CN112527980A - Information response processing method, intelligent device and storage medium - Google Patents
Information response processing method, intelligent device and storage medium Download PDFInfo
- Publication number
- CN112527980A CN112527980A CN202011245401.5A CN202011245401A CN112527980A CN 112527980 A CN112527980 A CN 112527980A CN 202011245401 A CN202011245401 A CN 202011245401A CN 112527980 A CN112527980 A CN 112527980A
- Authority
- CN
- China
- Prior art keywords
- response
- information
- response information
- limited
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses an information response processing method, intelligent equipment and a computer readable storage medium, wherein in the interaction process of the intelligent equipment and a user, the intelligent equipment sends first interaction information to the user; then displaying a response interface corresponding to the first interactive information; and then responding to different operations of the user under the response interface, and executing one of the following two response modes: in a first response mode, limited response information corresponding to selection operation or input operation is received in response to the selection operation or the input operation of a user aiming at the limited response information under the response interface; outputting response information corresponding to the limited response information to a user; in the response mode II, in response to the non-limited response information input by the user under the response interface, the limited response information matched with the non-limited response information is identified according to the first interaction information; and outputting response information corresponding to the limited response information to the user.
Description
Technical Field
The present invention relates to information processing technologies, and in particular, to an information response processing method, an intelligent device, and a storage medium.
Background
In the customer service chat robot, the user's intention can be divided into an intra-domain intention and a cross-domain general intention. Where it is intended that different classification systems be used depending on the domain. However, since there is a difference in definition and understanding of a general purpose in different fields, it is impossible to recognize an intention using a unified corpus and a model, and it is impossible to quickly and accurately feed back a response word to a user.
Disclosure of Invention
In order to solve the above problems in the prior art, embodiments of the present invention creatively provide an information response processing method, an intelligent device, and a computer-readable storage medium.
According to a first aspect of the present invention, there is provided an information response processing method, including: sending first interaction information to a user; displaying a response interface corresponding to the first interaction information; responding to different operations of the user under the response interface, and executing one of the following two response modes: in a first response mode, limited response information corresponding to selection operation or input operation is received in response to the selection operation or the input operation of a user aiming at the limited response information under the response interface; outputting response information corresponding to the limited response information to a user; in the response mode II, responding to the non-limited response information input by the user under the response interface, and receiving the non-limited response information; identifying the non-limited response information matched limited response information according to the first interaction information; and outputting response information corresponding to the limited response information to the user.
According to an embodiment of the present invention, identifying the qualified response information matching the unqualified response information according to the first interaction information includes: extracting special phrases in the first interactive information and the non-limited response information by using a domain semantic library; carrying out normalization processing on the special phrase by using a domain knowledge map to obtain a normalized special phrase; and identifying the qualified response information matched with the non-qualified response information according to the normalized special phrase.
According to an embodiment of the invention, the method further comprises: collecting domain keywords and common phrases; and constructing a word vector set of the domain keywords and the common phrases according to semantics to form a domain semantic library.
According to an embodiment of the invention, the method further comprises: collecting domain corpora; analyzing the incidence relation among the entity words in the collected domain linguistic data; and constructing a domain knowledge graph based on the association relation between the entity words in the collected domain linguistic data.
According to a second aspect of the present invention, there is also provided a smart device, comprising: the sending module is used for sending first interaction information to a user; the display module is used for controlling and displaying a response interface corresponding to the first interactive information; the execution control module is used for responding to different operations of the user under the response interface and executing one of the following two response modes: in a first response mode, limited response information corresponding to selection operation or input operation is received in response to the selection operation or the input operation of a user aiming at the limited response information under the response interface; outputting response information corresponding to the limited response information to a user; in the response mode II, responding to the non-limited response information input by the user under the response interface, and receiving the non-limited response information; identifying the non-limited response information matched limited response information according to the first interaction information; and outputting response information corresponding to the limited response information to the user.
According to an embodiment of the present invention, the execution control module is specifically configured to extract a special phrase in the first interaction information and the undefined response information by using a domain semantic library; carrying out normalization processing on the special phrase by using a domain knowledge map to obtain a normalized special phrase; and identifying the qualified response information matched with the non-qualified response information according to the normalized special phrase.
According to an embodiment of the present invention, the smart device further includes: the first collection module is used for collecting the domain keywords and the common phrases; and the semantic library construction module is used for constructing a word vector set of the domain keywords and the common phrases according to semantics to form a domain semantic library.
