CN113051386B - Adjustment method and device for transferring manual service, electronic equipment and storage medium - Google Patents
Adjustment method and device for transferring manual service, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113051386B CN113051386B CN202110482031.5A CN202110482031A CN113051386B CN 113051386 B CN113051386 B CN 113051386B CN 202110482031 A CN202110482031 A CN 202110482031A CN 113051386 B CN113051386 B CN 113051386B
- Authority
- CN
- China
- Prior art keywords
- user
- text
- emotion
- manual service
- automatic switching
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 82
- 230000008451 emotion Effects 0.000 claims abstract description 178
- 230000003993 interaction Effects 0.000 claims abstract description 62
- 230000008569 process Effects 0.000 claims abstract description 39
- 238000001514 detection method Methods 0.000 claims abstract description 27
- 230000002452 interceptive effect Effects 0.000 claims abstract description 20
- 230000001960 triggered effect Effects 0.000 claims description 25
- 238000010276 construction Methods 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 10
- 230000010365 information processing Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000013075 data extraction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The application provides a method and device for adjusting manual service, electronic equipment and a storage medium. In the method for adjusting the manual service, when the interaction between the user and the robot is detected, the interaction process between the user and the robot is monitored, and user behavior information of the user and interaction information input by the user are obtained. Wherein the interactive information includes text information and voice information. Analyzing the interactive information input by the user to obtain the emotion value of the user. And detecting whether the emotion value of the user is lower than a preset threshold value and whether the user behavior information of the user triggers an automatic switching manual service condition in the process of interacting with the robot to obtain a detection result. And based on the detection result, adjusting parameters of the automatic switching manual service condition of the user. And taking the adjusted automatic switching manual service condition as the automatic switching manual service condition of the user.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technologies, and in particular, to a method and an apparatus for adjusting an artificial service, an electronic device, and a storage medium.
Background
Human-machine interaction is the science of studying the interaction relationship between a system and a user. The system may be a variety of machines, as well as computerized systems and software. For example, various artificial intelligence systems can be implemented through man-machine interaction, wherein an intelligent question-answering system is a typical application of man-machine interaction, and when a user presents a question, the intelligent question-answering system finds a question corresponding to the user question from a knowledge base, and then finds an answer matched with the question.
With the wide application of intelligent question and answer systems, more and more enterprises establish intelligent robot customer services through the intelligent question and answer systems to answer questions and solve questions for users. However, the robot customer service can only search according to the information input by the user due to the data limitation of the knowledge base, and when the data in the knowledge base can not find the answer required by the user, the robot customer service can only answer through switching the manual customer service. In the process of interaction with the robot customer service, the setting of the condition for changing the manual service is always fixed, but because of different tolerance of each user, some users have dissatisfied emotion on the current interaction when the condition for changing the manual service is not triggered, and the satisfaction degree of the users to enterprises is reduced.
Disclosure of Invention
In view of this, the present application provides a method, an apparatus, an electronic device, and a storage medium for adjusting a manual service to solve the problem in the prior art that users have generated dissatisfaction to current interactions when manual conditions are not triggered, thereby reducing satisfaction of users to enterprises.
In order to achieve the above purpose, the present application provides the following technical solutions:
the first aspect of the application discloses a method for adjusting manual service conversion, which comprises the following steps:
when the interaction between the user and the robot is detected, monitoring the interaction process between the user and the robot, and acquiring user behavior information of the user and interaction information input by the user; wherein the interactive information comprises text information and voice information;
analyzing the interactive information input by the user to obtain the emotion value of the user;
detecting whether the emotion value of the user is lower than a preset threshold value and whether the user behavior information of the user triggers an automatic switching manual service condition in the process of interacting with the robot to obtain a detection result;
based on the detection result, adjusting parameters of the automatic switching manual service condition of the user; the lower the parameter is, the easier the automatic switching manual service condition is triggered, and the higher the parameter is, the less the automatic switching manual service condition is triggered;
and taking the adjusted automatic switching manual service condition as the automatic switching manual service condition of the user.
Optionally, in the above method, the analyzing the interaction information input by the user to obtain the emotion value of the user includes:
when the text information is input by the user, word segmentation is carried out on the text information;
performing text vectorization on the segmented text by using a language model in the customer service field to obtain a text vector;
inputting the text vector into a pre-constructed text emotion model to obtain an emotion value of the user; the text emotion model is constructed in advance according to a text data set marked with text emotion.
Optionally, in the above method, the analyzing the interaction information input by the user to obtain the emotion value of the user includes:
when the voice information is input by the user, extracting voiceprint feature data of the user;
inputting the voiceprint characteristic data into a pre-constructed voice emotion model to obtain an emotion value of the user; the voice emotion model is constructed in advance according to a voiceprint feature data set marked with voice emotion.
Optionally, in the above method, the process of constructing the text emotion model includes:
acquiring a text data set of the marked text emotion;
inputting the text data set marked with the text emotion into an initial model for operation to obtain an emotion value of the current text data;
judging whether the emotion value of the current text data is consistent with the emotion value of the actually marked text data or not;
if the emotion value of the current text data is consistent with the emotion value of the actually marked text data, completing the construction of the text emotion model;
if the emotion value of the current text data is inconsistent with the emotion value of the actually marked text data, an error function is obtained, and parameters of the neural network model are adjusted by utilizing the error function until the emotion value of the output current text data is consistent with the emotion value of the actually marked text data, and then the construction of the text emotion model is completed.
Optionally, in the above method, the adjusting the parameter of the automatic switching manual service condition of the user based on the detection result includes:
if the emotion value of the user is detected to be lower than a preset threshold value and the user behavior information of the user does not trigger the automatic switching manual service condition, the parameters of the automatic switching manual service condition of the user are reduced;
if the emotion value of the user is detected not to be lower than a preset threshold value and the user behavior information of the user triggers the automatic switching manual service condition, the parameters of the automatic switching manual service condition of the user are adjusted to be high.
The second aspect of the application discloses an adjusting device for transferring manual service, comprising:
the monitoring unit is used for monitoring the interaction process of the user and the robot when the interaction between the user and the robot is detected, and acquiring user behavior information of the user and interaction information input by the user; wherein the interactive information comprises text information and voice information;
the analysis unit is used for analyzing the interaction information input by the user to obtain the emotion value of the user;
the detection unit is used for detecting whether the emotion value of the user is lower than a preset threshold value and whether the user behavior information of the user triggers an automatic switching manual service condition in the process of interacting with the robot to obtain a detection result;
the adjusting unit is used for adjusting parameters of the automatic switching manual service condition of the user based on the detection result; the lower the parameter is, the easier the automatic switching manual service condition is triggered, and the higher the parameter is, the less the automatic switching manual service condition is triggered;
and the determining unit is used for taking the adjusted automatic switching manual service condition as the automatic switching manual service condition of the user.
Optionally, in the foregoing apparatus, the parsing unit includes:
the first information processing subunit is used for word segmentation of the text information when the text information is input by the user;
the second information processing subunit is used for carrying out text vectorization on the text after word segmentation by utilizing a language model in the customer service field to obtain a text vector;
the first operation subunit is used for inputting the text vector into a pre-constructed text emotion model to obtain an emotion value of the user; the text emotion model is constructed in advance according to a text data set marked with text emotion.
Optionally, in the foregoing apparatus, the parsing unit includes:
the data extraction unit is used for extracting voiceprint feature data of the user when the voice information is input by the user;
the second operation subunit is used for inputting the voiceprint feature data into a pre-constructed voice emotion model to obtain an emotion value of the user; the voice emotion model is constructed in advance according to a voiceprint feature data set marked with voice emotion.
Optionally, in the foregoing apparatus, the first operation subunit includes:
the obtaining subunit is used for obtaining the text data set marked with the text emotion;
the third operation subunit is used for inputting the text data set marked with the text emotion into the initial model for operation to obtain the emotion value of the current text data;
the judging subunit is used for judging whether the emotion value of the current text data is consistent with the emotion value of the actually marked text data;
a construction subunit, configured to complete the construction of the text emotion model if the emotion value of the current text data is consistent with the emotion value of the actually-marked text data;
and the parameter adjusting subunit is used for solving an error function if the emotion value of the current text data is inconsistent with the emotion value of the actually-marked text data, and adjusting parameters of the neural network model by utilizing the error function until the emotion value of the output current text data is consistent with the emotion value of the actually-marked text data, so that the text emotion model is built.
Optionally, in the foregoing apparatus, the adjusting unit includes:
the first adjusting subunit is used for adjusting down parameters of the automatic switching manual service condition of the user if the emotion value of the user is detected to be lower than a preset threshold value and the user behavior information of the user does not trigger the automatic switching manual service condition;
and the second adjusting subunit is used for adjusting the parameters of the automatic switching manual service condition of the user if the emotion value of the user is detected not to be lower than a preset threshold value and the user behavior information of the user triggers the automatic switching manual service condition.
A third aspect of the present application discloses an electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of the first aspects of the present invention.
A fourth aspect of the present application discloses a computer storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements a method according to any of the first aspects of the present invention.
According to the technical scheme, in the adjustment method for converting the manual service, when the interaction between the user and the robot is detected, the interaction process between the user and the robot is monitored, and the user behavior information of the user and the interaction information input by the user are obtained. Wherein the interactive information includes text information and voice information. Analyzing the interactive information input by the user to obtain the emotion value of the user. And detecting whether the emotion value of the user is lower than a preset threshold value and whether the user behavior information of the user triggers an automatic switching manual service condition in the process of interacting with the robot to obtain a detection result. And based on the detection result, adjusting parameters of the automatic switching manual service condition of the user. The lower the parameter is, the easier the automatic switching manual service condition is triggered, and the higher the parameter is, the less the automatic switching manual service condition is triggered. And taking the adjusted automatic switching manual service condition as the automatic switching manual service condition of the user. Therefore, by utilizing the method, when the user interacts with the robot customer service, whether the emotion value of the user is lower than the preset threshold value in the interaction process of the user and the robot customer service and whether the user behavior information of the user triggers the automatic switching manual service condition can be detected in real time, and the automatic switching manual service condition parameters of the user are adjusted according to the detection result, so that the special automatic switching manual service condition is set for the user according to the user condition, and the user experience is improved. The method solves the problems that in the prior art, users generate dissatisfaction to the current interaction when the manual condition is not triggered, and the satisfaction degree of the users to enterprises is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings may be obtained according to the provided drawings without inventive effort to a person skilled in the art.
Fig. 1 is a flowchart of a method for adjusting a manual service according to an embodiment of the present application;
FIG. 2 is a flow chart of one implementation of a text emotion model construction process disclosed in another embodiment of the present application;
FIG. 3 is a schematic diagram of an adjusting device for transferring manual services according to another embodiment of the present disclosure;
fig. 4 is a schematic diagram of an electronic device according to another embodiment of the present disclosure.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
In this application, 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 one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Moreover, 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.
As known from the background technology, along with the wide application of the intelligent question and answer system, more and more enterprises set up intelligent robot customer services to answer questions and confusion for users through the intelligent question and answer system. However, the robot customer service can only search according to the information input by the user due to the data limitation of the knowledge base, and when the data in the knowledge base can not find the answer required by the user, the robot customer service can only answer through switching the manual customer service. In the process of interaction with the robot customer service, the setting of the condition for changing the manual service is always fixed, but because of different tolerance of each user, some users have dissatisfied emotion on the current interaction when the condition for changing the manual service is not triggered, and the satisfaction degree of the users to enterprises is reduced.
In view of this, the application provides a method, a device, an electronic device and a storage medium for adjusting a manual service, so as to solve the problem that in the prior art, users have dissatisfied emotion to current interaction when the manual service is not triggered, and the satisfaction degree of the users to enterprises is reduced.
The embodiment of the application provides a method for adjusting manual service, as shown in fig. 1, specifically including:
s101, monitoring the interaction process of a user and a robot when the interaction of the user and the robot is detected, and acquiring user behavior information of the user and interaction information input by the user; wherein the interactive information includes text information and voice information.
When the user incoming line is detected to interact with the robot customer service, the interaction process of the user and the robot is monitored in real time, and meanwhile, user behavior information of the user and interaction information input by the user are obtained. The interactive information comprises text information and voice information, such as online text interaction or telephone voice interaction between a user and a robot customer service. The behavior information of the user includes which operations the user makes during the interaction, such as scoring the robot customer service, actively performing a manual service transfer operation, etc.
S102, analyzing the interaction information input by the user to obtain the emotion value of the user.
After the interactive information input by the user is obtained each time, the interactive information input by the user is analyzed, so that the emotion value of the user reflected in the interactive information input by the user is obtained through analysis. For example, the user's input information includes words expressing emotion, such as mood words, which reflect the current rough emotion change of the user.
Optionally, in another embodiment of the present application, an implementation of step S102 includes:
when the text information is input by the user, word segmentation is carried out on the text information; performing text vectorization on the segmented text by using a language model in the customer service field to obtain a text vector; and inputting the text vector into a pre-constructed text emotion model to obtain an emotion value of the user.
When the text information is input by the user, the acquired text information is subjected to word segmentation, and then text vectorization is performed on the segmented text by using a language model in the customer service field, so that a text vector is obtained. Inputting the text vector into a pre-constructed text emotion model for operation, so as to obtain an emotion value of the user; the text emotion model is constructed in advance according to a text data set marked with text emotion, and adopts a neural network structure of a biglu+an attribute layer+a full-connection layer.
Optionally, in another embodiment of the present application, an implementation of step S102 includes:
and when the voice information is input by the user, extracting voiceprint characteristic data of the user.
Inputting voiceprint characteristic data into a pre-constructed voice emotion model to obtain an emotion value of a user; the voice emotion model is constructed in advance according to a voiceprint feature data set marked with voice emotion.
When the user inputs voice information, the voice information is firstly converted into text information through a voice recognition technology, then word segmentation is carried out on the text information, and after word segmentation is completed, voice print characteristic data of the user are extracted by segmentation of the result of the dark combat text word segmentation. And then inputting the extracted voiceprint characteristic data into a pre-constructed voice emotion model for operation, so that the emotion value of the user can be obtained. The voice emotion model is constructed in advance according to a voiceprint characteristic data set marked with voice emotion, and adopts a neural network structure of a bigrou, an Attention layer and a full connection layer.
Optionally, in another embodiment of the present application, a method for constructing the text emotion model in the above step, as shown in fig. 2, includes:
s201, acquiring a text data set marked with text emotion.
The text data set of the emotion of the text is first labeled, and these text data are used as training data and input into the neural network model for training.
S202, inputting the text data set marked with the text emotion into an initial model for operation, and obtaining the emotion value of the current text data.
S203, judging whether the emotion value of the current text data is consistent with the emotion value of the actually marked text data.
After the emotion value of the current text data is calculated in the initial calculation model, the emotion value of the text data obtained by calculation is compared with the emotion value of the text data actually marked, so that whether the emotion value of the text data obtained by calculation in the initial calculation model is accurate or not is judged.
S204, if the emotion value of the current text data is consistent with the emotion value of the actually marked text data, the construction of the text emotion model is completed.
S205, if the emotion value of the current text data is inconsistent with the emotion value of the actually-marked text data, an error function is obtained, and parameters of the neural network model are adjusted by using the error function until the emotion value of the output current text data is consistent with the emotion value of the actually-marked text data, and then the construction of the text emotion model is completed.
If the emotion value of the calculated text data is inconsistent with the emotion value of the actually marked text data, an error function of the neural network model is obtained, parameters of the neural network model are adjusted by the error function, a new round of operation is carried out again until the emotion value of the output text data is consistent with the emotion value of the actually marked text data, and then the construction of the text emotion model is completed.
S103, detecting whether the emotion value of the user is lower than a preset threshold value and whether the user behavior information of the user triggers an automatic switching manual service condition in the process of interacting with the robot to obtain a detection result.
It should be noted that, during the interaction process of the user with the robot, whether the emotion value of the user is lower than a preset threshold value is detected in real time, the threshold value can be set according to the actual situation, and the emotion of the user described by the lower threshold value is worsened. And detecting whether the user behavior information of the user triggers an automatic switching manual service condition or not to obtain a detection result. The automatic switching manual service condition can set the times that the scoring value of the robot is lower than the threshold value a by a user to reach n times; the user repeatedly asks a question m times; the robot is repeatedly matched to a problem p times, etc., wherein the value of a, n, m, p can be set according to the actual situation.
S104, adjusting parameters of the automatic switching manual service condition of the user based on the detection result; the lower the parameter is, the easier the automatic switching manual service condition is triggered, and the higher the parameter is, the less the automatic switching manual service condition is triggered.
It should be noted that, after the detection result is obtained, parameters of the automatic switching manual service condition of the current user are adjusted appropriately according to the behavior and emotion change of the user in the interaction process. For example, if the emotion of the user is poor, it indicates that the user may not be satisfied with the robot customer service, and the parameters of the automatic switching manual service condition of the user should be adjusted at this time, so that the automatic switching manual service condition is easier to trigger for the user.
Optionally, in another embodiment of the present application, an implementation manner of step S104 specifically includes:
if the emotion value of the user is detected to be lower than the preset threshold value and the user behavior information of the user does not trigger the automatic switching manual service condition, the parameters of the automatic switching manual service condition of the user are reduced.
If the condition value of the user is detected not to be lower than the preset threshold value and the user behavior information of the user triggers the automatic switching manual service condition, the parameters of the automatic switching manual service condition of the user are increased.
It should be noted that if the emotion value of the user is detected to be lower than the preset threshold value, and the user behavior information of the user does not trigger the automatic switching manual service condition, it is indicated that the user is not satisfied in the interaction of the robot, and the parameters of the automatic switching manual service condition of the user should be reduced, so that the user can switch manual service more easily. If the condition value of the user is detected not to be lower than the preset threshold value, and the user behavior information of the user triggers the automatic switching manual service condition, the condition that the user is satisfied in the interaction of the robot is indicated, and at the moment, the parameters of the automatic switching manual service condition of the user can be properly adjusted.
S105, taking the adjusted automatic switching manual service condition as the automatic switching manual service condition of the user.
After the automatic switching manual service condition is adjusted, the adjusted automatic switching manual service condition is used as the special automatic switching manual service condition of the current user, and if the user is led in again, the automatic switching manual service condition of the user is the most according to the adjusted automatic switching manual service condition.
In the adjustment method for converting manual service provided by the embodiment of the application, when the interaction between the user and the robot is detected, the interaction process between the user and the robot is monitored, and the user behavior information of the user and the interaction information input by the user are obtained. Wherein the interactive information includes text information and voice information. Analyzing the interactive information input by the user to obtain the emotion value of the user. And detecting whether the emotion value of the user is lower than a preset threshold value and whether the user behavior information of the user triggers an automatic switching manual service condition in the process of interacting with the robot to obtain a detection result. And based on the detection result, adjusting parameters of the automatic switching manual service condition of the user. The lower the parameter is, the easier the automatic switching manual service condition is triggered, and the higher the parameter is, the less the automatic switching manual service condition is triggered. And taking the adjusted automatic switching manual service condition as the automatic switching manual service condition of the user. Therefore, by utilizing the method, when the user interacts with the robot customer service, whether the emotion value of the user is lower than the preset threshold value in the interaction process of the user and the robot customer service and whether the user behavior information of the user triggers the automatic switching manual service condition can be detected in real time, and the automatic switching manual service condition parameters of the user are adjusted according to the detection result, so that the special automatic switching manual service condition is set for the user according to the user condition, and the user experience is improved. The method solves the problems that in the prior art, users generate dissatisfaction to the current interaction when the manual condition is not triggered, and the satisfaction degree of the users to enterprises is reduced.
The other embodiment of the application also discloses an adjusting device for transferring manual service, as shown in fig. 3, specifically including:
the monitoring unit 301 is configured to monitor an interaction process between the user and the robot when detecting that the user interacts with the robot, and obtain user behavior information of the user and interaction information input by the user; wherein the interactive information includes text information and voice information.
And the parsing unit 302 is configured to parse the interaction information input by the user to obtain an emotion value of the user.
The detecting unit 303 is configured to detect whether an emotion value of a user is lower than a preset threshold value and whether user behavior information of the user triggers an automatic switching manual service condition in an interaction process of the user with the robot, so as to obtain a detection result.
The adjusting unit 304 is configured to adjust parameters of the automatic switching manual service condition of the user based on the detection result; the lower the parameter is, the easier the automatic switching manual service condition is triggered, and the higher the parameter is, the less the automatic switching manual service condition is triggered.
The determining unit 305 is configured to take the adjusted automatic switching manual service condition as an automatic switching manual service condition of the user.
In this embodiment, the specific execution processes of the monitoring unit 301, the parsing unit 302, the detecting unit 303, the adjusting unit 304, and the determining unit 305 can be referred to in the embodiment of the method corresponding to fig. 1, and will not be described herein.
In the adjusting device for converting manual service provided in the embodiment of the present application, when detecting that a user interacts with a robot, the monitoring unit 301 monitors the interaction process between the user and the robot, and obtains user behavior information of the user and interaction information input by the user. Wherein the interactive information includes text information and voice information. The parsing unit 302 parses the interactive information input by the user to obtain the emotion value of the user. The detection unit 303 detects whether the emotion value of the user is lower than a preset threshold value and whether the user behavior information of the user triggers an automatic switching manual service condition in the process of interacting with the robot to obtain a detection result. Based on the detection result, the adjustment unit 304 adjusts parameters of the automatic switching manual service condition of the user. The lower the parameter is, the easier the automatic switching manual service condition is triggered, and the higher the parameter is, the less the automatic switching manual service condition is triggered. The determination unit 305 takes the adjusted automatic transfer manual service condition as the automatic transfer manual service condition of the user. Therefore, by utilizing the method, when the user interacts with the robot customer service, whether the emotion value of the user is lower than the preset threshold value in the interaction process of the user and the robot customer service and whether the user behavior information of the user triggers the automatic switching manual service condition can be detected in real time, and the automatic switching manual service condition parameters of the user are adjusted according to the detection result, so that the special automatic switching manual service condition is set for the user according to the user condition, and the user experience is improved. The method solves the problems that in the prior art, users generate dissatisfaction to the current interaction when the manual condition is not triggered, and the satisfaction degree of the users to enterprises is reduced.
Optionally, in another embodiment of the present application, an implementation of the parsing unit 302 includes:
and the first information processing subunit is used for segmenting the text information when the text information is input by the user.
And the second information processing subunit is used for carrying out text vectorization on the text after word segmentation by utilizing a language model in the customer service field to obtain a text vector.
The first operation subunit is used for inputting the text vector into a pre-constructed text emotion model to obtain an emotion value of a user; the text emotion model is constructed in advance according to a text data set marked with text emotion.
In this embodiment, the specific execution process of the first information processing subunit, the second information processing subunit, and the first operation subunit may refer to the content corresponding to the foregoing method embodiment, which is not described herein again.
Optionally, in another embodiment of the present application, an implementation of the parsing unit 302 includes:
and the data extraction unit is used for extracting voiceprint feature data of the user when the voice information is input by the user.
The second operation subunit is used for inputting voiceprint feature data into a pre-constructed voice emotion model to obtain an emotion value of a user; the voice emotion model is constructed in advance according to a voiceprint feature data set marked with voice emotion.
In this embodiment, the specific execution process of the data extraction unit and the second operation subunit may refer to the content corresponding to the foregoing method embodiment, which is not described herein again.
Optionally, in another embodiment of the present application, an implementation of the first operation subunit includes:
and the acquisition subunit is used for acquiring the text data set marked with the text emotion.
And the third operation subunit is used for inputting the text data set marked with the text emotion into the initial model for operation to obtain the emotion value of the current text data.
And the judging subunit is used for judging whether the emotion value of the current text data is consistent with the emotion value of the actually marked text data.
And the construction subunit is used for completing the construction of the text emotion model if the emotion value of the current text data is consistent with the emotion value of the actually marked text data.
And the parameter adjusting subunit is used for solving an error function if the emotion value of the current text data is inconsistent with the emotion value of the actually-marked text data, and adjusting parameters of the neural network model by utilizing the error function until the emotion value of the output current text data is consistent with the emotion value of the actually-marked text data, so that the construction of the text emotion model is completed.
In this embodiment, the specific execution processes of the obtaining subunit, the operating subunit, the judging subunit, the constructing subunit, and the parameter adjusting subunit may refer to the content of the method embodiment corresponding to fig. 2, which is not described herein again.
Optionally, in another embodiment of the present application, an implementation of the adjusting unit 304 includes:
the first adjusting subunit is configured to, if it is detected that the emotion value of the user is lower than a preset threshold, and the user behavior information of the user does not trigger the automatic switching manual service condition, reduce a parameter of the automatic switching manual service condition of the user.
And the second adjusting subunit is used for adjusting the parameters of the automatic switching manual service condition of the user if the condition value of the user is detected not to be lower than the preset threshold value and the user behavior information of the user triggers the automatic switching manual service condition.
In this embodiment, the specific execution process of the first adjustment subunit and the second adjustment subunit may refer to the content of the corresponding method embodiment, which is not described herein.
Another embodiment of the present application further provides an electronic device, as shown in fig. 4, specifically including:
one or more processors 401.
A storage device 402, on which one or more programs are stored.
The one or more programs, when executed by the one or more processors 401, cause the one or more processors 401 to implement the method as in any of the embodiments described above.
Another embodiment of the present application also provides a computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a method according to any of the above embodiments.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a system or system embodiment, since it is substantially similar to a method embodiment, the description is relatively simple, with reference to the description of the method embodiment being made in part. The systems and system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. 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 application. Thus, the present application 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 (8)
1. A method for tuning to manual service, comprising:
when the interaction between the user and the robot is detected, monitoring the interaction process between the user and the robot, and acquiring user behavior information of the user and interaction information input by the user; wherein the interactive information comprises text information and voice information;
analyzing the interactive information input by the user to obtain the emotion value of the user;
detecting whether the emotion value of the user is lower than a preset threshold value and whether the user behavior information of the user triggers an automatic switching manual service condition in the process of interacting with the robot to obtain a detection result;
if the emotion value of the user is detected to be lower than a preset threshold value and the user behavior information of the user does not trigger the automatic switching manual service condition, the parameters of the automatic switching manual service condition of the user are reduced;
if the emotion value of the user is detected not to be lower than a preset threshold value and the user behavior information of the user triggers the automatic switching manual service condition, the parameter of the automatic switching manual service condition of the user is adjusted to be high; the lower the parameter is, the easier the automatic switching manual service condition is triggered, and the higher the parameter is, the less the automatic switching manual service condition is triggered;
and taking the adjusted automatic switching manual service condition as the automatic switching manual service condition of the user.
2. The method of claim 1, wherein the parsing the interaction information input by the user to obtain the emotion value of the user comprises:
when the text information is input by the user, word segmentation is carried out on the text information;
performing text vectorization on the segmented text by using a language model in the customer service field to obtain a text vector;
inputting the text vector into a pre-constructed text emotion model to obtain an emotion value of the user; the text emotion model is constructed in advance according to a text data set marked with text emotion.
3. The method of claim 1, wherein the parsing the interaction information input by the user to obtain the emotion value of the user comprises:
when the voice information is input by the user, extracting voiceprint feature data of the user;
inputting the voiceprint characteristic data into a pre-constructed voice emotion model to obtain an emotion value of the user; the voice emotion model is constructed in advance according to a voiceprint feature data set marked with voice emotion.
4. The method of claim 2, wherein the process of constructing the text emotion model comprises:
acquiring a text data set of the marked text emotion;
inputting the text data set marked with the text emotion into an initial model for operation to obtain an emotion value of the current text data;
judging whether the emotion value of the current text data is consistent with the emotion value of the actually marked text data or not;
if the emotion value of the current text data is consistent with the emotion value of the actually marked text data, completing the construction of the text emotion model;
if the emotion value of the current text data is inconsistent with the emotion value of the actually marked text data, an error function is obtained, and parameters of the text emotion model are adjusted by using the error function until the emotion value of the output current text data is consistent with the emotion value of the actually marked text data, and then the construction of the text emotion model is completed.
5. An adjustment device for converting manual service, comprising:
the monitoring unit is used for monitoring the interaction process of the user and the robot when the interaction between the user and the robot is detected, and acquiring user behavior information of the user and interaction information input by the user; wherein the interactive information comprises text information and voice information;
the analysis unit is used for analyzing the interaction information input by the user to obtain the emotion value of the user;
the detection unit is used for detecting whether the emotion value of the user is lower than a preset threshold value and whether the user behavior information of the user triggers an automatic switching manual service condition in the process of interacting with the robot to obtain a detection result;
the first adjusting unit is used for adjusting down parameters of the automatic switching manual service condition of the user if the emotion value of the user is detected to be lower than a preset threshold value and the user behavior information of the user does not trigger the automatic switching manual service condition;
the second adjusting unit is used for adjusting the parameters of the automatic switching manual service condition of the user if the emotion value of the user is detected to be not lower than a preset threshold value and the user behavior information of the user triggers the automatic switching manual service condition; the lower the parameter is, the easier the automatic switching manual service condition is triggered, and the higher the parameter is, the less the automatic switching manual service condition is triggered;
and the determining unit is used for taking the adjusted automatic switching manual service condition as the automatic switching manual service condition of the user.
6. The apparatus of claim 5, wherein the parsing unit comprises:
the first information processing subunit is used for word segmentation of the text information when the text information is input by the user;
the second information processing subunit is used for carrying out text vectorization on the text after word segmentation by utilizing a language model in the customer service field to obtain a text vector;
the first operation subunit is used for inputting the text vector into a pre-constructed text emotion model to obtain an emotion value of the user; the text emotion model is constructed in advance according to a text data set marked with text emotion.
7. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-4.
8. A computer storage medium, having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of any of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110482031.5A CN113051386B (en) | 2021-04-30 | 2021-04-30 | Adjustment method and device for transferring manual service, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110482031.5A CN113051386B (en) | 2021-04-30 | 2021-04-30 | Adjustment method and device for transferring manual service, electronic equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113051386A CN113051386A (en) | 2021-06-29 |
CN113051386B true CN113051386B (en) | 2024-02-02 |
Family
ID=76518344
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110482031.5A Active CN113051386B (en) | 2021-04-30 | 2021-04-30 | Adjustment method and device for transferring manual service, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113051386B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114971652A (en) * | 2022-05-16 | 2022-08-30 | 山东浪潮爱购云链信息科技有限公司 | Online customer service method, equipment and medium for enterprise purchasing platform |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018006727A1 (en) * | 2016-07-08 | 2018-01-11 | 阿里巴巴集团控股有限公司 | Method and apparatus for transferring from robot customer service to human customer service |
CN110033281A (en) * | 2018-01-11 | 2019-07-19 | 中兴通讯股份有限公司 | A kind of method and device that intelligent customer service is converted to artificial customer service |
CN110149450A (en) * | 2019-05-22 | 2019-08-20 | 欧冶云商股份有限公司 | Intelligent customer service answer method and system |
CN110472023A (en) * | 2019-07-10 | 2019-11-19 | 深圳追一科技有限公司 | Customer service switching method, device, computer equipment and storage medium |
CN111667284A (en) * | 2020-06-05 | 2020-09-15 | 中国银行股份有限公司 | Customer service switching method and device |
CN112307186A (en) * | 2020-11-06 | 2021-02-02 | 中国平安财产保险股份有限公司 | Question-answering service method, system, terminal device and medium based on emotion recognition |
-
2021
- 2021-04-30 CN CN202110482031.5A patent/CN113051386B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018006727A1 (en) * | 2016-07-08 | 2018-01-11 | 阿里巴巴集团控股有限公司 | Method and apparatus for transferring from robot customer service to human customer service |
CN110033281A (en) * | 2018-01-11 | 2019-07-19 | 中兴通讯股份有限公司 | A kind of method and device that intelligent customer service is converted to artificial customer service |
CN110149450A (en) * | 2019-05-22 | 2019-08-20 | 欧冶云商股份有限公司 | Intelligent customer service answer method and system |
CN110472023A (en) * | 2019-07-10 | 2019-11-19 | 深圳追一科技有限公司 | Customer service switching method, device, computer equipment and storage medium |
CN111667284A (en) * | 2020-06-05 | 2020-09-15 | 中国银行股份有限公司 | Customer service switching method and device |
CN112307186A (en) * | 2020-11-06 | 2021-02-02 | 中国平安财产保险股份有限公司 | Question-answering service method, system, terminal device and medium based on emotion recognition |
Also Published As
Publication number | Publication date |
---|---|
CN113051386A (en) | 2021-06-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108509619B (en) | Voice interaction method and device | |
CN112365894B (en) | AI-based composite voice interaction method and device and computer equipment | |
CN111932144B (en) | Customer service agent distribution method and device, server and storage medium | |
CN108513175B (en) | Bullet screen information processing method and system | |
CN109753663B (en) | Customer emotion grading method and device | |
CN108182937A (en) | Keyword recognition method, device, equipment and storage medium | |
CN111191450B (en) | Corpus cleaning method, corpus input device and computer readable storage medium | |
CN111179935A (en) | Voice quality inspection method and device | |
CN111143537A (en) | Service method, device, equipment and medium based on intelligent customer service system | |
CN113282737B (en) | Man-machine cooperation intelligent customer service dialogue method and device | |
CN106407393A (en) | An information processing method and device for intelligent apparatuses | |
CN111400466A (en) | Intelligent dialogue method and device based on reinforcement learning | |
CN113051386B (en) | Adjustment method and device for transferring manual service, electronic equipment and storage medium | |
JP2022125222A (en) | Information processing system, information processing method and information processing device | |
CA3147634A1 (en) | Method and apparatus for analyzing sales conversation based on voice recognition | |
WO2018013366A1 (en) | Intelligent software agent | |
CN115512696A (en) | Simulation training method and vehicle | |
CN109693244B (en) | Method and device for optimizing conversation robot | |
CN110674276A (en) | Robot self-learning method, robot terminal, device and readable storage medium | |
CN112151034B (en) | Voice control method and device of equipment, electronic equipment and storage medium | |
CN112671984B (en) | Service mode switching method and device, robot customer service and storage medium | |
CN113240345A (en) | Customer service satisfaction management method and device, storage medium and electronic equipment | |
CN110858234A (en) | Method and device for pushing information according to human emotion | |
CN114328821A (en) | Multi-round conversation control method and device based on control slot position and service data slot position | |
CN108536811B (en) | Voice interaction path determining method and device based on machine learning, storage medium and terminal |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |