CN105138671A - Human-computer interaction guiding method and device based on artificial intelligence - Google Patents
Human-computer interaction guiding method and device based on artificial intelligence Download PDFInfo
- Publication number
- CN105138671A CN105138671A CN201510564818.0A CN201510564818A CN105138671A CN 105138671 A CN105138671 A CN 105138671A CN 201510564818 A CN201510564818 A CN 201510564818A CN 105138671 A CN105138671 A CN 105138671A
- Authority
- CN
- China
- Prior art keywords
- topic
- data
- user
- actualite
- associated data
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
-
- 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a human-computer interaction guiding method and device based on artificial intelligence. The method comprises the following steps that S1, interaction information input by a user is received, and a current topic is determined according to the interaction information; S2, multiple to-be-chosen guiding topics which are related to the current topic are obtained on the basis of a topic graph; S3, user image data of the user are obtained; S4, the guiding topic is chosen from the multiple to-be-chosen guiding topics which are related to the current topic according to the user image data and fed back to the user. According to the human-computer interaction guiding method and device based on the artificial intelligence, the current topic is determined by receiving the interaction information input by the user, the multiple to-be-chosen guiding topics which are related to the current topic are obtained on the basis of the topic graph, and then the guiding topic is chosen from the multiple to-be-chosen guiding topics which are related to the current topic by combining the user image data and fed back to the user, so that the sustainability of human-computer interaction is improved, and the human-computer interaction is more fluent and natural.
Description
Technical field
The present invention relates to field of artificial intelligence, particularly relate to a kind of mutual bootstrap technique and device of the man-machine interaction based on artificial intelligence.
Background technology
Artificial intelligence (ArtificialIntelligence) is a branch of computer science, english abbreviation is AI, is research, develops the theory of intelligence for simulating, extending and expand people, method, one of application system new technological sciences.
In traditional interactive process, the position that people has the initiative, machine is in passive position.User initiatively proposes topic, and machine receives and resolves the topic of user's proposition, from the dialogue storehouse set up in advance, select suitable answer to feed back to user; Or machine, by mutual further, specified the topic that user proposes, is carried out reasoning, calculate suitable answer and feed back to user by knowledge base.
But after actualite terminates, machinery requirement continues the next topic waiting for that user proposes, and then answers.Owing to lacking the information of the association between topic, machine cannot continue on one's own initiative or guide the topic made new advances, and cannot carry out mutual constantly, lack initiative and Asn as interpersonal.
Summary of the invention
The present invention is intended to solve one of technical matters in correlation technique at least to a certain extent.For this reason, one object of the present invention is the mutual bootstrap technique proposing a kind of man-machine interaction based on artificial intelligence, can improve the continuation of man-machine interaction, makes man-machine interaction more smooth, natural.
Second object of the present invention is the mutual guiding device proposing a kind of man-machine interaction based on artificial intelligence.
To achieve these goals, first aspect present invention embodiment proposes a kind of mutual bootstrap technique of the man-machine interaction based on artificial intelligence, comprising: the interactive information of S1, reception user input, and according to described interactive information determination actualite; S2, based on topic collection of illustrative plates obtain multiple to be selected guiding topic relevant with described actualite, wherein, described topic collection of illustrative plates comprises the incidence relation between multiple topic and described topic; S3, obtain user's representation data of described user; And S4, select to guide topic from described multiple to be selected guiding topic relevant with described actualite according to described user's representation data, and guide topic described in described user feedback.
The mutual bootstrap technique of the man-machine interaction based on artificial intelligence of the embodiment of the present invention, by receiving the interactive information determination actualite of user's input, and obtain multiple to be selected guiding topic relevant to actualite based on topic collection of illustrative plates, user's representation data again in conjunction with user is selected to guide topic from guiding topic to be selected, and guide topic to user feedback, improve the continuation of man-machine interaction, make man-machine interaction more smooth, natural.
Second aspect present invention embodiment proposes a kind of mutual guiding device of the man-machine interaction based on artificial intelligence, comprising: determination module, for receiving the interactive information of user's input, and according to described interactive information determination actualite; Obtain module, for obtaining multiple to be selected guiding topic relevant with described actualite based on topic collection of illustrative plates, wherein, described topic collection of illustrative plates comprises the incidence relation between multiple topic and described topic; Acquisition module, for obtaining user's representation data of described user; And feedback module, for selecting to guide topic from described multiple to be selected guiding topic relevant with described actualite according to described user's representation data, and guide topic described in described user feedback.
The mutual guiding device of the man-machine interaction based on artificial intelligence of the embodiment of the present invention, by receiving the interactive information determination actualite of user's input, and obtain multiple to be selected guiding topic relevant to actualite based on topic collection of illustrative plates, user's representation data again in conjunction with user is selected to guide topic from guiding topic to be selected, and guide topic to user feedback, improve the continuation of man-machine interaction, make man-machine interaction more smooth, natural.
Accompanying drawing explanation
Fig. 1 is according to an embodiment of the invention based on the process flow diagram of the mutual bootstrap technique of the man-machine interaction of artificial intelligence.
Fig. 2 is the effect schematic diagram of topic collection of illustrative plates according to an embodiment of the invention.
Fig. 3 is effect schematic diagram when network text data is semi-structured data according to an embodiment of the invention.
Fig. 4 is effect schematic diagram when network text data is structural data according to an embodiment of the invention.
Fig. 5 is the effect schematic diagram obtaining user browsing behavior data according to an embodiment of the invention.
Fig. 6 is the effect schematic diagram setting up topic collection of illustrative plates according to an embodiment of the invention.
Fig. 7 is according to an embodiment of the invention based on the structural representation one of the mutual guiding device of the man-machine interaction of artificial intelligence.
Fig. 8 is according to an embodiment of the invention based on the structural representation two of the mutual guiding device of the man-machine interaction of artificial intelligence.
Embodiment
Be described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar module or has module that is identical or similar functions from start to finish.Be exemplary below by the embodiment be described with reference to the drawings, be intended to for explaining the present invention, and can not limitation of the present invention be interpreted as.
Below with reference to the accompanying drawings mutual bootstrap technique and the device of the man-machine interaction based on artificial intelligence of the embodiment of the present invention are described.
Fig. 1 is according to an embodiment of the invention based on the process flow diagram of the mutual bootstrap technique of the man-machine interaction of artificial intelligence.
As shown in Figure 1, the mutual bootstrap technique based on the man-machine interaction of artificial intelligence can comprise:
The interactive information of S1, reception user input, and according to interactive information determination actualite.
Particularly, first can receive the interactive information of user's input such as: " stealing dream space good-looking? ", then demand identification and correlation calculations are carried out to this interactive information, thus determine that actualite is " stealing dream evaluation space ".
S2, based on topic collection of illustrative plates obtain multiple to be selected guiding topic relevant to actualite.
Wherein, topic collection of illustrative plates can comprise the incidence relation between multiple topic and topic.
Particularly, multiple to be selected guiding topic relevant to actualite can be obtained based on the topic collection of illustrative plates set up in advance.Such as: actualite is " stealing dream evaluation space ", then can obtain multiple guiding topic relevant to " stealing dream evaluation space " as " film that Nolan directs ", " film that Leonardo is acted the leading role " etc. according to topic collection of illustrative plates, and the incidence relation between they and " stealing dream evaluation space ".
User's representation data of S3, acquisition user.
Wherein, user's representation data is the set of the data such as attribute, state, interest of user, initiatively input by user or obtain according to the history intersection record of user, then it being integrated, thus generating the user's representation data about the personalization of user.
S4, according to user's representation data select from multiple guiding topic to be selected relevant to actualite guide topic, and to user feedback guide topic.
Particularly, the intent information of user can be determined according to the contextual information of user's representation data and interactive information, then select to guide topic from multiple guiding topic to be selected relevant to actualite according to the intent information of user, and guide topic to user feedback.
For example, guiding topic can be the extension of actualite.Such as: interactive information for " how chicken is cooked? ", then actualite can be " way of chicken ".After actualite terminates alternately, can extend actualite, in conjunction with user's representation data as " user is pregnant woman ", then can guide topic " it is relatively good how pregnant woman eats chicken " to user feedback.
Certainly, guiding topic also can be the recommendation based on actualite.Such as: interactive information be " steal dream space good-looking? ", then actualite can be " stealing dream evaluation space ".After actualite terminates alternately, based on actualite, and in conjunction with user's representation data as " user likes seeing a film ", then can guide topic " film of Nolan " to user feedback.
And when the intent information of user cannot be determined according to the contextual information of user's representation data and interactive information, then need to clarify the intent information of user.Such as: interactive information for " how to get to removing the Forbidden City? " and Beijing, Shenyang and the Taibei have " the Forbidden City ", therefore need to clarify the intent information of user, can according to interactive information to user return intention clarification question sentence " may I ask you and will remove which the Forbidden City? "
In addition, before step S2, the mutual bootstrap technique based on the man-machine interaction of artificial intelligence also can comprise step S5.
S5, set up topic collection of illustrative plates.
As shown in Figure 2, a node in topic collection of illustrative plates represents the topic that user proposes or a demand, the reply that can include corresponding topic in each node and the resource of meeting consumers' demand, and associate by limit between related node, thus the webbed topic collection of illustrative plates of shape.
Particularly, the method setting up topic collection of illustrative plates is as follows: can obtain topic associated data, then sets up topic collection of illustrative plates according to topic associated data.
More specifically, obtain topic associated data and can be divided into two kinds of situations.
The first situation: first can obtain network text data, and from network text data, obtain topic associated data.Wherein, network text data can be divided into unstructured data, semi-structured data and structural data.
When network text data is unstructured data, topic associated data can be obtained based on entity extraction and syntactic analysis.Wherein, unstructured data can comprise news, forum, blog, video etc.Such as: for network text data, " the flowers are in blossom master for the Nobel prize in literature attracted most attention, and Frenchman's Modiano becomes new lucky man.Certainly, repeatedly to nominate in the village that always encourages with promise and narrowly miss the spring tree or that " encourage nearest people from promise ".China poet Bei Dao, also just allows compatriots fanatic one time.", entity information " Nobel prize in literature ", " Frenchman's Modiano ", " in village, the spring sets ", " Chinese poet Bei Dao " can be extracted based on entity extraction technology, and know to there is association between above-mentioned entity information based on syntactic analysis.Further, also can analyze Frenchman's Modiano is Nobel Prize for literature, in village the spring tree and Chinese poet Bei Dao there is no Nobel prize in literature etc.
When network text data is semi-structured data, obtain topic associated data based on page layout analysis, tag extraction, Entity recognition.Wherein, semi-structured data can comprise the encyclopaedia such as wikipedia, Baidupedia data, or thematic data etc.Such as: as shown in Figure 3, can based on page layout analysis, tag extraction, Entity recognition, " living after the match " of obtaining " De Yuekeweiqi " comprises " family life " and " charitable activity ".
When network text data is structural data, from knowledge mapping, obtain topic associated data.Wherein, structural data can comprise knowledge mapping data.Such as: as shown in Figure 4, the director of film " steal dream space " and film " interspace pass through " be " Christoffer. Nolan ".
The second situation: search behavior data or the navigation patterns data that first can obtain user, then according to search behavior data or navigation patterns data genaration topic associated data.
Particularly, the search behavior data of user can be obtained, and the object search corresponding according to search behavior data acquisition, then generate topic associated data according to object search.Such as: user searched for continuously " Nolan ", " film of Nolan " and " Christian. Bel ", then can associate above-mentioned topic, thus generate topic associated data.
Certainly, also can obtain the navigation patterns data of user, and according to navigation patterns data acquisition corresponding browse object, generate topic associated data according to browsing object.Such as: as shown in Figure 5, the multiple news clicked when user can be browsed webpage or video associate, thus generate topic associated data.
After acquisition topic associated data, by one or more in RandomWalk algorithm, association analysis algorithm, collaborative filtering, set up topic collection of illustrative plates according to topic associated data.For example, as shown in Figure 6, q1, q2, q3 and q1 ', q2 ', q3 ', q4 ' they are topic, d1, d2, d3 and d4 are resource data.As can be known from Fig. 6, resource data d1 and d2 is associated with topic q1; Resource data d1, d2, d3 are associated with topic q2; Resource data d4 is associated with topic q3, has between the topic of incidence relation and resource data and is connected with solid line.Iterative computation can go out between topic q1 and resource data d3 there is incidence relation based on RandomWalk algorithm, be connected with dotted line between them.And topic q1 ' is for user is after having browsed resource data d1 or d4, according to the topic that resource data d1 or d4 sends, the incidence relation between them has ordinal relation.In like manner, topic q2 ' is the topic sent according to resource data d2, and topic q3 ' is the topic sent according to resource data d2 or d3, and topic q4 ' is the topic sent according to resource data d3 or d4.Further, can derive topic q1 and topic q1 ' has incidence relation, topic q1 and topic q2 ' has incidence relation etc., the final topic collection of illustrative plates set up as shown in Figure 2.
The mutual bootstrap technique of the man-machine interaction based on artificial intelligence of the embodiment of the present invention, by receiving the interactive information determination actualite of user's input, and obtain multiple to be selected guiding topic relevant to actualite based on topic collection of illustrative plates, user's representation data again in conjunction with user is selected to guide topic from guiding topic to be selected, and guide topic to user feedback, improve the continuation of man-machine interaction, make man-machine interaction more smooth, natural.
For achieving the above object, the present invention also proposes a kind of mutual guiding device of the man-machine interaction based on artificial intelligence.
Fig. 7 is according to an embodiment of the invention based on the structural representation one of the mutual guiding device of the man-machine interaction of artificial intelligence.
As shown in Figure 7, can should comprise based on the mutual guiding device of the man-machine interaction of artificial intelligence: determination module 110, acquisition module 120, acquisition module 130 and feedback module 140.
The interactive information that determination module 110 inputs for receiving user, and according to interactive information determination actualite.
Particularly, determination module 110 first can receive the interactive information of user's input such as: " stealing dream space good-looking? ", then demand identification and correlation calculations are carried out to this interactive information, thus determine that actualite is " stealing dream evaluation space ".
Obtain module 120 for obtaining multiple to be selected guiding topic relevant to actualite based on topic collection of illustrative plates.
Wherein, topic collection of illustrative plates can comprise the incidence relation between multiple topic and topic.
Particularly, obtain module 120 and can obtain multiple to be selected guiding topic relevant to actualite based on the topic collection of illustrative plates set up in advance.Such as: actualite is " stealing dream evaluation space ", then can obtain multiple guiding topic relevant to " stealing dream evaluation space " as " film that Nolan directs ", " film that Leonardo is acted the leading role " etc. according to topic collection of illustrative plates, and the incidence relation between they and " stealing dream evaluation space ".
Acquisition module 130 is for obtaining user's representation data of user.
Wherein, user's representation data is the set of the data such as attribute, state, interest of user, initiatively input by user or obtain according to the history intersection record of user, then it being integrated, thus generating the user's representation data about the personalization of user.
Feedback module 140 guides topic for selecting from multiple guiding topic to be selected relevant to actualite according to user's representation data, and guides topic to user feedback.
Particularly, feedback module 140 can determine the intent information of user according to the contextual information of user's representation data and interactive information, then select to guide topic from multiple guiding topic to be selected relevant to actualite according to the intent information of user, and guide topic to user feedback.
For example, guiding topic can be the extension of actualite.Such as: interactive information for " how chicken is cooked? ", then actualite can be " way of chicken ".After actualite terminates alternately, can extend actualite, in conjunction with user's representation data as " user is pregnant woman ", then can guide topic " it is relatively good how pregnant woman eats chicken " to user feedback.
Certainly, guiding topic also can be the recommendation based on actualite.Such as: interactive information be " steal dream space good-looking? ", then actualite can be " stealing dream evaluation space ".After actualite terminates alternately, based on actualite, and in conjunction with user's representation data as " user likes seeing a film ", then can guide topic " film of Nolan " to user feedback.
And when the intent information of user cannot be determined according to the contextual information of user's representation data and interactive information, then need to clarify the intent information of user.Such as: interactive information for " how to get to removing the Forbidden City? " and Beijing, Shenyang and the Taibei have " the Forbidden City ", therefore need to clarify the intent information of user, can according to interactive information to user return intention clarification question sentence " may I ask you and will remove which the Forbidden City? "
In addition, as shown in Figure 8, the mutual guiding device of the man-machine interaction based on artificial intelligence of the embodiment of the present invention also can comprise and sets up module 150.
Set up module 150 for setting up topic collection of illustrative plates.
As shown in Figure 2, a node in topic collection of illustrative plates represents the topic that user proposes or a demand, the reply that can include corresponding topic in each node and the resource of meeting consumers' demand, and associate by limit between related node, thus the webbed topic collection of illustrative plates of shape.
Particularly, set up module 150 comprise acquiring unit 151 and set up unit 152.
Acquiring unit 151 can obtain topic associated data.
Acquiring unit 151 obtains topic associated data can be divided into two kinds of situations.
The first situation: first can obtain network text data, and from network text data, obtain topic associated data.Wherein, network text data can be divided into unstructured data, semi-structured data and structural data.
When network text data is unstructured data, topic associated data can be obtained based on entity extraction and syntactic analysis.Wherein, unstructured data can comprise news, forum, blog, video etc.Such as: for network text data, " the flowers are in blossom master for the Nobel prize in literature attracted most attention, and Frenchman's Modiano becomes new lucky man.Certainly, repeatedly to nominate in the village that always encourages with promise and narrowly miss the spring tree or that " encourage nearest people from promise ".China poet Bei Dao, also just allows compatriots fanatic one time.", entity information " Nobel prize in literature ", " Frenchman's Modiano ", " in village, the spring sets ", " Chinese poet Bei Dao " can be extracted based on entity extraction technology, and know to there is association between above-mentioned entity information based on syntactic analysis.Further, also can analyze Frenchman's Modiano is Nobel Prize for literature, in village the spring tree and Chinese poet Bei Dao there is no Nobel prize in literature etc.
When network text data is semi-structured data, obtain topic associated data based on page layout analysis, tag extraction, Entity recognition.Wherein, semi-structured data can comprise the encyclopaedia such as wikipedia, Baidupedia data, or thematic data etc.Such as: as shown in Figure 3, can based on page layout analysis, tag extraction, Entity recognition, " living after the match " of obtaining " De Yuekeweiqi " comprises " family life " and " charitable activity ".
When network text data is structural data, from knowledge mapping, obtain topic associated data.Wherein, structural data can comprise knowledge mapping data.Such as: as shown in Figure 4, the director of film " steal dream space " and film " interspace pass through " be " Christoffer. Nolan ".
The second situation: the behavioral data that first can obtain user, then generates topic associated data according to behavioral data.Wherein, behavioral data can comprise search behavior data and navigation patterns data.
Particularly, the search behavior data of user can be obtained, and the object search corresponding according to search behavior data acquisition, then generate topic associated data according to object search.Such as: user searched for continuously " Nolan ", " film of Nolan " and " Christian. Bel ", then can associate above-mentioned topic, thus generate topic associated data.
Certainly, also can obtain the navigation patterns data of user, and according to navigation patterns data acquisition corresponding browse object, generate topic associated data according to browsing object.Such as: as shown in Figure 5, the multiple news clicked when user can be browsed webpage or video associate, thus generate topic associated data.
After acquiring unit 151 obtains topic associated data, set up unit 152 by one or more in RandomWalk algorithm, association analysis algorithm, collaborative filtering, set up topic collection of illustrative plates according to topic associated data.
For example, as shown in Figure 6, q1, q2, q3 and q1 ', q2 ', q3 ', q4 ' they are topic, d1, d2, d3 and d4 are resource data.As can be known from Fig. 6, resource data d1 and d2 is associated with topic q1; Resource data d1, d2, d3 are associated with topic q2; Resource data d4 is associated with topic q3, has between the topic of incidence relation and resource data and is connected with solid line.Iterative computation can go out between topic q1 and resource data d3 there is incidence relation based on RandomWalk algorithm, be connected with dotted line between them.And topic q1 ' is for user is after having browsed resource data d1 or d4, according to the topic that resource data d1 or d4 sends, the incidence relation between them has ordinal relation.In like manner, topic q2 ' is the topic sent according to resource data d2, and topic q3 ' is the topic sent according to resource data d2 or d3, and topic q4 ' is the topic sent according to resource data d3 or d4.Further, can derive topic q1 and topic q1 ' has incidence relation, topic q1 and topic q2 ' has incidence relation etc., the final topic collection of illustrative plates set up as shown in Figure 2.
The mutual guiding device of the man-machine interaction based on artificial intelligence of the embodiment of the present invention, by receiving the interactive information determination actualite of user's input, and obtain multiple to be selected guiding topic relevant to actualite based on topic collection of illustrative plates, user's representation data again in conjunction with user is selected to guide topic from guiding topic to be selected, and guide topic to user feedback, improve the continuation of man-machine interaction, make man-machine interaction more smooth, natural.
In the present invention, term " first ", " second " only for describing object, and can not be interpreted as instruction or hint relative importance or imply the quantity indicating indicated technical characteristic.Thus, be limited with " first ", the feature of " second " can express or impliedly comprise at least one this feature.In describing the invention, the implication of " multiple " is at least two, such as two, three etc., unless otherwise expressly limited specifically.
In this manual, to the schematic representation of above-mentioned term not must for be identical embodiment or example.And the specific features of description or feature can combine in one or more embodiment in office or example in an appropriate manner.In addition, when not conflicting, the feature of the different embodiment described in this instructions or example and different embodiment or example can carry out combining and combining by those skilled in the art.
Although illustrate and describe embodiments of the invention above, be understandable that, above-described embodiment is exemplary, can not be interpreted as limitation of the present invention, and those of ordinary skill in the art can change above-described embodiment within the scope of the invention, revises, replace and modification.
Claims (16)
1., based on a mutual bootstrap technique for the man-machine interaction of artificial intelligence, it is characterized in that, comprise the following steps:
The interactive information of S1, reception user input, and according to described interactive information determination actualite;
S2, based on topic collection of illustrative plates obtain multiple to be selected guiding topic relevant with described actualite, wherein, described topic collection of illustrative plates comprises the incidence relation between multiple topic and described topic;
S3, obtain user's representation data of described user; And
S4, select to guide topic according to described user's representation data from described multiple guiding topic to be selected relevant with described actualite, and guide topic described in described user feedback.
2. the method for claim 1, is characterized in that, before described step S2, also comprises:
S5, set up described topic collection of illustrative plates.
3. method as claimed in claim 2, it is characterized in that, described step S5 specifically comprises:
Obtain topic associated data; And
Described topic collection of illustrative plates is set up according to described topic associated data.
4. method as claimed in claim 3, it is characterized in that, described acquisition topic associated data, specifically comprises:
Obtain network text data;
When described network text data is unstructured data, obtain described topic associated data based on entity extraction and syntactic analysis; Or
When described network text data is semi-structured data, obtain described topic associated data based on page layout analysis, tag extraction, Entity recognition; Or
When described network text data is structural data, from knowledge mapping, obtain described topic associated data.
5. method as claimed in claim 3, it is characterized in that, described acquisition topic associated data, comprising:
Obtain the search behavior data of described user, and the object search corresponding according to described search behavior data acquisition, and generate described topic associated data according to described object search; Or
Obtain the navigation patterns data of described user, and according to described navigation patterns data acquisition corresponding browse object, generate described topic associated data according to described object of browsing.
6. method as claimed in claim 3, is characterized in that, describedly sets up described topic collection of illustrative plates according to described topic associated data, specifically comprises:
By one or more in RandomWalk algorithm, association analysis algorithm, collaborative filtering, set up described topic collection of illustrative plates according to described topic associated data.
7. the method for claim 1, is characterized in that, described according to described interactive information determination actualite, specifically comprises:
Demand identification and correlation calculations are carried out to determine described actualite to described interactive information.
8. the method for claim 1, is characterized in that, described step S4 specifically comprises:
The intent information of described user is determined according to the contextual information of described user's representation data and described interactive information;
Intent information according to described user is selected to guide topic from described multiple guiding topic to be selected relevant with described actualite, and guides topic described in described user feedback.
9., based on a mutual guiding device for the man-machine interaction of artificial intelligence, it is characterized in that, comprising:
Determination module, for receiving the interactive information of user's input, and according to described interactive information determination actualite;
Obtain module, for obtaining multiple to be selected guiding topic relevant with described actualite based on topic collection of illustrative plates, wherein, described topic collection of illustrative plates comprises the incidence relation between multiple topic and described topic;
Acquisition module, for obtaining user's representation data of described user; And
Feedback module, for selecting to guide topic from described multiple to be selected guiding topic relevant with described actualite according to described user's representation data, and guides topic described in described user feedback.
10. device as claimed in claim 9, is characterized in that, also comprise:
Set up module, for setting up described topic collection of illustrative plates.
11. devices as claimed in claim 10, is characterized in that, describedly set up module, specifically comprise:
Acquiring unit, for obtaining topic associated data; And
Set up unit, for setting up described topic collection of illustrative plates according to described topic associated data.
12. devices as claimed in claim 11, is characterized in that, described acquiring unit, specifically for:
Obtain network text data;
When described network text data is unstructured data, obtain described topic associated data based on entity extraction and syntactic analysis; Or
When described network text data is semi-structured data, obtain described topic associated data based on page layout analysis, tag extraction, Entity recognition; Or
When described network text data is structural data, from knowledge mapping, obtain described topic associated data.
13. devices as claimed in claim 11, is characterized in that, described acquiring unit, specifically for:
Obtain the search behavior data of described user, and the object search corresponding according to described search behavior data acquisition, and generate described topic associated data according to described object search; Or
Obtain the navigation patterns data of described user, and according to described navigation patterns data acquisition corresponding browse object, generate described topic associated data according to described object of browsing.
14. devices as claimed in claim 11, is characterized in that, describedly set up unit, specifically for:
By one or more in RandomWalk algorithm, association analysis algorithm, collaborative filtering, set up described topic collection of illustrative plates according to described topic associated data.
15. devices as claimed in claim 9, is characterized in that, described determination module, specifically for:
Demand identification and correlation calculations are carried out to determine described actualite to described interactive information.
16. devices as claimed in claim 9, is characterized in that, described feedback module, specifically for:
The intent information of described user is determined according to the contextual information of described user's representation data and described interactive information, and select to guide topic from described multiple to be selected guiding topic relevant with described actualite according to the intent information of described user, and guide topic described in described user feedback.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510564818.0A CN105138671A (en) | 2015-09-07 | 2015-09-07 | Human-computer interaction guiding method and device based on artificial intelligence |
| PCT/CN2015/096339 WO2017041369A1 (en) | 2015-09-07 | 2015-12-03 | Man-machine interaction guiding method and device based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510564818.0A CN105138671A (en) | 2015-09-07 | 2015-09-07 | Human-computer interaction guiding method and device based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105138671A true CN105138671A (en) | 2015-12-09 |
Family
ID=54724018
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510564818.0A Pending CN105138671A (en) | 2015-09-07 | 2015-09-07 | Human-computer interaction guiding method and device based on artificial intelligence |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105138671A (en) |
| WO (1) | WO2017041369A1 (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701208A (en) * | 2016-01-13 | 2016-06-22 | 北京光年无限科技有限公司 | Questions and answers evaluation method and device for questions and answers system |
| CN106448670A (en) * | 2016-10-21 | 2017-02-22 | 竹间智能科技（上海）有限公司 | Dialogue automatic reply system based on deep learning and reinforcement learning |
| CN106557410A (en) * | 2016-10-25 | 2017-04-05 | 北京百度网讯科技有限公司 | User behavior analysis method and apparatus based on artificial intelligence |
| CN106559321A (en) * | 2016-12-01 | 2017-04-05 | 竹间智能科技（上海）有限公司 | The method and system of dynamic adjustment dialog strategy |
| CN106599179A (en) * | 2016-12-13 | 2017-04-26 | 竹间智能科技（上海）有限公司 | Method and device for controlling man-machine conversation based on fusion of knowledge graph and memory graph |
| CN106777364A (en) * | 2017-01-22 | 2017-05-31 | 竹间智能科技（上海）有限公司 | Artificial intelligence response method and device that topic drives |
| CN106843461A (en) * | 2016-12-13 | 2017-06-13 | 北京光年无限科技有限公司 | A kind of interactive output intent and robot for robot |
| CN107025278A (en) * | 2017-03-27 | 2017-08-08 | 竹间智能科技（上海）有限公司 | Based on interactive user portrait extraction method and device |
| CN107391512A (en) * | 2016-05-17 | 2017-11-24 | 北京邮电大学 | The method and apparatus of knowledge mapping prediction |
| CN107833082A (en) * | 2017-09-15 | 2018-03-23 | 广州唯品会研究院有限公司 | A kind of recommendation method and apparatus of commodity picture |
| CN107967308A (en) * | 2017-11-16 | 2018-04-27 | 百度在线网络技术（北京）有限公司 | A kind of processing method of intelligent interaction, device, equipment and computer-readable storage medium |
| CN108108340A (en) * | 2017-11-28 | 2018-06-01 | 北京光年无限科技有限公司 | For the dialogue exchange method and system of intelligent robot |
| CN108197189A (en) * | 2017-12-26 | 2018-06-22 | 上海科大讯飞信息科技有限公司 | Active exchange method and device |
| CN108415932A (en) * | 2018-01-23 | 2018-08-17 | 苏州思必驰信息科技有限公司 | Interactive method and electronic equipment |
| CN108804603A (en) * | 2018-05-29 | 2018-11-13 | 北京灵智优诺科技有限公司 | Man-machine written dialogue method and system, server, medium |
| CN109002477A (en) * | 2018-06-19 | 2018-12-14 | 深圳市元征科技股份有限公司 | Information processing method, device, terminal and medium |
| CN109683727A (en) * | 2018-12-26 | 2019-04-26 | 联想(北京)有限公司 | A kind of data processing method and device |
| CN109783733A (en) * | 2019-01-15 | 2019-05-21 | 三角兽（北京）科技有限公司 | User's portrait generating means and method, information processing unit and storage medium |
| CN111046160A (en) * | 2019-12-16 | 2020-04-21 | 联想(北京)有限公司 | Interaction method, interaction device and computer system |
| CN111177339A (en) * | 2019-12-06 | 2020-05-19 | 百度在线网络技术（北京）有限公司 | Dialog generation method and device, electronic equipment and storage medium |
| WO2022048170A1 (en) * | 2020-09-02 | 2022-03-10 | 平安科技（深圳）有限公司 | Method and apparatus for conducting human-machine conversation, computer device, and storage medium |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110704596B (en) * | 2019-09-29 | 2023-03-31 | 北京百度网讯科技有限公司 | Topic-based conversation method and device and electronic equipment |
| CN111427993A (en) * | 2019-11-15 | 2020-07-17 | 西安海的电子科技有限公司 | Multi-conversation implementation method based on android system |
| CN112163085A (en) * | 2020-10-30 | 2021-01-01 | 珠海格力电器股份有限公司 | Method and device for interaction of companion robot, storage medium and electronic device |
| CN114331789B (en) * | 2022-03-07 | 2022-06-24 | 联通高新大数据人工智能科技(成都)有限公司 | Intelligent cheap and clean knowledge recommendation method, device, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1435781A (en) * | 2003-02-24 | 2003-08-13 | 杨炳儒 | Intelligent decision supporting configuration method based on information excavation |
| CN102184262A (en) * | 2011-06-15 | 2011-09-14 | 悠易互通（北京）广告有限公司 | Web-based text classification mining system and web-based text classification mining method |
| CN102456018A (en) * | 2010-10-18 | 2012-05-16 | 腾讯科技（深圳）有限公司 | Interactive search method and device |
| CN102866990A (en) * | 2012-08-20 | 2013-01-09 | 北京搜狗信息服务有限公司 | Thematic conversation method and device |
| CN103000052A (en) * | 2011-09-16 | 2013-03-27 | 上海先先信息科技有限公司 | Man-machine interactive spoken dialogue system and realizing method thereof |
| US8423580B2 (en) * | 2008-04-16 | 2013-04-16 | Tomasz Wojcicki | System and method for specifying and implementing IT systems |
| CN103577579A (en) * | 2013-11-08 | 2014-02-12 | 南方电网科学研究院有限责任公司 | Resource recommendation method and system based on potential demands of users |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110295688A1 (en) * | 2010-05-28 | 2011-12-01 | Microsoft Corporation | Defining user intent |
| CN102063453A (en) * | 2010-05-31 | 2011-05-18 | 百度在线网络技术（北京）有限公司 | Method and device for searching based on demands of user |
| US10685065B2 (en) * | 2012-03-17 | 2020-06-16 | Haizhi Wangju Network Technology (Beijing) Co., Ltd. | Method and system for recommending content to a user |
| CN102831220B (en) * | 2012-08-23 | 2015-01-07 | 江苏物联网研究发展中心 | Subject-oriented customized news information extraction system |
| CN103226569A (en) * | 2013-03-21 | 2013-07-31 | 天脉聚源(北京)传媒科技有限公司 | Video providing method, device and system |
-
2015
- 2015-09-07 CN CN201510564818.0A patent/CN105138671A/en active Pending
- 2015-12-03 WO PCT/CN2015/096339 patent/WO2017041369A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1435781A (en) * | 2003-02-24 | 2003-08-13 | 杨炳儒 | Intelligent decision supporting configuration method based on information excavation |
| US8423580B2 (en) * | 2008-04-16 | 2013-04-16 | Tomasz Wojcicki | System and method for specifying and implementing IT systems |
| CN102456018A (en) * | 2010-10-18 | 2012-05-16 | 腾讯科技（深圳）有限公司 | Interactive search method and device |
| CN102184262A (en) * | 2011-06-15 | 2011-09-14 | 悠易互通（北京）广告有限公司 | Web-based text classification mining system and web-based text classification mining method |
| CN103000052A (en) * | 2011-09-16 | 2013-03-27 | 上海先先信息科技有限公司 | Man-machine interactive spoken dialogue system and realizing method thereof |
| CN102866990A (en) * | 2012-08-20 | 2013-01-09 | 北京搜狗信息服务有限公司 | Thematic conversation method and device |
| CN103577579A (en) * | 2013-11-08 | 2014-02-12 | 南方电网科学研究院有限责任公司 | Resource recommendation method and system based on potential demands of users |
Non-Patent Citations (3)
| Title |
|---|
| 人民日报社: "《融合元年 中国媒体融合发展年度报告 2014》", 30 June 2015, 人民日报出版社 * |
| 李东进，秦勇，朴世桓: "《网络营销》", 31 August 2015, 中国发展出版社 * |
| 田萍芳: "《面向云出版的语义关键技术》", 30 April 2015, 武汉大学出版社 * |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701208B (en) * | 2016-01-13 | 2018-11-30 | 北京光年无限科技有限公司 | A kind of question and answer evaluation method and device towards question answering system |
| CN105701208A (en) * | 2016-01-13 | 2016-06-22 | 北京光年无限科技有限公司 | Questions and answers evaluation method and device for questions and answers system |
| CN107391512A (en) * | 2016-05-17 | 2017-11-24 | 北京邮电大学 | The method and apparatus of knowledge mapping prediction |
| CN107391512B (en) * | 2016-05-17 | 2021-05-11 | 北京邮电大学 | Method and device for predicting knowledge graph |
| CN106448670A (en) * | 2016-10-21 | 2017-02-22 | 竹间智能科技（上海）有限公司 | Dialogue automatic reply system based on deep learning and reinforcement learning |
| CN106448670B (en) * | 2016-10-21 | 2019-11-19 | 竹间智能科技（上海）有限公司 | Conversational system is automatically replied based on deep learning and intensified learning |
| CN106557410A (en) * | 2016-10-25 | 2017-04-05 | 北京百度网讯科技有限公司 | User behavior analysis method and apparatus based on artificial intelligence |
| CN106557410B (en) * | 2016-10-25 | 2019-05-31 | 北京百度网讯科技有限公司 | User behavior analysis method and apparatus based on artificial intelligence |
| CN106559321A (en) * | 2016-12-01 | 2017-04-05 | 竹间智能科技（上海）有限公司 | The method and system of dynamic adjustment dialog strategy |
| CN106599179A (en) * | 2016-12-13 | 2017-04-26 | 竹间智能科技（上海）有限公司 | Method and device for controlling man-machine conversation based on fusion of knowledge graph and memory graph |
| CN106843461A (en) * | 2016-12-13 | 2017-06-13 | 北京光年无限科技有限公司 | A kind of interactive output intent and robot for robot |
| CN106599179B (en) * | 2016-12-13 | 2020-02-14 | 竹间智能科技（上海）有限公司 | Man-machine conversation control method and device integrating knowledge graph and memory graph |
| CN106777364A (en) * | 2017-01-22 | 2017-05-31 | 竹间智能科技（上海）有限公司 | Artificial intelligence response method and device that topic drives |
| CN107025278A (en) * | 2017-03-27 | 2017-08-08 | 竹间智能科技（上海）有限公司 | Based on interactive user portrait extraction method and device |
| CN107833082B (en) * | 2017-09-15 | 2022-04-12 | 唯品会(海南)电子商务有限公司 | Commodity picture recommendation method and device |
| CN107833082A (en) * | 2017-09-15 | 2018-03-23 | 广州唯品会研究院有限公司 | A kind of recommendation method and apparatus of commodity picture |
| US11308948B2 (en) | 2017-11-16 | 2022-04-19 | Baidu Online Network Technology (Beijing) Co., Ltd. | Intelligent interaction processing method and apparatus, device and computer storage medium |
| CN107967308A (en) * | 2017-11-16 | 2018-04-27 | 百度在线网络技术（北京）有限公司 | A kind of processing method of intelligent interaction, device, equipment and computer-readable storage medium |
| CN108108340B (en) * | 2017-11-28 | 2021-07-23 | 北京光年无限科技有限公司 | Dialogue interaction method and system for intelligent robot |
| CN108108340A (en) * | 2017-11-28 | 2018-06-01 | 北京光年无限科技有限公司 | For the dialogue exchange method and system of intelligent robot |
| CN108197189B (en) * | 2017-12-26 | 2020-07-28 | 上海科大讯飞信息科技有限公司 | Active interaction method and device |
| CN108197189A (en) * | 2017-12-26 | 2018-06-22 | 上海科大讯飞信息科技有限公司 | Active exchange method and device |
| CN108415932A (en) * | 2018-01-23 | 2018-08-17 | 苏州思必驰信息科技有限公司 | Interactive method and electronic equipment |
| CN108804603B (en) * | 2018-05-29 | 2021-07-23 | 北京灵智优诺科技有限公司 | Man-machine written dialogue method and system, server and medium |
| CN108804603A (en) * | 2018-05-29 | 2018-11-13 | 北京灵智优诺科技有限公司 | Man-machine written dialogue method and system, server, medium |
| CN109002477A (en) * | 2018-06-19 | 2018-12-14 | 深圳市元征科技股份有限公司 | Information processing method, device, terminal and medium |
| CN109002477B (en) * | 2018-06-19 | 2022-04-12 | 深圳市元征科技股份有限公司 | Information processing method, device, terminal and medium |
| CN109683727A (en) * | 2018-12-26 | 2019-04-26 | 联想(北京)有限公司 | A kind of data processing method and device |
| CN109683727B (en) * | 2018-12-26 | 2021-07-16 | 联想(北京)有限公司 | Data processing method and device |
| CN109783733A (en) * | 2019-01-15 | 2019-05-21 | 三角兽（北京）科技有限公司 | User's portrait generating means and method, information processing unit and storage medium |
| CN111177339A (en) * | 2019-12-06 | 2020-05-19 | 百度在线网络技术（北京）有限公司 | Dialog generation method and device, electronic equipment and storage medium |
| CN111046160A (en) * | 2019-12-16 | 2020-04-21 | 联想(北京)有限公司 | Interaction method, interaction device and computer system |
| WO2022048170A1 (en) * | 2020-09-02 | 2022-03-10 | 平安科技（深圳）有限公司 | Method and apparatus for conducting human-machine conversation, computer device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2017041369A1 (en) | 2017-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105138671A (en) | Human-computer interaction guiding method and device based on artificial intelligence | |
| KR102122373B1 (en) | Method and apparatus for obtaining user portrait | |
| CN105426436B (en) | Information providing method and device based on artificial intelligence robot | |
| CN108287864B (en) | Interest group dividing method, device, medium and computing equipment | |
| US20150074112A1 (en) | Multimedia Question Answering System and Method | |
| CN102253996B (en) | Multi-visual angle stagewise image clustering method | |
| Maleszka et al. | A method for collaborative recommendation using knowledge integration tools and hierarchical structure of user profiles | |
| US8229909B2 (en) | Multi-dimensional algorithm for contextual search | |
| CN104036002A (en) | Technical method for intelligently recommending data | |
| CN106649742A (en) | Database maintenance method and device | |
| CN106250513A (en) | A kind of event personalization sorting technique based on event modeling and system | |
| CN106446195A (en) | News recommending method and device based on artificial intelligence | |
| CN105512316B (en) | A kind of Knowledge Service System of combination mobile terminal | |
| CN101124609A (en) | Search systems and methods using in-line contextual queries | |
| CN101986293A (en) | Method and equipment for displaying search answer information on search interface | |
| CN108305180B (en) | Friend recommendation method and device | |
| CN103186834A (en) | Method and device of business process configuration | |
| CN103425686B (en) | A kind of information issuing method and device | |
| CN106485328A (en) | Information processing system and method | |
| CN106294500A (en) | The method for pushing of content item, Apparatus and system | |
| CN107636643A (en) | Locally applied search result is provided together with web search result | |
| CN106294358A (en) | The search method of a kind of information and system | |
| CN104281648A (en) | Search-result multi-dimensional navigating method on basis of dimension label | |
| CN106708829A (en) | Data recommendation method and data recommendation system | |
| CN105022797A (en) | Resource topic processing method and apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151209 |