According to an embodiment of the present invention, the smart device further includes: the second collection module is used for collecting the domain linguistic data; the analysis module is used for analyzing the incidence relation among the entity words in the collected domain linguistic data; and the knowledge map building module is used for building a domain knowledge map based on the incidence relation among the entity words in the collected domain linguistic data.
According to a third aspect of the present invention, there is also provided a smart device comprising one or more processors; a memory for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement any of the aforementioned information response processing methods.
According to a fourth aspect of the present invention, there is also provided a computer-readable storage medium comprising a set of computer-executable instructions which, when executed, are operable to perform any of the aforementioned message reply processing methods.
According to the information response processing method, the intelligent device and the computer readable storage medium, in the interaction process of the intelligent device and a user, the intelligent device sends first interaction information to the user; then displaying a response interface corresponding to the first interactive information; and then responding to different operations of the user under the response interface, and executing one of the following two response modes: in a first response mode, limited response information corresponding to selection operation or input operation is received in response to the selection operation or the input operation of a user aiming at the limited response information under the response interface; outputting response information corresponding to the limited response information to a user; in the response mode II, in response to the non-limited response information input by the user under the response interface, the limited response information matched with the non-limited response information is identified according to the first interaction information; and outputting response information corresponding to the limited response information to the user. Therefore, the invention is based on the unused response strategy, and when the limited response information (belonging to the general purpose intention information) is received, the corresponding response words can be directly fed back to the user; when receiving the non-limited response information (belonging to the non-general purpose intention information), the non-limited response information can be identified and inferred by combining the context (such as the first interactive information) to obtain the matched limited response information, and further the corresponding response words are fed back to the user, so that the problem that in the prior art, the intention identification is difficult or the response words cannot be fed back to the user quickly and accurately due to the definition and understanding difference of general purpose in different fields is solved.
It is to be understood that the teachings of the present invention need not achieve all of the above-described benefits, but rather that specific embodiments may achieve specific technical results, and that other embodiments of the present invention may achieve benefits not mentioned above.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
FIG. 1 is a first schematic diagram illustrating a first implementation flow of an information response processing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram showing a second implementation flow of the information response processing method according to the embodiment of the present invention;
FIG. 3 is a diagram illustrating the display effect of a response interface of an embodiment of the present invention;
FIG. 4 is a flow chart illustrating an implementation of the present invention for identifying non-qualified response information matching qualified response information according to the first interaction information;
FIG. 5 is a diagram illustrating the structure of an application instance domain knowledge graph in accordance with the present invention;
fig. 6 shows a schematic structural diagram of an intelligent device according to an embodiment of the present invention.
Detailed Description
The principles and spirit of the present invention will be described with reference to a number of exemplary embodiments. It is understood that these embodiments are given only to enable those skilled in the art to better understand and to implement the present invention, and do not limit the scope of the present invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The technical solution of the present invention is further elaborated below with reference to the drawings and the specific embodiments.
Fig. 1 is a first schematic flow chart illustrating an implementation of an information response processing method according to an embodiment of the present invention.
Referring to fig. 1, an embodiment of the present invention provides an information response processing method, where the method includes: operation 101, sending first interaction information to a user; an operation 102 of displaying a response interface corresponding to the first interactive information; operation 103, responding to different operations of the user under the response interface, and executing one of the following two response modes: in a first response mode, limited response information corresponding to selection operation or input operation is received in response to the selection operation or the input operation of a user aiming at the limited response information under the response interface; outputting response information corresponding to the limited response information to a user; in the response mode II, responding to the non-limited response information input by the user under the response interface, and receiving the non-limited response information; identifying the non-limited response information matched limited response information according to the first interaction information; and outputting response information corresponding to the limited response information to the user.
In operation 101, in an interaction process between the smart device and the user, the smart device sends first interaction information to the user, where the first interaction information may be voice information, text information, or instruction information.
The intelligent device related to the embodiment of the invention can be an intelligent voice device with voice interaction or voice recognition, which is developed at present or to be developed in the future, can also be a robot device bot, and can also be an intelligent customer service system.
In operation 102, the smart device displays a response interface corresponding to the first interaction information after or while transmitting the first interaction information to the user.
The response interface may generally include an option button or an input area for the limited response information, so as to facilitate the user to perform a selection operation or an input operation for the limited response information and to input the non-limited response information.
Here, the response information is defined to belong to general intention information, i.e., the smart device can recognize the determined intention information based on the semantic library. The non-limited response information belongs to non-general purpose intention information, namely, the intelligent device cannot directly identify the determined intention information based on the semantic library.
In an application example, when the robot bot sends a first interactive message to the user asking if do you try to restart the phone? After "the bot expects the user to enter a defined response message, i.e. answer" yes "or" no ", i.e. general intention information. When the user inputs the non-limited response information, i.e., the answer "i switch on and off, or do not react", the bot cannot directly recognize the non-limited response information as the "positive" or "negative" general intention information in the general intention recognition.
In operation 103, since the user may input the limited response information or the non-limited response information to the smart device through different operations on the response interface, the smart device may perform two completely different answering manners.
In response to a selection operation or an input operation aiming at the limited response information by a user under the response interface, the intelligent device receives the limited response information corresponding to the selection operation or the input operation; and then outputting response information corresponding to the limited response information to the user.
In a response mode II, in response to the non-limited response information input by the user under the response interface, the intelligent device identifies the limited response information matched with the non-limited response information according to the first interaction information; and then outputting response information corresponding to the limited response information to the user.
Therefore, the invention is based on the unused response strategy, and when the limited response information (belonging to the general purpose intention information) is received, the corresponding response words can be directly fed back to the user; when receiving the non-limited response information (belonging to the non-general purpose intention information), the non-limited response information can be identified and inferred by combining the context (such as the first interactive information) to obtain the matched limited response information, and further the corresponding response words are fed back to the user, so that the problem that in the prior art, the intention identification is difficult or the response words cannot be fed back to the user quickly and accurately due to the definition and understanding difference of general purpose in different fields is solved.
FIG. 2 is a schematic diagram showing a second implementation flow of the information response processing method according to the embodiment of the present invention; FIG. 3 is a diagram illustrating the display effect of a response interface of an embodiment of the present invention; FIG. 4 is a flow chart illustrating an implementation of the present invention for identifying non-qualified response information matching qualified response information according to the first interaction information; FIG. 5 is a diagram illustrating the structure of an application instance domain knowledge graph in accordance with the present invention;
referring to fig. 2, the information response processing method according to the embodiment of the present invention includes: operation 201, sending first interaction information to a user; operation 202, displaying a response interface corresponding to the first interaction information; operation 203, receiving the non-limited response information in response to the non-limited response information input by the user under the response interface; operation 204, identifying the qualified response information matched with the non-qualified response information according to the first interaction information; in operation 205, response information corresponding to the limited response information is output to the user.
In operation 201, in an interaction process between the smart device and the user, the smart device sends first interaction information to the user, where the first interaction information may be voice information, text information, or instruction information.
The intelligent device related to the embodiment of the invention can be an intelligent voice device with voice interaction or voice recognition, which is developed at present or to be developed in the future, can also be a robot device bot, and can also be an intelligent customer service system.
In operation 202, the smart device displays a response interface corresponding to the first interaction information after or while sending the first interaction information to the user. The response interface may generally include an option button or an input area for the limited response information, so as to facilitate the user to perform a selection operation or an input operation for the limited response information and to input the non-limited response information.
In an application example, as shown in fig. 3, when the robot bot sends the first interactive message to the user, it is asked "do you try to restart the mobile phone? "thereafter, the bot expects the user to input a defined response message, i.e., answers" yes "or" no ", i.e., general intention information; when the user inputs the non-limited response information, namely, the answer of 'i switch on and off, or do not react' or 'my mobile phone APP does not open', the bot cannot directly identify the non-limited response information as 'positive' or 'negative' general intention information in general intention identification.
In operations 203-205, in response to the non-limited response information input by the user under the response interface, the smart device receives the non-limited response information; and then the intelligent equipment performs recognition and reasoning on the non-limited response information by combining the context, namely according to the first interactive information to obtain the limited response information matched with the non-limited response information, and further feeds back a corresponding response word to the user.
The non-limited response information belongs to non-general intention information, namely the intelligent device cannot directly identify the determined intention information based on the semantic library.
According to an embodiment of the present invention, in operation 204, referring to fig. 4, the identifying, by the smart device, the qualified response information that matches the non-qualified response information according to the first interaction information includes: operation 2041, extracting a special phrase in the first interaction information and the undefined response information using a domain semantic library; operation 2042, performing normalization processing on the special phrase by using a domain knowledge graph to obtain a normalized special phrase; operation 2043, identify the qualified response information matched with the non-qualified response information according to the normalized special phrase.
Before operation 2041 is implemented, the smart device needs to pre-build a domain semantic library. Specifically, the method comprises the steps of collecting domain keywords and common phrases, and then constructing a word vector set of the domain keywords and the common phrases according to semantics to form a domain semantic library.
The smart device also needs to pre-build a domain knowledge graph before operation 2042 is implemented. Specifically, the domain corpora are collected first; analyzing the association relation between the entity words in the collected domain linguistic data; and finally, constructing a domain knowledge graph based on the association relation among the entity words in the collected domain linguistic data. The domain knowledge graph shown in fig. 5 is a diagram, in which oval nodes are used to represent entity words, such as "mobile phone", "color", "memory", and "SIM card", and connecting lines between the oval nodes are used to represent an association relationship between the entity words, for example, the association relationship between "mobile phone" and "color" is an attribute that "color" is "mobile phone", and the association relationship between "mobile phone" and "memory" is an element that "memory" is "mobile phone".
In an application example, referring to fig. 3, when receiving an undefined response message input by a user, that is, answering "i switch on or off, or do not react", the smart device extracts the undefined response message "i switch on or off, or do not react" and a first interaction message "whether you try to restart the mobile phone" from a special phrase "restart the mobile phone", "switch on or off", and "do not react". Furthermore, the intelligent equipment uses the domain knowledge graph { K } to normalize the extracted special phrase to obtain the meaning of 'on/off' and 'restarting the mobile phone', and 'no reaction' is equivalent to 'the problem still exists', so that the normalized special phrase is obtained; further, the intelligent device identifies and obtains two pieces of general intention information, namely ' i power on and power off ' of non-limited response information or ' affirmation ' and ' problem unsolved ' of ' matched limited response information according to the normalized special phrase.
According to the information response processing method, the intelligent device and the computer readable storage medium, in the interaction process of the intelligent device and a user, the intelligent device sends first interaction information to the user; then displaying a response interface corresponding to the first interactive information; then responding to the non-limited response information input by the user under the response interface, and receiving the non-limited response information; identifying the non-limited response information matched limited response information according to the first interaction information; in operation 205, response information corresponding to the limited response information is output to the user. Therefore, in the interaction process of the intelligent device and the user, when the non-limited response information (belonging to the non-general intention information) is received, the non-limited response information can be identified and inferred by combining the context (such as the first interaction information) to obtain the matched limited response information, and the corresponding answer is further fed back to the user, so that the problems that in the prior art, the intention identification is difficult or the answer cannot be fed back to the user quickly and accurately due to the definition and understanding difference of the general intention in different fields are solved effectively.
Similarly, based on the information response processing method as described above, an embodiment of the present invention further provides a computer-readable storage medium, which stores a program that, when executed by a processor, causes the processor to perform at least the following operation steps: operation 101, sending first interaction information to a user; an operation 102 of displaying a response interface corresponding to the first interactive information; operation 103, responding to different operations of the user under the response interface, and executing one of the following two response modes: in a first response mode, limited response information corresponding to selection operation or input operation is received in response to the selection operation or the input operation of a user aiming at the limited response information under the response interface; outputting response information corresponding to the limited response information to a user; in the response mode II, responding to the non-limited response information input by the user under the response interface, and receiving the non-limited response information; identifying the non-limited response information matched limited response information according to the first interaction information; and outputting response information corresponding to the limited response information to the user.
Further, based on the information response processing method described above, an embodiment of the present invention further provides an intelligent device, where the intelligent device includes one or more processors; memory for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to perform the operational steps of: operation 101, sending first interaction information to a user; an operation 102 of displaying a response interface corresponding to the first interactive information; operation 103, responding to different operations of the user under the response interface, and executing one of the following two response modes: in a first response mode, limited response information corresponding to selection operation or input operation is received in response to the selection operation or the input operation of a user aiming at the limited response information under the response interface; outputting response information corresponding to the limited response information to a user; in the response mode II, responding to the non-limited response information input by the user under the response interface, and receiving the non-limited response information; identifying the non-limited response information matched limited response information according to the first interaction information; and outputting response information corresponding to the limited response information to the user.
Furthermore, based on the information response processing method described above, an embodiment of the present invention further provides an intelligent device, as shown in fig. 6, where the intelligent device 60 includes: a sending module 601, configured to send first interaction information to a user; a display module 602, configured to control to display a response interface corresponding to the first interaction information; the execution control module 603 is configured to, in response to different operations of the user under the response interface, execute one of the following two response modes: in a first response mode, limited response information corresponding to selection operation or input operation is received in response to the selection operation or the input operation of a user aiming at the limited response information under the response interface; outputting response information corresponding to the limited response information to a user; in the response mode II, responding to the non-limited response information input by the user under the response interface, and receiving the non-limited response information; identifying the non-limited response information matched limited response information according to the first interaction information; and outputting response information corresponding to the limited response information to the user.
According to an embodiment of the present invention, the execution control module 603 is specifically configured to extract a special phrase in the first interaction information and the undefined response information by using a domain semantic library; carrying out normalization processing on the special phrase by using a domain knowledge map to obtain a normalized special phrase; and identifying the qualified response information matched with the non-qualified response information according to the normalized special phrase.
According to an embodiment of the present invention, the smart device 60 further includes: the first collection module is used for collecting the domain keywords and the common phrases; and the semantic library construction module is used for constructing a word vector set of the domain keywords and the common phrases according to semantics to form a domain semantic library.
According to an embodiment of the present invention, the smart device 60 further includes: the second collection module is used for collecting the domain linguistic data; the analysis module is used for analyzing the incidence relation among the entity words in the collected domain linguistic data; and the knowledge map building module is used for building a domain knowledge map based on the incidence relation among the entity words in the collected domain linguistic data.
Here, it should be noted that: the above description of the embodiment of the smart device is similar to the description of the embodiment of the method shown in fig. 1 to 5, and has similar beneficial effects to the embodiment of the method shown in fig. 1 to 5, and therefore, the description is omitted. For technical details not disclosed in the embodiment of the intelligent device of the present invention, please refer to the description of the method embodiment shown in fig. 1 to 5 of the present invention for understanding, and therefore, for brevity, will not be described again.
It should be noted that, in this document, 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 like elements in a process, method, article, or apparatus that comprises the element.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. An information response processing method, characterized in that the method comprises:
sending first interaction information to a user;
displaying a response interface corresponding to the first interaction information;
responding to different operations of the user under the response interface, and executing one of the following two response modes:
in a first response mode, limited response information corresponding to selection operation or input operation is received in response to the selection operation or the input operation of a user aiming at the limited response information under the response interface; outputting response information corresponding to the limited response information to a user;
in the response mode II, responding to the non-limited response information input by the user under the response interface, and receiving the non-limited response information; identifying the non-limited response information matched limited response information according to the first interaction information; and outputting response information corresponding to the limited response information to the user.
2. The method of claim 1, wherein identifying the qualified response information that matches the unqualified response information based on the first interaction information comprises:
extracting special phrases in the first interactive information and the non-limited response information by using a domain semantic library;
carrying out normalization processing on the special phrase by using a domain knowledge map to obtain a normalized special phrase;
and identifying the qualified response information matched with the non-qualified response information according to the normalized special phrase.
3. The method of claim 2, further comprising:
collecting domain keywords and common phrases;
and constructing a word vector set of the domain keywords and the common phrases according to semantics to form a domain semantic library.
4. The method of claim 2, further comprising:
collecting domain corpora;
analyzing the incidence relation among the entity words in the collected domain linguistic data;
and constructing a domain knowledge graph based on the association relation between the entity words in the collected domain linguistic data.
5. A smart device, the smart device comprising:
the sending module is used for sending first interaction information to a user;
the display module is used for controlling and displaying a response interface corresponding to the first interactive information;
the execution control module is used for responding to different operations of the user under the response interface and executing one of the following two response modes: in a first response mode, limited response information corresponding to selection operation or input operation is received in response to the selection operation or the input operation of a user aiming at the limited response information under the response interface; outputting response information corresponding to the limited response information to a user; in the response mode II, responding to the non-limited response information input by the user under the response interface, and receiving the non-limited response information; identifying the non-limited response information matched limited response information according to the first interaction information; and outputting response information corresponding to the limited response information to the user.
6. The smart device of claim 5,
the execution control module is specifically configured to extract a special phrase in the first interaction information and the non-limited response information by using a domain semantic library; carrying out normalization processing on the special phrase by using a domain knowledge map to obtain a normalized special phrase; and identifying the qualified response information matched with the non-qualified response information according to the normalized special phrase.
7. The smart device of claim 6, further comprising:
the first collection module is used for collecting the domain keywords and the common phrases;
and the semantic library construction module is used for constructing a word vector set of the domain keywords and the common phrases according to semantics to form a domain semantic library.
8. The smart device of claim 6, further comprising:
the second collection module is used for collecting the domain linguistic data;
the analysis module is used for analyzing the incidence relation among the entity words in the collected domain linguistic data;
and the knowledge map building module is used for building a domain knowledge map based on the incidence relation among the entity words in the collected domain linguistic data.
9. A smart device comprising one or more processors; a memory for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the information response processing method of any one of claims 1 to 4.
10. A computer-readable storage medium comprising a set of computer-executable instructions which, when executed, perform the information response processing method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011245401.5A CN112527980A (en) | 2020-11-10 | 2020-11-10 | Information response processing method, intelligent device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011245401.5A CN112527980A (en) | 2020-11-10 | 2020-11-10 | Information response processing method, intelligent device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112527980A true CN112527980A (en) | 2021-03-19 |
Family
ID=74980018
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011245401.5A Pending CN112527980A (en) | 2020-11-10 | 2020-11-10 | Information response processing method, intelligent device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112527980A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239450A (en) * | 2017-06-02 | 2017-10-10 | 上海对岸信息科技有限公司 | Natural language method is handled based on Interaction context |
| CN110322888A (en) * | 2019-05-21 | 2019-10-11 | 平安科技（深圳）有限公司 | Credit card unlocking method, device, equipment and computer readable storage medium |
| CN111339781A (en) * | 2020-02-10 | 2020-06-26 | 科大讯飞华南人工智能研究院（广州）有限公司 | Intention recognition method and device, electronic equipment and storage medium |
| CN111737411A (en) * | 2020-05-20 | 2020-10-02 | 华为技术有限公司 | Response method in man-machine conversation, conversation system and storage medium |
-
2020
- 2020-11-10 CN CN202011245401.5A patent/CN112527980A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239450A (en) * | 2017-06-02 | 2017-10-10 | 上海对岸信息科技有限公司 | Natural language method is handled based on Interaction context |
| CN110322888A (en) * | 2019-05-21 | 2019-10-11 | 平安科技（深圳）有限公司 | Credit card unlocking method, device, equipment and computer readable storage medium |
| CN111339781A (en) * | 2020-02-10 | 2020-06-26 | 科大讯飞华南人工智能研究院（广州）有限公司 | Intention recognition method and device, electronic equipment and storage medium |
| CN111737411A (en) * | 2020-05-20 | 2020-10-02 | 华为技术有限公司 | Response method in man-machine conversation, conversation system and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 烈风: "工程化的多轮对话机器人框架 CommuneChatbot 介绍", pages 1 - 17, Retrieved from the Internet <URL:https://zhuanlan.zhihu.com/p/88842152> * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109727041B (en) | Intelligent customer service multi-turn question and answer method, equipment, storage medium and device | |
| CN110168535B (en) | Information processing method and terminal, computer storage medium | |
| CN105719647B (en) | Assistant is recognized using the background sound that speaker examines | |
| US20160019885A1 (en) | Word cloud display | |
| CN108268591A (en) | It is chatted based on active and builds the method and apparatus of user's portrait | |
| CN111783439A (en) | Man-machine interaction dialogue processing method and device, computer equipment and storage medium | |
| CN112559865A (en) | Information processing system, computer-readable storage medium, and electronic device | |
| CN109902146A (en) | Credit information acquisition methods, device, terminal and storage medium | |
| CN110399473B (en) | Method and device for determining answers to user questions | |
| CN112307166B (en) | Intelligent question-answering method and device, storage medium and computer equipment | |
| CN112527980A (en) | Information response processing method, intelligent device and storage medium | |
| CN114490975B (en) | User question labeling method and device | |
| EP3962073A1 (en) | Online interview method and system | |
| CN113918703A (en) | Intelligent customer service question and answer method, device, server and storage medium | |
| CN114118937A (en) | Information recommendation method and device based on task, electronic equipment and storage medium | |
| CN112417095A (en) | Voice message processing method and device | |
| CN112416143A (en) | Text information editing method and device and electronic equipment | |
| CN112559701A (en) | Man-machine interaction method, device and storage medium | |
| CN111753548A (en) | Information acquisition method and device, computer storage medium and electronic equipment | |
| CN109788128A (en) | A kind of income prompting method, incoming call prompting device and terminal device | |
| US11862165B1 (en) | Optimized virtual assistant for connecting a user to a live agent | |
| CN112035613B (en) | Information pushing method and device based on multi-round dialogue, storage medium and electronic device | |
| CN111061854B (en) | Interaction method and device of intelligent conversation and electronic equipment | |
| CN113344550B (en) | Flow processing method, device, equipment and storage medium | |
| CN112530422A (en) | Response processing method, intelligent device and storage medium |
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 |