the customer service end so as to be used by the customer service to adjust or maintain the emotion in the follow-up task execution process.
5. The emotion-analysis-based task follow-up method as recited in any one of claims 1 to 4, wherein after the step of sending a corresponding emotion management prompt to the customer service end according to the current emotion of the customer service, so that the customer service can adjust or maintain the emotion in the process of executing the follow-up task, the method further comprises:
after the follow-up task is finished, extracting key data which are generated in the process of executing the follow-up task by the customer service and are related to the follow-up object;
drawing a task data curve according to the key data, wherein the task data curve takes time as an abscissa and the key data as an ordinate;
performing trend prediction on the task data curve through a preset trend prediction algorithm to obtain a trend prediction result;
and importing the trend prediction result into a follow-up task strategy of the follow-up object to be used as a judgment basis for executing the follow-up task on the follow-up object next time.
6. The emotion-analysis-based task following method, as recited in claim 5, wherein the trend prediction of the task data curve by a preset trend prediction algorithm, and the obtaining of the trend prediction result comprises:
sequentially acquiring adjacent key data pairs corresponding to each time point in the task data curve;
calculating the data average value of all key data pairs, and drawing a data average value curve according to the data average value, wherein the data average value curve takes time as an abscissa and the data average value as an ordinate;
and performing trend prediction on the data average value curve through a calculation formula corresponding to the following trend prediction algorithm to obtain a trend prediction result:
Yt＝m*xt+(1-m)*Yt-1；
wherein t represents time, YtIndicates the predicted value, x, corresponding to time ttRepresents the average value of data corresponding to time t, Yt-1The predicted value corresponding to the time t-1 is represented, and the value range of the m constant is [0.5, 1 ]]。
7. The emotion analysis-based task follow-up method as recited in claim 6, wherein the introducing the trend prediction result into the follow-up task policy of the follow-up object as a judgment basis for the next follow-up task execution on the follow-up object comprises:
importing the trend prediction result into the task data curve, and generating a trend line of the task data curve according to a least square method;
judging whether the slope of the trend line is greater than a preset threshold value or not;
if yes, performing trend prediction on the task data curve again;
if not, the trend prediction result is imported into a follow-up urging task strategy of the follow-up urging object to be used as a judgment basis for executing the follow-up urging task on the follow-up urging object next time.
8. A task follow-up and urging device based on emotion analysis, which is characterized by comprising:
the acquisition module is used for acquiring a follow-up task request initiated by a customer service end;
the first generation module is used for extracting task information from the follow-up task request and generating a follow-up task list according to the task information;
the calling module is used for extracting follow-up task from the follow-up task list and calling a corresponding follow-up task utterance template according to the task information of the follow-up task;
the second generation module is used for generating a corresponding follow-up and urging task text according to the follow-up and urging task utterance template and a preset follow-up and urging task strategy and sending the follow-up and urging task text to a follow-up and urging object terminal;
the emotion analysis module is used for recording follow-up traffic content between the customer service end and the follow-up traffic object end, and performing emotion analysis on the follow-up traffic content to obtain the current emotion of the customer service;
and the prompt module is used for sending a corresponding emotion management prompt to the customer service end according to the current emotion of the customer service so as to adjust or keep the emotion of the customer service in the follow-up task execution process.
9. A task follow-up and urging device based on emotion analysis, wherein the task follow-up and urging device based on emotion analysis comprises a memory, a processor and a task follow-up and urging program stored on the memory and operable on the processor, and when executed by the processor, the task follow-up and urging program realizes the steps of the task follow-up and urging method based on emotion analysis according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a task follow-up program, which when executed by a processor implements the steps of the method for task follow-up based on emotional analysis according to any of claims 1-7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910990755.3A CN110929005A (en) | 2019-10-18 | 2019-10-18 | Emotion analysis-based task follow-up method, device, equipment and storage medium |
| PCT/CN2020/111405 WO2021073258A1 (en) | 2019-10-18 | 2020-08-26 | Task follow-up method, apparatus and device based on emotion analysis, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910990755.3A CN110929005A (en) | 2019-10-18 | 2019-10-18 | Emotion analysis-based task follow-up method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110929005A true CN110929005A (en) | 2020-03-27 |
Family
ID=69849016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910990755.3A Pending CN110929005A (en) | 2019-10-18 | 2019-10-18 | Emotion analysis-based task follow-up method, device, equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110929005A (en) |
| WO (1) | WO2021073258A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021073258A1 (en) * | 2019-10-18 | 2021-04-22 | 平安科技（深圳）有限公司 | Task follow-up method, apparatus and device based on emotion analysis, and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103970864A (en) * | 2014-05-08 | 2014-08-06 | 清华大学 | Emotion classification and emotion component analyzing method and system based on microblog texts |
| CN108427916A (en) * | 2018-02-11 | 2018-08-21 | 上海复旦通讯股份有限公司 | A kind of monitoring system and monitoring method of mood of attending a banquet for customer service |
| CN109064315A (en) * | 2018-08-02 | 2018-12-21 | 平安科技（深圳）有限公司 | Overdue bill intelligence collection method, apparatus, computer equipment and storage medium |
| CN109767765A (en) * | 2019-01-17 | 2019-05-17 | 平安科技（深圳）有限公司 | Talk about art matching process and device, storage medium, computer equipment |
| CN109859032A (en) * | 2019-01-22 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Funds on account collection method, apparatus, equipment and storage medium based on intelligent sound |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784414A (en) * | 2019-01-24 | 2019-05-21 | 出门问问信息科技有限公司 | Customer anger detection method, device and electronic equipment in a kind of phone customer service |
| CN109767787B (en) * | 2019-01-28 | 2023-03-10 | 腾讯科技（深圳）有限公司 | Emotion recognition method, device and readable storage medium |
| KR20190018666A (en) * | 2019-02-18 | 2019-02-25 | 네이버 주식회사 | Method and system for automatic activation of machine |
| CN109949103B (en) * | 2019-03-29 | 2021-10-22 | 联想(北京)有限公司 | Data processing method and device and electronic equipment |
| CN110929005A (en) * | 2019-10-18 | 2020-03-27 | 平安科技（深圳）有限公司 | Emotion analysis-based task follow-up method, device, equipment and storage medium |
-
2019
- 2019-10-18 CN CN201910990755.3A patent/CN110929005A/en active Pending
-
2020
- 2020-08-26 WO PCT/CN2020/111405 patent/WO2021073258A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103970864A (en) * | 2014-05-08 | 2014-08-06 | 清华大学 | Emotion classification and emotion component analyzing method and system based on microblog texts |
| CN108427916A (en) * | 2018-02-11 | 2018-08-21 | 上海复旦通讯股份有限公司 | A kind of monitoring system and monitoring method of mood of attending a banquet for customer service |
| CN109064315A (en) * | 2018-08-02 | 2018-12-21 | 平安科技（深圳）有限公司 | Overdue bill intelligence collection method, apparatus, computer equipment and storage medium |
| CN109767765A (en) * | 2019-01-17 | 2019-05-17 | 平安科技（深圳）有限公司 | Talk about art matching process and device, storage medium, computer equipment |
| CN109859032A (en) * | 2019-01-22 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Funds on account collection method, apparatus, equipment and storage medium based on intelligent sound |
Non-Patent Citations (1)
| Title |
|---|
| 客户世界: "某商业银行智能质检应用案例", pages 1 - 6, Retrieved from the Internet <URL:https://www.sohu.com/a/325062978_753232> * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021073258A1 (en) * | 2019-10-18 | 2021-04-22 | 平安科技（深圳）有限公司 | Task follow-up method, apparatus and device based on emotion analysis, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021073258A1 (en) | 2021-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107818798B (en) | Customer service quality evaluation method, device, equipment and storage medium | |
| US20210224832A1 (en) | Method and apparatus for predicting customer purchase intention, electronic device and medium | |
| US11062220B2 (en) | Integrated virtual cognitive agents and message communication architecture | |
| CN109767787B (en) | Emotion recognition method, device and readable storage medium | |
| US20160117624A1 (en) | Intelligent meeting enhancement system | |
| CN111917878B (en) | Message processing method, device, equipment and storage medium | |
| CN109254669A (en) | A kind of expression picture input method, device, electronic equipment and system | |
| CN113051362B (en) | Data query method, device and server | |
| CN115083434B (en) | Emotion recognition method and device, computer equipment and storage medium | |
| CN113360622A (en) | User dialogue information processing method and device and computer equipment | |
| JP2017215943A (en) | Information sharing support system, information sharing support device, information sharing support method, and program | |
| CN111651571A (en) | Man-machine cooperation based session realization method, device, equipment and storage medium | |
| WO2013184667A1 (en) | System, method and apparatus for voice analytics of recorded audio | |
| CN115665325A (en) | Intelligent outbound method, device, electronic equipment and storage medium | |
| US11816741B2 (en) | Automatically labeling data using natural language processing | |
| CN110543550A (en) | Method and device for automatically generating test questions | |
| KR102283134B1 (en) | METHOD AND APPARATUS FOR GENERATING READING DOCUMENT Of MINUTES | |
| CN111127213A (en) | Information processing method and device, storage medium and electronic equipment | |
| KR102171658B1 (en) | Crowd transcription apparatus, and control method thereof | |
| CN110929005A (en) | Emotion analysis-based task follow-up method, device, equipment and storage medium | |
| CN117196630A (en) | Transaction risk prediction method, device, terminal equipment and storage medium | |
| US10701006B2 (en) | Method and system for facilitating computer-generated communication with user | |
| US20220207066A1 (en) | System and method for self-generated entity-specific bot | |
| CN114141235A (en) | Voice corpus generation method and device, computer equipment and storage medium | |
| CN112307186A (en) | Question-answering service method, system, terminal device and medium based on emotion recognition |
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 |