CN109697230B - Information processing method and electronic equipment - Google Patents
Information processing method and electronic equipment Download PDFInfo
- Publication number
- CN109697230B CN109697230B CN201811601059.0A CN201811601059A CN109697230B CN 109697230 B CN109697230 B CN 109697230B CN 201811601059 A CN201811601059 A CN 201811601059A CN 109697230 B CN109697230 B CN 109697230B
- Authority
- CN
- China
- Prior art keywords
- information
- intention
- scene
- input
- combination
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the application discloses an information processing method and electronic equipment, wherein the method comprises the following steps: acquiring user input information; extracting scene information and intention information in the input information; and acquiring and outputting the feedback information based on the scene information and the intention information. According to the method, when feedback information is provided for a user based on user input information, intention information included in the input information is considered, and scene information in the input information is included, so that the feedback information is acquired and output based on an integral formed by the intention information and the scene information in the input information, the similarity between the feedback information and an expected answer of the user is improved, the user is guided to have a more smooth conversation, the problem is solved for the user more quickly, the probability of unsmooth or invalid communication is reduced, and the user experience is improved.
Description
Technical Field
The present application relates to the field of information processing technologies, and in particular, to an information processing method and an electronic device.
Background
With the development of electronic technology, more and more applications integrate intelligent dialog systems that are capable of responding to question-answer information input by a user and providing reply information that is closer to the expected answer of the user, the more efficient the conversation, and the higher the user experience.
Therefore, how to improve the similarity between the reply information and the expected answer of the user, thereby improving the conversation efficiency and the user experience, becomes a technical problem to be solved by those skilled in the art.
Disclosure of Invention
The application provides the following technical scheme:
an information processing method applied to an intelligent conversation system, wherein the intelligent conversation system can respond to received input information and provide feedback information, and the method comprises the following steps:
acquiring user input information, wherein the input information represents that a user expects the intelligent session system to feed back the feedback information;
extracting scene information and intention information in the input information;
and acquiring and outputting the feedback information based on the scene information and the intention information.
Optionally, obtaining and outputting the feedback information based on the scene information and the intention information includes:
and acquiring and outputting different feedback information based on the same intention information and different scene information.
Optionally, obtaining and outputting the feedback information based on the scene information and the intention information includes:
determining at least one combined relation based on scene information and intention information in the input information, wherein any combined relation in the at least one combined relation comprises one intention information and one scene information, and at least one piece of intention information and at least one piece of scene information in different combined relations are different;
determining a user input intention corresponding to each combination relation based on each combination relation in the at least one combination relation;
and acquiring and outputting feedback information corresponding to each combination relation based on the user input intention corresponding to each combination relation.
Optionally, determining at least one combination relationship based on the scene information and the intention information in the input information includes:
and querying a first database based on scene information and intention information in the input information, and determining at least one combined relation.
Optionally, querying the first database based on the scene information and the intention information in the input information, and determining at least one combination relationship includes:
querying the first database based on each intention information in the input information, and determining scene information corresponding to each intention information in the first database;
and determining at least one combination relation based on each intention information and the corresponding scene information.
Optionally, determining, based on each combination relationship in the at least one combination relationship, a user input intention corresponding to each combination relationship includes:
continuously querying the first database based on each combination relation in the at least one combination relation, and determining a user input intention corresponding to each combination relation;
or the like, or, alternatively,
and querying the second database based on each combination relation in the at least one combination relation, and determining the user input intention corresponding to each combination relation.
Optionally, the obtaining and outputting feedback information corresponding to each combination relationship based on the user input intention corresponding to each combination relationship includes:
determining the conversation guide corresponding to each combination relation based on the user input intention corresponding to each combination relation;
and acquiring and outputting feedback information corresponding to each combination relation based on the session guidance of each combination relation.
Optionally, if the input information includes at least two pieces of scene information, the contents of different pieces of scene information are at least partially different.
An electronic device for use in an intelligent conversational system, the intelligent conversational system being capable of responding to received input information and providing feedback information, the electronic device comprising a memory and a processor, wherein the processor is configured to execute a program stored in the memory; the memory is to store a program to at least:
acquiring user input information, wherein the input information represents that a user expects the intelligent session system to feed back the feedback information;
extracting scene information and intention information in the input information;
and acquiring and outputting the feedback information based on the scene information and the intention information.
Optionally, the same scene information with different intention information corresponds to different feedback information.
