CN111984761A - Information response processing method, equipment and storage medium - Google Patents
Information response processing method, equipment and storage medium Download PDFInfo
- Publication number
- CN111984761A CN111984761A CN202010690945.6A CN202010690945A CN111984761A CN 111984761 A CN111984761 A CN 111984761A CN 202010690945 A CN202010690945 A CN 202010690945A CN 111984761 A CN111984761 A CN 111984761A
- Authority
- CN
- China
- Prior art keywords
- information
- intention information
- intention
- response
- substructure
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3335—Syntactic pre-processing, e.g. stopword elimination, stemming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/008—Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
Abstract
The invention discloses an information response processing method, equipment and a storage medium, wherein input information is received firstly; then identifying intention information represented by the input information to obtain an identification result; if the identification result comprises a plurality of intention information, acquiring a response language structure corresponding to each intention information in the plurality of intention information; and generating response information matched with the input information by using the acquired response language structure. Therefore, the invention fully utilizes the corresponding relation between the intention information and the response language structure to automatically generate the reasonable response information corresponding to multiple intentions, so that the human-computer interaction is smoother and the user experience is good.
Description
Technical Field
The present invention relates to information processing technologies, and in particular, to an information response processing method, device, and storage medium.
Background
In the intelligent customer service conversation process, the user solves the problem of the user by communicating with the bot. In the answer mode, the reply mode of the bot is preset, the main aim is to solve the problem of the user, and meanwhile, the processing flow of social chat (social talk) is also included. The method comprises the steps that a preset solving range exists for a user question bot, but the range of the social talk is relatively divergent, the chatting range of the user is expanded according to the bot, the user and responses of the bot, and the responses of the bot are response words edited manually. Corresponding answer words are manually edited for all the user's simple drawings, but for the user's multiple intentions (i.e. multiple ordered intentions), because any n types of intentions can be combined, and the great number of intentions cannot be easily manually edited for each combination.
Disclosure of Invention
The embodiment of the invention provides an information response processing method, equipment and a storage medium, aiming at solving the problem of generating a response word under the condition of multiple intentions of the conventional social talk.
According to a first aspect of the present invention, there is provided an information response processing method, including: receiving input information; identifying intention information represented by the input information to obtain an identification result; if the identification result comprises a plurality of intention information, acquiring a response language structure corresponding to each intention information in the plurality of intention information; and generating response information matched with the input information by using the acquired response language structure.
According to the second aspect of the present invention, there is also provided an information response processing apparatus comprising: the receiving module is used for receiving input information; the intention identification module is used for identifying intention information represented by the input information to obtain an identification result; the acquisition module is used for acquiring a response language structure corresponding to each intention information in the intention information if the identification result comprises the intention information; and the generating module is used for generating response information matched with the input information by using the acquired response language structure.
According to a third aspect of the present invention, there is also provided an information response processing apparatus comprising: one or more processors; a memory for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the above-described information response processing method.
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 adapted to perform the above-mentioned information response processing method.
The information response processing method, the equipment and the storage medium of the embodiment of the invention firstly receive input information; then identifying intention information represented by the input information to obtain an identification result; if the identification result comprises a plurality of intention information, acquiring a response language structure corresponding to each intention information in the plurality of intention information; and generating response information matched with the input information by using the acquired response language structure. Therefore, the invention fully utilizes the corresponding relation between the intention information and the response language structure to automatically generate the reasonable response information corresponding to multiple intentions, so that the human-computer interaction is smoother and the user experience is good.
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 a response message processing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram showing a second implementation flow of a reply information processing method according to an embodiment of the present invention;
FIG. 3 is a flow chart illustrating a specific implementation of a response message processing method according to an embodiment of the present invention;
FIG. 4 is a diagram showing a first configuration of a reply information processing apparatus according to an embodiment of the present invention;
fig. 5 is a schematic diagram showing a configuration of a response information processing apparatus 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 a response message processing method according to an embodiment of the present invention.
Referring to fig. 1, an embodiment of the present invention provides a response information processing method, where the method includes: an operation 101 of receiving input information; operation 102, identifying intention information represented by the input information to obtain an identification result; operation 103, if the recognition result includes a plurality of intention information, acquiring a response language structure corresponding to each intention information in the plurality of intention information; in operation 104, response information matching the input information is generated using the acquired response language structure.
In operation 101, the smart device receives input information, where the input information may be voice information from a user or operation instruction information, such as query instruction information, automatically generated by the smart device in response to a user trigger. The intelligent device can be an intelligent voice device which is developed at present or to be developed in the future and has a voice interaction or voice recognition function, a robot device bot and an intelligent client system in any form.
Of course, it should be understood by those skilled in the art that after the input information is received in operation 101, the input information may be further preprocessed, such as performing preprocessing operations on the input sentence, removing stop words, removing special characters, etc.; thereafter, the subsequent operation 102 is continued.
In operation 102, the smart device performs intention recognition on the input information through its own intention recognition system, resulting in a recognition result including intention information.
It should be added that, in the embodiment of the present invention, a main application scenario is how to automatically generate a reasonable response word under the condition of multiple intentions, so that when an identification result including multiple intention information is obtained through operation 102, a subsequent operation flow is continuously executed; otherwise, directly acquiring the response words matched with the single intention information and outputting the response words.
In operation 103, when the recognition result includes a plurality of intention information, the smart device obtains a response language structure corresponding to each intention information in the plurality of intention information in two ways:
the first method is as follows: and directly searching a response language structure corresponding to each intention information from a response language structure library.
The second method comprises the following steps: searching a response language corresponding to each intention information in the plurality of intention information from a response language library; and structuring the response words corresponding to the intention information to obtain the response word structure corresponding to the intention information.
Naturally, the implementation of the first method requires that the correspondence between the intention information and the response words in the response language library is converted into the correspondence between the intention information and the response language structures in advance, that is, the correspondence between the intention information and the response language structures is obtained by analyzing the intention function corresponding to the intention information and structuring the response words corresponding to the intention information.
Similarly, the implementation of the second method requires searching for a response word corresponding to each intention information from the response word library in real time, analyzing an intention function (i.e., intention functionalization) corresponding to the intention information, and performing structuring processing on the searched response word in real time to obtain a response word structure corresponding to each intention information.
In one example, if the input information is "user: hi ", the answer is" bot: Hey ther. I'm Moli, your virtual agent. how can I help you? "; then, by analyzing the intention function corresponding to the intention information and performing structuring processing on the answer word corresponding to the intention information, the following results are obtained: intention functionalization: the non-strategic intent a, chat _ harvesting _ influencing __ hi; structuring the answer: direct recovery Aa 1: hey ther. additional reply Aa 2: (empty).
In another example, the input information is "user: what's your name? ", the answer is" bot: I'm Moli. "; then, by analyzing the intention function corresponding to the intention information and performing structuring processing on the answer word corresponding to the intention information, the following results are obtained: intention functionalization: question intention B, chat _ bot _ about _ name; structuring the answer: direct recovery of Ba 1: i'm moli. additional recovery Ba 2: (empty); questioning content Bq 1: (empty).
In yet another example, if the input information is "user: i am lose", the answer is "Pleasure to meet you"; then, by analyzing the intention function corresponding to the intention information and performing structuring processing on the answer word corresponding to the intention information, the following results are obtained: intention functionalization: non-strategic intent A, chat _ user _ introduce __ name; structuring the answer: direct recovery Aa 1: plus to meeet you, additional reply Aa 2: (empty); content of questions Aq 1: how can How he help you?
In operation 104, the smart device generates response information matching the input information using the acquired response language structure.
In one example, if the input information is "user: hello, what's your name? "; identifying an idea graph to obtain a plurality of intention information, namely non-strategic intention + problem intention, chat _ marking _ influencing __ hi chat _ bot _ about __ name; therefore, through operations 103-104, response message information is generated: aa1+ Ba1 ═ Hey ther.
In yet another example, if the input information is "user: hi, i am rose"; through idea recognition, obtaining a plurality of intention information, namely non-strategic intention + non-strategic intention, chat _ harvesting _ influencing __ hi chat _ bot _ about __ name; therefore, through operations 103-104, response message information is generated: aa1+ Ba1, Aq 1?
Therefore, the invention fully utilizes the corresponding relation between the intention information and the response language structure to automatically generate the reasonable response information corresponding to multiple intentions, so that the human-computer interaction is smoother and the user experience is good.
FIG. 2 is a schematic diagram showing a second implementation flow of a reply information processing method according to an embodiment of the present invention; fig. 3 is a flowchart illustrating a specific implementation of an application example response message processing method according to the present invention.
Referring to fig. 2, a method for processing response information according to an embodiment of the present invention includes: operation 201, receiving input information; operation 202, identifying intention information represented by the input information to obtain an identification result; in operation 203, if the recognition result includes a plurality of intention information, searching a response word corresponding to each intention information in the plurality of intention information from a response word library; operation 204, performing structuring processing on the response words corresponding to each intention information to obtain a response word structure corresponding to each intention information; an operation 205 of sequentially and circularly generating response language structures of two adjacent intention information by using the acquired response language structures respectively corresponding to each intention information according to the sequential relationship among the plurality of intention information; in operation 206, the finally generated response sentence structures of the adjacent two intention information are determined as the response information matching the input information.
In operation 201, the smart device receives input information, where the input information may be voice information from a user or operation instruction information, such as query instruction information, automatically generated by the smart device in response to a user trigger. The intelligent device can be an intelligent voice device which is developed at present or to be developed in the future and has a voice interaction or voice recognition function, a robot device bot and an intelligent client system in any form.
Of course, it will be understood by those skilled in the art that after the input information is received in operation 201, the input information may be further preprocessed, such as performing preprocessing operations on the input sentence, removing stop words, removing special characters, etc.; thereafter, subsequent operations 202 continue to be performed.
In operation 202, referring to fig. 3, the smart device performs intention recognition on input information through its own intention recognition system, resulting in a recognition result including intention information.
It should be added that, the main application scenario of the embodiment of the present invention is how to automatically generate a reasonable response language under the condition of multiple intentions, so that when an identification result including multiple intention information (mul _ intent) is obtained through operation 202, the subsequent operation 203 is continued; otherwise, directly acquiring the response words matched with the single intention information and outputting the response words.
In operation 203, when the recognition result includes a plurality of intention information, the smart device searches a response word corresponding to each intention information in the plurality of intention information from a response word library.
In operation 204, referring to fig. 3, for the response words corresponding to each intention information, the smart device performs structuring processing according to content types to obtain a response word structure including a reply content substructure and a question content substructure corresponding to each intention information; wherein the reply content substructure comprises a direct reply content substructure and/or an additional reply content substructure.
In one example, if the input information is "user: hi ", the answer is" bot: Hey ther. I'm Moli, your virtual agent. how can I help you? "; then by analyzing the intention information: the non-strategic intent a, chat _ harvesting _ influencing __ hi; structuring the response words corresponding to each intention information according to the content types to obtain the following response word structures: direct recovery Aa 1: hey ther. additional reply Aa 2: (empty).
In another example, the input information is "user: what's your name? ", the answer is" bot: I'm Moli. "; then by analyzing the intention information: question intention B, chat _ bot _ about _ name; structuring the response words corresponding to each intention information according to the content types to obtain the following response word structures: direct recovery of Ba 1: i'm moli. additional recovery Ba 2: (empty); questioning content Bq 1: (empty).
In yet another example, if the input information is "user: i am lose", the answer is "Peasure to meetyou"; then by analyzing the intention information: non-strategic intent A, chat _ user _ introduce __ name; structuring the response words corresponding to each intention information according to the content types to obtain the following response word structures: direct recovery Aa 1: plus to meeet you, additional reply Aa 2: (empty); content of questions Aq 1: how can How he help you?
In operations 205-206, referring to fig. 3, the smart device cyclically generates response word structures of adjacent intention information according to a forward relationship between a plurality of intention information, and determines the finally generated response word structures of two adjacent intention information as response information matching the input information.
In one embodiment, operation 205 comprises: sequentially judging the bearing relationship between the question content substructure of the current intention information and the next adjacent intention information according to the sequence relationship among the intention information; if the question content substructure of the current intention information and the next adjacent intention information are judged to be in a bearing relationship, the question content substructure of the current intention information is used as a hollow structure to generate a question content substructure in response language structures of the two adjacent intention information; if the question content substructure of the current intention information and the next adjacent intention are not in a bearing relationship after judgment, further judging a first corresponding relationship between the question content substructure of the current intention information and the question content substructure of the next adjacent intention; if the first corresponding relation is similar, taking one of the questioning content substructure of the current intention information and the questioning content substructure of the next adjacent intention as the questioning content substructure of the answer language structure of the two adjacent intention information; and if the first corresponding relation is other than the similar relation, taking the question content substructure of the next adjacent intention information as the question content substructure in the answer language structures of the two adjacent intention information. Where other relationships typically include independent relationships, mutually exclusive relationships, or relationships other than those similar.
In yet another possible implementation, operation 205 includes: according to the sequence relation among the plurality of intention information, sequentially determining a second corresponding relation between the reply content substructure of the current intention information and the reply content substructure of the next adjacent intention information; if the determined second corresponding relationship is an inclusion relationship, using a reply content substructure with a larger range in a reply content substructure of the current intention information and a reply content substructure of the next adjacent intention information as a reply content substructure in a reply language structure of the adjacent two intention information; and if the determined second corresponding relation is other than the containing relation, taking the reply content substructure of the next adjacent intention information as the reply content substructure of the response language structures of the two adjacent intention information. For example, two different answer structures corresponding to intention information a | B are taken as an example: the types of relationships between Aa1 and Ba1 include: containment relationships, independent relationships, mutual exclusion relationships, other; the relationship types of Bq1 and Aq1 comprise: similar relationship, others.
In one example, take "bot (button)" [ helpful ] [ unelful ]; taking user's helpful, thanks, bye' as an example, the intention information of the user is extracted as follows:
A|B|C＝chat_bu_answer_feedback__solved|chat_bu_answer_feedback__gratitu de|chat_greeting__closing；
the function of analyzing intent information, i.e. intent functionalization: context policy intent | not trivial intent | context policy intent;
the answer language structure corresponding to the intention information:
A＝{Aa1＝“Happy to help.”,Aa2＝“”,Aq1＝“Do you have any other questions？”}；
B＝{Ba1＝“Glad to help！”,Ba2＝“”,Bq1＝“”}；
C＝{Ca1＝“Thanks for visiting.”,Ca2＝“”,Cq1＝“”}。
the structure of the response words for generating the adjacent intention information by looping through operation 205 is as follows:
a)A:{Aa1,Aa2,Aq1}+B:{Ba1,Ba2,Bq1}＝AB；
b) aq1 and B are not in a bearing relationship;
c) aa1 and Ba1 are inclusive relationships Ba1 includes Aa1, (AB) a1 ═ Ba 1;
d) bq1 ═ so (AB) q1 ═ Aq 1;
e)AB＝{(AB)a1＝“Glad to help！”，(AB)q1＝“Do you have any other questions？”}
f) further analysis: (AB) { (AB) a1, (AB) q1} + C { Ca1, Ca2, Cq1} ═ AB) C;
g) (AB) q1 and C are in a bearing relationship, (AB) q1 ═ q;
h) (AB) a1 and Ca1 are independent, (ABC) a1 ═ a1+ Ca 1;
i) (AB) q1 ═ Cq1 ═ and so (ABC) q1 ═ for ";
j)ABC＝{(ABC)a1＝“Glad to help！Thanks for visiting.”，(ABC)q1＝“”}。
therefore, according to the forward relation among the plurality of intention information, the embodiment of the invention circularly generates the answer word structure of the adjacent intention information, specifically analyzes the relation between the answer word structure and the intention information, judges whether the question content substructure and the intention information are in a bearing relation, and generates the answer information corresponding to the multi-intention based on the relation between the answer word structure corresponding to the adjacent intention information, so that reasonable answer information can be provided for any unforeseen multi-intention, the man-machine interaction is smoother, and the user experience is better.
Similarly, based on the above response message processing method, an embodiment of the present invention further provides a computer-readable storage medium, where a program is stored, and when the program is executed by a processor, the processor is caused to perform at least the following operation steps: an operation 101 of receiving input information; operation 102, identifying intention information represented by the input information to obtain an identification result; operation 103, if the recognition result includes a plurality of intention information, acquiring a response language structure corresponding to each intention information in the plurality of intention information; in operation 104, response information matching the input information is generated using the acquired response language structure.
Similarly, based on the above response information processing method, an embodiment of the present invention further provides an information response processing apparatus, where the apparatus 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 at least the operational steps of: an operation 101 of receiving input information; operation 102, identifying intention information represented by the input information to obtain an identification result; operation 103, if the recognition result includes a plurality of intention information, acquiring a response language structure corresponding to each intention information in the plurality of intention information; in operation 104, response information matching the input information is generated using the acquired response language structure.
Further, based on the above response information processing method, an embodiment of the present invention further provides a response information processing apparatus, and as shown in fig. 4, the apparatus 40 at least includes: a receiving module 401, configured to receive input information; the intention identification module 402 is used for identifying intention information represented by the input information to obtain an identification result; an obtaining module 403, configured to obtain, if the identification result includes multiple pieces of intention information, a response language structure corresponding to each piece of intention information in the multiple pieces of intention information; and a generating module 404, configured to generate response information matching the input information by using the obtained response language structure.
In one possible implementation, as shown in fig. 5, the generating module 404 includes: a loop generation unit 4041, configured to sequentially and cyclically generate response language structures of two adjacent pieces of intention information by using the acquired response language structures respectively corresponding to each piece of intention information according to a sequential relationship between the plurality of pieces of intention information; a determining unit 4042, configured to determine the response language structure of the finally generated two adjacent intention information as the response information matching the input information.
In an implementation manner, the obtaining module 403 is specifically configured to directly search the answer phrase structure corresponding to each intention information from the answer phrase structure library.
In one embodiment, as shown in fig. 5, the obtaining module 403 includes: a searching unit 4031, configured to search, from a response language library, a response language corresponding to each piece of intention information in the plurality of pieces of intention information; a structuring unit 4032, configured to perform a structuring process on the response words corresponding to each piece of intention information to obtain a response word structure corresponding to each piece of intention information.
In an implementation manner, the structuring processing unit 4032 is specifically configured to perform structuring processing on the response words corresponding to each intention information according to content types to obtain a response word structure corresponding to each intention information, where the response word structure includes a reply content substructure and a question content substructure; wherein the reply content substructure comprises a direct reply content substructure and/or an additional reply content substructure.
In an embodiment, the loop generating unit 4041 is specifically configured to sequentially determine, according to the sequential relationship between the plurality of intention information, a bearing relationship between the question content substructure of the current intention information and the next adjacent intention information; if the question content substructure of the current intention information and the next adjacent intention information are judged to be in a bearing relationship, the question content substructure of the current intention information is used as a hollow structure to generate a question content substructure in response language structures of the two adjacent intention information; if the question content substructure of the current intention information and the next adjacent intention are not in a bearing relationship after judgment, further judging a first corresponding relationship between the question content substructure of the current intention information and the question content substructure of the next adjacent intention; if the first corresponding relation is similar, taking one of the questioning content substructure of the current intention information and the questioning content substructure of the next adjacent intention as the questioning content substructure of the answer language structure of the two adjacent intention information; and if the first corresponding relation is other than the similar relation, taking the question content substructure of the next adjacent intention information as the question content substructure in the answer language structures of the two adjacent intention information.
In an embodiment, the loop generating unit 4041 is specifically configured to sequentially determine, according to the sequential relationship between the plurality of intention information, a second corresponding relationship between the reply content substructure of the current intention information and the reply content substructure of the next adjacent intention information; if the determined second corresponding relationship is an inclusion relationship, using a reply content substructure with a larger range in a reply content substructure of the current intention information and a reply content substructure of the next adjacent intention information as a reply content substructure in a reply language structure of the adjacent two intention information; and if the determined second corresponding relation is other than the containing relation, taking the reply content substructure of the next adjacent intention information as the reply content substructure of the response language structures of the two adjacent intention information.
Here, it should be noted that: the above description of the embodiment of the response information processing apparatus is similar to the description of the method embodiment shown in fig. 1 to 3, and has similar beneficial effects to the method embodiment shown in fig. 1 to 3, and therefore, the description is omitted. For technical details that are not disclosed in the embodiment of the response message processing apparatus of the present invention, please refer to the description of the method embodiments shown in fig. 1 to 3 of the present invention, which will not be repeated herein for brevity.
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:
receiving input information;
identifying intention information represented by the input information to obtain an identification result;
if the identification result comprises a plurality of intention information, acquiring a response language structure corresponding to each intention information in the plurality of intention information;
and generating response information matched with the input information by using the acquired response language structure.
2. The method of claim 1, wherein generating response information matching the input information using the retrieved response syntax structure comprises:
according to the sequence relation among the plurality of intention information, sequentially and circularly generating answer language structures of two adjacent intention information by using the acquired answer language structures respectively corresponding to each intention information;
and determining the finally generated response language structure of the two adjacent intention information as response information matched with the input information.
3. The method according to claim 1 or 2, wherein obtaining the answer structure corresponding to each intention information in the plurality of intention information comprises:
and directly searching a response language structure corresponding to each intention information from a response language structure library.
4. The method according to claim 1 or 2, wherein the obtaining of the answer structure corresponding to each intention information in the plurality of intention information comprises:
searching a response language corresponding to each intention information in the plurality of intention information from a response language library;
and structuring the response words corresponding to the intention information to obtain the response word structure corresponding to the intention information.
5. The method according to claim 4, wherein the structuring of the answer for each intention message comprises:
structuring the response words corresponding to each intention information according to the content types to obtain response word structures corresponding to each intention information and comprising a reply content substructure and a question content substructure; wherein the reply content substructure comprises a direct reply content substructure and/or an additional reply content substructure.
6. The method according to claim 4, wherein sequentially and circularly generating the answer phrase structures of two adjacent intention information by using the obtained answer phrase structure corresponding to each intention information according to the sequential relationship among the plurality of intention information comprises:
sequentially judging the bearing relationship between the question content substructure of the current intention information and the next adjacent intention information according to the sequential relationship among the plurality of intention information;
if the question content substructure of the current intention information and the next adjacent intention information are judged to be in a bearing relationship, the question content substructure of the current intention information is used as a hollow structure to generate a question content substructure in response language structures of the two adjacent intention information;
if the question content substructure of the current intention information and the next adjacent intention are not in a bearing relationship after judgment, further judging a first corresponding relationship between the question content substructure of the current intention information and the question content substructure of the next adjacent intention;
if the first corresponding relation is similar, taking one of the questioning content substructure of the current intention information and the questioning content substructure of the next adjacent intention as the questioning content substructure of the answer language structure of the two adjacent intention information;
and if the first corresponding relation is other than the similar relation, taking the question content substructure of the next adjacent intention information as the question content substructure in the answer language structures of the two adjacent intention information.
7. The method according to claim 4, wherein sequentially and circularly generating the answer phrase structures of two adjacent intention information by using the obtained answer phrase structure corresponding to each intention information according to the sequential relationship among the plurality of intention information comprises:
according to the sequence relation among the plurality of intention information, sequentially determining a second corresponding relation between the reply content substructure of the current intention information and the reply content substructure of the next adjacent intention information;
if the determined second corresponding relationship is an inclusion relationship, using a reply content substructure with a larger range in a reply content substructure of the current intention information and a reply content substructure of the next adjacent intention information as a reply content substructure in a reply language structure of the adjacent two intention information;
and if the determined second corresponding relation is other than the containing relation, taking the reply content substructure of the next adjacent intention information as the reply content substructure of the response language structures of the two adjacent intention information.
8. An information response processing apparatus characterized by comprising:
the receiving module is used for receiving input information;
the intention identification module is used for identifying intention information represented by the input information to obtain an identification result;
the acquisition module is used for acquiring a response language structure corresponding to each intention information in the intention information if the identification result comprises the intention information;
and the generating module is used for generating response information matched with the input information by using the acquired response language structure.
9. An information response processing apparatus 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 7.
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 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010690945.6A CN111984761A (en) | 2020-07-17 | 2020-07-17 | Information response processing method, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010690945.6A CN111984761A (en) | 2020-07-17 | 2020-07-17 | Information response processing method, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111984761A true CN111984761A (en) | 2020-11-24 |
Family
ID=73438689
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010690945.6A Pending CN111984761A (en) | 2020-07-17 | 2020-07-17 | Information response processing method, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111984761A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113076406A (en) * | 2021-03-19 | 2021-07-06 | 联想(北京)有限公司 | Information processing method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107885874A (en) * | 2017-11-28 | 2018-04-06 | 上海智臻智能网络科技股份有限公司 | Data query method and apparatus, computer equipment and computer-readable recording medium |
| CN110019712A (en) * | 2017-12-07 | 2019-07-16 | 上海智臻智能网络科技股份有限公司 | More intent query method and apparatus, computer equipment and computer readable storage medium |
| CN110019713A (en) * | 2017-12-07 | 2019-07-16 | 上海智臻智能网络科技股份有限公司 | Based on the data retrieval method and device, equipment and storage medium for being intended to understand |
| CN111159375A (en) * | 2019-12-27 | 2020-05-15 | 深圳前海微众银行股份有限公司 | Text processing method and device |
-
2020
- 2020-07-17 CN CN202010690945.6A patent/CN111984761A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107885874A (en) * | 2017-11-28 | 2018-04-06 | 上海智臻智能网络科技股份有限公司 | Data query method and apparatus, computer equipment and computer-readable recording medium |
| CN110019712A (en) * | 2017-12-07 | 2019-07-16 | 上海智臻智能网络科技股份有限公司 | More intent query method and apparatus, computer equipment and computer readable storage medium |
| CN110019713A (en) * | 2017-12-07 | 2019-07-16 | 上海智臻智能网络科技股份有限公司 | Based on the data retrieval method and device, equipment and storage medium for being intended to understand |
| CN111159375A (en) * | 2019-12-27 | 2020-05-15 | 深圳前海微众银行股份有限公司 | Text processing method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113076406A (en) * | 2021-03-19 | 2021-07-06 | 联想(北京)有限公司 | Information processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9805024B2 (en) | Anaphora resolution for semantic tagging | |
| US8516052B2 (en) | Dynamically managing online communication groups | |
| US20210150150A1 (en) | Method and apparatus for intelligent automated chatting | |
| US11250839B2 (en) | Natural language processing models for conversational computing | |
| CN107135140B (en) | Instant messaging method and device | |
| CN109635094B (en) | Method and device for generating answer | |
| CN108062316A (en) | A kind of method and apparatus for aiding in customer service | |
| CN111859119A (en) | Information processing method and device | |
| CN108306813B (en) | Session message processing method, server and client | |
| CN111984761A (en) | Information response processing method, equipment and storage medium | |
| CN109388695B (en) | User intention recognition method, apparatus and computer-readable storage medium | |
| Prabu et al. | Enhancing customer service using Chatbot application through artificial intelligence | |
| CN116186771A (en) | Text processing method, device and medium applied to artificial intelligence generated content | |
| CN112748828B (en) | Information processing method, device, terminal equipment and medium | |
| CN110535749B (en) | Dialogue pushing method and device, electronic equipment and storage medium | |
| IO et al. | COMMENTS ABOUT THE SIRI CHATBOT: A SENTIMENT ANALYSIS OF THE POSTINGS AT A MICROBLOGGING SITE. | |
| CN111046151A (en) | Message processing method and device | |
| Catizone et al. | Information extraction tools and methods for understanding dialogue in a companion | |
| CN116775815B (en) | Dialogue data processing method and device, electronic equipment and storage medium | |
| CN110956035B (en) | Questionnaire optimization method, system and storage medium | |
| CN113641803B (en) | Data processing method, device, equipment and storage medium | |
| CN113344550B (en) | Flow processing method, device, equipment and storage medium | |
| CN117010413A (en) | Community question and answer method and device, storage medium and computer equipment | |
| JP2024003862A (en) | Chat system and chat program | |
| CN105939252A (en) | Method and device for issuing information in friend making platform |
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 |