CN106656732A - Scene information-based method and device for obtaining chat reply content - Google Patents
Scene information-based method and device for obtaining chat reply content Download PDFInfo
- Publication number
- CN106656732A CN106656732A CN201510741292.9A CN201510741292A CN106656732A CN 106656732 A CN106656732 A CN 106656732A CN 201510741292 A CN201510741292 A CN 201510741292A CN 106656732 A CN106656732 A CN 106656732A
- Authority
- CN
- China
- Prior art keywords
- chat
- sentence
- entry
- scene
- content
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/02—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a scene information-based method and device for obtaining chat reply content. According to the method, a chat initiation sentence is received; a topic type to which the chat initiation sentence belongs can be obtained according to the chat initiation sentence; preset content information of auxiliary scene entries relevant to the topic type is collected, auxiliary scene information can be obtained, the chat initiation sentence is subjected to data matching operation in a preset topic database corresponding to the topic type according to the auxiliary scene information, and a data matching result is used as chat reply content corresponding to the chat initiation sentence; the method and device can help solve a technical problem that monotonous and fixed obtained chat reply content, low chat intelligentization and poor user experience are caused as scene information of both communication parties taking part in a chat cannot be obtained via a conventional chat reply content obtaining method; different chat reply content can be obtained according to different scene information, and a high intelligentization level and a high individuation level can be reflected.
Description
Technical field
The present invention relates to communication technical field, and in particular to a kind of method and device that chat reply content is obtained based on scene information.
Background technology
At present, the intelligence chat reply content or communicating terminal that either intelligent chat robots system is provided is supplied to communication
Both sides are used for the chat reply content of selection or intelligent replying, are obtained by way of database matching.It is this by number
The method for obtaining chat reply content according to storehouse matching process is broadly divided into two steps, i.e., initiate sentence to chat first and pre-process,
Participle text is obtained, then the participle text of acquisition is matched with the database for pre-building, replys interior so as to obtain chat
Hold.
But this matching way do not combine any scene information of the communication two party for participating in intelligence chat, attribute information or other
Status information etc., therefore cause the single fixation of chat reply content for obtaining, the intelligence degree of chat is low and Consumer's Experience is not good.
The content of the invention
The invention provides a kind of method and device that chat reply content is obtained based on scene information, is chatted with solving existing acquisition
The method of reply content is not bound with the scene information of the communication two party for participating in chat, causes the chat reply content for obtaining single solid
It is fixed, the technical problem that intelligence degree is low and Consumer's Experience is not good of chat.
According to an aspect of the present invention, there is provided it is a kind of based on scene information obtain chat reply content method, including：
Receive chat and initiate sentence；
Sentence is initiated according to chat and obtains the topic classification belonging to initiating sentence of chatting；
The content information of the collection auxiliary scene entry associated with topic classification set in advance, obtains auxiliary scene information；
Initiating sentence to chat in topic database corresponding with topic classification set in advance according to auxiliary scene information carries out data
Matching, and using the result of Data Matching as chat reply content corresponding with chat initiation sentence.
Further, the topic classification according to belonging to sentence acquisition chat initiation sentence is initiated in chat includes：
The chat content above that sentence is initiated in chat is obtained, and the chat content above that chat initiation sentence and chat initiate sentence is merged into
The preprocessed text of text formatting；
Extract the keyword of preprocessed text；
Topic classification according to belonging to keyword obtains chat initiation sentence.
Further, the content information of the auxiliary scene entry associated with topic classification set in advance is gathered, auxiliary scene is obtained
Information includes：
The auxiliary scene entry associated with topic classification is preset, association auxiliary scene entry is obtained；
Content corresponding with association auxiliary scene entry is obtained by the way of calculating, reasoning, inquiry, search or its any combination
Information, obtains auxiliary scene information.
Further, according to auxiliary scene information chat is initiated in topic database corresponding with topic classification set in advance
Sentence carries out Data Matching to be included：
Topic database corresponding with topic classification is created, wherein, topic database includes at least one with topic classification as chat
The sample chat of theme is right, and sample chat including sample chat to initiating sentence and corresponding reply condition ID of sentence is initiated in sample chat
And conclusion content corresponding with condition ID of reply；
Using the establishment rule of reply condition ID is created to aiding in scene information to be identified, mark ID is obtained；
The matching in topic database initiates the chat of sentence identical sample and initiates sentence with chat, and right sentence is initiated with sample chat
Matching replys condition ID with mark ID identicals in reply condition ID answered, and will reply condition ID pair with mark ID identicals
Result of the conclusion content answered as Data Matching.
Further, scene entry is aided in include：
Send and/or receive name entries, sex entry, age entry, instant messaging account that the communicating terminal of sentence is initiated in chat
Entry, E-mail address entry, home address entry, occupational group's entry, post entry, work unit's entry, unit
Address entry, Bank Account Number entry, good friend's impression entry, address list packet entry, relationship entries, hobby entry, friend
Friend's circle state entry, recently mood entry, concern topic entry, time entry, red-letter day entry, season entry, geographical position
Data entries, apart from entry, scene image entry.
Further, the content information of the scene image entry in collection auxiliary scene entry includes：
Collection sends and/or receives the scene image that the communicating terminal of sentence is initiated in chat；
Using the area-of-interest of DOG operator extraction scene training images, and calculate the area-of-interest of scene training image
SIFT feature；
The SIFT feature of the area-of-interest of scene training image is clustered using K mean cluster algorithm, obtains multiple clusters
Center, and set up the vision word dictionary being made up of vision word corresponding with each cluster centre；
Using the area-of-interest of DOG operator extraction scene images, and match in vision word dictionary emerging with the sense of scene image
The immediate vision word of SIFT feature in interesting region；
The good SVMs of training in advance is adopted to scene image according to the distribution of the vision word of the area-of-interest of scene image
Grader is classified, and is sent and/or received the content information of the scene image entry of the communicating terminal of chat initiation sentence.
According to a further aspect in the invention, there is provided it is a kind of based on scene information obtain chat reply content device, including：
Reception device, for receiving chat sentence is initiated；
Topic classification acquisition device, for initiating sentence according to chat the topic classification belonging to initiating sentence of chatting is obtained；
Auxiliary scene information acquisition device, the content for gathering the auxiliary scene entry associated with topic classification set in advance is believed
Breath, obtains auxiliary scene information；
Coalignment, for according to auxiliary scene information in topic database corresponding with topic classification set in advance to chat
Initiating sentence carries out Data Matching, and using the result of Data Matching as chat reply content corresponding with chat initiation sentence.
Further, topic classification acquisition device includes：
Preprocessed text acquisition device, for obtaining the chat content above that sentence is initiated in chat, and chat initiation sentence and chat is sent out
The chat content above of the first line of a poem is merged into the preprocessed text of text formatting；
Keyword extracting device, for extracting the keyword of preprocessed text；
Topic classification determining device, for determining the topic classification belonging to initiating sentence of chatting according to keyword.
Further, scene information acquisition device is aided in include：
Setting device, for presetting the auxiliary scene entry associated with topic classification, obtains association auxiliary scene entry；
Computational reasoning device, for being obtained by the way of calculating, reasoning, inquiry, search or its any combination and associating auxiliary
The corresponding content information of scene entry, obtains auxiliary scene information.
Further, coalignment includes：
Topic database creating device, for creating topic database corresponding with topic classification, wherein, topic database includes
At least one sample chat with topic classification as theme of chatting is right, and sample chat initiates sentence to chatting including sample and sample is chatted
It initiates corresponding reply condition ID of sentence and conclusion content corresponding with condition ID of reply；
Identity device, for using the establishment rule of reply condition ID is created to aiding in scene information to be identified, obtaining mark ID；
ID coalignments, initiate the chat of sentence identical sample and initiate sentence for the matching in topic database and chat, and with
Sample chat initiates matching in corresponding reply condition ID of sentence and replys condition ID with mark ID identicals, and will be with mark ID phases
Result of the same corresponding conclusion content of reply condition ID as Data Matching.
The invention has the advantages that：
The invention provides a kind of method and device that chat reply content is obtained based on scene information, the method is by automatic data collection
The content information that the classification associated auxiliary scene entry of the topic belonging to sentence is initiated with the chat for receiving obtains auxiliary scene information, and
Chat reply content corresponding with chat initiation sentence is obtained with reference to auxiliary scene information, existing acquisition chat reply content is solved
Method is not bound with the scene information of the communication two party for participating in chat, causes the single fixation of chat reply content for obtaining, chat
The technical problem that intelligence degree is low and Consumer's Experience is not good, realizes and obtains different chats time according to different scene informations
Multiple content, and the chat reply content for obtaining fully combines the scene information of communication two party, and it is closely bound up with communication two party,
Embody higher intellectuality and personalized level.Additionally, obtaining chat reply content automatically without the need for manually compiling based on scene information
Volume, chat sessions speed is improve, improve Consumer's Experience.
In addition to objects, features and advantages described above, the present invention also has other objects, features and advantages.Below
By reference picture, the present invention is further detailed explanation.
Description of the drawings
The accompanying drawing for constituting the part of the application is used for providing a further understanding of the present invention, the illustrative examples of the present invention and
It is illustrated for explaining the present invention, does not constitute inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is the method flow diagram that chat reply content is obtained based on scene information of the preferred embodiment of the present invention；
Fig. 2 is that the preferred embodiment of the present invention assumes that the scene image of the communicating terminal of sentence is initiated in the reception chat of collection；
Fig. 3 is the scene image and vision list that the preferred embodiment of the present invention initiates the reception chat for assuming collection the communicating terminal of sentence
The vision word result figure obtained after word dictionary matching；
Fig. 4 is that the preferred embodiment of the present invention simplifies the method flow diagram that embodiment obtains chat reply content for first；
Fig. 5 is that the preferred embodiment of the present invention simplifies the method flow diagram that embodiment obtains chat reply content for second；
Fig. 6 is the apparatus structure block diagram that chat reply content is obtained based on scene information of the preferred embodiment of the present invention.
Description of reference numerals：
10th, reception device；20th, topic classification acquisition device；30th, scene information acquisition device is aided in；40th, coalignment.
Specific embodiment
Embodiments of the invention are described in detail below in conjunction with accompanying drawing, but the present invention can be defined by the claims and cover
Multitude of different ways implement.
With reference to Fig. 1, the preferred embodiments of the present invention provide a kind of method for obtaining chat reply content based on scene information, including：
Step S101, receives chat and initiates sentence；
Step S102, initiates sentence and obtains the topic classification belonging to initiating sentence of chatting according to chat；
Step S103, gathers the content information of the auxiliary scene entry associated with topic classification set in advance, obtains auxiliary scene
Information；
Step S104, initiates chat according to auxiliary scene information in topic database corresponding with topic classification set in advance
Sentence carries out Data Matching, and using the result of Data Matching as chat reply content corresponding with chat initiation sentence.
The method for obtaining chat reply content based on scene information that the present invention is provided, is initiated by automatic data collection with the chat for receiving
The content information of the classification associated auxiliary scene entry of topic belonging to sentence obtains auxiliary scene information, and combines and aid in scene information
Chat reply content corresponding with chat initiation sentence is obtained, the existing method for obtaining chat reply content is solved and is not bound with participation
The scene information of the communication two party of chat, causes the single fixation of chat reply content for obtaining, the intelligence degree of chat it is low and
The not good technical problem of Consumer's Experience, realizes according to the different chat reply contents of different scene information acquisitions, and obtain
Chat reply content fully combines the scene information of communication two party, and closely bound up with communication two party, embodies higher intelligence
Change and personalized level.Additionally, obtaining chat reply content automatically without the need for human-edited based on scene information, chat meeting is improve
Words speed, improves Consumer's Experience.
Auxiliary scene entry in the present embodiment is set in advance for obtaining the communicating terminal phase initiated or receive chat initiation sentence
The entry of pass information, such as hobby entry, circle of friends state entry, recently mood entry, concern topic entry etc..
The present embodiment can primarily determine that the reply theme of chat reply content by obtaining the topic classification belonging to chat initiation sentence first
Or direction is replied, and topic classification division is carried out by initiating sentence to chat first, be conducive to what is subsequently obtained based on topic classification
Chat reply content is more targeted, professional, while improve the acquisition efficiency for obtaining chat reply content.
With reference to table 1, table 1 gives several different topic classifications and auxiliary scene entry associated with it.For example, if topic
When being categorized as " tourism " topic classification, then by daily experience, communicating terminal is chatted belonging to " tourism " topic classification
It initiates sentence when being replied, must consider the factor of weather quality, the factor either with or without the time, locality factors and
Whether tour interest hobby factor etc. is had, and when " sending out mail " topic classification is categorized as to topic, then can by daily experience
Know, when communicating terminal is replied the chat initiation sentence for belonging to " sending out mail " topic classification, E-mail address must be can take into account
The E-mail address factor for sending or receiving, and the factor of weather quality is not taken into account that substantially, it should be noted that this enforcement
Example is not fixed for the auxiliary scene entry of different topic classification associateds set in advance, and is only according to day
Often experience is artificially given, namely user can auxiliary scene entry that as needed sets itself is associated with topic classification.
Table 1
Alternatively, the topic classification according to belonging to sentence acquisition chat initiation sentence is initiated in chat includes：
The chat content above that sentence is initiated in chat is obtained, and the chat content above that chat initiation sentence and chat initiate sentence is merged into
The preprocessed text of text formatting；
Extract the keyword of preprocessed text；
Topic classification according to belonging to keyword determines chat initiation sentence.
Specifically, the present embodiment can determine pretreatment according to the word frequency statisticses of the participle text to obtaining after preprocessed text participle
The keyword of text, it is also possible to which pretreatment is determined according to the Weighted Term Frequency statistics of the participle text to obtaining after preprocessed text participle
The keyword of text.It is not merely based on chat that this determines that the topic classification belonging to sentence is initiated in chat mainly due to the present embodiment
Sentence is initiated, but initiates sentence and chat based on chat to initiate the chat content above of sentence, and in actual implementation process, chat
Initiate sentence and have more reference price to obtaining the topic classification that chat is initiated belonging to sentence relative to the chat content above that sentence is initiated in chat
Value, therefore the present embodiment determines preprocessed text using the Weighted Term Frequency statistics of the participle text to obtaining after preprocessed text participle
Keyword, namely to from chat initiate sentence closer to chat content give weight bigger weight coefficient.The present embodiment is in basis
Preprocessed text is obtained after keyword, can adopt the corresponding content of keyword that the topic classification belonging to sentence is initiated as chat,
Topic classification corresponding with keyword can be inquired about with the relationship maps table of topic classification according to default keyword.