Compared with the prior art, the technical scheme has the following advantages:
according to the technical scheme, when feedback information is provided for the user based on user input information, intention information included in the input information can be considered, and the intention information can also be included in the input information, so that the feedback information is obtained and output based on the intention information in the input information and the whole formed by the scene information, the similarity of the feedback information and expected answers of the user is improved, the user is guided to carry out more smooth conversation, the problem is solved for the user more quickly, the probability of unsmooth or invalid communication is reduced, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of an information processing method according to an embodiment of the present application;
FIG. 2 is a flow chart of an information processing method according to another embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to another embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, but the present application may be practiced in other ways than those described herein, and it will be apparent to those of ordinary skill in the art that the present application is not limited to the specific embodiments disclosed below.
In the process of dialogue with the intelligent customer service, the intelligent conversation system extracts intention information from information input by a user, pushes out a set reply to the user based on the extracted intention information, waits for the feedback of the user, and adjusts the conversation direction according to the feedback of the user, so that the conversation taking the user as the leading part is realized, and the question asked by the user can be solved by the pushed-out reply. However, in actual use, input information of a user is various, and information to be expressed by the user is completely different when the same intention information is in different contexts, so that when the intelligent customer service session system replies based on the intention information input by the user, a phenomenon of wrong reply is easily generated, communication is not smooth or invalid, and user experience is affected.
For example, the input information of the A user is "I found A batting in the shopping mall, do you sell A batting? (I see battery A in The store, do you sell battery A alone)', and The input information of user B is "The cell phone battery is book, do you select A battery? (do you sell battery a if you are bad); the latter inputs information intended to buy the battery. When the existing intelligent conversation system faces the two input information, only intention information 'sell A battery' is extracted, the user A and the user B are considered to buy the battery and reply to feedback of how the user A and the user B buy the battery, so that the user A is unsatisfied in the reply, the input information needs to be readjusted to adjust the conversation direction or directly end the conversation, communication is improper or invalid, and user experience is influenced.
In view of this, an embodiment of the present application provides an information processing method, which is applied to an intelligent session system, where the intelligent session system is capable of responding to received input information and providing feedback information, as shown in fig. 1, the method includes:
s1: and acquiring user input information, wherein the input information represents that the user expects the intelligent conversation system to feed back the feedback information.
In the embodiment of the present application, the form and content of the input information of the user are not limited in the present application, as long as the input information can represent that the user expects the intelligent conversation system to perform feedback.
Optionally, in this embodiment of the application, after the input information is input, the intelligent session system is triggered to analyze the input information, and feedback is performed based on an analysis result of the input information.
S2: and extracting scene information and intention information in the input information.
It should be noted that, in the embodiment of the present application, the input information may include one piece of scene information and one piece of intention information, may also include one piece of intention information and at least two pieces of scene information, may also include one piece of scene information and at least two pieces of intention information, or includes at least two pieces of scene information and at least two pieces of intention information, which is not limited in this application as long as the input information includes at least one piece of scene information and at least one piece of intention information.
In the above embodiment, if at least two pieces of scene information are included in the input information, at least part of contents of different pieces of scene information are different. The content of at least part of the different scene information may be the same content of the different scene information, the content of part of the different scene information is different, or the content of all the different scene information is different.
If the user inputs information "I found A batting in the shopping mall, do you sell A batting? "the extracted scene information may include only" in the cropping mall ", and may also include: the scene information 1 "in the cropping map" and the scene information 2 "found a game in the cropping map", which is not limited in this application and is determined according to the situation; the intention information it extracts includes "sell A battery".
S3: and acquiring and outputting the feedback information based on the scene information and the intention information.
Optionally, in an embodiment of the present application, if the input information includes at least two pieces of scene information, acquiring and outputting the feedback information based on the scene information and the intention information includes: and acquiring and outputting different feedback information based on the same intention information and different scene information.
In another embodiment of the present application, if the input information includes at least two intention information and one scene information, acquiring and outputting the feedback information based on the scene information and the intention information includes: and acquiring and outputting different feedback information based on the same scene information and different intention information.
In yet another embodiment of the present application, if the input information includes at least two intention information and at least two scenario information, acquiring and outputting the feedback information based on the scenario information and the intention information further includes: and acquiring and outputting different feedback information based on different scene information and different intention information. However, the present application is not limited thereto, as the case may be.
On the basis of any of the above embodiments, in an embodiment of the present application, acquiring and outputting the feedback information based on the scene information and the intention information includes:
determining at least one combined relation based on the scene information and the intention information in the input information, wherein any one combined relation in the at least one combined relation comprises intention information and scene information, and at least one piece of information in the intention information and the scene information which are contained in different combined relations is different;
determining a user input intention corresponding to each combination relation based on each combination relation in the at least one combination relation;
and acquiring and outputting feedback information corresponding to each combination relation based on the user input intention corresponding to each combination relation.
It should be noted that, in the embodiment of the present application, at least one of the intention information and the scenario information included in different combination relationships includes: and the intention information and the scene information contained in different combination relations are different, the intention information and the scene information and the intention information and the scene information contained in different combination relations are different, and the intention information and the scene information contained in different combination relations are different.
On The basis of The above embodiments, in an embodiment of The present application, if The input information of The user is "The cell phone battery is book, do you select a battery (is a battery of a mobile phone is bad)", only one piece of scene information is extracted, namely scene information 1 'The cell phone book is book', only one piece of intention information is extracted, namely intention information 1 'sell A book', in the present embodiment, based on the scene information and the intention information in the input information, a combination relationship (scene information 1, intention information 1) can be obtained, then, the input intention 1 of the user is determined based on the combination ((scene information 1, intention information 1)), and then the feedback information 1 is acquired and outputted based on the input intention 1 of the user, and the feedback information 1 is provided to the user to match the expected answer of the user.
In another embodiment of the present application, the input information of the user is "I found A batting in the shopping mall, do you sell A batting? ", the extracted scene information is two, including: scene information 1 "in the cropping map" and scene information 2 "found A batting in the cropping map"; only 1 piece of extracted intention information is intention information 1 "sell a battery", and then in this embodiment, based on the scene information and the intention information in the input information, two combination relationships (scene information 1, intention information 1) and (scene information 2, intention information 2) can be obtained.
Determining an input intention 1 of the user based on the (scene information 1, intention information 1) combination; determining the input intention 2 of the user based on the combination of (scene information 2 and intention information 2), acquiring and outputting at least one feedback information 1 based on the input intention 1 of the user, and acquiring and outputting at least one feedback information 2 based on the input intention 2 of the user so as to provide two responses of the feedback information 1 and the feedback information 2 for the user to match the expected answer of the user.
On the basis of any of the above embodiments, in an embodiment of the present application, determining at least one combination relationship based on the scene information and the intention information in the input information includes:
and querying a first database based on scene information and intention information in the input information, and determining at least one combined relation.
Specifically, on the basis of the above embodiment, in an embodiment of the present application, as shown in fig. 2, the determining, by the first database, at least one combination relationship based on the scene information and the intention information in the input information includes:
matching each scene information stored in a database by using input information so as to extract the scene information included in the input information;
matching each intention information stored in a database by using input information so as to extract the intention information included in the input information;
and searching a relational network database of the scene information and the intention information based on the scene information and the intention information extracted from the input information so as to determine the combined relation of each scene information and each intention information.
On the basis of the above embodiments, in an embodiment of the present application, any intention information in the input information may form a combined relationship with each scene information in the input information, and any scene information may form a combined relationship with each intention information in the input information. For the sake of clarity, taking the example that the input information includes two pieces of scene information and two pieces of intention information, namely scene information 1, scene information 2, intention information 1, and intention information 2, in the present embodiment, the at least one combination relationship includes four combinations of (scene information 1, intention information 1) combination, (scene information 1, intention information 2) combination, (scene information 2, intention information 1) combination, and (scene information 2, intention information 2) combination.
In another embodiment of the present application, the presence of at least one piece of intention information in the input information may form a combined relationship with only a part of the scene information in the input information, and at least one piece of scene information may form a combined relationship with only a part of the intention information in the input information. In this embodiment, the at least one combination relationship may include a combination of (scene information 1, intention information 1), (scene information 1, intention information 2), a combination of (scene information 2, intention information 1), a combination of (scene information 2, intention information 2), a combination of (scene information 1, intention information 1), a combination of (scene information 1, intention information 2), a combination of (scene information 2, intention information 1), a combination of (scene information 1, intention information 2), a combination of (scene information 2, intention information 1), a combination of (scene information 2, intention information 2), or other combinations, which is not limited in this application, depending on the circumstances.
In another embodiment of the present application, the context information, the intention information, and the relationship between the context information and the intention information are stored together, then in this embodiment, querying the first database based on the context information and the intention information in the input information, and determining at least one combined relationship includes:
querying the first database based on each intention information in the input information, and determining scene information corresponding to each intention information in the first database;
and determining at least one combination relation based on each intention information and the corresponding scene information.
Continuing to take the example that the input information includes scene information 1, scene information 2, intention information 1 and intention information 2, first using the intention information 1 as an index to search a first database, finding that the scene information corresponding to the intention information 1 in the first database includes both the scene information 1 and the scene information 2 through the search, and thus determining two combination relations of (intention information 1, scene information 1) and (intention information 1, scene information 2); and then searching the first database by taking the intention information 2 as an index, and finding that the scene information corresponding to the intention information 2 in the first database only comprises the scene information 1 through searching, thereby determining the combination relationship (the intention information 2 and the scene information 1). In this embodiment, the at least one combination relationship includes: three combined relationships of intention information 1, scene information 1), (intention information 1, scene information 2), and (intention information 2, scene information 1).
