CN107832433A - Information recommendation method, device, server and storage medium based on dialogue interaction - Google Patents
Information recommendation method, device, server and storage medium based on dialogue interaction Download PDFInfo
- Publication number
- CN107832433A CN107832433A CN201711129842.7A CN201711129842A CN107832433A CN 107832433 A CN107832433 A CN 107832433A CN 201711129842 A CN201711129842 A CN 201711129842A CN 107832433 A CN107832433 A CN 107832433A
- Authority
- CN
- China
- Prior art keywords
- user
- topic
- theme
- query message
- dialogue
- 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.)
- Granted
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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Abstract
The embodiment of the invention discloses information recommendation method, device, server and the storage medium based on dialogue interaction.Methods described includes：According to the user behavior feature and/or user model of history read interface, theme query message is read in generation, and the user model includes following at least one：User interest, user pay close attention to topic and user pays close attention to author；Reading theme query message according to generation engages in the dialogue with user to be interacted；The reading theme of the user is determined according to dialogue interaction content；By the message push matched with the reading theme to the user.The embodiment of the present invention is by natural language understanding and based on artificial intelligence technologys such as dialogue interactions, different topic information flows is connected, helps user to explore potential interest, improves user's duration and viscosity, user model is more accurately built and controlled simultaneously, improves Consumer's Experience.
Description
Technical field
The present embodiments relate to technical field of information interaction, more particularly to based on dialogue interaction information recommendation method,
Device, server and storage medium.
Background technology
With the development of science and technology and being continuously increased for internet information, requirement of the user to internet recommendation information is increasingly
It is high.
The information recommendation mode of mobile Internet is broadly divided into two classes at present, and one kind is interested by user's Behavior mining
Label structure user model recommended, another kind of pushed away by using the dynamic concern of householder people interested or topic
Recommend.All there is the problem of certain in this two category informations way of recommendation, the user model of the first kind is excavated by indirect user behavior
Obtain, therefore the accuracy recommended is not very good, user model is typically implicit in addition, and user can not actively be set or directly
Modification, causes the new interest tags of user can not add in time, out-of-date or wrong interest tags can not be deleted in time, influence to use
Experience at family；Second class is due to needing user actively to initiate concern, it is difficult to excavates potential (the not paying close attention to) interest of user, is unfavorable for
Improve user and use duration and viscosity.
The content of the invention
, can the embodiments of the invention provide information recommendation method, device, server and the storage medium based on dialogue interaction
To improve user's duration and viscosity, user model is more accurately built and controlled, improves Consumer's Experience.
In a first aspect, the embodiments of the invention provide the information recommendation method based on dialogue interaction, including：
According to the user behavior feature and/or user model of history read interface, theme query message is read in generation, described
User model includes following at least one：User interest, user pay close attention to topic and user pays close attention to author；
Reading theme query message according to generation engages in the dialogue with user to be interacted；
The reading theme of the user is determined according to dialogue interaction content；
By the message push matched with the reading theme to the user.
Second aspect, the embodiment of the present invention additionally provide the information recommending apparatus based on dialogue interaction, including：
Query message acquisition module, for the user behavior feature and/or user model according to history read interface, generation
Theme query message is read, the user model includes following at least one：User interest, user pay close attention to topic and user's concern
Author；
Talk with interactive module, interacted for being engaged in the dialogue according to the reading theme query message of generation with user；
Topic module is read, for determining the reading theme of the user according to dialogue interaction content；
Pushing module, for will be with the message push that matches of reading theme to the user.
The third aspect, the embodiment of the present invention additionally provide a kind of server, and the server includes：
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are by one or more of computing devices so that one or more of processing
Device realizes the information recommendation method as described above based on dialogue interaction.
Fourth aspect, the embodiment of the present invention additionally provide a kind of computer-readable recording medium, are stored thereon with computer
Program, the information recommendation method as described above based on dialogue interaction is realized when the program is executed by processor.
The embodiment of the present invention is read by the user behavior feature and/or user model according to history read interface, generation
Theme query message, and engage in the dialogue and interact with user according to the reading theme query message of generation, according to dialogue interaction content
The reading theme of the user is determined, by the message push matched with the reading theme to the user.Due to of the invention real
Example is applied by the artificial intelligence technology such as natural language understanding and dialogue interaction, different topic information flows is connected, helped
User explores potential interest, improves user's duration and viscosity, while more accurately builds and control user model, improves user's body
Test.
Brief description of the drawings
Fig. 1 is the flow chart of the information recommendation method based on dialogue interaction in the embodiment of the present invention one；
Fig. 2 is the flow chart of the information recommendation method based on dialogue interaction in the embodiment of the present invention two；
Fig. 3 is the strong interactive form surface chart of the information recommendation method based on dialogue interaction in the embodiment of the present invention two；
Fig. 4 is the weak interactive form surface chart of the information recommendation method based on dialogue interaction in the embodiment of the present invention two；
Fig. 5 is the structural representation of the information recommending apparatus based on dialogue interaction in the embodiment of the present invention three；
Fig. 6 is the structural representation of the server in the embodiment of the present invention four.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is the flow chart of the information recommendation method based on dialogue interaction in the embodiment of the present invention one, and the present embodiment can
Suitable for the situation of information recommendation, this method can be performed by the information recommendation method device based on dialogue interaction, and the device can
Realized in a manner of using software and/or hardware, such as the device is configured in server.As shown in figure 1, this method is specific
It can include：
Theme inquiry is read in step 110, user behavior feature and/or user model according to history read interface, generation
Information, the user model include following at least one：User interest, user pay close attention to topic and user pays close attention to author.
In the present embodiment, the user behavior of the history read interface is characterized in readding history by statistical analysis user
The user that the behavioral data at reading interface obtains accesses the behavioural habits and rule at interface, such as user behavior feature can be click on
The interest tags number that includes of article or click maximum first three the interest tags number of the number that includes of article.It is described to read master
Topic query message is that the historic user obtained according to user behavior feature and/or user model accesses more or interested reading
The suitable related inquiry sentence of theme generation.
Step 120, the reading theme query message according to generation engage in the dialogue with user and interacted.
Specifically, being interacted with the dialogue of user by natural language understanding technology to realize, inquiry sentence is sent to use
Family, user answer this inquiry, can propose new inquiry sentence according to the answer of user or carry out follow-up step 130, so as to complete
Interacted into dialogue.Wherein, the sentence of inquiry is answered for user, is first scanned from left to right by word, recognizes each single according to dictionary
The meaning of a word and usage of word, the combination of phrase and sentence is determined according to syntactic rule, is obtained according to semantic rules and inference rule defeated
Enter the implication of sentence, search knowledge base, exported according to thematic knowledge and the response of sentence create-rule tissue, vocabulary therein, syntax
Rule, semantic rules, inference rule and thematic knowledge prestore.
Exemplary, if according to news was read before user, generating inquiry sentence, " wanting to understand has what big new today
Hear", if user answers " good ", propose that new inquiry sentence " is wanted to understand the news of amusement circles according to the answer of user
", user continues to answer.
It should be noted that the selection of candidate's information options for user can also be generated according to theme query message is read, use
Family can also be by selecting candidate's information to answer a question inquiry back and forth, wherein candidate's information option is according to reading theme query message
The picture of obtained relevent information or link, such as " information 1 ", " information 2 " and " information 3 " in Fig. 3.
Step 130, foundation dialogue interaction content determine the reading theme of the user.
Specifically, the answer content by the user in being interacted with user session, it may be determined that user currently wants to know about
Information, the current reading theme of user can be determined according to the information, wherein read theme refer to read main contents, read
It can be meeting to read theme, race, moved, personage etc., such as the Olympic Games.
Step 140, by with the message push that matches of reading theme to the user.
Specifically, the various default labels for reading theme can be built in advance, and master is read for information addition is corresponding
Label is inscribed, will be matched with the reading theme with the label of each information, the information that the match is successful is defined as readding with described
Read the information of theme matching.Alternatively, it is also possible to be determined institute according to the subject key words included in reading theme and each information
State and read theme and the matching degree of each information, and matching degree is met that the information of condition is defined as what is matched with the reading theme
Information.
The embodiment of the present invention is read by the user behavior feature and/or user model according to history read interface, generation
Theme query message, and engage in the dialogue and interact with user according to the reading theme query message of generation, according to dialogue interaction content
The reading theme of the user is determined, by the message push matched with the reading theme to the user.Due to of the invention real
Example is applied by natural language understanding and based on the artificial intelligence technologys such as interaction are talked with, different topic information flows is connected,
User can be helped to explore potential interest, improve user's duration and viscosity, while more accurately build and control user model, carried
High Consumer's Experience.
Exemplary, 110 can include：According to the user behavior feature and/or user model of history read interface, it is determined that
The topic that the user currently pays close attention to；The update status generation for the topic currently paid close attention to according to the user, which is reminded, reads in renewal
The query message of appearance.Specifically, it can be that user compares pass that user, which during historical viewings interface, has the content of some topics,
Note, the topic of these users concern is determined according to the user behavior feature and/or user model of history read interface, if institute
Stating the topic of concern has renewal, then the query message of user's reading more new content is reminded in generation, such as " topic that you pay close attention to has newly
Selected article, be now to look at”.
Further, can also include after the topic that the above-mentioned determination user currently pays close attention to：Read according to history
The user behavior feature at interface, there is provided more information that the user currently pays close attention to topic select for the user；According to history
The user behavior feature of read interface, there is provided the information that the user currently pays close attention to the associated topic of topic is selected for the user
Select.Specifically, according to the behavioural characteristic of user's history read interface, from depth and range both direction, recommend more current
The information of topic and associated topic is paid close attention to, the inquiry sentence of generation is as " you still want to understand in depth on which topic of B" or
" recommending the related more topics of B for you " etc..
Exemplary, it can also include after step 120：The dialogue interaction content of foundation user, determine the yardstick of user
And/or style；According to the yardstick label and/or style label added in advance in information, the information that user matches is determined.Specifically
, the measurement of the yardstick and/or style of the user is that some pre-set can express yardstick and/or style rank
Word, such as " terror " " rudimentary " etc., can voluntarily be set as needed.By the text of user session interaction content carry out classification and
Extraction, the word extracted are contrasted with the word pre-set, and maximally related word is defined as to the yardstick and/or style at family.So
The word for representing user's yardstick and/or style and the yardstick label added in advance in information and/or style label are carried out pair again afterwards
Than, by maximally related information be defined as user matching information.
Exemplary, it can also include after step 140：If user closes a upper read interface, and is read to upper one
Interface does not have reading behavior, then generates the feedback query message of a upper read interface.Specifically, if user is to a upper read interface
There is no any behavior to be shut off, then generate the inquiry sentence of feedback, such as " recommend you to be satisfied with above", " recommend you above all
It is unsatisfied with" or " recommend where you are unsatisfied with above" etc..Wherein, the behavior of a upper read interface includes the article clicked on
Count, the interest tags number being present in user model, the point that the interest tags number that the article of click includes, the article of click include
Maximum first three of number that interest tags number that what the article hit included be not present in user model, the article clicked on include
First three interest tags for the number maximum that interest tags number and/or the article of click include account for ratio of whole labels etc..
Embodiment two
The flow chart of the information recommendation method based on dialogue interaction in Fig. 2 embodiment of the present invention two.The present embodiment is upper
On the basis of stating embodiment, the above-mentioned information recommendation method based on dialogue interaction is further optimized.Accordingly, as shown in Fig. 2
The method of the present embodiment specifically includes：
Step 211, user behavior feature and/or user model according to history read interface, are determined residing for the user
Current scene type.
In the present embodiment, the scene type is presently in time and state including user, and scene type can basis
Need voluntarily to set.According to the user behavior feature and/or user model of history read interface, it may be determined that the specific field of user
Scape type.Such as current time is 8 points of morning, according to the time, it may be determined that the scene type of user be " getting up the time " or
" having breakfast the time ".
Step 212, according to default scene type and read theme between incidence relation, by the current scene type
The reading theme of matching is as theme to be recommended.
Specifically, the reading theme associated with this scene type is searched for according to the scene type of user, and according to association
The significance level selected section of relation is read theme and can voluntarily set as theme to be recommended, the wherein significance level of incidence relation
Put.
Step 213, according to the theme to be recommended generation reading theme query message.
The inquiry sentence of the reading theme can be generated according to theme to be recommended, if such as the scene type of user be
" at 3 points in afternoon ", the proposed topic for the treatment of each other determined according to step 212 is " cross-talk of making laughs ", and inquiry sentence can be that " feel sleepy in the afternoon
Some selected cross-talks of making laughs, want to look at”.
Step 220, the reading theme query message according to generation engage in the dialogue with user and interacted.
Step 231, the dialogue interaction content according to user, determine the intention of user；
Wherein, the intention of the user refer to user to from dialogue interaction content in extract user interest, concern
Topic or author want the operation carried out.
Step 232, the intention according to user, pay close attention to user interest, user topic or user pays close attention to author and carries out additions and deletions
Processing.
Specifically, according to the intention of user, add new user interest, user pays close attention to topic or user pay close attention to author or
Delete user interest, user pays close attention to topic or user pays close attention to author.
Step 240, foundation dialogue interaction content determine the reading theme of the user.
Step 250, by with the message push that matches of reading theme to the user.
Step 261, in user's closing after a read interface, if detect user click on any topic information the frequency it is big
In predetermined threshold value, then topic is paid close attention to using the topic as recommendation.
In the present embodiment, the frequency that topic information can be clicked on to user pre-sets suitable threshold value, if user's point
The frequency for hitting some topic information is more than the threshold value, then using the topic as concern topic is recommended, words are wherein clicked on the day of user
The frequency of topic includes whether the number that the same day first enters into the topic and the same day enters the topic.
Step 262, the query message according to recommendation concern topic generation concern topic addition.
Specifically, according to recommend concern topic can generate concern topic add inquiry sentence, if such as step 261 it is true
Fixed recommendation concern topic is " A topics ", and inquiry sentence can be that " you want to pay close attention to A topicsThere is new selected article to push away
Recommend to you！”.
Exemplary, Fig. 3 is the strong interaction shape of the information recommendation method based on dialogue interaction in the embodiment of the present invention two
Formula surface chart, as shown in figure 3, strong interactive form is embodied in special interactive interface, in the interactive interface according to with
The theme information and related information, such as user that the dialogue interaction content meeting recommended user at family currently wants to know about are wanted " to recommend
The article of some machine learning ", reply " relevent information that machine learning is recommended for you " and pushed correlation " information 1,2 and afterwards
3 " select for user, while can generate new inquiry sentence " helping you to recommend other related topics of some machine learning ", root
It may proceed to recommend information according to the reply of user or produce new inquiry sentence.In addition, can be with good grounds user in interactive interface
The inquiry sentence of historical behavior generation, such as " looks at external major issue " or " sports news " efficiently selects for user.User selects
After selecting the information for wanting reading, into read interface, in read interface the information that user selects can be adjusted to be read for user automatically,
Concern, topic of interest can also be selected, do not like topic or closes the operation such as this read interface.
Fig. 4 is the weak interactive form surface chart of the information recommendation method based on dialogue interaction in the embodiment of the present invention two,
Weak interactive form is embodied in no special interactive interface, but realizes that the dialogue with user is handed over by the interactive dialogue frame of ejection
Mutually.As shown in figure 4, in addition to the information recommended according to user's history behavior, new inquiry language can be generated in interactive dialogue frame
Sentence, such as " needing me to help you to pay close attention to A topics ", there can be simple options for user selection to be asked to answer in interactive dialogue frame
Ask.
User behavior feature and/or user model of the present embodiment according to history read interface, are determined residing for the user
Current scene type or the topic currently paid close attention to, and accordingly generate query message and engaged in the dialogue with user and interacted, according to dialogue
Interactive content determines the intention and style of user, and the information for selecting to match with reading the intention and style of theme and user is recommended
To user, in addition after a read interface is closed in user, the frequency generation addition concern of topic can be clicked on according to user
The query message of topic or the generation feedback query message when user does not have reading behavior.The present embodiment, which possesses, actively pays close attention to function
While, moreover it is possible to by dialogue, guiding user explores and found the potential interest of oneself, improves using duration and gluing for user
Property, and the content for being not desired to see just can be masked by the instruction of simple natural language, Consumer's Experience is more preferable.
Embodiment three
Fig. 5 is the structural representation of the information recommending apparatus based on dialogue interaction in the embodiment of the present invention three.Such as Fig. 5 institutes
Show, described device can include：
Query message acquisition module 310, for according to history read interface user behavior feature and/or user model,
Theme query message is read in generation, and the user model includes following at least one：User interest, user pay close attention to topic and user
Pay close attention to author；
Talk with interactive module 320, interacted for being engaged in the dialogue according to the reading theme query message of generation with user；
Topic module 330 is read, for determining the reading theme of the user according to dialogue interaction content；
Pushing module 340, for will be with the message push that matches of reading theme to the user.
Exemplary, the query message acquisition module 310 can include：
Scene type unit, is specifically used for：The user behavior feature and/or user model of foundation history read interface, really
Current scene type residing for the fixed user；According to default scene type and the incidence relation between theme is read, by institute
The reading theme of current scene type matching is stated as theme to be recommended；The reading theme is generated according to the theme to be recommended
Query message.
Exemplary, the query message acquisition module 310 can include：
Topic unit, is specifically used for：According to the user behavior feature and/or user model of history read interface, institute is determined
State the topic that user currently pays close attention to；The update status generation for the topic currently paid close attention to according to the user, which is reminded, reads more new content
Query message.
Further, the topic unit specifically can be used for：
After determining the topic that the user currently pays close attention to, the user behavior feature according to history read interface, there is provided institute
State user and currently pay close attention to more information of topic for user selection；According to the user behavior feature of history read interface, carry
The information that the associated topic of topic is currently paid close attention to for the user selects for the user.
Exemplary, the query message acquisition module 310 can also include：
Information option cell, for the user behavior feature and/or user model according to history read interface, generation is read
After theme query message, according to reading theme query message generation candidate's information options for user selection.
Exemplary, the device can also include frequency judging unit, be specifically used for：
In user's closing after a read interface, if detecting, user clicks on the frequency of any topic information more than default threshold
Value, then pay close attention to topic using the topic as recommendation；According to the query message for recommending concern topic generation concern topic addition.
Exemplary, the device can also include：
Feedback unit, if closing a upper read interface for user, and there is no reading behavior to a upper read interface, then give birth to
The feedback query message of Cheng Shangyi read interfaces.
Exemplary, the dialogue interactive module 320 can include：
It is intended to unit, is specifically used for：The dialogue interaction content of foundation user, determine the intention of user；Meaning according to user
Figure, pays close attention to user interest, user topic or user pays close attention to author and carries out additions and deletions processing.
Exemplary, the dialogue interactive module 320 can also include：
Multi-scale, it is specifically used for：The dialogue interaction content of foundation user, determine the yardstick and/or style of user；Foundation
The yardstick label and/or style label added in advance in information, determine the information of user's matching.
The information recommending apparatus based on dialogue interaction that the embodiment of the present invention is provided can perform any embodiment of the present invention
The information recommendation method based on dialogue interaction provided, possesses the corresponding functional module of execution method and beneficial effect.
Example IV
Fig. 6 is the structural representation of the server in the embodiment of the present invention four.Fig. 6 is shown suitable for being used for realizing the present invention
The block diagram of the exemplary servers 412 of embodiment.The server 412 that Fig. 6 is shown is only an example, should not be to the present invention
The function and use range of embodiment bring any restrictions.
As shown in fig. 6, server 412 is showed in the form of universal computing device.The component of server 412 can include but
It is not limited to：One or more processor 416, system storage 428, connection different system component (including system storage 428
With processor 416) bus 418.
Bus 418 represents the one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor 416 or total using the local of any bus structures in a variety of bus structures
Line.For example, these architectures include but is not limited to industry standard architecture (ISA) bus, MCA
(MAC) bus, enhanced isa bus, VESA's (VESA) local bus and periphery component interconnection (PCI) are total
Line.
Server 412 typically comprises various computing systems computer-readable recording medium.These media can be it is any being capable of bedding and clothing
The usable medium that business device 412 accesses, including volatibility and non-volatile media, moveable and immovable medium.
System storage 428 can include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 430 and/or cache memory 432.Server 412 may further include it is other it is removable/can not
Mobile, volatile/non-volatile computer system storage medium.Only as an example, storage system 434 can be used for read-write not
Movably, non-volatile magnetic media (Fig. 6 is not shown, is commonly referred to as " hard disk drive ").Although not shown in Fig. 6, can with
There is provided for the disc driver to may move non-volatile magnetic disk (such as " floppy disk ") read-write, and to removable non-volatile
The CD drive of CD (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driving
Device can be connected by one or more data media interfaces with bus 418.Memory 428 can include at least one journey
Sequence product, the program product have one group of (for example, at least one) program module, and these program modules are configured to perform this hair
The function of bright each embodiment.
Program/utility 440 with one group of (at least one) program module 442, can be stored in such as memory
In 428, such program module 442 includes but is not limited to operating system, one or more application program, other program modules
And routine data, the realization of network environment may be included in each or certain combination in these examples.Program module 442
Generally perform the function and/or method in embodiment described in the invention.
Server 412 can also be with one or more external equipments 414 (such as keyboard, sensing equipment, display 424 etc.)
Communication, can also enable a user to the equipment communication interacted with the server 412 with one or more, and/or with causing the clothes
Any equipment (such as network interface card, modem etc.) that business device 412 can be communicated with one or more of the other computing device
Communication.This communication can be carried out by input/output (I/O) interface 422.Also, server 412 can also pass through network
Adapter 420 and one or more network (such as LAN (LAN), wide area network (WAN) and/or public network, such as because of spy
Net) communication.As illustrated, network adapter 420 is communicated by bus 418 with other modules of server 412.It should be understood that
Although not shown in the drawings, can combine server 412 uses other hardware and/or software module, include but is not limited to：Micro- generation
Code, device driver, redundant processing unit, external disk drive array, RAID systems, tape drive and data backup
Storage system etc..
Processor 416 is stored in program in system storage 428 by operation, so as to perform various function application and
Data processing, such as the information recommendation method based on dialogue interaction that the embodiment of the present invention is provided is realized, this method includes：
According to the user behavior feature and/or user model of history read interface, theme query message is read in generation, described
User model includes following at least one：User interest, user pay close attention to topic and user pays close attention to author；
Reading theme query message according to generation engages in the dialogue with user to be interacted；
The reading theme of the user is determined according to dialogue interaction content；
By the message push matched with the reading theme to the user.
Embodiment five
The embodiment of the present invention five additionally provides a kind of computer-readable recording medium, is stored thereon with computer program, should
The information recommendation method based on dialogue interaction provided such as the embodiment of the present invention, this method are provided when program is executed by processor
Including：
According to the user behavior feature and/or user model of history read interface, theme query message is read in generation, described
User model includes following at least one：User interest, user pay close attention to topic and user pays close attention to author；
Reading theme query message according to generation engages in the dialogue with user to be interacted；
The reading theme of the user is determined according to dialogue interaction content；
By the message push matched with the reading theme to the user.
The computer-readable storage medium of the embodiment of the present invention, any of one or more computer-readable media can be used
Combination.Computer-readable medium can be computer-readable signal media or computer-readable recording medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any combination above.The more specifically example (non exhaustive list) of computer-readable recording medium includes：Tool
There are the electrical connections of one or more wires, portable computer diskette, hard disk, random access memory (RAM), read-only storage
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any includes or the tangible medium of storage program, the program can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media can include in a base band or as carrier wave a part propagation data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium beyond storage medium is read, the computer-readable medium, which can send, propagates or transmit, to be used for
By instruction execution system, device either device use or program in connection.
The program code included on computer-readable medium can be transmitted with any appropriate medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc., or above-mentioned any appropriate combination.
It can be write with one or more programming languages or its combination for performing the computer that operates of the present invention
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Also include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
Fully perform, partly perform on the user computer on the user computer, the software kit independent as one performs, portion
Divide and partly perform or performed completely on remote computer or server on the remote computer on the user computer.
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including LAN (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as carried using Internet service
Pass through Internet connection for business).
Pay attention to, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (15)
1. the information recommendation method based on dialogue interaction, it is characterised in that including：
According to the user behavior feature and/or user model of history read interface, theme query message, the user are read in generation
Model includes following at least one：User interest, user pay close attention to topic and user pays close attention to author；
Reading theme query message according to generation engages in the dialogue with user to be interacted；
The reading theme of the user is determined according to dialogue interaction content；
By the message push matched with the reading theme to the user.
2. according to the method for claim 1, it is characterised in that the user behavior feature according to history read interface
And/or theme query message is read in user model, generation, including：
According to the user behavior feature and/or user model of history read interface, the current scene class residing for the user is determined
Type；
According to default scene type and the incidence relation between theme is read, by the reading master of the current scene type matching
Topic is used as theme to be recommended；
According to the theme generation reading theme query message to be recommended.
3. according to the method for claim 1, it is characterised in that the user behavior feature according to history read interface
And/or theme query message is read in user model, generation, in addition to：
According to the user behavior feature and/or user model of history read interface, the topic that the user currently pays close attention to is determined；
The query message for reading more new content is reminded in the update status generation for the topic currently paid close attention to according to the user.
4. according to the method for claim 3, it is characterised in that after the topic for determining the user and currently paying close attention to also
Including：
User behavior feature according to history read interface, there is provided the user currently pays close attention to more information of topic for described
Family selects；
User behavior feature according to history read interface, there is provided the information that the user currently pays close attention to the associated topic of topic supplies
User's selection.
5. according to the method for claim 1, it is characterised in that the user behavior feature according to history read interface
And/or user model, after theme query message is read in generation, in addition to：
According to reading theme query message generation candidate's information options for user selection.
6. according to the method for claim 1, it is characterised in that also include：
In user's closing after a read interface, if detecting, the frequency of any topic information of user's click is more than predetermined threshold value,
Then topic is paid close attention to using the topic as recommendation；
According to the query message for recommending concern topic generation concern topic addition.
7. according to the method for claim 1, it is characterised in that also include：
If user closes a upper read interface, and does not have reading behavior to a upper read interface, then a upper read interface is generated
Feed back query message.
8. according to the method for claim 1, it is characterised in that the reading theme query message and user according to generation
Engage in the dialogue after interacting, in addition to：
The dialogue interaction content of foundation user, determine the intention of user；
According to the intention of user, pay close attention to user interest, user topic or user pays close attention to author and carries out additions and deletions processing.
9. according to the method for claim 1, it is characterised in that the reading theme query message and user according to generation
Engage in the dialogue after interacting, in addition to：
The dialogue interaction content of foundation user, determine the yardstick and/or style of user；
According to the yardstick label and/or style label added in advance in information, the information that user matches is determined.
10. the information recommending apparatus based on dialogue interaction, it is characterised in that including：
Query message acquisition module, for the user behavior feature and/or user model according to history read interface, generation is read
Theme query message, the user model include following at least one：User interest, user pay close attention to topic and user pays close attention to and made
Person；
Talk with interactive module, interacted for being engaged in the dialogue according to the reading theme query message of generation with user；
Topic module is read, for determining the reading theme of the user according to dialogue interaction content；
Pushing module, for will be with the message push that matches of reading theme to the user.
11. device according to claim 10, it is characterised in that the query message acquisition module includes scene type list
Member, the scene type unit, is specifically used for：
According to the user behavior feature and/or user model of history read interface, the current scene class residing for the user is determined
Type；
According to default scene type and the incidence relation between theme is read, by the reading master of the current scene type matching
Topic is used as theme to be recommended；
According to the theme generation reading theme query message to be recommended.
12. device according to claim 10, it is characterised in that the dialogue interactive module also includes：
It is intended to unit, is specifically used for：
The dialogue interaction content of foundation user, determine the intention of user；
According to the intention of user, pay close attention to user interest, user topic or user pays close attention to author and carries out additions and deletions processing.
13. device according to claim 10, it is characterised in that the dialogue interactive module also includes：
Multi-scale, it is specifically used for：
The dialogue interaction content of foundation user, determine the yardstick and/or style of user；
According to the yardstick label and/or style label added in advance in information, the information that user matches is determined.
14. a kind of server, it is characterised in that the server includes：
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are by one or more of computing devices so that one or more of processors are real
The now information recommendation method based on dialogue interaction as described in any in claim 1-9.
15. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor
The information recommendation method based on dialogue interaction as described in any in claim 1-9 is realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711129842.7A CN107832433B (en) | 2017-11-15 | 2017-11-15 | Information recommendation method, device, server and storage medium based on conversation interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711129842.7A CN107832433B (en) | 2017-11-15 | 2017-11-15 | Information recommendation method, device, server and storage medium based on conversation interaction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107832433A true CN107832433A (en) | 2018-03-23 |
| CN107832433B CN107832433B (en) | 2020-08-11 |
Family
ID=61654429
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711129842.7A Active CN107832433B (en) | 2017-11-15 | 2017-11-15 | Information recommendation method, device, server and storage medium based on conversation interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107832433B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108377273A (en) * | 2018-05-15 | 2018-08-07 | 北京奇虎科技有限公司 | A kind of information-pushing method, server and device |
| CN108521366A (en) * | 2018-03-27 | 2018-09-11 | 联想(北京)有限公司 | Expression method for pushing and electronic equipment |
| CN108920651A (en) * | 2018-06-29 | 2018-11-30 | 百度在线网络技术（北京）有限公司 | Information-pushing method, device, server and storage medium |
| CN108920649A (en) * | 2018-06-29 | 2018-11-30 | 北京百度网讯科技有限公司 | A kind of information recommendation method, device, equipment and medium |
| CN109147801A (en) * | 2018-09-30 | 2019-01-04 | 深圳市元征科技股份有限公司 | voice interactive method, system, terminal and storage medium |
| CN109166572A (en) * | 2018-09-11 | 2019-01-08 | 深圳市沃特沃德股份有限公司 | The method and reading machine people that robot is read |
| CN109558199A (en) * | 2018-11-29 | 2019-04-02 | 广州市百果园信息技术有限公司 | A kind of information-pushing method, device, equipment and storage medium |
| CN109857967A (en) * | 2019-01-09 | 2019-06-07 | 平安科技（深圳）有限公司 | Report method for subscribing and system based on big data |
| CN109977215A (en) * | 2019-03-29 | 2019-07-05 | 百度在线网络技术（北京）有限公司 | Sentence recommended method and device based on association point of interest |
| CN110276456A (en) * | 2019-06-20 | 2019-09-24 | 山东大学 | A kind of machine learning model auxiliary construction method, system, equipment and medium |
| CN110413885A (en) * | 2019-07-17 | 2019-11-05 | 咪咕互动娱乐有限公司 | A kind of exchange method and relevant device |
| CN111026932A (en) * | 2019-12-20 | 2020-04-17 | 北京百度网讯科技有限公司 | Man-machine conversation interaction method and device, electronic equipment and storage medium |
| CN111144708A (en) * | 2019-12-06 | 2020-05-12 | 星络智能科技有限公司 | Information interaction method and system and readable storage medium |
| CN111800445A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | Message pushing method and device, storage medium and electronic equipment |
| CN112100491A (en) * | 2020-09-08 | 2020-12-18 | 中国平安人寿保险股份有限公司 | Information recommendation method, device and equipment based on user data and storage medium |
| CN112328892A (en) * | 2020-11-24 | 2021-02-05 | 北京百度网讯科技有限公司 | Information recommendation method, device, equipment and computer storage medium |
| CN113158031A (en) * | 2021-03-15 | 2021-07-23 | 北京健康之家科技有限公司 | Method and device for determining user resource information, computer storage medium and terminal |
| CN113255801A (en) * | 2021-06-02 | 2021-08-13 | 北京字节跳动网络技术有限公司 | Data processing method and device, computer equipment and storage medium |
| CN114650268A (en) * | 2022-04-14 | 2022-06-21 | 北京字跳网络技术有限公司 | Content pushing method, content pushing device, electronic equipment, medium and program product |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1894713A (en) * | 2003-12-15 | 2007-01-10 | 皇家飞利浦电子股份有限公司 | Information recommendation system and method |
| CN101276375A (en) * | 2007-03-31 | 2008-10-01 | 索尼德国有限责任公司 | Method for content recommendation |
| CN102208086A (en) * | 2010-03-31 | 2011-10-05 | 北京邮电大学 | Field-oriented personalized intelligent recommendation system and implementation method |
| CN102713908A (en) * | 2009-11-19 | 2012-10-03 | 厦姆技术有限公司 | Apparatus and method of adaptive questioning and recommending |
| CN103348369A (en) * | 2011-01-06 | 2013-10-09 | 电子湾有限公司 | Interestingness recommendations in a computing advice facility |
| CN103793537A (en) * | 2014-03-04 | 2014-05-14 | 南京大学 | System for recommending individual music based on multi-dimensional time series analysis and achieving method of system |
| CN103927354A (en) * | 2014-04-11 | 2014-07-16 | 百度在线网络技术（北京）有限公司 | Interactive searching and recommending method and device |
| CN104166707A (en) * | 2014-08-08 | 2014-11-26 | 百度在线网络技术（北京）有限公司 | Search recommendation method and device |
| CN104572797A (en) * | 2014-05-12 | 2015-04-29 | 深圳市智搜信息技术有限公司 | Individual service recommendation system and method based on topic model |
| CN104809154A (en) * | 2015-03-19 | 2015-07-29 | 百度在线网络技术（北京）有限公司 | Method and device for recommending information |
| CN106372195A (en) * | 2016-08-31 | 2017-02-01 | 北京光年无限科技有限公司 | Human-computer interaction method and device for intelligent robot |
| CN106802951A (en) * | 2017-01-17 | 2017-06-06 | 厦门快商通科技股份有限公司 | A kind of topic abstracting method and system for Intelligent dialogue |
| CN106815217A (en) * | 2015-11-30 | 2017-06-09 | 北京云莱坞文化传媒有限公司 | Story recommends method and story recommendation apparatus |
| CN106844769A (en) * | 2017-02-27 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | With reference to the pattern of passing through and in limited time reading model information flow recommend method and apparatus |
| CN106897284A (en) * | 2015-12-17 | 2017-06-27 | 腾讯科技（深圳）有限公司 | The recommendation method and device of e-book |
-
2017
- 2017-11-15 CN CN201711129842.7A patent/CN107832433B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1894713A (en) * | 2003-12-15 | 2007-01-10 | 皇家飞利浦电子股份有限公司 | Information recommendation system and method |
| CN101276375A (en) * | 2007-03-31 | 2008-10-01 | 索尼德国有限责任公司 | Method for content recommendation |
| CN102713908A (en) * | 2009-11-19 | 2012-10-03 | 厦姆技术有限公司 | Apparatus and method of adaptive questioning and recommending |
| CN102208086A (en) * | 2010-03-31 | 2011-10-05 | 北京邮电大学 | Field-oriented personalized intelligent recommendation system and implementation method |
| CN103348369A (en) * | 2011-01-06 | 2013-10-09 | 电子湾有限公司 | Interestingness recommendations in a computing advice facility |
| CN103793537A (en) * | 2014-03-04 | 2014-05-14 | 南京大学 | System for recommending individual music based on multi-dimensional time series analysis and achieving method of system |
| CN103927354A (en) * | 2014-04-11 | 2014-07-16 | 百度在线网络技术（北京）有限公司 | Interactive searching and recommending method and device |
| CN104572797A (en) * | 2014-05-12 | 2015-04-29 | 深圳市智搜信息技术有限公司 | Individual service recommendation system and method based on topic model |
| CN104166707A (en) * | 2014-08-08 | 2014-11-26 | 百度在线网络技术（北京）有限公司 | Search recommendation method and device |
| CN104809154A (en) * | 2015-03-19 | 2015-07-29 | 百度在线网络技术（北京）有限公司 | Method and device for recommending information |
| CN104809154B (en) * | 2015-03-19 | 2019-03-08 | 百度在线网络技术（北京）有限公司 | The method and device recommended for information |
| CN106815217A (en) * | 2015-11-30 | 2017-06-09 | 北京云莱坞文化传媒有限公司 | Story recommends method and story recommendation apparatus |
| CN106897284A (en) * | 2015-12-17 | 2017-06-27 | 腾讯科技（深圳）有限公司 | The recommendation method and device of e-book |
| CN106372195A (en) * | 2016-08-31 | 2017-02-01 | 北京光年无限科技有限公司 | Human-computer interaction method and device for intelligent robot |
| CN106802951A (en) * | 2017-01-17 | 2017-06-06 | 厦门快商通科技股份有限公司 | A kind of topic abstracting method and system for Intelligent dialogue |
| CN106844769A (en) * | 2017-02-27 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | With reference to the pattern of passing through and in limited time reading model information flow recommend method and apparatus |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108521366A (en) * | 2018-03-27 | 2018-09-11 | 联想(北京)有限公司 | Expression method for pushing and electronic equipment |
| CN108377273A (en) * | 2018-05-15 | 2018-08-07 | 北京奇虎科技有限公司 | A kind of information-pushing method, server and device |
| CN108920651A (en) * | 2018-06-29 | 2018-11-30 | 百度在线网络技术（北京）有限公司 | Information-pushing method, device, server and storage medium |
| CN108920649A (en) * | 2018-06-29 | 2018-11-30 | 北京百度网讯科技有限公司 | A kind of information recommendation method, device, equipment and medium |
| CN109166572A (en) * | 2018-09-11 | 2019-01-08 | 深圳市沃特沃德股份有限公司 | The method and reading machine people that robot is read |
| CN109147801A (en) * | 2018-09-30 | 2019-01-04 | 深圳市元征科技股份有限公司 | voice interactive method, system, terminal and storage medium |
| CN109558199A (en) * | 2018-11-29 | 2019-04-02 | 广州市百果园信息技术有限公司 | A kind of information-pushing method, device, equipment and storage medium |
| CN109857967A (en) * | 2019-01-09 | 2019-06-07 | 平安科技（深圳）有限公司 | Report method for subscribing and system based on big data |
| CN109857967B (en) * | 2019-01-09 | 2024-03-29 | 平安科技（深圳）有限公司 | Report subscription method and system based on big data |
| CN109977215A (en) * | 2019-03-29 | 2019-07-05 | 百度在线网络技术（北京）有限公司 | Sentence recommended method and device based on association point of interest |
| US11593434B2 (en) | 2019-03-29 | 2023-02-28 | Baidu Online Network Technology (Beijing) Co., Ltd. | Sentence recommendation method and apparatus based on associated points of interest |
| CN111800445B (en) * | 2019-04-09 | 2023-02-28 | Oppo广东移动通信有限公司 | Message pushing method and device, storage medium and electronic equipment |
| CN111800445A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | Message pushing method and device, storage medium and electronic equipment |
| CN110276456B (en) * | 2019-06-20 | 2021-08-20 | 山东大学 | Auxiliary construction method, system, equipment and medium for machine learning model |
| CN110276456A (en) * | 2019-06-20 | 2019-09-24 | 山东大学 | A kind of machine learning model auxiliary construction method, system, equipment and medium |
| CN110413885A (en) * | 2019-07-17 | 2019-11-05 | 咪咕互动娱乐有限公司 | A kind of exchange method and relevant device |
| CN111144708A (en) * | 2019-12-06 | 2020-05-12 | 星络智能科技有限公司 | Information interaction method and system and readable storage medium |
| CN111026932A (en) * | 2019-12-20 | 2020-04-17 | 北京百度网讯科技有限公司 | Man-machine conversation interaction method and device, electronic equipment and storage medium |
| CN111026932B (en) * | 2019-12-20 | 2023-05-26 | 北京百度网讯科技有限公司 | Man-machine dialogue interaction method and device, electronic equipment and storage medium |
| CN112100491A (en) * | 2020-09-08 | 2020-12-18 | 中国平安人寿保险股份有限公司 | Information recommendation method, device and equipment based on user data and storage medium |
| CN112328892A (en) * | 2020-11-24 | 2021-02-05 | 北京百度网讯科技有限公司 | Information recommendation method, device, equipment and computer storage medium |
| CN113158031A (en) * | 2021-03-15 | 2021-07-23 | 北京健康之家科技有限公司 | Method and device for determining user resource information, computer storage medium and terminal |
| CN113158031B (en) * | 2021-03-15 | 2024-04-23 | 北京水滴科技集团有限公司 | Method and device for determining user resource information, computer storage medium and terminal |
| CN113255801A (en) * | 2021-06-02 | 2021-08-13 | 北京字节跳动网络技术有限公司 | Data processing method and device, computer equipment and storage medium |
| CN114650268A (en) * | 2022-04-14 | 2022-06-21 | 北京字跳网络技术有限公司 | Content pushing method, content pushing device, electronic equipment, medium and program product |
| CN114650268B (en) * | 2022-04-14 | 2024-01-30 | 北京字跳网络技术有限公司 | Content pushing method, device, electronic equipment, medium and program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107832433B (en) | 2020-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107832433A (en) | Information recommendation method, device, server and storage medium based on dialogue interaction | |
| Bragg et al. | Sign language recognition, generation, and translation: An interdisciplinary perspective | |
| US10733197B2 (en) | Method and apparatus for providing information based on artificial intelligence | |
| US11599729B2 (en) | Method and apparatus for intelligent automated chatting | |
| US11302337B2 (en) | Voiceprint recognition method and apparatus | |
| US10515086B2 (en) | Intelligent agent and interface to provide enhanced search | |
| US20170242886A1 (en) | User intent and context based search results | |
| US20170243107A1 (en) | Interactive search engine | |
| Hawkins et al. | Characterizing the dynamics of learning in repeated reference games | |
| US20150243279A1 (en) | Systems and methods for recommending responses | |
| JP2021524079A (en) | Extension of training data for natural language classification | |
| US20190340200A1 (en) | Multi-modal interaction between users, automated assistants, and other computing services | |
| US10838951B2 (en) | Query interpretation disambiguation | |
| Keyvan et al. | How to approach ambiguous queries in conversational search: A survey of techniques, approaches, tools, and challenges | |
| US20130246392A1 (en) | Conversational System and Method of Searching for Information | |
| CN110073349A (en) | Consider the word order suggestion of frequency and formatted message | |
| CN109815482B (en) | News interaction method, device, equipment and computer storage medium | |
| Guo et al. | Conditional text generation for harmonious human-machine interaction | |
| Park et al. | Systematic review on chatbot techniques and applications | |
| CN110851650B (en) | Comment output method and device and computer storage medium | |
| Abdulkader et al. | A Review of Arabic Intelligent Chatbots: Developments and Challenges | |
| CN113068077A (en) | Subtitle file processing method and device | |
| US11880664B2 (en) | Identifying and transforming text difficult to understand by user | |
| CN114519347A (en) | Method and device for generating conversation content for language and vocabulary learning training | |
| Caldarini et al. | A Literature Survey of Recent Advances in Chatbots. Information 2022, 13, 41 |
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 |