The present embodiment is initiated the chat content above of sentence by combining chat initiation sentence and chat and obtains the topic chatted belonging to initiation sentence
Classification, has taken into full account that the chat linguistic context residing for sentence is initiated in chat, obtains belonging to it relative to chat initiation sentence is relied solely on
The degree of accuracy of topic classification is higher.And weighting by way of to preprocessed text participle after obtain participle text word frequency statisticses it is true
Determine keyword so that the affiliated topic classification that sentence is initiated in the chat of acquisition is more accurate.
It should be noted that when initiation sentence of chatting in the present embodiment does not chat content above, the present embodiment is then only according to merely
It is initiated sentence and obtains topic classification belonging to it, and obtain in the present embodiment chat initiate sentence chat content above scope by with
Family is self-defined, for example, can obtain the chat content above in the chat content above in certain hour, or certain content bar number.
Alternatively, the content information of the auxiliary scene entry associated with topic classification set in advance is gathered, auxiliary scene letter is obtained
Breath includes：
The auxiliary scene entry associated with topic classification is preset, association auxiliary scene entry is obtained；
Content corresponding with association auxiliary scene entry is obtained by the way of calculating, reasoning, inquiry, search or its any combination
Information, obtains auxiliary scene information.
In actual implementation process, the present embodiment can by the personal information to communication two party, social information, communication information,
Shopping online information, online footprint information, user behavior information, the calculating of the data such as user service information, reasoning, inquiry,
The mode of search or its any combination obtains content information corresponding with association auxiliary scene entry, wherein, user behavior information is
Finger user seeks the information of the behaviors such as requirement express, acquisition of information, the Information Pull showed during his required information.
Communication information is included the history log of user oneself, is remembered using the history communication of the other users of same communication applications software again
The log that record and third-party application software are provided.Specifically, log includes that message registration and note are recorded again, and
Note record includes SMS record or instant communication information record again, and message registration includes mobile phone call history and IMU again
News voice and video message registration.
For example when it is geographical location information entry to aid in scene entry, the acquisition of information of inquiry GPS location can be passed through, work as auxiliary
Scene entry be apart from entry when, then the geographical position difference that can pass through to calculate communication two party is obtained, when auxiliary scene entry is for most
During nearly concern topic entry, the nearest web page browsing record of search communication user can be passed through and obtained, when auxiliary scene entry is weather
During entry, both can be obtained by inquiry weather web page, can also pass through the weather information reasonings such as temperature, wind direction, the humidity of collection
Obtain.
Alternatively, sentence is initiated to chat in topic database corresponding with topic classification set in advance according to auxiliary scene information
Carrying out Data Matching includes：
Topic database corresponding with topic classification is created, wherein, topic database includes at least one with topic classification as chat
The sample chat of theme is right, and sample chat including sample chat to initiating sentence and corresponding reply condition ID of sentence is initiated in sample chat
And conclusion content corresponding with condition ID of reply；
Using the establishment rule of reply condition ID is created to aiding in scene information to be identified, mark ID is obtained；
The matching in topic database initiates the chat of sentence identical sample and initiates sentence with chat, and right sentence is initiated with sample chat
Matching replys condition ID with mark ID identicals in reply condition ID answered, and will reply condition ID pair with mark ID identicals
Result of the conclusion content answered as Data Matching.
The topic database corresponding with topic classification that the present embodiment is created includes at least one sample with topic classification as theme of chatting
This chat is right, sample chat to initiate sentence including sample chat and sample chat initiate corresponding reply condition ID of sentence and with return
The corresponding conclusion content of multiple condition ID, initiates sentence and is chatting with sample by matching and chat initiation sentence identical sample chat
Initiate matching in corresponding reply condition ID of sentence and reply condition ID with mark ID identicals, it is contemplated that the institute associated with topic classification
There is the content information of auxiliary scene entry, so that the chat reply content for obtaining fully combines the scene information of communication two party,
And it is closely bound up with communication two party, embody higher intellectuality and personalized level.It should be noted that in actual enforcement
During, the present embodiment can also initiate the most like sample chat initiation sentence of sentence and chat with sample by matching and chat
Initiate matching in corresponding reply condition ID of sentence and reply condition ID with mark ID identicals, obtain the result of Data Matching.
The establishment of establishment condition ID in the present embodiment is regular by User Defined, such as when topic classification is greeted for blessing, and with
When the auxiliary scene entry of the topic classification association only includes 2, specially send chat initiation sentence and receive chat and initiate sentence
The weather entry of the communicating terminal of sentence is initiated in the relationship entries of communicating terminal and transmission chat.Then it is directed to each in topic database
Sentence is initiated in sample chat, is being respectively created transmission chat initiation sentence and is being received the relationship entries of the communicating terminal for initiating sentence of chatting and send out
The reply condition ID during the weather entry of the communicating terminal for initiating sentence of chatting is sent by User Defined, such as weather entry,
" 1 " can be defined and represent that weather is good, " 2 " represent that weather is poor, it is also possible to be defined " 1 " and represent sunny, " 2 " represent and rain, " 3 "
Expression is snowed etc..Assume chat initiation sentence is sent in the present embodiment and chat is received to initiate the relationship entries of sentence including 4 kinds of contents
(specially " 1 " represents that relatives' relation, " 2 " represent that friends, " 3 " represent that Peer Relationships, " 4 " represent that classmate is closed to option
System), send the weather entry of the communicating terminal that sentence is initiated in chat include 2 kinds of content options (specially " 1 " represent weather it is good, " 2 "
Represent that weather is poor), then in the corresponding topic database of the daily blessing greeting topic classification of establishment, need foundation to include total Options
The conclusion content of combination, that is, replying condition ID includes { " 11 ", " 21 ", " 31 ", " 41 ", " 12 ", " 22 ", " 32 ", " 42 " },
Totally eight reply conditions ID, namely the topic database initiate sentence for the chat of each sample, return including 8
Multiple condition ID and conclusion content corresponding with condition ID difference is replied, it should be noted that the present embodiment is for each
The conclusion content of individual reply condition ID can be a session content, or a plurality of session content.Create in the present embodiment
There is the function of learning automatically and automatically update with the topic database of topic classification, specifically, when collecting auxiliary scene entry
Content information be not included in the topic database for having created aid in scene entry content information when, for example with regard to " blessing
In greeting " topic database, for " weather " aids in the content information option of scene entry only to include three, respectively：“1”
Represent sunny, " 2 " represent and rain, " 3 " represent and snow, then when the content information for collecting " weather " auxiliary scene entry is
When " cloudy day ", system will create the content information option that field number " 4 " represents the cloudy day in the case where " weather " aids in scene entry,
And correspondence updates reply condition ID and corresponding conclusion content.
The present embodiment is regular to aiding in scene information initially with the establishment for creating reply condition ID after auxiliary scene information is obtained
It is identified, obtains mark ID, specifically, it is assumed that the chat that sends of the present embodiment collection initiates sentence and receive to chat to initiate sentence
The content information of the relationship entries of communicating terminal is " colleague ", sends the content letter of the weather entry of the communicating terminal of chat initiation sentence
Cease for " good ", then the mark for obtaining ID is " 31 ", then matching initiates sentence identical sample with chat in topic database
Sentence is initiated in chat, and matching replys condition with mark ID identicals in reply condition ID corresponding with sample chat initiation sentence
ID, and conclusion content corresponding with mark ID identical replies condition ID is replied into interior as chat corresponding with chat initiation sentence
Hold.So, sentence is initiated for same chat, different marks ID can be obtained according to different auxiliary scene informations, so as to obtain
Different conclusion contents, that is, reply content of chatting are obtained, it is achieved thereby that intelligently obtaining and chat according to the scene information of communication two party
Initiate the corresponding chat reply content of sentence so that the chat reply content obtained based on scene information is properer, more intelligent and human nature
Change, with higher intelligence degree and personalized level.