In other embodiments of the present application, other manners may also be adopted, and at least one combination relationship is determined based on the scene information and the intention information in the input information, which is not limited in the present application, and is specifically determined as the case may be.
On the basis of any of the foregoing embodiments, in an embodiment of the present application, determining, based on each combination relationship in the at least one combination relationship, a user input intention corresponding to each combination relationship includes: and continuously querying the first database based on each combination relation in the at least one combination relation, and determining the user input intention corresponding to each combination relation.
In another embodiment of the present application, determining, based on each combination relationship of the at least one combination relationship, the user input intention corresponding to the combination relationship includes: and querying the second database based on each combination relation in the at least one combination relation, and determining the user input intention corresponding to each combination relation. In other embodiments of the present application, the user input intention corresponding to each of the at least one combination relationship may also be determined based on each of the at least one combination relationship in other manners, which is not limited in this application, and is determined as the case may be.
On the basis of any of the above embodiments, in an embodiment of the present application, acquiring and outputting feedback information corresponding to each combination relationship based on a user input intention corresponding to each combination relationship includes:
determining the conversation guide corresponding to each combination relation based on the user input intention corresponding to each combination relation;
and acquiring and outputting feedback information corresponding to each combination relation based on the session guidance corresponding to each combination relation.
Optionally, in an embodiment of the present application, determining, based on the user input intention corresponding to each of the combination relationships, a session guide corresponding to each of the combination relationships includes:
based on the user input intention corresponding to each combination relationship, searching a third database, and determining a session guide corresponding to each combination relationship, where the third database includes intention processing policies under each scene, but this application is not limited thereto.
On the basis of the above embodiment, in an embodiment of the present application, the number of user input intentions obtained based on the input information is small, and the number of feedback information that needs to be output based on each user input intention is small, so that all feedback information can be output at one time, and the expected answer of the user is matched to the greatest extent, thereby improving the conversation efficiency; in another embodiment of the present application, the number of the input intentions of the user is obtained based on the input information, the number of the feedback information to be output based on the input intentions of the user is large, only a part of the feedback information may be output at a time, and if the currently output part of the feedback information cannot match the expectation of the user, at least a part of the remaining feedback information is obtained by clicking a trigger operation such as "page turning" or "more" to reduce the difficulty of reading the feedback information by the user.
Optionally, on the basis of the foregoing embodiment, in an embodiment of the present application, the acquiring and outputting the feedback information includes: and N pieces of feedback information are acquired and output at a time, wherein N is a positive integer not less than 1. If the number of the feedback information which needs to be output by each user input intention is not more than N, all the feedback information is output at one time, and if the number of the feedback information which needs to be output by each user input intention is more than N, only N pieces of feedback information are output at one time at most.
Specifically, in an embodiment of the present application, a value range of N may be any value from 3 to 10, which is not limited in the present application, and is determined as the case may be.
On the basis of any one of the above embodiments, in an embodiment of the present application, if the number of feedback information that each user inputs an intention and needs to be output is large, and all feedback information cannot be output at one time, the feedback information is sorted according to the weight of the feedback information from top to bottom, and the feedback information is output according to the sort, wherein the feedback information with a high weight is output before the feedback information with a low weight, so as to improve the probability that the output feedback information matches the user expectation on the basis of the difficulty of reading the feedback information by the user.
Optionally, on the basis of the foregoing embodiment, in an embodiment of the present application, the more effective information included in the scene information corresponding to the feedback information (or the more information amount included in the scene information corresponding to the feedback information), the higher the weight of the feedback information is, and/or the more effective information included in the intention information corresponding to the feedback information (or the more information amount included in the intention information corresponding to the feedback information), the higher the weight of the feedback information is.
Specifically, in an embodiment of the present application, if there are two feedback information, namely first feedback information and second feedback information, where the number of effective information included in the scene information corresponding to the first feedback information is greater than the number of effective information included in the scene information corresponding to the second feedback information, and the number of effective information included in the intention information corresponding to the first feedback information is less than the number of effective information included in the intention information corresponding to the second feedback information, in an embodiment of the present application, the weight of the second feedback information is greater than the weight of the first feedback information, but the present application does not limit this.
The information processing method will be described below with reference to specific examples. Specifically, the information processing method includes:
acquiring input information of a user;
extracting intention information and scene information in the input information, if the input information comprises a plurality of intention information, the intention information is arranged according to a descending weight order, M times before the intention information can be taken as required during actual use, if the input information comprises a plurality of scene information, the scene information is arranged according to a descending weight order, K times before the intention information and the scene information can be taken as required during actual use, wherein M and K are positive integers not less than 1;
determining user input intentions based on the intention information and the scene information, if a plurality of input intentions exist, the input intentions are arranged in a descending order, and in actual use, the first G input intentions can be taken as required, wherein G is a positive integer not less than 1;
and acquiring and outputting at least one piece of feedback information corresponding to each input intention based on the input intentions of the user, wherein the first S pieces of feedback information can be taken as required in actual use, and S is a positive integer not less than 1.
Specifically, if the user enters "I found Motorola battary in the shopping mall, do you sell A battary? ", M and K are 1, then: the information processing method includes:
extracting each scene information in the input information, selecting the scene information 'found A basic in mall', extracting each intention information in the input information, and selecting the intention information 'if select basic';
determining at least one combination relation based on the scene information and the intention information, and selecting a combination (found A battery in mail, if self battery) from the combination relation;
based on this combination (found Motorola battery in mail, if sel battery), the feedback information "yes, we do sel A battery (yes, we do sell A battery alone)" is obtained and output. If other feedback information is obtained, the feedback information may be output simultaneously or sequentially, which is not limited in this application, and is determined according to the situation.
If The user enters "The cell phone book is book, do you sell A book? (is the mobile phone battery bad, ask for asking for selling a battery: the information processing method includes:
extracting each scene information in the input information, selecting scene information 'battery is browser' from the scene information, extracting each intention information in the input information, and selecting intention information 'if select A bat' from the intention information;
determining at least one combination relation based on the scene information and the intention information, and selecting a combination (style is book, if select A style);
based on the combination (battery is broken, if select battery), feedback information "yes, if you want to buy, please click on the following link http: _ \. If other feedback information is obtained, the feedback information may be output simultaneously or sequentially, which is not limited in this application, and is determined according to the situation.
If the user enters "When I went to the underseground gateway today, my cell phone was out of signal. (I go to basement today, mobile phone does not have signal) ", M and K are 1, then: the information processing method includes:
extracting each scene information in the input information, selecting the scene information 'the underseground gate', extracting each intention information in the input information, and selecting the intention information 'out of signal';
selecting a combination (out of signal) from the at least one combination relation based on the scene information and the intention information;
based on the combination, feedback information "Don't work, it's basic utilization of the underground garage a signal (without worry, probably because the underground garage signal is not good)" is obtained and output. If other feedback information is obtained, the feedback information may be output simultaneously or sequentially, which is not limited in this application, and is determined according to the situation.
Therefore, when feedback information is provided for a user based on user input information, the information processing method provided by the embodiment of the application not only considers intention information included in the input information, but also includes scene information in the input information, so that feedback information is acquired and output based on the whole formed by the intention information in the input information and the scene information, the similarity between the feedback information and an expected answer of the user is improved, the probability of unsmooth or invalid communication is reduced, and the user experience is improved.
It should be noted that, in each of the above embodiments, the input information includes both intention information and scene information as an example, but this is not limited in this application, in other embodiments of the application, the input information may also include only intention information and not include scene information, and if the input information includes only intention information and not includes scene information, the information processing method further includes, after acquiring the user input information: extracting the information of the intention in the input information; and acquiring and outputting the feedback information based on the intention information.
On the basis of the above embodiments, in an embodiment of the present application, the input information may include only one intention information, or may include a plurality of intention information, which is not limited in the present application, as the case may be.
Specifically, in this embodiment of the application, obtaining and outputting the feedback information based on the intention information includes: determining a user input intent based on the intent information; feedback information corresponding to each input intention is acquired and output based on the user input intention.
Similar to the specific implementation of extracting the intention information from the input information, determining the user input intention based on the intention information, and acquiring and outputting the feedback information based on the user intention, the input information includes the scene information and the intention information, and thus, detailed description thereof is omitted.
Correspondingly, the embodiment of the present application further provides an electronic device, which is applied in an intelligent conversation system, wherein the intelligent conversation system is capable of responding to received input information and providing feedback information, as shown in fig. 3, the electronic device includes a memory 10 and a processor 20, wherein the processor 20 is configured to execute a program stored in the memory 10; the memory 10 is intended to store a program for at least:
acquiring user input information, wherein the input information represents that a user expects the intelligent session system to feed back the feedback information;
extracting scene information and intention information in the input information;
and acquiring and outputting the feedback information based on the scene information and the intention information.
On the basis of the above embodiments, in an embodiment of the present application, as shown in fig. 4, the electronic device further includes a display 30, and the display 30 is configured to display the input information and/or the feedback information.
It should be noted that, in the embodiment of the present application, the input information may include one piece of scene information and one piece of intention information, may also include one piece of intention information and at least two pieces of scene information, may also include one piece of scene information and at least two pieces of intention information, or includes at least two pieces of scene information and at least two pieces of intention information, which is not limited in this application as long as the input information includes at least one piece of scene information and at least one piece of intention information.
In the above embodiment, if at least two pieces of scene information are included in the input information, at least part of contents of different pieces of scene information are different. The content of at least part of the different scene information may be the same content of the different scene information, the content of part of the different scene information is different, or the content of all the different scene information is different.
Optionally, in an embodiment of the present application, the input information includes at least two pieces of scene information, and the same intention information and different pieces of scene information correspond to different pieces of feedback information.
In another embodiment of the present application, the input information includes at least two intention information and one scene information, and the intention information different from the same scene information corresponds to different feedback information.
In yet another embodiment of the present application, the input information includes at least two intention information and at least two scene information, and different scene information and different intention information correspond to different feedback information. However, the present application is not limited thereto, as the case may be.
On the basis of any of the above embodiments, in an embodiment of the present application, acquiring and outputting the feedback information based on the scene information and the intention information includes:
determining at least one combined relation based on the scene information and the intention information in the input information, wherein any one combined relation in the at least one combined relation comprises intention information and scene information, and at least one piece of information in the intention information and the scene information which are contained in different combined relations is different;
determining a user input intention corresponding to each combination relation based on each combination relation in the at least one combination relation;
and acquiring and outputting feedback information corresponding to each combination relation based on the user input intention corresponding to each combination relation.
It should be noted that, in the embodiment of the present application, at least one of the intention information and the scenario information included in different combination relationships includes: and the intention information and the scene information contained in different combination relations are different, the intention information and the scene information and the intention information and the scene information contained in different combination relations are different, and the intention information and the scene information contained in different combination relations are different.
On the basis of any of the above embodiments, in an embodiment of the present application, determining at least one combination relationship based on the scene information and the intention information in the input information includes:
and querying a first database based on scene information and intention information in the input information, and determining at least one combined relation.
Specifically, on the basis of the above embodiment, in an embodiment of the present application, as shown in fig. 2, the determining, by the first database, at least one combination relationship based on the scene information and the intention information in the input information includes:
matching each scene information stored in a database by using input information so as to extract the scene information included in the input information;
matching each intention information stored in a database by using input information so as to extract the intention information included in the input information;
and searching a relational network database of the scene information and the intention information based on the scene information and the intention information extracted from the input information so as to determine the combined relation of each scene information and each intention information.
On the basis of the above embodiments, in an embodiment of the present application, any intention information in the input information may form a combined relationship with each scene information in the input information, and any scene information may form a combined relationship with each intention information in the input information. In another embodiment of the present application, the presence of at least one piece of intention information in the input information may form a combined relationship with only a part of the scene information in the input information, and at least one piece of scene information may form a combined relationship with only a part of the intention information in the input information. The present application is not limited thereto, as the case may be.
In another embodiment of the present application, the context information, the intention information, and the relationship between the context information and the intention information are stored together, then in this embodiment, querying the first database based on the context information and the intention information in the input information, and determining at least one combined relationship includes:
querying the first database based on each intention information in the input information, and determining scene information corresponding to each intention information in the first database;
and determining at least one combination relation based on each intention information and the corresponding scene information.
In other embodiments of the present application, other manners may also be adopted, and at least one combination relationship is determined based on the scene information and the intention information in the input information, which is not limited in the present application, and is specifically determined as the case may be.
On the basis of any of the foregoing embodiments, in an embodiment of the present application, determining, based on each combination relationship in the at least one combination relationship, a user input intention corresponding to each combination relationship includes: and continuously querying the first database based on each combination relation in the at least one combination relation, and determining the user input intention corresponding to each combination relation. In another embodiment of the present application, determining, based on each combination relationship of the at least one combination relationship, the user input intention corresponding to the combination relationship includes: and querying the second database based on each combination relation in the at least one combination relation, and determining the user input intention corresponding to each combination relation. In other embodiments of the present application, the user input intention corresponding to each of the at least one combination relationship may also be determined based on each of the at least one combination relationship in other manners, which is not limited in this application, and is determined as the case may be.
On the basis of any of the above embodiments, in an embodiment of the present application, acquiring and outputting feedback information corresponding to each combination relationship based on a user input intention corresponding to each combination relationship includes:
determining the conversation guide corresponding to each combination relation based on the user input intention corresponding to each combination relation;
and acquiring and outputting feedback information corresponding to each combination relation based on the session guidance corresponding to each combination relation.
Optionally, in an embodiment of the present application, determining, based on the user input intention corresponding to each of the combination relationships, a session guide corresponding to each of the combination relationships includes:
based on the user input intention corresponding to each combination relationship, searching a third database, and determining a session guide corresponding to each combination relationship, where the third database includes intention processing policies under each scene, but this application is not limited thereto.
On the basis of the above embodiment, in an embodiment of the present application, the number of user input intentions obtained based on the input information is small, and the number of feedback information that needs to be output based on each user input intention is small, so that all feedback information can be output at one time, and the expected answer of the user is matched to the greatest extent, thereby improving the conversation efficiency; in another embodiment of the present application, the number of the input intentions of the user is obtained based on the input information, the number of the feedback information to be output based on the input intentions of the user is large, only a part of the feedback information may be output at a time, and if the currently output part of the feedback information cannot match the expectation of the user, at least a part of the remaining feedback information is obtained by clicking a trigger operation such as "page turning" or "more" to reduce the difficulty of reading the feedback information by the user.
Optionally, on the basis of the foregoing embodiment, in an embodiment of the present application, the acquiring and outputting the feedback information includes: and N pieces of feedback information are acquired and output at a time, wherein N is a positive integer not less than 1. If the number of the feedback information which needs to be output by each user input intention is not more than N, all the feedback information is output at one time, and if the number of the feedback information which needs to be output by each user input intention is more than N, only N pieces of feedback information are output at one time at most.
On the basis of any one of the above embodiments, in an embodiment of the present application, if the number of feedback information that each user inputs an intention and needs to be output is large, and all feedback information cannot be output at one time, the feedback information is sorted according to the weight of the feedback information from top to bottom, and the feedback information is output according to the sort, wherein the feedback information with a high weight is output before the feedback information with a low weight, so as to improve the probability that the output feedback information matches the user expectation on the basis of the difficulty of reading the feedback information by the user.
Optionally, on the basis of the foregoing embodiment, in an embodiment of the present application, the more effective information included in the scene information corresponding to the feedback information (or the more information amount included in the scene information corresponding to the feedback information), the higher the weight of the feedback information is, and/or the more effective information included in the intention information corresponding to the feedback information (or the more information amount included in the intention information corresponding to the feedback information), the higher the weight of the feedback information is.
Specifically, in an embodiment of the present application, if there are two feedback information, namely first feedback information and second feedback information, where the number of effective information included in the scene information corresponding to the first feedback information is greater than the number of effective information included in the scene information corresponding to the second feedback information, and the number of effective information included in the intention information corresponding to the first feedback information is less than the number of effective information included in the intention information corresponding to the second feedback information, in an embodiment of the present application, the weight of the second feedback information is greater than the weight of the first feedback information, but the present application does not limit this.
The electronic equipment that this application embodiment provided, when providing feedback information for the user based on user input information, not only can consider intention information that includes in the input information, still can include scene information among the input information, thereby based on intention information among the input information with the whole that scene information constitutes goes to obtain and output feedback information, has improved feedback information and the degree of similarity of user's expected answer, and then guide the user to go more smooth carrying on the conversation, and the more quick solves the problem for the user, has reduced the probability of unsmooth or invalid communication, has improved user experience.
In the description, each part is described in a progressive manner, each part is emphasized to be different from other parts, and the same and similar parts among the parts are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. An information processing method applied to an intelligent conversation system, wherein the intelligent conversation system can respond to received input information and provide feedback information, and the method comprises the following steps:
acquiring user input information, wherein the input information represents that a user expects the intelligent session system to feed back the feedback information;
extracting scene information and intention information in the input information;
acquiring and outputting the feedback information based on the scene information and the intention information;
wherein, based on the scene information and the intention information, acquiring and outputting the feedback information comprises:
determining at least one combined relation based on scene information and intention information in the input information, wherein any combined relation in the at least one combined relation comprises one intention information and one scene information, at least one of the intention information and the scene information which are included in different combined relations is different, and intentions expressed by the same intention information in different scene information are different;
determining a user input intention corresponding to each combination relation based on each combination relation in the at least one combination relation;
and acquiring and outputting feedback information corresponding to each combination relation based on the user input intention corresponding to each combination relation.
2. The information processing method according to claim 1, wherein acquiring and outputting the feedback information based on the scene information and the intention information includes:
and acquiring and outputting different feedback information based on the same intention information and different scene information.
3. The information processing method according to claim 1, wherein determining at least one combined relationship based on the scene information and the intention information in the input information comprises:
and querying a first database based on scene information and intention information in the input information, and determining at least one combined relation.
4. The information processing method according to claim 3, wherein the first database is queried based on the scene information and the intention information in the input information, and the determining of the at least one combined relationship comprises:
querying the first database based on each intention information in the input information, and determining scene information corresponding to each intention information in the first database;
and determining at least one combination relation based on each intention information and the corresponding scene information.
5. The information processing method of claim 3, wherein determining, based on each of the at least one combined relationship, the user input intent corresponding to the respective combined relationship comprises:
continuously querying the first database based on each combination relation in the at least one combination relation, and determining a user input intention corresponding to each combination relation;
or the like, or, alternatively,
and querying a second database based on each combination relation in the at least one combination relation, and determining the user input intention corresponding to each combination relation.
6. The processing method according to claim 5, wherein the obtaining and outputting the feedback information corresponding to each combination relationship based on the user input intention corresponding to each combination relationship comprises:
determining the conversation guide corresponding to each combination relation based on the user input intention corresponding to each combination relation;
and acquiring and outputting feedback information corresponding to each combination relation based on the session guidance of each combination relation.
7. The information processing method according to claim 1, wherein if at least two pieces of scene information are included in the input information, contents of different pieces of scene information are at least partially different.
8. An electronic device for use in an intelligent conversational system, the intelligent conversational system being capable of responding to received input information and providing feedback information, the electronic device comprising a memory and a processor, wherein the processor is configured to execute a program stored in the memory; the memory is to store a program to at least:
acquiring user input information, wherein the input information represents that a user expects the intelligent session system to feed back the feedback information;
extracting scene information and intention information in the input information;
acquiring and outputting the feedback information based on the scene information and the intention information;
wherein, based on the scene information and the intention information, acquiring and outputting the feedback information comprises:
determining at least one combined relation based on scene information and intention information in the input information, wherein any combined relation in the at least one combined relation comprises one intention information and one scene information, at least one of the intention information and the scene information which are included in different combined relations is different, and intentions expressed by the same intention information in different scene information are different;
determining a user input intention corresponding to each combination relation based on each combination relation in the at least one combination relation;
and acquiring and outputting feedback information corresponding to each combination relation based on the user input intention corresponding to each combination relation.
9. The electronic device of claim 8, wherein the same scene information with different intention information corresponds to different feedback information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811601059.0A CN109697230B (en) | 2018-12-26 | 2018-12-26 | Information processing method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811601059.0A CN109697230B (en) | 2018-12-26 | 2018-12-26 | Information processing method and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109697230A CN109697230A (en) | 2019-04-30 |
| CN109697230B true CN109697230B (en) | 2021-07-16 |
Family
ID=66232136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811601059.0A Active CN109697230B (en) | 2018-12-26 | 2018-12-26 | Information processing method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109697230B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110929014B (en) * | 2019-12-09 | 2023-05-23 | 联想(北京)有限公司 | Information processing method, information processing device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105930527A (en) * | 2016-06-01 | 2016-09-07 | 北京百度网讯科技有限公司 | Searching method and device |
| CN107992543A (en) * | 2017-11-27 | 2018-05-04 | 上海智臻智能网络科技股份有限公司 | Question and answer exchange method and device, computer equipment and computer-readable recording medium |
-
2018
- 2018-12-26 CN CN201811601059.0A patent/CN109697230B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105930527A (en) * | 2016-06-01 | 2016-09-07 | 北京百度网讯科技有限公司 | Searching method and device |
| CN107992543A (en) * | 2017-11-27 | 2018-05-04 | 上海智臻智能网络科技股份有限公司 | Question and answer exchange method and device, computer equipment and computer-readable recording medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109697230A (en) | 2019-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108595695B (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN104951428B (en) | User's intension recognizing method and device | |
| CN107122369B (en) | Service data processing method, device and system | |
| EP3352094A1 (en) | Image retrieval method and system | |
| CN110765295A (en) | Graph database-based query method and device, computer equipment and storage medium | |
| US9720982B2 (en) | Method and apparatus for natural language search for variables | |
| US20230244862A1 (en) | Form processing method and apparatus, device, and storage medium | |
| CN109697230B (en) | Information processing method and electronic equipment | |
| WO2018001040A1 (en) | Method and device for providing service data, and computer storage medium | |
| CN110086894B (en) | Personnel association information mining method, communication recommendation method and related device | |
| CN107562432A (en) | Information processing method and related product | |
| CN110929014B (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN109120509B (en) | Information collection method and device | |
| CN115563262B (en) | Processing method and related device for dialogue data in machine voice call-out scene | |
| US20220027419A1 (en) | Smart search and recommendation method for content, storage medium, and terminal | |
| CN114970559A (en) | Intelligent response method and device | |
| CN109213937B (en) | Intelligent search method and device | |
| CN111324820B (en) | Inviting method, inviting device, terminal equipment and computer storage medium | |
| CN113191711A (en) | Express delivery sending strategy determining method, device, equipment and storage medium | |
| CN112597287A (en) | Statement processing method, statement processing device and intelligent equipment | |
| CN112182177A (en) | User problem processing method and device, electronic equipment and storage medium | |
| CN111309884A (en) | Robot dialogue method, device, medium, and electronic apparatus | |
| CN111046151A (en) | Message processing method and device | |
| US20240221056A1 (en) | Method and apparatus for presenting search screening items, electronic device, and storage medium | |
| CN116894084A (en) | Customer service method, device, electronic equipment 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |