CN109726277B - Data processing method and device - Google Patents
Data processing method and device Download PDFInfo
- Publication number
- CN109726277B CN109726277B CN201811644626.0A CN201811644626A CN109726277B CN 109726277 B CN109726277 B CN 109726277B CN 201811644626 A CN201811644626 A CN 201811644626A CN 109726277 B CN109726277 B CN 109726277B
- Authority
- CN
- China
- Prior art keywords
- feedback information
- user
- degree
- information
- conversation
- 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
Images
Abstract
After the user's degree of cooperation in a man-machine conversation is obtained through an intelligent conversation system, if the degree of cooperation of the user is a first degree of cooperation, first feedback information is obtained based on input information in the man-machine conversation process, and the first feedback information is output; and if the user's degree of cooperation is the second degree of cooperation, based on the input information in the man-machine conversation process, obtaining second feedback information, and outputting the second feedback information, thereby realizing outputting different feedback information based on the degree of cooperation of the user, wherein the first feedback information and the second feedback information can trigger the man-machine conversation to carry out different times of interaction after the input information, so that in order to reduce the probability of interruption of the man-machine conversation, the first feedback information and the second feedback information are related to the input information as much as possible, that is to say, the first feedback information and the second feedback information can solve the user requirements represented by the input information of the man-machine conversation, and further can reduce the probability of interruption of the man-machine conversation.
Description
Technical Field
The present application belongs to the field of data processing technologies, and in particular, to a data processing method and apparatus.
Background
With the development of information technology, the intelligent customer service can provide more and more abundant online business services for users, for example, a human-computer conversation is performed between the online business services and the users to solve problems proposed by the users, but in the process of the human-computer conversation, contents input by the users are different from input contents expected by the intelligent customer service, so that the process of the human-computer conversation is interrupted.
Disclosure of Invention
In view of the above, an object of the present application is to disclose a data processing method and apparatus for outputting different feedback information based on the user's fitness to reduce the probability of interruption of a human-machine session.
The application discloses a data processing method, which is applied to an intelligent session system, wherein the intelligent session system can respond to received input information and provide feedback information, and the method comprises the following steps:
the method comprises the steps of obtaining the degree of cooperation of a user in a man-machine conversation through an intelligent conversation system;
if the user's degree of cooperation is a first degree of cooperation, obtaining first feedback information based on input information in the human-computer conversation process, and outputting the first feedback information;
and if the user's fitness is a second fitness, obtaining second feedback information based on the input information in the human-computer conversation process, and outputting the second feedback information, wherein the first feedback information and the second feedback information can trigger the human-computer conversation to carry out interaction for different times after the input information.
Preferably, one of the first feedback information and the second feedback information is a system answer of the input information, and the other is prompt information, and the prompt information can guide the human-computer conversation;
or
The first feedback information and the second feedback information are both prompt information, but the first feedback information and the second feedback information comprise different prompt information in at least one of quantity, output form and description mode.
Preferably, one of the first and second degrees of complexation is higher in complexation than the other;
the number of times that the other feedback information corresponding to the other degree of cooperation in the first feedback information and the second feedback information triggers the human-computer session to interact after the input information is less than the number of times that the other feedback information triggers the human-computer session to interact after the input information.
Preferably, the content in the feedback information corresponding to the another degree of matching is: the further feedback information comprises part of the content.
Preferably, the content in the feedback information corresponding to the another degree of matching is: the content of the other feedback information which is output in a specific form, and/or the content of the other feedback information which is output in the same form but is described simply.
Preferably, the obtaining of the degree of matching of the user in the human-computer conversation through the intelligent conversation system comprises:
and obtaining the user's degree of coordination based on at least one of the response of the user to the feedback information in the man-machine session, the response expected by the feedback information and the response of the user to the feedback information, the user emotion indicated by the response of the user to the feedback information and the historical data of the user in the past man-machine session.
The application also discloses a data processing device, is applied to intelligent conversational system, intelligent conversational system can respond to the input information that receives and provide feedback information, the device includes:
the first obtaining unit is used for obtaining the degree of cooperation of a user in a man-machine conversation through the intelligent conversation system;
a second obtaining unit, configured to obtain first feedback information based on the input information in the human-computer conversation process if the degree of cooperation of the user is a first degree of cooperation, and obtain second feedback information based on the input information in the human-computer conversation process if the degree of cooperation of the user is a second degree of cooperation, where the first feedback information and the second feedback information are capable of triggering the human-computer conversation to perform different times of interaction after the input information;
and the output unit is used for outputting the first feedback information if the coordination degree of the user is a first coordination degree, and outputting the second feedback information if the coordination degree of the user is a second coordination degree.
Preferably, one of the first feedback information and the second feedback information is a system answer of the input information, and the other is prompt information, and the prompt information is used for guiding the human-computer conversation;
or
The first feedback information and the second feedback information are both prompt information, but the first feedback information and the second feedback information comprise different prompt information in at least one of quantity, output form and description mode.
Preferably, one of the first and second degrees of complexation is higher in complexation than the other;
the number of times that the other feedback information corresponding to the other degree of cooperation in the first feedback information and the second feedback information triggers the human-computer session to interact after the input information is less than the number of times that the other feedback information triggers the human-computer session to interact after the input information.
Preferably, the content in the feedback information corresponding to the another degree of matching is: the further feedback information comprises part of the content.
Preferably, the content in the feedback information corresponding to the another degree of matching is: the content of the other feedback information which is output in a specific form, and/or the content of the other feedback information which is output in the same form but is described simply.
Preferably, the first obtaining unit is specifically configured to obtain the degree of matching of the user based on at least one of a reply to the feedback information from the user in the human-computer session, a reply expected by the feedback information, a reply to the feedback information from the user, a user emotion indicated by the reply to the feedback information from the user, and historical data of the user in a past human-computer session.
The application also discloses an electronic device, comprising a processor and a display, wherein the processor is provided with an intelligent conversation system, and the intelligent conversation system can respond to the received input information and provide feedback information;
the processor is used for acquiring the degree of matching of a user in a man-machine conversation through an intelligent conversation system, acquiring first feedback information and triggering the display to output the first feedback information based on input information in the man-machine conversation process if the degree of matching of the user is a first degree of matching, and acquiring second feedback information and triggering the display to output the second feedback information based on the input information in the man-machine conversation process if the degree of matching of the user is a second degree of matching;
the first feedback information and the second feedback information can trigger the human-computer conversation to carry out interaction for different times after the input information.
The application also discloses a storage medium, wherein the storage medium is stored with computer program codes, and the computer program codes realize the data processing method when executed.
According to the technical scheme, after the degree of cooperation of the user in the man-machine conversation through the intelligent conversation system is obtained, if the degree of cooperation of the user is the first degree of cooperation, first feedback information is obtained based on input information in the man-machine conversation process, and the first feedback information is output; and if the user's degree of coordination is the second degree of coordination, obtaining second feedback information based on the input information in the human-computer conversation process, and outputting the second feedback information, thereby realizing outputting different feedback information based on the degree of coordination of the user, wherein the first feedback information and the second feedback information can trigger the human-computer conversation to perform different times of interaction after the input information, in order to reduce the probability of interruption of the human-computer conversation, the first feedback information and the second feedback information obtained based on the degree of coordination of the user are feedback information related to the input information as much as possible, that is, the first feedback information and the second feedback information can meet the user requirements represented by the input information of the human-computer conversation, and further can reduce the probability of interruption of the human-computer conversation.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of an intelligent conversational system disclosed in embodiments of the application;
FIG. 2 is a flow chart of a data processing method disclosed in an embodiment of the present application;
FIG. 3 is a schematic diagram of a display area of an extended electronic device disclosed in an embodiment of the present application;
fig. 4 is a schematic diagram of a form of feedback information disclosed in an embodiment of the present application;
FIG. 5 is a schematic diagram of an output feedback information disclosed in an embodiment of the present application;
FIG. 6 is a schematic diagram of another output feedback information disclosed in an embodiment of the present application;
fig. 7 is a schematic diagram of the same feedback information disclosed in the embodiment of the present application with different descriptions;
FIG. 8 is a flow chart of another data processing method disclosed in an embodiment of the present application;
FIG. 9 is a schematic view of a second degree of compliance scenario disclosed in an embodiment of the present application;
FIG. 10 is a schematic view of a first degree of fit scenario disclosed in an embodiment of the present application;
fig. 11 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application.
Detailed Description
Currently, in the process of performing a human-computer conversation through an intelligent conversation system, input information (such as a user reply) received by the intelligent conversation system may be different from a reply expected by the intelligent conversation system, for example, the intelligent conversation system is applied to an electronic device, for example, the intelligent conversation system is installed in the electronic device in the form of an APP (application program), and when the electronic device runs the APP, a user can perform a human-computer conversation through the electronic device.
As shown in fig. 1, when a user asks a user problem (which may be regarded as input information) of "how to connect to a network" through an intelligent session system, the intelligent session system outputs feedback information of "please provide a model that needs to connect to the network", if a reply input through the intelligent session system by the user is just the model, the intelligent session system outputs a network connection mode of the model, but sometimes the user does not know what the model is, and at this time, the user may not know what the model is, for example, in fig. 1, the user replies that "i buy a mobile phone on a, i know what model is", the reply of the user has a large gap from a reply expected by the intelligent session system, which further causes the feedback information output by the intelligent session system to have a large gap from a network connection mode of the model B from the user requirement (the requirement represented by the input information of the current man-machine session), thereby causing the interruption of the man-machine conversation.
Therefore, the embodiment of the application discloses a data processing method and device, which are used for outputting different feedback information based on the user matching degree, so that the output feedback information is feedback information related to input information as much as possible, that is, the first feedback information and the second feedback information can meet the user requirements represented by the input information of the current man-machine conversation, and the probability of interruption of the man-machine conversation is reduced.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 2, which illustrates a data processing method disclosed in an embodiment of the present application, the data processing method is applied to an intelligent session system, and the intelligent session system is capable of responding to received input information and providing feedback information, and may include the following steps:
201: and obtaining the degree of matching of the user in the man-machine conversation through the intelligent conversation system.
The user matching degree can indicate whether the input information feedback is timely after the intelligent conversation system gives a system question in the man-machine conversation, and/or the correlation degree between the received input information and the reply expected by the intelligent conversation system, wherein the higher the feedback is timely and/or the correlation degree is, the higher the user matching degree is.
The reply expected by the intelligent conversation system is the answer to the system question in the intelligent conversation system, and the system question is a question asked back after the intelligent conversation system receives the user question, for example, for the user question "how to connect to the network", the system question is "please provide the model which needs to connect to the network", and then the reply expected by the intelligent conversation system is the model. If the reply of the user obtained by the intelligent conversation system after the system question is asked is a model, the input information (namely the user reply) in the man-machine conversation is just the reply expected by the intelligent conversation system, the correlation degree of the two is very high, so that the matching degree of the user is very high, if the reply of the user obtained by the intelligent conversation system after the system question is asked is a order number, and multiple models possibly exist in the order number to indicate that the difference between the input information in the man-machine conversation and the reply expected by the intelligent conversation system is very large, so that the correlation degree is very low, and the matching degree of the user is very low.
In this embodiment, the user's fitness may be: the feedback information is acquired based on at least one of a reply to the feedback information by the user in the human-computer session, a reply expected by the feedback information, a reply to the feedback information by the user, a user emotion indicated by the reply to the feedback information by the user, and historical data of the user in the past human-computer session. That is, the user's fitness is obtained based on at least one of the following four aspects:
in a first aspect: replying feedback information by the user in the man-machine session; in a second aspect: the expected reply of the feedback information and the reply of the user to the feedback information; in a third aspect: user emotion indicated by a user's reply to the feedback information; in a fourth aspect: historical data of a user in past human-machine sessions.
For the above four aspects, the way to obtain the user's fitness is, but not limited to, the following way:
in a first aspect: the reply of the user to the feedback information can be the reply of the user to a system question output by the intelligent session system, and the mode of obtaining the user's fitness on the basis can be as follows: the method comprises the steps of obtaining the user's degree of cooperation based on the difference between the reply of a user to a system question output by an intelligent session system and the reply expected by the system question output by the intelligent session system, for example, establishing the corresponding relation between the difference and the degree of cooperation, and obtaining the degree of cooperation of the user in the man-machine session based on the corresponding relation between the difference and the degree of cooperation after calculating the difference between the reply of the user to the system question output by the intelligent session system and the reply expected by the system question output by the intelligent session system in the man-machine session.
The corresponding relation between the gap and the matching degree can be obtained through a machine learning algorithm, and the training sample and the testing sample related to the machine learning algorithm can be obtained by: the user involved in the human-computer conversation and/or other users except the user involved in the human-computer conversation are obtained by constructing replies in the previous human-computer conversation and system questions in the previous human-computer conversation, and the specific process is not described in this embodiment. Or the correspondence between the difference and the degree of matching can be represented in a numerical manner, for example, the correspondence between the difference and the degree of matching can indicate the degree of matching when the value of the difference is greater, and the specific embodiment is not described again.
Another example is: in the first aspect, the feedback information is information provided by the intelligent session system based on the user's fitness, for example, prompt information provided by the intelligent session system for guiding the human-computer session, and a reply of the user to the feedback information is a response provided by the user to the prompt information, for example, the prompt information may be an option for guiding the human-computer session, a reply of the user to the feedback information is an option selected by the user among the options, and then the user's fitness is obtained based on a gap between the reply of the user to the feedback information and a reply expected by a system question corresponding to the current feedback information, and for how to obtain the user's fitness based on the gap, the above description in the first aspect is referred to, and this embodiment is not described again.
In a second aspect: the reply expected by the feedback information may be a reply expected by a system question output by the intelligent session system, and the reply of the user to the feedback information may refer to the description of the first aspect, so as to obtain the user's fitness based on the difference between the reply expected by the feedback information and the reply of the user to the feedback information, and refer to the description of the first aspect for how to obtain the user's fitness based on the difference, which is not described in this embodiment.
In a third aspect: the user emotion indicated by the reply of the user to the feedback information can be obtained through an emotion recognition technology, and in the embodiment, corresponding coordination degrees can be set for different types of user emotions, so that the coordination degree of the user can be determined after the user emotion is obtained, for example, the user emotion is negative emotion such as dysphoria, anger, mania and the like, which indicates that the coordination degree of the user is low, and if the user emotion is positive emotion such as calm, calm and mild, the coordination degree of the user is high.
In a fourth aspect: historical data of a user in past human-machine sessions may include, but is not limited to: user reply, user evaluation and the like in the previous man-machine conversation, wherein the user evaluation is satisfaction evaluation given by the user to the previous man-machine conversation so as to determine whether the reply can be accurately made in time in the previous man-machine conversation, if so, the user has high fitness, otherwise, the user has low fitness. Of course, historical data of the user in the previous human-computer conversation can be combined with a machine learning algorithm to construct a machine model capable of obtaining the user's fitness, so that the user's fitness can be predicted through the machine model when data of the user in the current human-computer conversation, such as a reply of the user in the current human-computer conversation, are obtained.
The points to be explained here are: in this embodiment, at least two of the four aspects may be combined to obtain the user's degree of matching, and if the degree of matching obtained by combining multiple aspects is not in one level, a low-level degree of matching needs to be selected from the degrees of matching of the levels as the degree of matching of the user, where the low-level degree of matching indicates that the user has poor matching, i.e., indicates that the difference between the user's reply and the reply expected by the intelligent conversation system is large, the user replies untimely, and the user shows a negative emotion during the human-computer conversation.
202: and if the user's degree of cooperation is the first degree of cooperation, obtaining first feedback information based on input information in the man-machine conversation process, and outputting the first feedback information.
In this embodiment, the first feedback information is information related to input information in the current human-computer conversation process, so that the first feedback information can guide the current human-computer conversation process, and reduce the probability of interruption of the human-computer conversation, and the content included in the first feedback information needs to be determined according to the input information.
For example, for the user question "how to connect to a network" as one of the input information, in order to keep the human-machine conversation process uninterrupted, it is necessary to obtain the model of the device currently requiring network connection, and thus the first feedback information may be: the types of various devices which need to be connected with the network can guide the reply of the user to be possibly the device types, so that the difference between the reply of the user and the reply expected by the intelligent conversation system is reduced, and the probability of the interruption of the man-machine conversation at this time is reduced.
One point to be pointed out here is: before the first feedback information is obtained, the intelligent conversation system may receive a plurality of input information, where the plurality of input information may include input information unrelated to the user requirement of the man-machine conversation and/or input information which may be related to the user requirement but may erroneously guide the man-machine conversation, for example, the man-machine conversation process only includes input information representing the user emotion, such as input information about how i know what the device model is, and so on, and guides the user requirement from the initial user requirement to other user requirements, such as how to connect the initial user requirement to the network and guide the initial user requirement to the device intelligent operation, based on which at least one input information needs to be extracted from the plurality of input information before the first feedback information is obtained, and the extracted input information can correctly guide the first feedback information of the man-machine conversation, for example, the extracted input information may be the first user question in the current session, such as "how to connect to the network" described above.
And the manner of outputting the first feedback information may be: the first feedback information is output to the electronic equipment through the intelligent session system, and then the first feedback information is displayed by the electronic equipment, for example, the first feedback information is displayed on a display area through the electronic equipment, wherein the display area can belong to the electronic equipment or a display area expanded for the electronic equipment, as shown in fig. 3, a projection area of the projector is used as the display area of the electronic equipment, the electronic equipment is connected with the projector, the electronic equipment outputs the first feedback information to the projector, and the first feedback information is displayed by means of a projection function of the projector, so that a user can view the first feedback information.
203: and if the user's degree of cooperation is the second degree of cooperation, obtaining second feedback information based on the input information in the man-machine conversation process, and outputting the second feedback information.
Similar to the first feedback information, the second feedback information is also information related to input information in the process of the current human-computer conversation, so that the second feedback information can also guide the process of the current human-computer conversation, but the first feedback information and the second feedback information are different in that: the first feedback information and the second feedback information can trigger the man-machine conversation to carry out interaction with different times after information is input, namely the interaction times of the man-machine conversation process are different after the first feedback information and the second feedback information are output.
In this embodiment, the difference between the first feedback information and the second feedback information may include, but is not limited to, the following ways:
one way is as follows: one of the first feedback information and the second feedback information is a system answer to the input information, and the other is a prompt information, wherein the prompt information can guide the man-machine conversation. That is to say, the intelligent conversation system does not need to interact again based on one of the first feedback information and the second feedback information, but directly takes the system answer of the man-machine conversation as one feedback information.
Another feedback message is a prompt message capable of guiding the human-computer conversation, and the prompt message can guide the user to input a reply which is favorable for the intelligent conversation system to give a system answer, for example, the reply expected by the intelligent conversation system is used as the prompt message. For the user question "how to connect to the network" shown in fig. 1, the prompt message capable of guiding the human-machine session may be, but is not limited to: presenting, by the intelligent dialog system, prompt options regarded as prompt information, which may include: the model series is shown in fig. 4.
In fig. 4, any model identifier in the model series is output in a drop-down box manner, so that the user can select a model identifier from the drop-down box, and the intelligent session system can determine that the connection mode consulted by the current user is the connection mode of the model matched with the model identifier, so that the intelligent session system can output the connection mode of the model, and the purpose of guiding the current human-computer session through the prompt option is achieved. Of course, the model identifier shown in fig. 4 may also be output in other manners, for example, the model identifier may be output in a text manner, and the user may input one model identifier with reference to the model identifiers, or output the model identifier in a video and voice manner, and the like, which is not limited in this embodiment.
For another example, the other feedback information may use the system question in the current human-machine conversation as the prompt information, and the system question is used to solve the user question in the current human-machine conversation, so that the human-machine conversation can be guided by the system question, and therefore, the system question may be regarded as the prompt information, and the system question used as the prompt information in the practical application may be: repeating one of at least one system question before the current human-computer session and at least one system question to be output subsequently, and modifying the system question when repeating at least one system question before the current human-computer session, for example, changing at least one of an output mode of the system question and a description of the system question, which is not described in this embodiment.
In another mode: the first feedback information and the second feedback information are both prompt information, but the first feedback information and the second feedback information comprise different prompt information in at least one of quantity, output form and description mode. That is, if the first feedback information and the second feedback information are both prompt information, the first feedback information and the second feedback information are different in at least one of the following three aspects:
the number of the prompt messages, the output form of the prompt messages and the description mode of the prompt messages.
The output form of the prompt message may include, but is not limited to, including: text, voice, video, picture, etc., and if one of the first feedback information and the second feedback information is selected from one of the output forms as described above, the other feedback information is selected from an output form other than the selected output form, for example, if one of the feedback information is selected from the output form of text, the other feedback information may be selected from the output form of voice. For the same output form, it is possible to include a plurality of different sub-form outputs, and in this case the output forms may be different: different sub-forms under the same output form, taking the output form of text as an example, including output in a text content manner, output in an option manner, and the like, one of the feedback information may be output in a text content manner shown in fig. 5, and the other feedback information may be output in an option manner shown in fig. 6, and in fig. 5 and 6, a model identifier is taken as the feedback information.
The description mode of the prompt message indicates the text characters, voice intonation and the like adopted when the same prompt message is stated, and the description mode is different when the adopted text characters and the voice intonation are different. For example, when the prompt is described in text characters, the text characters used may be: different words, punctuation, word order, etc. differ in at least one respect and are considered to be described differently. For example, when describing the network connection mode, the description mode adopted by the network connection mode can be two modes shown in fig. 7, and the two modes have different terms.
According to the technical scheme, after the degree of cooperation of the user in the man-machine conversation through the intelligent conversation system is obtained, if the degree of cooperation of the user is the first degree of cooperation, first feedback information is obtained based on input information in the man-machine conversation process, and the first feedback information is output; and if the user's degree of coordination is the second degree of coordination, obtaining second feedback information based on the input information in the human-computer conversation process, and outputting the second feedback information, thereby realizing outputting different feedback information based on the degree of coordination of the user, wherein the first feedback information and the second feedback information can trigger the human-computer conversation to perform different times of interaction after the input information, in order to reduce the probability of interruption of the human-computer conversation, the first feedback information and the second feedback information obtained based on the degree of coordination of the user are feedback information related to the input information as much as possible, that is, the first feedback information and the second feedback information can meet the user requirements represented by the input information of the human-computer conversation, and further can reduce the probability of interruption of the human-computer conversation.
In addition, in this embodiment, values of the first degree of cooperation and the second degree of cooperation are different, for example, the degree of cooperation of one of the first degree of cooperation and the second degree of cooperation is higher than the other degree of cooperation, and the number of times that the corresponding feedback information of the other degree of cooperation in the first feedback information and the second feedback information triggers the human-computer session to interact after the information is input is less than the number of times that the other feedback information triggers the human-computer session to interact after the information is input.
The reason why the number of interactions triggered by the feedback information with low degree of matching is smaller than the number of interactions triggered by the feedback information with high degree of matching is that: the higher the degree of matching is, the user can reply input information in time in the process of the man-machine conversation, the difference between the reply of the user and the reply expected by the intelligent conversation system is smaller, and even the user emotion can not fluctuate greatly after the user interacts for many times, so for the user with high degree of matching, the intelligent conversation system can interact with the user for many times to obtain more information, so that the intelligent conversation system can accurately output system answers, and the lower the degree of matching is, the user emotion is likely to fluctuate greatly after the user interacts for many times, therefore, in order to reduce the probability of interruption of the man-machine conversation, feedback information with few triggering interaction times needs to be output for the user with low degree of matching, so that the intelligent conversation system can give system answers through fewer interactions.
For the feedback information corresponding to high matching degree, the contents in the feedback information are as follows: the other feedback information comprises part of the content to achieve the purpose of simplifying the feedback information. In this embodiment, the contents of the feedback information corresponding to the high degree of matching are: the content of the other feedback information that is output in a specific form, and/or the content of the other feedback information that is output in the same form but is described simply.
The specific form can reduce the time interval from the output of the feedback information to the re-reception of the input information, so that the content output through the specific form can enable the user to quickly respond to the feedback information.
What is called the same form of output but described simply is: although the same form is used for output, the complex description is excluded and the selection description is simple when selecting, so that the feedback information is convenient for the user to understand through a simplified description mode, for example, two feedback information output in text form are shown in fig. 7, and the selection description of the simple feedback information, for example, the mode of 'setting-application a-network data', is simple and convenient for the user to operate for the user with low degree of matching.
The following describes the data processing method disclosed in the embodiment of the present application with the first degree of matching being smaller than the second degree of matching, and the flowchart thereof is shown in fig. 8, and may include the following steps:
801: and obtaining the user matching degree in the man-machine session at this time based on at least one of the user reply to the feedback information, the feedback expected reply to the feedback information, the user emotion indicated by the user reply to the feedback information and the historical data of the user in the past man-machine session.
802: and if the user matching degree is the second matching degree, all prompt information related to the user question is used as second feedback information based on the user question in the man-machine conversation process.
803: and acquiring prompt information selected by the user from all prompt information.
804: based on the selected prompt information, obtaining a system answer corresponding to the user question, and outputting the system answer corresponding to the user question in a first mode.
805: if the user's degree of cooperation is the first degree of cooperation, based on the user's question in the man-machine conversation process, select some prompt information as first feedback information from all prompt information related to the user's question, and the selection mode is not described in detail in this embodiment.
806: and acquiring prompt information selected by the user from the selected prompt information.
807: and obtaining a system answer corresponding to the user question based on the selected prompt information, and outputting the system answer corresponding to the user question in a second mode, wherein the first mode is different from the second mode, and the first mode is more complex than the second mode.
In this embodiment, two scene diagrams are used to illustrate the difference of the output when the user's degree of coordination is the first degree of coordination and the second degree of coordination, as shown in fig. 9 and 10, where the degree of coordination corresponding to the user in fig. 9 is the second degree of coordination, the degree of coordination corresponding to the user in fig. 10 is the first degree of coordination, and the user questions input in the human-machine session in fig. 9 and 10 are: "how to connect to the network".
In fig. 9, when the degree of matching of the user is obtained as the second degree of matching, all models related to the user question are output as the second feedback information, and the form adopted for outputting the second feedback information is the text data form, one model input by the user is obtained, the model is one model selected by the user from all models, and after the model input by the user is received, the network connection mode related to the model is output in the text mode.
In fig. 10, when the degree of cooperation of the user is obtained as the first degree of cooperation, a part of models are selected from all models related to the user question as the first feedback information to be output, and the form of outputting the first feedback information is an option form, so that the intelligent session system can automatically receive the model selected by the user after the user performs a selection operation on a certain option in the manner shown in fig. 9, and output the network connection mode related to the model in a text manner after receiving the model selected by the user, but the description of the text is simple in comparison with the manner shown in fig. 9, so that the user can know the network connection mode of the model at a glance.
As can be seen from fig. 9 and 10, no matter the user's degree of matching is the first degree of matching or the second degree of matching, feedback information adapted to the degree of matching of the user can be output by the intelligent conversation system, and the feedback information can guide the current human-machine conversation, so that the willingness of the user to continue chatting is improved by the feedback information, the human-machine conversation is promoted, and the probability of interrupting the human-machine conversation is reduced.
While, for purposes of simplicity of explanation, the foregoing method embodiments have been described as a series of acts or combination of acts, it will be appreciated by those skilled in the art that the present application is not limited by the order of acts or acts described, as some steps may occur in other orders or concurrently with other steps in accordance with the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.
Corresponding to the above method embodiments, the present application embodiment discloses a data processing apparatus, which is applied to an intelligent session system, where the intelligent session system is capable of responding to received input information and providing feedback information, and a structure of the data processing apparatus is shown in fig. 11, and may include: a first obtaining unit 11, a second obtaining unit 12 and an output unit 13.
A first obtaining unit 11, configured to obtain the degree of matching of the user in the human-computer conversation performed through the intelligent conversation system.
The user matching degree can indicate whether the input information feedback is timely after the intelligent conversation system gives a system question in the man-machine conversation, and/or the correlation degree between the received input information and the reply expected by the intelligent conversation system, wherein the higher the feedback is timely and/or the correlation degree is, the higher the user matching degree is.
In this embodiment, the first obtaining unit 11 can obtain the user's fitness from at least one of four aspects, that is, a reply to the feedback information by the user in the human-computer session, a reply expected by the feedback information, a reply to the feedback information by the user, a user emotion indicated by the reply to the feedback information by the user, and historical data of the user in the previous human-computer session, and please refer to the description in the above method embodiment for specific description, which is not described again in this embodiment.
A second obtaining unit 12, configured to obtain the first feedback information based on the input information in the human-computer conversation process if the degree of fit of the user is the first degree of fit, and to obtain the second feedback information based on the input information in the human-computer conversation process if the degree of fit of the user is the second degree of fit.
In this embodiment, the first feedback information and the second feedback information are both information related to input information in the process of the current human-machine conversation, so that the first feedback information and the second feedback information can guide the process of the current human-machine conversation, but the first feedback information and the second feedback information are different, and the difference is that: the first feedback information and the second feedback information can trigger the human-computer session to carry out interaction for different times after information is input. Wherein the difference of the first feedback information and the second feedback information may include, but is not limited to, the following:
one way is as follows: one of the first feedback information and the second feedback information is a system answer to the input information, and the other is a prompt information, wherein the prompt information can guide the man-machine conversation. That is to say, the intelligent conversation system does not need to interact again based on one of the first feedback information and the second feedback information, but directly takes the system answer of the man-machine conversation as one feedback information. The other feedback information is prompt information capable of guiding the human-computer conversation, and the prompt information can guide a user to input a reply which is favorable for the intelligent conversation system to give a system answer, for example, the reply expected by the intelligent conversation system is used as the prompt information, and for example, the other feedback information can be used for asking the system question in the current human-computer conversation as the prompt information.
In another mode: the first feedback information and the second feedback information are both prompt information, but the first feedback information and the second feedback information comprise different prompt information in at least one of quantity, output form and description mode. That is, if the first feedback information and the second feedback information are both prompt information, the first feedback information and the second feedback information are different in at least one of the following three aspects: the number of the prompt messages, the output form of the prompt messages and the description mode of the prompt messages.
For the detailed description of the two modes, refer to the related description in the method embodiment, and this embodiment will not be described again.
An output unit 13 for outputting the first feedback information if the user's degree of coordination is a first degree of coordination, and for outputting the second feedback information if the user's degree of coordination is a second degree of coordination. The first feedback information and the second feedback information are used as current feedback information, and the mode of outputting the current feedback information may be: the first feedback information is output to the electronic device through the intelligent conversation system, and then is displayed by the electronic device, for example, the first feedback information is displayed on a display area through the electronic device, and the display area can belong to the electronic device or a display area extended for the electronic device.
According to the technical scheme, after the degree of cooperation of the user in the man-machine conversation through the intelligent conversation system is obtained, if the degree of cooperation of the user is the first degree of cooperation, first feedback information is obtained based on input information in the man-machine conversation process, and the first feedback information is output; and if the user's degree of coordination is the second degree of coordination, obtaining second feedback information based on the input information in the human-computer conversation process, and outputting the second feedback information, thereby realizing outputting different feedback information based on the degree of coordination of the user, wherein the first feedback information and the second feedback information can trigger the human-computer conversation to perform different times of interaction after the input information, in order to reduce the probability of interruption of the human-computer conversation, the first feedback information and the second feedback information obtained based on the degree of coordination of the user are feedback information related to the input information as much as possible, that is, the first feedback information and the second feedback information can meet the user requirements represented by the input information of the human-computer conversation, and further can reduce the probability of interruption of the human-computer conversation.
In addition, in this embodiment, values of the first degree of cooperation and the second degree of cooperation are different, for example, the degree of cooperation of one of the first degree of cooperation and the second degree of cooperation is higher than the other degree of cooperation, and the number of times that the corresponding feedback information of the other degree of cooperation in the first feedback information and the second feedback information triggers the human-computer session to interact after the information is input is less than the number of times that the other feedback information triggers the human-computer session to interact after the information is input.
The reason why the number of interactions triggered by the feedback information with low degree of matching is smaller than the number of interactions triggered by the feedback information with high degree of matching is that: the higher the degree of matching is, the user can reply input information in time in the process of the man-machine conversation, the difference between the reply of the user and the reply expected by the intelligent conversation system is smaller, and even the user emotion can not fluctuate greatly after the user interacts for many times, so for the user with high degree of matching, the intelligent conversation system can interact with the user for many times to obtain more information, so that the intelligent conversation system can accurately output system answers, and the lower the degree of matching is, the user emotion is likely to fluctuate greatly after the user interacts for many times, therefore, in order to reduce the probability of interruption of the man-machine conversation, feedback information with few triggering interaction times needs to be output for the user with low degree of matching, so that the intelligent conversation system can give system answers through fewer interactions.
For the feedback information corresponding to high matching degree, the contents in the feedback information are as follows: the other feedback information comprises part of the content to achieve the purpose of simplifying the feedback information. In this embodiment, the contents of the feedback information corresponding to the high degree of matching are: for the description of the specific form, please refer to the above method embodiment, and details are not repeated herein.
In addition, the embodiment of the application further discloses electronic equipment which comprises a processor and a display, wherein the processor is provided with an intelligent conversation system, and the intelligent conversation system can respond to the received input information and provide feedback information.
And the processor is used for acquiring the degree of matching of the user in the man-machine conversation through the intelligent conversation system, acquiring first feedback information and triggering the display to output the first feedback information based on the input information in the man-machine conversation process if the degree of matching of the user is the first degree of matching, acquiring second feedback information and triggering the display to output the second feedback information based on the input information in the man-machine conversation process if the degree of matching of the user is the second degree of matching, wherein the first feedback information and the second feedback information are used for triggering the man-machine conversation to carry out interaction with different times after the information is input. For the detailed description of the functions in the processor, reference is made to the above method embodiments, which are not described again.
The embodiment of the application also discloses a storage medium, wherein the storage medium is stored with computer program codes, and the data processing method is realized when the computer program codes are executed.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. For the device-like embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. 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.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (10)
1. A data processing method is applied to an intelligent conversation system, the intelligent conversation system can respond to received input information and provide feedback information, and the method comprises the following steps:
the method comprises the steps of obtaining the degree of cooperation of a user in a man-machine conversation through an intelligent conversation system;
if the user's degree of cooperation is a first degree of cooperation, obtaining first feedback information based on input information in the human-computer conversation process, and outputting the first feedback information;
if the user's degree of cooperation is the second degree of cooperation, based on input information in the man-machine conversation process, obtain second feedback information, and output second feedback information, first feedback information with second feedback information can trigger the man-machine conversation is in carry out the interaction of different numbers of times behind the input information, just first feedback information with second feedback information is used for guiding this man-machine conversation to improve the user and continue the will of chatting, promote the man-machine conversation and go on.
2. The method of claim 1, wherein one of the first feedback information and the second feedback information is a system answer to the input information, and the other is a prompt, the prompt being capable of directing the human-machine session;
or
The first feedback information and the second feedback information are both prompt information, but the first feedback information and the second feedback information comprise different prompt information in at least one of quantity, output form and description mode.
3. The method of claim 1, wherein one of the first and second degrees of compliance is higher than the other;
the number of times that the other feedback information corresponding to the other degree of cooperation in the first feedback information and the second feedback information triggers the human-computer session to interact after the input information is less than the number of times that the other feedback information triggers the human-computer session to interact after the input information.
4. The method of claim 3, wherein the content in the feedback information corresponding to the another degree of fitness is: the further feedback information comprises part of the content.
5. The method of claim 4, wherein the content in the feedback information corresponding to the another degree of fitness is: the content of the other feedback information which is output in a specific form, and/or the content of the other feedback information which is output in the same form but is described simply.
6. The method of claim 1, obtaining a degree of engagement of a user in a human-machine conversation over an intelligent conversational system comprising:
and obtaining the user's degree of coordination based on at least one of the response of the user to the feedback information in the man-machine session, the response expected by the feedback information and the response of the user to the feedback information, the user emotion indicated by the response of the user to the feedback information and the historical data of the user in the past man-machine session.
7. A data processing apparatus for use in an intelligent conversational system, the intelligent conversational system being capable of responding to received input information and providing feedback information, the apparatus comprising:
the first obtaining unit is used for obtaining the degree of cooperation of a user in a man-machine conversation through the intelligent conversation system;
a second obtaining unit, configured to obtain first feedback information based on the input information in the human-computer conversation process if the degree of cooperation of the user is a first degree of cooperation, and obtain second feedback information based on the input information in the human-computer conversation process if the degree of cooperation of the user is a second degree of cooperation, where the first feedback information and the second feedback information are capable of triggering the human-computer conversation to perform different times of interaction after the input information;
and the output unit is used for outputting the first feedback information if the user's degree of coordination is first degree of coordination, and outputting the second feedback information if the user's degree of coordination is second degree of coordination, wherein the first feedback information and the second feedback information are used for guiding the current human-computer conversation so as to improve the willingness of the user to continue chatting and promote the human-computer conversation to be carried out.
8. The apparatus of claim 7, wherein one of the first feedback information and the second feedback information is a system answer to the input information, and the other is a prompt information, and the prompt information is used for guiding the human-machine conversation;
or
The first feedback information and the second feedback information are both prompt information, but the first feedback information and the second feedback information comprise different prompt information in at least one of quantity, output form and description mode.
9. The apparatus of claim 7, one of said first and second degrees of compliance being higher than the other;
the number of times that the other feedback information corresponding to the other degree of cooperation in the first feedback information and the second feedback information triggers the human-computer session to interact after the input information is less than the number of times that the other feedback information triggers the human-computer session to interact after the input information.
10. An electronic device comprising a processor and a display, the processor having an intelligent dialog system capable of responding to received input information and providing feedback information;
the processor is used for acquiring the degree of matching of a user in a man-machine conversation through an intelligent conversation system, acquiring first feedback information and triggering the display to output the first feedback information based on input information in the man-machine conversation process if the degree of matching of the user is a first degree of matching, and acquiring second feedback information and triggering the display to output the second feedback information based on the input information in the man-machine conversation process if the degree of matching of the user is a second degree of matching;
the first feedback information and the second feedback information can trigger the human-computer conversation to carry out interaction for different times after the information is input, and the first feedback information and the second feedback information are used for guiding the human-computer conversation so as to improve the willingness of a user to continue chatting and promote the human-computer conversation to be carried out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811644626.0A CN109726277B (en) | 2018-12-30 | 2018-12-30 | Data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811644626.0A CN109726277B (en) | 2018-12-30 | 2018-12-30 | Data processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109726277A CN109726277A (en) | 2019-05-07 |
| CN109726277B true CN109726277B (en) | 2021-08-17 |
Family
ID=66299414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811644626.0A Active CN109726277B (en) | 2018-12-30 | 2018-12-30 | Data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109726277B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101685454A (en) * | 2008-09-28 | 2010-03-31 | 华为技术有限公司 | Human-computer interactive method and system |
| CN106844378A (en) * | 2015-12-04 | 2017-06-13 | 中国移动通信集团公司 | A kind of response mode determines method and apparatus |
| CN105760362B (en) * | 2016-02-04 | 2018-07-27 | 北京光年无限科技有限公司 | A kind of question and answer evaluation method and device towards intelligent robot |
| CN106200962A (en) * | 2016-07-08 | 2016-12-07 | 北京光年无限科技有限公司 | Exchange method and system towards intelligent robot |
| CN107092664B (en) * | 2017-03-30 | 2020-04-28 | 华为技术有限公司 | Content interpretation method and device |
| CN107545029A (en) * | 2017-07-17 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | Voice feedback method, equipment and the computer-readable recording medium of smart machine |
| CN107423440B (en) * | 2017-08-04 | 2020-09-01 | 逸途（北京）科技有限公司 | Question-answer context switching and reinforced selection method based on emotion analysis |
| CN108090174B (en) * | 2017-12-14 | 2022-01-07 | 北京邮电大学 | Robot response method and device based on system function grammar |
| CN109033053B (en) * | 2018-07-10 | 2022-05-17 | 广州极天信息技术股份有限公司 | Scene-based knowledge editing method and device |
-
2018
- 2018-12-30 CN CN201811644626.0A patent/CN109726277B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109726277A (en) | 2019-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110096191B (en) | Man-machine conversation method and device and electronic equipment | |
| US10776580B2 (en) | Method for providing dialogue service with chatbot assisted by human agents | |
| CN109514586B (en) | Method and system for realizing intelligent customer service robot | |
| CN107818798A (en) | Customer service quality evaluating method, device, equipment and storage medium | |
| US10304013B2 (en) | Real time animation generator for voice content representation | |
| CN109688042A (en) | A kind of message treatment method and device | |
| CN109948151A (en) | The method for constructing voice assistant | |
| CN111405224A (en) | Online interaction control method and device, storage medium and electronic equipment | |
| CN109271503A (en) | Intelligent answer method, apparatus, equipment and storage medium | |
| CN112417107A (en) | Information processing method and device | |
| CN111611365A (en) | Flow control method, device, equipment and storage medium of dialog system | |
| CN111507754A (en) | Online interaction method and device, storage medium and electronic equipment | |
| CN112286485B (en) | Method and device for controlling application through voice, electronic equipment and storage medium | |
| CN110047473B (en) | Man-machine cooperative interaction method and system | |
| CN109726277B (en) | Data processing method and device | |
| CN109547632B (en) | Auxiliary call response method, user terminal device and server | |
| CN114490975B (en) | User question labeling method and device | |
| CN113079086B (en) | Message transmission method, message transmission device, electronic device, and storage medium | |
| CN113630309B (en) | Robot conversation system, method, device, computer equipment and storage medium | |
| CN112915550B (en) | Comment information generation method and device, electronic equipment and storage medium | |
| CN113961689A (en) | Conversation method, conversation device, electronic equipment and computer-readable storage medium | |
| CN110633361A (en) | Input control method and device and intelligent session server | |
| CN112071313A (en) | Voice broadcasting method and device, electronic equipment and medium | |
| CN111400475A (en) | Information processing method and device and electronic equipment | |
| CN108763488A (en) | Phonetic prompt method, device and the terminal device to ask for help for user |
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 |