Alternatively, scene entry is aided in include：
Send and/or receive name entries, sex entry, age entry, instant messaging account that the communicating terminal of sentence is initiated in chat
Entry, E-mail address entry, home address entry, occupational group's entry, post entry, work unit's entry, unit
Address entry, Bank Account Number entry, good friend's impression entry, address list packet entry, relationship entries, hobby entry, friend
Friend's circle state entry, recently mood entry, concern topic entry, time entry, red-letter day entry, season entry, geographical position
Data entries, apart from entry, scene image entry.
The scene entry of the present embodiment is not limited to only including above-mentioned scene entry, while being also not necessarily limited to include above-mentioned whole scene
Entry, is specifically chosen by User Defined or as needed with system design complexity and design accuracy.
Alternatively, the content information of the scene image entry in collection auxiliary scene entry includes：
Collection sends and/or receives the scene image that the communicating terminal of sentence is initiated in chat；
Using the area-of-interest of DOG operator extraction scene training images, and calculate the area-of-interest of scene training image
SIFT feature；
The SIFT feature of the area-of-interest of scene training image is clustered using K mean cluster algorithm, obtains multiple clusters
Center, and set up the vision word dictionary being made up of vision word corresponding with each cluster centre；
Using the area-of-interest of DOG operator extraction scene images, and match in vision word dictionary emerging with the sense of scene image
The immediate vision word of SIFT feature in interesting region；
The good SVMs of training in advance is adopted to scene image according to the distribution of the vision word of the area-of-interest of scene image
Grader is classified, and is sent and/or received the content information of the scene image entry of the communicating terminal of chat initiation sentence.
SIFT feature in the present embodiment is a kind of scale invariant feature conversion, is that extreme point is found in space scale, and is extracted
Go out its position, yardstick, rotational invariants.Specifically, the present embodiment matches emerging with the sense of scene image in vision word dictionary
The detailed process of the immediate vision word of SIFT feature in interesting region is：By the SIFT of each area-of-interest of scene image
The SIFT feature of feature cluster centre corresponding with each vision word in vision word dictionary carries out Similarity Measure, works as calculating
When going out the similarity of area-of-interest and vision word more than predetermined threshold value, it is with the area-of-interest most to be considered as the vision word
Close vision word.So, just all area-of-interests of scene image can be represented with vision word, and based on scene graph
The distribution situation design of the vision word as in and training grader, so as to finally be sent and/or be received chat the logical of sentence is initiated
The content information of the scene image entry of news terminal.
With reference to Fig. 2, Fig. 2 is present embodiment assumes that the communicating terminal that sentence is initiated in the reception chat of collection receives the scene that sentence is initiated in chat
Image, is extracted by the SIFT feature of five area-of-interests to the scene image, and by calculating each region of interest
The SIFT feature in domain and the similarity of vision word dictionary, so as to obtain and the immediate vision word of above-mentioned five area-of-interests,
Respectively " sky ", " national flag ", " building ", " lion ", " bridge ", referring in particular to Fig. 3, then further according to obtain with it is upper
The immediate vision word of five area-of-interests is stated, is obtained using the good SVMs of training in advance and is received chat and initiate sentence
The content information of the scene image entry of communicating terminal.
The present embodiment is sent by collection and/or is received the scene image of the communicating terminal that sentence is initiated in chat and sent and/or received
The content information of the scene image entry of the communicating terminal of sentence is initiated in chat so that the auxiliary scene based on scene image acquisition of information
Information closer to real scene information, and cause using based on scene image information acquisition and chat initiate the corresponding chat of sentence
Reply content more has personalization, and more meets communication linguistic context.
Simplify embodiment below for two is carried out to the process and principle that obtain chat reply content based on scene information of the present invention
Illustrate further.
Simplifying the communication scene that embodiment one is directed to is：Communicating terminal A is " to want to go together to communicating terminal B transmission contents
Go window-shopping" the chat of text formatting initiate sentence, with reference to Fig. 4, communicating terminal B obtains chat reply content based on scene information
Method includes：
Step S201, receives chat and initiates sentence.Specifically, character string of the sentence for text formatting is initiated in the chat that the present embodiment is received,
" want to go to go window-shopping together”.
Step S202, obtains the chat content above that sentence is initiated in chat, and chat initiation sentence and chat are initiated into the chat above of sentence
Content is merged into the preprocessed text of text formatting.Specifically, it is assumed that the content above of chat initiation sentence is wrapped altogether in the present embodiment
Four conversation contents are included, specially：Communicating terminal A：Hurry/ communicating terminal B：Fortunately./ communicating terminal A：Feel recently
Wear without suitable clothes！/ communicating terminal B：Right.The preprocessed text for then obtaining is { busy/ not bad./ feel recently
Wear without suitable clothes！/ right./ want to go to go window-shopping together}.
Step S203, extracts the keyword of preprocessed text.By the way that participle is carried out to preprocessed text, stop words, part of speech is removed
After the operations such as mark, semantic disambiguation, it is assumed that the participle text of extraction includes { " busy ", " clothes ", " wearing ", " going window-shopping " }, and this
Embodiment takes the mode that Weighted Term Frequency is counted to carry out word frequency statisticses, and chooses the corresponding participle text of maximum weighted word frequency statisticses value
For the keyword of preprocessed text.Specifically, because the preprocessed text of the present embodiment includes five chat contents altogether, then divide
Five weight coefficients not arranged are respectively k1=0.5, k2=0.2, k3=0.15, k4=0.1, k5=0.05, wherein weight coefficient with
Chat content in preprocessed text from chat initiate sentence time interval gradually successively decrease from small to large, and the occurrence of weight coefficient by
User is self-defined as needed.
Because the word frequency number of the participle text of the present embodiment extraction is all one, therefore passes through and word frequency meter is weighted to each participle text
After calculation, it is possible to obtain keyword is " going window-shopping ".
Step S204, the topic classification according to belonging to keyword determines chat initiation sentence.Specifically, the present embodiment adopts keyword
Corresponding content initiates the topic classification belonging to sentence as chat, i.e., the topic that chat is initiated belonging to sentence in the present embodiment is categorized as " strolling
Street ".
Step S205, gathers the content information of the auxiliary scene entry associated with topic classification set in advance, obtains auxiliary scene
Information.Specifically, it is assumed that the present embodiment scene entry associated with topic classification set in advance has 3, and respectively f1=sends out
Send chat initiation sentence and receive the relationship entries of the communicating terminal for initiating sentence of chatting, f2=transmission chats and initiate sentence and reception chat initiation
The weather entry of the communicating terminal that chat initiation sentence is received apart from entry, f3=of the communicating terminal of sentence, is specifically shown in Table 1.And assume
The present embodiment pass through inquire-receive chat initiate sentence communicating terminal address list remark information, obtain f1=send chat initiate sentence and
Receive chat initiate sentence communicating terminal relationship entries content information be " friend ", and by calculate send chat initiate sentence and
The geographical position difference acquisition f2=for receiving the communicating terminal for initiating sentence of chatting sends the communication for initiating sentence and reception chat initiation sentence of chatting
The content information apart from entry of terminal is that " remote " (returns " remote " content letter when pre-defined geographical position difference is more than 10 kilometers
Cease to apart from entry), and by searching for the Weather information for receiving the communicating terminal geographic location that sentence is initiated in chat on the internet
The content information for obtaining the weather entry that f3=receives the communicating terminal for initiating sentence of chatting is " sunny ".
Step S206, creates topic database corresponding with topic classification, wherein, topic database includes at least one with topic
The sample chat for being categorized as chat theme is right, and sample chat is corresponding to initiating sentence including sample chat initiation sentence and sample chat
Reply condition ID and conclusion content corresponding with condition ID of reply.Specifically, it is assumed that the present embodiment definition is for f1 entries
Content information option has Nf1Kind, the content information option for f2, f3 entry have respectively Nf2And Nf3Kind, then words of " going window-shopping "
Chat for same sample in topic database and initiate the reply condition ID number of combinations=N of sentencef1*Nf2*Nf3Kind.
Step S207, using the establishment rule of reply condition ID is created to aiding in scene information to be identified, obtains mark ID.
Specifically, it is assumed that the present embodiment Nf1Number be 6, Nf2Number be 3, Nf3Number be 5, be specifically shown in Table two, then pass through
The establishment rule of inquiry establishment reply condition ID can obtain expression and send the communication end for initiating sentence and reception chat initiation sentence of chatting
Corresponding field number is " 2 " to the relation at end when being " friend ", expression sends chat initiation sentence and reception is chatted and initiates the communication of sentence
Terminal apart from entry be " remote " when corresponding field number be " 1 ", represent that the weather of communicating terminal for receiving chat initiation sentence is
Corresponding field number is " 1 " when " sunny ", so as to being expressed as auxiliary scene information and replying condition No. ID consistent No. ID.
It should be noted that in specific implementation process, the present embodiment is respectively provided with content information bag for each auxiliary scene entry
Containing the situation (specifically being represented with " 0 " field number) for " sky ", this is because in actual implementation process, in fact it could happen that do not have
Method obtains the corresponding content information of auxiliary scene entry, such as in the present embodiment, do not have if receiving the communicating terminal of chat initiation sentence
When installing GPS location or not opening acquisition geographical position authority, then the data that system is returned are sky.For example need at some again
The situation of auxiliary scene entry content information is obtained by internet checking and search, in communicating terminal network linking or entrance are disconnected
It is the Search Results that can not obtain correlation during without network signal region.
Table 2
| Relationship entries | Field number | Apart from entry | Field number | Weather entry | Field number |
| It is empty | 0 | It is empty | 0 | It is empty | 0 |
| Colleague | 1 | Far | 1 | It is sunny | 1 |
| Friend | 2 | Closely | 2 | Cloudy day | 2 |
| Relatives | 3 | Rain | 3 | ||
| Classmate | 4 | Snow | 4 | ||
| The superior and the subordinate | 5 |
Step S208, matching initiates the chat of sentence identical sample and initiates sentence with chat in topic database, and is chatting with sample
It is initiated matching in corresponding reply condition ID of sentence and replys condition ID with mark ID identicals, and will return with mark ID identicals
Result of the multiple corresponding conclusion content of condition ID as Data Matching.Specifically, the present embodiment is identical in matching and chat initiation sentence
Or similar sample chat is initiated after sentence, according to mark No. ID (" 2+1+1 ") same reply condition ID to be readily available
Number, so as to the corresponding conclusion content of condition ID will be replied as reply content corresponding with chat initiation sentence, it is assumed that the present embodiment pin
Sentence " wanting to go to go window-shopping together " is initiated sample chat, in the conclusion corresponding with condition ID " 2+1+1 " is replied of acquisition
Hold for 3, respectively " parent, I from you that too away from, next time about could again", " today, weather was pretty good, and I just also wants to
Out stroll.", " although I from you that very away from, today, weather was pretty good, so still figure out strolling ".Chat in actual
When it is replied, system will provide this three chat reply contents and select for user.
As can be seen that when the content information of the auxiliary scene entry of collection is different, mark ID of acquisition is different, so as to what is obtained
Chat reply content is different, therefore the method for solving existing acquisition chat reply content is not bound with the communication two party of participation chat
Scene information, causes the single fixation of chat reply content for obtaining, the skill that intelligence degree is low and Consumer's Experience is not good of chat
Art problem, realizes and obtains different chat reply contents according to different scene informations, and the chat reply content for obtaining is abundant
The scene information of communication two party is combined, and it is closely bound up with communication two party, embody higher intellectuality and personalized level.
Additionally, the present embodiment obtains chat reply content without the need for human-edited automatically based on scene information, chat sessions speed is improve,
Improve Consumer's Experience.
Simplifying the communication scene that embodiment two is directed to is：Communicating terminal A is " busy to communicating terminal B transmission contents" text
Sentence is initiated in the chat of this form, and with reference to Fig. 5, communicating terminal B is included based on the method that scene information obtains chat reply content：
Step S301, receives chat and initiates sentence.Specifically, character string of the sentence for text formatting is initiated in the chat that the present embodiment is received,
It is i.e. " busy”.
Step S302, initiates sentence and obtains the topic classification belonging to initiating sentence of chatting according to chat.Specifically, it is assumed that in the present embodiment
It is sky that the content above of sentence is initiated in chat, and in view of the chat content of initiating sentence is simple, therefore easily obtain chat and initiate belonging to sentence
Topic is categorized as " greeting ".
Step S303, presets the auxiliary scene entry associated with topic classification.Specifically, it is assumed that the present embodiment presets
The auxiliary scene entry associated with topic classification there was only 1, specially f1=receives the scene graph that the communicating terminal of sentence is initiated in chat
Slice mesh.
Step S304, collection receives the scene image that the communicating terminal of sentence is initiated in chat.
Step S305, extracts the area-of-interest of scene image, and matches in vision word dictionary interested with scene image
The immediate vision word of SIFT feature in region.
Specifically, the present embodiment is first by the region of interest of DOG (Difference of Gaussian) operator extraction scene image
Domain, then calculates the SIFT feature of each area-of-interest, and matches in vision word dictionary interested with scene image
The immediate vision word of SIFT feature in region.Assume that the present embodiment is matched and three area-of-interests pair after matching
The vision word answered is respectively " road sign ", " track ", " apart from direction board ".
Step S306 is good using training in advance to scene image according to the distribution of the vision word of the area-of-interest of scene image
Support vector machine classifier is classified, and obtains the content information of auxiliary scene entry.Specifically, the present embodiment using support to
The method design grader of amount machine, and 9 class images of known scene classification are trained in the training stage (airport, ocean,
Forest, village, street, trees, high building, highway, office), the different training sample of 100 width is included per class image
This image.By the scene image comprising three vision words that obtains step S305, (" road sign ", " track ", " distance refers to
Show board ") the good support vector machine classifier of training in advance is input to, can be received the scene that the communicating terminal of sentence is initiated in chat
The content information of image entry is " highway ".
Step S307, initiates chat according to auxiliary scene information in topic database corresponding with topic classification set in advance
Sentence carries out Data Matching, and using the result of Data Matching as chat reply content corresponding with chat initiation sentence.Specifically, it is false
If in the present embodiment topic database corresponding with topic classification " greeting " set in advance, initiating sentence for chat " busy”
And aid in scene entry content information for " highway " reply content include it is multinomial, for example " I in high speed, not side
Just write in reply and cease, lower high speed is contacted with you.", " it is too shy, be inconvenient to breath of writing in reply now, contact with you after a while " etc., then divide
These chat reply contents are not included being selected for user in communicating terminal.
The present embodiment receives the scene image that the communicating terminal of sentence is initiated in chat by collection, and the scene image based on collection is obtained
The content information of auxiliary scene entry so that the auxiliary scene information obtained based on the content information closer to real scene information,
So that using, the tool high with the chat reply content intelligence degree that chat initiation sentence is matched that are obtained based on auxiliary scene information
There is personalization.
With reference to Fig. 6, the device that chat reply content is obtained based on scene information that the preferred embodiments of the present invention are provided, including：
Reception device 10, for receiving chat sentence is initiated；
Topic classification acquisition device 20, for initiating sentence according to chat the topic classification belonging to initiating sentence of chatting is obtained；
Auxiliary scene information acquisition device 30, for gathering the content of the auxiliary scene entry associated with topic classification set in advance
Information, obtains auxiliary scene information；
Coalignment 40, for according to auxiliary scene information in topic database corresponding with topic classification set in advance to merely
It is initiated sentence and carries out Data Matching, and using the result of Data Matching as chat reply content corresponding with chat initiation sentence.
Further, topic classification acquisition device 20 includes：
Preprocessed text acquisition device, for obtaining the chat content above that sentence is initiated in chat, and chat initiation sentence and chat is sent out
The chat content above of the first line of a poem is merged into the preprocessed text of text formatting；
Keyword extracting device, for extracting the keyword of preprocessed text；
Topic classification determining device, for determining the topic classification belonging to initiating sentence of chatting according to keyword.
Further, scene information acquisition device 30 is aided in include：
Setting device, for presetting the auxiliary scene entry associated with topic classification, obtains association auxiliary scene entry；
Computational reasoning device, for being obtained by the way of calculating, reasoning, inquiry, search or its any combination and associating auxiliary
The corresponding content information of scene entry, obtains auxiliary scene information.
Further, coalignment 40 includes：
Topic database creating device, for creating topic database corresponding with topic classification, wherein, topic database includes
At least one sample chat with topic classification as theme of chatting is right, and sample chat initiates sentence to chatting including sample and sample is chatted
It initiates corresponding reply condition ID of sentence and conclusion content corresponding with condition ID of reply；
Identity device, for using the establishment rule of reply condition ID is created to aiding in scene information to be identified, obtaining mark ID；
ID coalignments, initiate the chat of sentence identical sample and initiate sentence for the matching in topic database and chat, and with
Sample chat initiates matching in corresponding reply condition ID of sentence and replys condition ID with mark ID identicals, and will be with mark ID phases
Result of the same corresponding conclusion content of reply condition ID as Data Matching.
The device that chat reply content is obtained based on scene information that the present invention is provided, is initiated by automatic data collection with the chat for receiving
The content information of the classification associated auxiliary scene entry of topic belonging to sentence obtains auxiliary scene information, and combines and aid in scene information
Chat reply content corresponding with chat initiation sentence is obtained, the existing method for obtaining chat reply content is solved and is not bound with participation
The scene information of the communication two party of chat, causes the single fixation of chat reply content for obtaining, the intelligence degree of chat it is low and
The not good technical problem of Consumer's Experience, realizes according to the different chat reply contents of different scene information acquisitions, and obtain
Chat reply content fully combines the scene information of communication two party, and closely bound up with communication two party, embodies higher intelligence
Change and personalized level.Additionally, obtaining chat reply content automatically without the need for human-edited based on scene information, chat meeting is improve
Words speed, improves Consumer's Experience.The present embodiment obtains the specific work process of the device of chat reply content based on scene information
It is former with work with the course of work of the method for obtaining chat reply content based on scene information that operation principle can refer to the present embodiment
Reason.Reception in the embodiment of the present invention or send chat initiate sentence communication terminal equipment can be desktop computer, panel computer,
Personal digital assistant, mobile phone, television set, vehicle-mounted computer, wearable communication equipment etc..
The preferred embodiments of the present invention are the foregoing is only, the present invention is not limited to, for those skilled in the art
For, the present invention can have various modifications and variations.All any modifications within the spirit and principles in the present invention, made, etc.
With replacement, improvement etc., should be included within the scope of the present invention.
Claims (10)
1. it is a kind of based on scene information obtain chat reply content method, it is characterised in that include：
Receive chat and initiate sentence；
Sentence is initiated according to the chat and obtains the topic classification belonging to initiating sentence of chatting；
The content information of the collection auxiliary scene entry associated with the topic classification set in advance, obtains auxiliary scene information；
Sentence is initiated the chat in topic database corresponding with the topic classification set in advance according to the auxiliary scene information carries out Data Matching, and using the result of Data Matching as chat reply content corresponding with the chat initiation sentence.
2. it is according to claim 1 based on scene information obtain chat reply content method, it is characterised in that according to it is described chat initiate sentence obtain it is described chat initiate sentence belonging to topic classification include：
The chat content above that sentence is initiated in the chat is obtained, and the chat content above that the chat initiation sentence and the chat initiate sentence is merged into the preprocessed text of text formatting；
Extract the keyword of the preprocessed text；
Topic classification according to belonging to the keyword obtains the chat initiation sentence.
3. the method that chat reply content is obtained based on scene information according to claim 2, it is characterised in that the content information of collection auxiliary scene entry associate with the topic classification set in advance, acquisition aids in scene information to include：
The auxiliary scene entry associated with the topic classification is preset, association auxiliary scene entry is obtained；
Content information corresponding with the association auxiliary scene entry is obtained by the way of calculating, reasoning, inquiry, search or its any combination, auxiliary scene information is obtained.
4. it is according to claim 3 based on scene information obtain chat reply content method, include characterized in that, initiating sentence to the chat in topic database corresponding with the topic classification set in advance according to the auxiliary scene information and carrying out Data Matching：
Create topic database corresponding with the topic classification, wherein, the topic database includes that at least one sample chat with the topic classification as theme of chatting is right, and the sample chat initiates corresponding reply condition ID of sentence and conclusion content corresponding with reply condition ID to initiating sentence including sample chat with sample chat；
The auxiliary scene information is identified using the establishment rule for creating reply condition ID, obtains mark ID；
Match in the topic database and initiate sentence identical sample chat initiation sentence with the chat, and initiating to be matched in corresponding reply condition ID of sentence with sample chat and the mark ID identicals reply condition ID, and using conclusion content corresponding with mark ID identicals reply condition ID as Data Matching result.
5. it is according to claim 4 based on scene information obtain chat reply content method, it is characterised in that the auxiliary scene entry includes：
Send and/or receive the name entries that the communicating terminal of sentence is initiated in the chat, sex entry, age entry, instant messaging account entry, E-mail address entry, home address entry, occupational group's entry, post entry, work unit's entry, unit address entry, Bank Account Number entry, good friend's impression entry, address list is grouped entry, relationship entries, hobby entry, circle of friends state entry, mood entry, topic entry is paid close attention to recently, time entry, red-letter day entry, season entry, geographical location information entry, apart from entry, scene image entry.
6. the method that chat reply content is obtained based on scene information according to claim 5, it is characterised in that the content information of scene image entry in the collection auxiliary scene entry includes：
Collection sends and/or receives the scene image that the communicating terminal of sentence is initiated in the chat；
Using the area-of-interest of DOG operator extraction scene training images, and calculate the SIFT feature of the area-of-interest of the scene training image；
The SIFT feature of the area-of-interest of the scene training image is clustered using K mean cluster algorithm, obtains multiple cluster centres, and set up the vision word dictionary being made up of vision word corresponding with cluster centre each described；
Using the area-of-interest of scene image described in DOG operator extractions, and match in the vision word dictionary and the immediate vision word of the SIFT feature of the area-of-interest of the scene image；
The scene image is classified using the good support vector machine classifier of training in advance according to the distribution of the vision word of the area-of-interest of the scene image, is sent and/or received the content information of the scene image entry of the communicating terminal of the chat initiation sentence.
7. it is a kind of based on scene information obtain chat reply content device, it is characterised in that include：
Reception device, for receiving chat sentence is initiated；
Topic classification acquisition device, for initiating sentence according to the chat topic classification belonging to initiating sentence of chatting is obtained；
Auxiliary scene information acquisition device, for gathering the content information of the auxiliary scene entry associated with the topic classification set in advance, obtains auxiliary scene information；
Coalignment, for sentence to be initiated the chat in topic database corresponding with the topic classification set in advance according to the auxiliary scene information carry out Data Matching, and using the result of Data Matching as chat reply content corresponding with the chat initiation sentence.
8. it is according to claim 7 based on scene information obtain chat reply content device, it is characterised in that the topic classification acquisition device includes：
Preprocessed text acquisition device, for obtaining the chat content above that sentence is initiated in the chat, and is merged into the preprocessed text of text formatting by the chat content above that the chat initiation sentence and the chat initiate sentence；
Keyword extracting device, for extracting the keyword of the preprocessed text；
Topic classification determining device, for determining the topic classification belonging to initiating sentence of chatting according to the keyword.
9. it is according to claim 8 based on scene information obtain chat reply content device, it is characterised in that the auxiliary scene information acquisition device includes：
Setting device, for presetting the auxiliary scene entry associated with the topic classification, obtains association auxiliary scene entry；
Computational reasoning device, for obtaining content information corresponding with the association auxiliary scene entry by the way of calculating, reasoning, inquiry, search or its any combination, obtains auxiliary scene information.
10. it is according to claim 9 based on scene information obtain chat reply content device, it is characterised in that the coalignment includes：
Topic database creating device, for creating topic database corresponding with the topic classification, wherein, the topic database includes that at least one sample chat with the topic classification as theme of chatting is right, and the sample chat initiates corresponding reply condition ID of sentence and conclusion content corresponding with reply condition ID to initiating sentence including sample chat with sample chat；
Identity device, for being identified to the auxiliary scene information using the establishment rule for creating reply condition ID, obtains mark ID；
ID coalignments, sentence identical sample chat initiation sentence is initiated for matching in the topic database with the chat, and initiating to be matched in corresponding reply condition ID of sentence with sample chat and the mark ID identicals reply condition ID, and using conclusion content corresponding with mark ID identicals reply condition ID as Data Matching result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510741292.9A CN106656732A (en) | 2015-11-04 | 2015-11-04 | Scene information-based method and device for obtaining chat reply content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510741292.9A CN106656732A (en) | 2015-11-04 | 2015-11-04 | Scene information-based method and device for obtaining chat reply content |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106656732A true CN106656732A (en) | 2017-05-10 |
Family
ID=58850843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510741292.9A Pending CN106656732A (en) | 2015-11-04 | 2015-11-04 | Scene information-based method and device for obtaining chat reply content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106656732A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107491493A (en) * | 2017-07-22 | 2017-12-19 | 长沙兔子代跑网络科技有限公司 | A kind of intelligence obtains the method and device for running chat record in generation |
| CN107526779A (en) * | 2017-07-22 | 2017-12-29 | 长沙兔子代跑网络科技有限公司 | A kind of method and device for excavating generation race client |
| CN108334388A (en) * | 2017-07-28 | 2018-07-27 | 腾讯科技（深圳）有限公司 | Session background process method, apparatus, computer equipment and storage medium |
| CN108416286A (en) * | 2018-03-02 | 2018-08-17 | 浙江天悦信息技术有限公司 | A kind of robot interactive approach based on real-time video chat scenario |
| CN108520046A (en) * | 2018-03-30 | 2018-09-11 | 上海掌门科技有限公司 | Search for the method and apparatus of chat record |
| CN109151044A (en) * | 2018-09-06 | 2019-01-04 | 广州酷狗计算机科技有限公司 | Information-pushing method, device, electronic equipment and storage medium |
| CN109977217A (en) * | 2019-04-09 | 2019-07-05 | 莫雨潜 | A kind of method, system and the storage medium of intelligence augmentative communication |
| CN110048934A (en) * | 2019-04-04 | 2019-07-23 | 厦门小圈网络科技有限公司 | A kind of method of the internal information classification and display of circle in chat tool |
| CN110216687A (en) * | 2019-04-29 | 2019-09-10 | 金华市盘古信息技术有限公司 | A kind of robot automatic chatting method, device, equipment and storage medium |
| WO2020078092A1 (en) * | 2018-10-17 | 2020-04-23 | 北京达佳互联信息技术有限公司 | Information processing method and apparatus, server, terminal and storage medium |
| CN111400502A (en) * | 2018-12-29 | 2020-07-10 | 北京快如科技有限公司 | Method and device for replying message |
| CN111475614A (en) * | 2020-03-09 | 2020-07-31 | 百度在线网络技术（北京）有限公司 | Knowledge inference dialogue method, knowledge inference dialogue device, electronic equipment and storage medium |
| CN112154640A (en) * | 2018-07-04 | 2020-12-29 | 华为技术有限公司 | Message playing method and terminal |
| CN112905770A (en) * | 2021-02-10 | 2021-06-04 | 华南师范大学 | Artificial intelligence mental health chatting robot facing professional profession based on corpus |
| CN112997451A (en) * | 2018-11-07 | 2021-06-18 | 微软技术许可有限责任公司 | Establishing an instant conference for active discussion threads |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1556631A (en) * | 2004-01-09 | 2004-12-22 | 贵阳朗玛信息技术有限公司北京分公司 | Method of realizing scene chat between customers in instant communication |
| CN101071418A (en) * | 2007-03-29 | 2007-11-14 | 腾讯科技（深圳）有限公司 | Chat method and system |
| CN101076061A (en) * | 2007-03-30 | 2007-11-21 | 腾讯科技（深圳）有限公司 | Robot server and automatic chatting method |
| US20080189367A1 (en) * | 2007-02-01 | 2008-08-07 | Oki Electric Industry Co., Ltd. | User-to-user communication method, program, and apparatus |
| CN101345717A (en) * | 2007-07-12 | 2009-01-14 | 英业达股份有限公司 | Instant communication system and method capable of automatic response |
| 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 |
| CN103390047A (en) * | 2013-07-18 | 2013-11-13 | 天格科技（杭州）有限公司 | Chatting robot knowledge base and construction method thereof |
| CN103955470A (en) * | 2014-03-28 | 2014-07-30 | 华为技术有限公司 | Hotspot topic pushing method and device |
| CN103995872A (en) * | 2014-05-21 | 2014-08-20 | 王青 | Method and system for discussions and chat on basis of scene in application |
| CN104461226A (en) * | 2013-09-23 | 2015-03-25 | 北京三星通信技术研究有限公司 | Chatting method, device and system used for network |
| US9037568B1 (en) * | 2013-03-15 | 2015-05-19 | Google Inc. | Factual query pattern learning |
| CN104951435A (en) * | 2015-07-28 | 2015-09-30 | 陈包容 | Method and device for displaying keywords intelligently during chatting process |
-
2015
- 2015-11-04 CN CN201510741292.9A patent/CN106656732A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1556631A (en) * | 2004-01-09 | 2004-12-22 | 贵阳朗玛信息技术有限公司北京分公司 | Method of realizing scene chat between customers in instant communication |
| US20080189367A1 (en) * | 2007-02-01 | 2008-08-07 | Oki Electric Industry Co., Ltd. | User-to-user communication method, program, and apparatus |
| CN101071418A (en) * | 2007-03-29 | 2007-11-14 | 腾讯科技（深圳）有限公司 | Chat method and system |
| CN101076061A (en) * | 2007-03-30 | 2007-11-21 | 腾讯科技（深圳）有限公司 | Robot server and automatic chatting method |
| CN101345717A (en) * | 2007-07-12 | 2009-01-14 | 英业达股份有限公司 | Instant communication system and method capable of automatic response |
| 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 |
| US9037568B1 (en) * | 2013-03-15 | 2015-05-19 | Google Inc. | Factual query pattern learning |
| CN103390047A (en) * | 2013-07-18 | 2013-11-13 | 天格科技（杭州）有限公司 | Chatting robot knowledge base and construction method thereof |
| CN104461226A (en) * | 2013-09-23 | 2015-03-25 | 北京三星通信技术研究有限公司 | Chatting method, device and system used for network |
| CN103955470A (en) * | 2014-03-28 | 2014-07-30 | 华为技术有限公司 | Hotspot topic pushing method and device |
| CN103995872A (en) * | 2014-05-21 | 2014-08-20 | 王青 | Method and system for discussions and chat on basis of scene in application |
| CN104951435A (en) * | 2015-07-28 | 2015-09-30 | 陈包容 | Method and device for displaying keywords intelligently during chatting process |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107526779A (en) * | 2017-07-22 | 2017-12-29 | 长沙兔子代跑网络科技有限公司 | A kind of method and device for excavating generation race client |
| CN107491493A (en) * | 2017-07-22 | 2017-12-19 | 长沙兔子代跑网络科技有限公司 | A kind of intelligence obtains the method and device for running chat record in generation |
| CN108334388A (en) * | 2017-07-28 | 2018-07-27 | 腾讯科技（深圳）有限公司 | Session background process method, apparatus, computer equipment and storage medium |
| CN108416286A (en) * | 2018-03-02 | 2018-08-17 | 浙江天悦信息技术有限公司 | A kind of robot interactive approach based on real-time video chat scenario |
| CN108520046A (en) * | 2018-03-30 | 2018-09-11 | 上海掌门科技有限公司 | Search for the method and apparatus of chat record |
| CN112154640A (en) * | 2018-07-04 | 2020-12-29 | 华为技术有限公司 | Message playing method and terminal |
| CN112154640B (en) * | 2018-07-04 | 2024-04-30 | 华为技术有限公司 | Message playing method and terminal |
| US11837217B2 (en) | 2018-07-04 | 2023-12-05 | Huawei Technologies Co., Ltd. | Message playing method and terminal |
| CN109151044B (en) * | 2018-09-06 | 2021-08-27 | 广州酷狗计算机科技有限公司 | Information pushing method and device, electronic equipment and storage medium |
| CN109151044A (en) * | 2018-09-06 | 2019-01-04 | 广州酷狗计算机科技有限公司 | Information-pushing method, device, electronic equipment and storage medium |
| US11483263B2 (en) | 2018-10-17 | 2022-10-25 | Beijing Dajia Internet Information Technology Co., Ltd. | Method and terminal for facilitating chat between users of two terminals |
| WO2020078092A1 (en) * | 2018-10-17 | 2020-04-23 | 北京达佳互联信息技术有限公司 | Information processing method and apparatus, server, terminal and storage medium |
| CN112997451B (en) * | 2018-11-07 | 2024-01-23 | 微软技术许可有限责任公司 | Establishing an instant conference for active discussion threads |
| CN112997451A (en) * | 2018-11-07 | 2021-06-18 | 微软技术许可有限责任公司 | Establishing an instant conference for active discussion threads |
| CN111400502A (en) * | 2018-12-29 | 2020-07-10 | 北京快如科技有限公司 | Method and device for replying message |
| CN110048934A (en) * | 2019-04-04 | 2019-07-23 | 厦门小圈网络科技有限公司 | A kind of method of the internal information classification and display of circle in chat tool |
| CN109977217A (en) * | 2019-04-09 | 2019-07-05 | 莫雨潜 | A kind of method, system and the storage medium of intelligence augmentative communication |
| CN110216687A (en) * | 2019-04-29 | 2019-09-10 | 金华市盘古信息技术有限公司 | A kind of robot automatic chatting method, device, equipment and storage medium |
| CN111475614B (en) * | 2020-03-09 | 2023-08-25 | 百度在线网络技术（北京）有限公司 | Knowledge reasoning dialogue method, apparatus, electronic device and storage medium |
| CN111475614A (en) * | 2020-03-09 | 2020-07-31 | 百度在线网络技术（北京）有限公司 | Knowledge inference dialogue method, knowledge inference dialogue device, electronic equipment and storage medium |
| CN112905770A (en) * | 2021-02-10 | 2021-06-04 | 华南师范大学 | Artificial intelligence mental health chatting robot facing professional profession based on corpus |
| CN112905770B (en) * | 2021-02-10 | 2024-09-13 | 华南师范大学 | Artificial intelligence psychological health chat robot based on corpus and oriented to professional occupation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106656732A (en) | Scene information-based method and device for obtaining chat reply content | |
| CN106649405A (en) | Method and device for acquiring reply prompt content of chat initiating sentence | |
| CN103631819B (en) | A kind of method and system of picture name | |
| CN106658441A (en) | Method and device of rapidly replaying unread information | |
| CN107577782B (en) | Figure similarity depicting method based on heterogeneous data | |
| CN101192235A (en) | Method, system and equipment for delivering advertisement based on user feature | |
| US20160110381A1 (en) | Methods and systems for social media-based profiling of entity location by associating entities and venues with geo-tagged short electronic messages | |
| CN105808695A (en) | Method and device for obtaining chat reply contents | |
| CN105718576B (en) | Personalized location recommender system relevant to geographical feature | |
| CN106649409A (en) | Method and apparatus for displaying search result based on scene information | |
| CN109033180A (en) | A kind of information-pushing method, device, computer installation and computer readable storage medium | |
| CN103279515B (en) | Recommendation method based on micro-group and micro-group recommendation apparatus | |
| CN106649404B (en) | Method and device for creating session scene database | |
| CN101834837A (en) | On-line landscape video active information service system of scenic spots in tourist attraction based on bandwidth network | |
| CN103279479A (en) | Emergent topic detecting method and system facing text streams of micro-blog platform | |
| CN104834695A (en) | Activity recommendation method based on user interest degree and geographic position | |
| CN102999507A (en) | Recommendation processing method and device for information of network microblog celebrities | |
| CN101350154A (en) | Method and apparatus for ordering electronic map data | |
| CN103514191A (en) | Method and device for determining keyword matching mode of target popularization information | |
| CN102323933A (en) | Information embedding and interaction system facing real-time communication and method | |
| CN107257362B (en) | Method and system for dynamically displaying events and matching chats on map according to attention degree of time | |
| CN103425649A (en) | Method and device for adding friend information | |
| CN103279483B (en) | A kind of topic Epidemic Scope appraisal procedure towards micro-blog and system | |
| CN104142936A (en) | Audio and video match method and audio and video match device | |
| CN101251853A (en) | System and method for digging user attribute based on user interactive records |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |