CN109033257A - Talk about art recommended method, device, computer equipment and storage medium - Google Patents
Talk about art recommended method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109033257A CN109033257A CN201810736928.4A CN201810736928A CN109033257A CN 109033257 A CN109033257 A CN 109033257A CN 201810736928 A CN201810736928 A CN 201810736928A CN 109033257 A CN109033257 A CN 109033257A
- Authority
- CN
- China
- Prior art keywords
- art
- words art
- user
- emotional state
- words
- 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
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000002996 emotional effect Effects 0.000 claims abstract description 108
- 230000036651 mood Effects 0.000 claims abstract description 82
- 230000008451 emotion Effects 0.000 claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 15
- 230000008859 change Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 239000012141 concentrate Substances 0.000 description 4
- 235000012054 meals Nutrition 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000001914 calming effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000002980 postoperative effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000007510 mood change Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Machine Translation (AREA)
Abstract
This application discloses a kind of words art recommended method, device, computer equipment and storage mediums, and wherein method includes: the voice messaging for acquiring user, and the voice messaging is parsed into semantic information and acoustic information；Institute's semantic information and sound information are input to operation in preset Emotion identification model, obtain the first emotional state of the user；Wherein, the Emotion identification model is the model obtained based on the semantic information sample that is mutually related, acoustic information sample and mood sample training；Searched in art database if default it is corresponding with first emotional state if art；The words art found is recommended to the contact staff with the user session.The application can help contact staff to grasp the mood of client in real time, avoid enraging client, improve user experience；Recommend words art to can be effectively reduced the burden of customer service staff, improves communication efficiency.
Description
Technical field
This application involves computer field is arrived, especially relate to a kind of words art recommended method, device, computer equipment and
Storage medium.
Background technique
The main task of contact staff is to explain different problems to different user, and under normal conditions, user only has
Service calls can be just dialed when going wrong.Because going wrong just dials service calls, the mood of user is mostly
Negative emotions accidentally occur sensitive word when contact staff can not accurately obtain the emotional state of user, link up with user,
The negative emotions of user can then be deepened, to influence the customer service experience of user.Meanwhile contact staff when being linked up with user always
Cautious, psychological burden is big, influences the working condition etc. of contact staff.
Summary of the invention
The main purpose of the application is to provide a kind of words art recommended method, device, computer equipment and storage medium, it is intended to
The emotional state of user can not accurately be obtained so that art if correspondence can not be used accurately by solving the problem of contact staff.
In order to achieve the above-mentioned object of the invention, the application proposes a kind of words art recommended method, comprising:
The voice messaging of user is acquired, and the voice messaging is parsed into semantic information and acoustic information；
Institute's semantic information and sound information are input to operation in preset Emotion identification model, obtain the user's
First emotional state；Wherein, the Emotion identification model be based on be mutually related semantic information sample, acoustic information sample and
The model that mood sample training obtains；
Searched in art database if default it is corresponding with first emotional state if art；
The words art found is recommended to the contact staff with the user session.
Further, art includes a plurality of if first emotional state is corresponding, and the words art that will be found pushes away
The step of recommending the contact staff for giving the user session, comprising:
It is ranked up according to the frequency of use of a plurality of words art, and described in a plurality of words art after sequence recommended
Contact staff.
Further, searched in the art database if default it is corresponding with first emotional state if art step
Suddenly, comprising:
A plurality of words art corresponding with institute's semantic information is searched in the words art database, forms the first words art collection；
It is concentrated in the first words art and searches the words art corresponding with first emotional state.
Further, searched in the art database if default it is corresponding with first emotional state if art step
Suddenly, comprising:
A plurality of words art corresponding with first emotional state is searched in the words art database, forms the second words art
Collection；
It is concentrated in the second words art and searches the words art corresponding with institute's semantic information.
Further, searched in the art database if default it is corresponding with first emotional state if art step
Suddenly, comprising:
First emotional state and semantic information are distinguished into vectorization, obtain corresponding mood vector sum semantic vector；
It calculates in conjunction with the mood vector sum semantic vector using preset similarity algorithm and meets preset requirement
Talk about art vector；
The words art vector is converted into the words art.
Further, the step of words art that will be found recommends the contact staff with the user session it
Afterwards, comprising:
Judge whether the contact staff states and completes the words art；
If it is, obtaining the feedback voice messaging of the user, and the use is judged according to the feedback voice messaging
Second emotional state at family；
Compare second emotional state and the first emotional state, with judge the user mood whether positive change.
Further, second emotional state and the first emotional state, to judge the mood of the user
Whether positive change the step of after, comprising:
If it is not, then stopping recommending words art to the contact staff.
The application also provides a kind of words art recommendation apparatus, comprising:
Acquire resolution unit, for acquiring the voice messaging of user, and by the voice messaging be parsed into semantic information and
Acoustic information；
Arithmetic element, for institute's semantic information and sound information to be input to operation in preset Emotion identification model,
Obtain the first emotional state of the user；Wherein, the Emotion identification model be based on be mutually related semantic information sample,
The model that acoustic information sample and mood sample training obtain；
Searching unit, for searched in the art database if default it is corresponding with first emotional state if art；
Recommendation unit, for the words art found to be recommended to the contact staff with the user session.
The application also provides a kind of computer equipment, including memory and processor, and the memory is stored with computer
The step of program, the processor realizes any of the above-described the method when executing the computer program.
The application also provides a kind of computer readable storage medium, is stored thereon with computer program, the computer journey
The step of method described in any of the above embodiments is realized when sequence is executed by processor.
Art recommended method, device, computer equipment and storage medium if the application, can help contact staff to slap in real time
The mood for holding client avoids enraging client, improves user experience；The recommendation words art of intelligence can be effectively reduced customer service staff
Burden, improve communication efficiency；The emotional information of user in dialog procedure can be collected, online under further mining analysis, grasp
User information promotes achievement.
Detailed description of the invention
The flow diagram of Fig. 1 art recommended method for one embodiment of the application；
The structural schematic block diagram of Fig. 2 art recommendation apparatus for one embodiment of the application；
Fig. 3 is the structural schematic block diagram of the recommendation unit of one embodiment of the application；
Fig. 4 is the structural schematic block diagram of the searching unit of one embodiment of the application；
The structural schematic block diagram of Fig. 5 art recommendation apparatus for one embodiment of the application；
Fig. 6 is the structural schematic block diagram of the computer equipment of one embodiment of the application.
The embodiments will be further described with reference to the accompanying drawings for realization, functional characteristics and the advantage of the application purpose.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Referring to Fig.1, the embodiment of the present application proposes a kind of words art recommended method, comprising steps of
S1, the voice messaging for acquiring user, and the voice messaging is parsed into semantic information and acoustic information；
S2, institute's semantic information and sound information are input to operation in preset Emotion identification model, obtain the use
First emotional state at family；Wherein, the Emotion identification model is based on be mutually related semantic information sample, acoustic information sample
This model obtained with mood sample training；
S3, searched in art database if default it is corresponding with first emotional state if art；
S4, the words art found is recommended to contact staff with the user session.
As described in above-mentioned steps S1, above-mentioned voice messaging refers to that user and contact staff carry out the interactive voices equipment such as phone
Carry out the voice messaging of sending when interactive voice.In the present embodiment, the method for the voice messaging of user is acquired including two kinds, first
Kind is the sound-recording function of always on subscribers' line, and no matter whether the terminal that user uses makes a sound, and can all be recorded, than
Such as, after user finishes one section of word, the language of contact staff is piped down and listens to, there is no upload users for above-mentioned terminal at this time
Voice, but be similarly in recording state；Another kind is that the sound that the terminal that uses user uploads identifies, for example,
Whether the sound decibel for judging that above-mentioned terminal uploads is greater than preset value, just will be considered that user is issuing if it is greater than the preset value
Effective sound, to record current voice messaging etc..Upper semantic information refers to what reflection user's spoken utterance to be expressed
Meaning information, is generally converted into text information for above-mentioned voice messaging by speech recognition technology, then passes through text information solution
Semantic information in reading.Above sound information generally comprises the letter such as variation of frequency, amplitude and frequency and amplitude of sound
Breath.
As described in above-mentioned steps S2, the above-mentioned semantic information sample that is mutually related, acoustic information sample and mood sample are
Refer to mutual corresponding sample data, for example, semantic information sample is " why not can with ", corresponding acoustic information sample is
" sound frequency changes between 100-150Hz, and amplitude changes between 150-200 decibels ", corresponding mood sample are " negative sense
Second level " etc..Known a large amount of sample data is input in preset neural network and is trained, it is both available corresponding
Model is not repeating herein because training pattern is well known training method.In the present embodiment, above-mentioned Emotion identification model is
It is obtained based on Bi-LSTM model training.After above-mentioned Emotion identification model refers to input semantic information and acoustic information, output is corresponded to
Mood model.In one embodiment, the first emotional state of above-mentioned Emotion identification model output is one group of vector, or
It is the corresponding mood grade of corresponding this group of vector.Mood grade may include a variety of, such as positive level-one, positive second level and forward direction three
Grade, positive higher grade, indicates good and negative sense level-one, negative sense second level, the negative sense three-level of the mood of user all the more, negative sense etc.
Grade is higher, indicates the mood of user all the more bad.
It is preset as described in above-mentioned steps S3, in above-mentioned words art database there are many art is talked about, each emotional state is associated with
At least one words art.After learning the first situation state of user, so that it may find art if corresponding to according to emotional state.On
State art in words art database be by summary of experience come, for example, when there is extreme negative sense three-level mood in user,
The mood that user can effectively be calmed down by art if what is that contact staff and psychologist etc. summarize.
As described in above-mentioned steps S4, when find it is corresponding with the first emotional state if it is postoperative, can both recommend customer service
Personnel, in order to which art engages in the dialogue contact staff with user according to recommendation.Contact staff is facilitated quickly and efficiently to alleviate use
The negative emotions at family improve the speech quality of contact staff and user, improve the customer service consulting experience of user, while can reduce
Contact staff worries to enrage user, deepens the psychological burden of user's negative emotions, while reducing complaint of the user to contact staff
Rate etc..
In one embodiment, art includes a plurality of if above-mentioned first emotional state is corresponding, it is described will find described in
Words art recommends the step S4 with the contact staff of the user session, comprising:
S41, it is ranked up according to the frequency of use of a plurality of words art, and a plurality of words art after sequence is recommended
The contact staff.
It, can be corresponding by the emotional state when a kind of emotional state is associated with a plurality of words art as described in above-mentioned steps S41
A plurality of words art all map out, and recommend contact staff together, and can be ranked up to a plurality of words art, ordering rule
It is that art sequence is before most by frequency of use highest, in order to which contact staff selects.Because frequency of use is high, illustrate this
It is more (universality is high) to talk about the corresponding usage scenario of art, the effect for calming down user emotion is good, the preceding words art of selected and sorted, usually
In the case of can obtain a positive reflection (the emotional state negative sense grade of user reduces, and such as becomes negative sense two from negative sense three-level
Grade etc.).
In one embodiment, searched in the above-mentioned art database if default it is corresponding with first emotional state if
The step S3 of art, comprising:
S301, a plurality of words art corresponding with institute's semantic information is searched in the words art database, form the first words art
Collection；
S302, it is concentrated in the first words art and searches the words art corresponding with first emotional state.
As described in above-mentioned steps S301 and S302, a plurality of words art corresponding with institute's semantic information refers to, semantic information with
The semantic connection of words art content meets the habit of people's normal voice interaction, for example A is asked: " B, you have had a meal ", B can have
A variety of answer-modes, including B1 " not having also, eat for a moment ", B2 " eating ", B3 " the Chongqing facet eaten " etc., the semanteme and B of such A
Answer be it is mutual corresponding, meet the normal interaction habits of people, if B4 be " I will go to Beijing ", asked with the A of front:
The correlation of " B, you have had a meal " is lower, does not meet the normal communication habit of people, therefore, above-mentioned B1, B2, B3 belong to A and ask
Art if correspondence, B4 are then not belonging to A and ask art if correspondence.In the present embodiment, will first it search corresponding with institute's semantic information more
Item talks about art, forms the first words art collection, then talks about art if art concentration searches corresponding first emotional state first again, can be quick
Ground find it is corresponding with current talking situation if art.In implementing one, searched in words art database with institute's semantic information
A plurality of words art corresponding with institute's semantic information, the method for forming the first words art collection include: to search to believe with semantic by keyword
Art if breath correspondence is matched, general that is, by the keyword in semantic information with the keyword of art in words art database
With degree reach specified requirement it is corresponding if art collect above-mentioned first words art and concentrate, for example, there are five in semantic information
Keyword, this five keywords are compared with each keyword in words art respectively, if there are five identical passes in words art
Keyword, then it is assumed that matching degree reaches 100%, if only 4 are identical, it may be considered that matching degree reach 80% with
On, when matching degree calculates, keyword first can also be subjected to vectorization, then pass through the similarity calculations such as Euclidean distance
Method calculates the similarity between vector, if similarity is greater than preset value, it is also assumed that of semantic information and words art
Reach preset requirement with degree.
In another embodiment, searched in the above-mentioned art database if default it is corresponding with first emotional state if
The step S3 of art, comprising:
S311, a plurality of words art corresponding with first emotional state is searched in the words art database, form second
Talk about art collection；
S312, it is concentrated in the second words art and searches the words art corresponding with institute's semantic information.
As described in above-mentioned steps S311 and S312, as the reversed order of above-mentioned steps S301 and S302 are carried out, first existed
It is produced in words art database and looks for a plurality of words art corresponding with the first emotional state of the user, form the second words art collection；Then, root
It is concentrated according to institute's semantic information in the second words art and searches words art corresponding with institute's semantic information.Equally can rapidly it find
Art if corresponding with current talking situation.
In one embodiment, searched in the above-mentioned art database if default it is corresponding with first emotional state if
The step S3 of art, comprising:
S321, first emotional state and semantic information are distinguished into vectorization, it is semantic obtains corresponding mood vector sum
Vector；
S322, using preset similarity algorithm, in conjunction with the mood vector sum semantic vector, calculate and meet default want
Art vector if asking；
S323, the words art vector is converted into the words art.
As described in above-mentioned steps S321, S322 and S323, above-mentioned preset similarity algorithm can be annoy
(Open-Source Tools that Approximate Nearest Neighbors Oh Yeah higher dimensional space vector quickly calculates similitude)
Algorithm can rapidly carry out similarity calculation.The method of the vectorization of above-mentioned user emotion, comprising: first by various possibility
User emotion carry out vectorization, then generate one respectively with various moods associated mood vector library, when needing to user
When mood carries out vectorization, it can both be searched into above-mentioned mood vector library.It in other embodiments, can also be directly
The mood vector exported using above-mentioned Emotion identification model.The acquisition methods of above-mentioned semantic vector, comprising: be likely to occur various
Text be input in DSSM (Deep Structured Semantic Models, deep structure semantic model) model, lead to
The term vector that DSSM model calculates text is crossed, then text and its corresponding term vector are put into the first corpus dictionary,
Form a corpus dictionary；When needing to obtain semantic vector, semantic information is first changed into text, is then extracted in each text
Keyword subsequently searches the corresponding vector of each keyword, to obtain semantic vector into above-mentioned corpus dictionary.This reality
It applies in example, above-mentioned to meet art vector if preset requirement may be respectively with the similarity of mood vector sum semantic vector is all most
High, it is also possible to it is not respectively highest with the similarity of mood vector sum semantic vector.In a specific embodiment,
It calculates and respectively talks about art vector progress similarity calculation in semantic vector and words art database, the first weight then is carried out to each similarity
Calculating, obtain each first weight similarity；And calculate mood vector with talk about in art database that respectively to talk about the progress of art vector similar
Degree calculates, and the calculating of the second weight is then carried out to each similarity, each second weight similarity is obtained, wherein the first weight adds
Second weight is equal to 1.Then it respectively talks about the corresponding first weight picture of art vector and is added calculating with the second weight similarity like degree, it is corresponding
Art vector is art vector if meeting the requirements if calculated result highest.Then words art vector is converted into art if corresponding to.
In one embodiment, the above-mentioned words art that will be found is recommended with the contact staff's of the user session
After step S4, comprising:
S5, judge whether the contact staff states the completion words art；
S6, if it is, obtain the feedback voice messaging of the user, and according to feedback voice messaging judgement
The second emotional state of user；
Second emotional state and the first emotional state described in S7, comparison, the whether positive change of mood to judge the user
Change.
As described in above-mentioned steps S5 to S7, after as judging customer service art and user linking up according to the rules, the feelings of user
Whether thread can occur positive change, which is the direction change that the emotional state of user is become better, such as by negative sense three
Grade becomes negative sense second level, illustrates that improvement etc. occurs for the mood of user.In the present embodiment, the deterministic process of the second emotional state with it is upper
It states and judges that the process of the first emotional state is identical, do not repeating herein.In the present embodiment, judge whether the customer service states completion
The method of the words art includes that the voice signal of customer service is converted into text, is then compared text with words art text, such as
Fruit similarity is greater than designated value, then illustrates that user has completed to recommend the statement of words art.Whether the mood by judging user is good
Turn, customer service can be helped to carry out subsequent communication, if it is determined that for example, the mood of the user is that positive change then continues
Art is talked about to recommend.In a specific embodiment, if it is decided that the mood of the user is negative sense variation, then stops to the customer service
Personnel recommend words art.Contact staff, which can choose, at this time adjusts to changed conditions, and the effect of processing may be more preferable, to prevent further
Enrage user.
Art recommended method if the embodiment of the present application can help contact staff to grasp the mood of client in real time, avoid swashing
Anger client improves user experience；The recommendation words art of intelligence can be effectively reduced the burden of customer service staff, improves and links up effect
Rate；The emotional information of user in dialog procedure can be collected, online under further mining analysis, grasp user information, promoted achievement.
Referring to Fig. 2, the embodiment of the present application also provides a kind of words art recommendation apparatus, comprising:
Resolution unit 10 is acquired, is parsed into semantic information for acquiring the voice messaging of user, and by the voice messaging
And acoustic information.
In above-mentioned acquisition resolution unit 10, above-mentioned voice messaging refers to that user and contact staff carry out the voices such as phone and hand over
Mutual equipment carries out the voice messaging of sending when interactive voice.In the present embodiment, the method for acquiring the voice messaging of user includes two
Kind, the first is the sound-recording function of always on subscribers' line, and no matter whether the terminal that user uses makes a sound, and can all be carried out
Recording, for example, pipe down and listen to the language of contact staff after user finishes one section of word, above-mentioned terminal is not at this time
The voice of upload user, but it is similarly in recording state；Another kind is that the sound that the terminal used user uploads is known
Not, for example, whether the sound decibel for judging that above-mentioned terminal uploads is greater than preset value, it just will be considered that use if it is greater than the preset value
Family is issuing effective sound, to record current voice messaging etc..Upper semantic information refers to reflection user's spoken utterance
Above-mentioned voice messaging is generally converted into text information by speech recognition technology, then passes through text by the meaning information to be expressed
This information interprets semantic information.Above sound information generally comprises frequency, amplitude and the frequency and amplitude of sound
The information such as variation.
Arithmetic element 20 is transported for institute's semantic information and sound information to be input in preset Emotion identification model
It calculates, obtains the first emotional state of the user；Wherein, the Emotion identification model is based on the semantic information sample that is mutually related
Originally, the model that acoustic information sample and mood sample training obtain.
In above-mentioned arithmetic element 20, the above-mentioned semantic information sample that is mutually related, acoustic information sample and mood sample
Refer to mutual corresponding sample data, for example, semantic information sample is " why not can with ", corresponding acoustic information sample
For " sound frequency changes between 100-150Hz, and amplitude changes between 150-200 decibels ", corresponding mood sample is " negative
To second level " etc..Known a large amount of sample data is input in preset neural network and is trained, both available correspondence
Model do not repeated herein because training pattern is well known training method.In the present embodiment, above-mentioned Emotion identification model
It is to be obtained based on Bi-LSTM model training.After above-mentioned Emotion identification model refers to input semantic information and acoustic information, output pair
The model for the mood answered.In one embodiment, the first emotional state of above-mentioned Emotion identification model output is one group of vector, or
Person is the corresponding mood grade of corresponding this group of vector.Mood grade may include a variety of, such as positive level-one, positive second level and forward direction
Three-level, positive higher grade, indicates good and negative sense level-one, negative sense second level, the negative sense three-level of the mood of user all the more, negative sense
Higher grade, indicates the mood of user all the more bad.
Searching unit 30, for searched in the art database if default it is corresponding with first emotional state if art.
It is preset in above-mentioned searching unit 30, in above-mentioned words art database there are many art is talked about, each emotional state is associated with
There is at least one words art.After learning the first situation state of user, so that it may find art if corresponding to according to emotional state.
Art is by summary of experience come for example, when extreme negative sense three-level mood occurs in user in above-mentioned words art database
When, it can effectively calm down the mood of user by art if what, be that contact staff and psychologist etc. summarize.
The words art found is recommended the contact staff with the user session by recommendation unit 40.
In above-mentioned recommendation unit 40, when find it is corresponding with the first emotional state if it is postoperative, can both recommend visitor
Personnel are taken, in order to which art engages in the dialogue contact staff with user according to recommendation.Contact staff is facilitated quickly and efficiently to alleviate
The negative emotions of user improve the speech quality of contact staff and user, improve the customer service consulting experience of user, while can subtract
Few contact staff worries to enrage user, deepens the psychological burden of user's negative emotions, while reducing throwing of the user to contact staff
Tell rate etc..
Referring to Fig. 3, in one embodiment, when art includes a plurality of if above-mentioned first emotional state is corresponding, above-mentioned recommendation
Unit 40, comprising:
Sort recommendations module 41, for being ranked up according to the frequency of use of a plurality of words art, and will be more after sequence
Words art described in item recommends the contact staff.
It, can be by the mood shape when a kind of emotional state is associated with a plurality of words art in above-mentioned sort recommendations module 41
The corresponding a plurality of words art of state, which all maps out, to be come, and recommends contact staff together, and can be ranked up to a plurality of words art, is arranged
Sequence rule is that art sequence is before most by frequency of use highest, in order to which contact staff selects.Because frequency of use is high,
Illustrate that the corresponding usage scenario of words art is more (universality is high), the effect for calming down user emotion is good, the preceding words of selected and sorted
Art, obtaining a positive reflection under normal conditions, (the emotional state negative sense grade of user reduces, and is such as become from negative sense three-level
Negative sense second level etc.).
In one embodiment, above-mentioned searching unit 30, comprising:
First searching module, for searching a plurality of words art corresponding with institute's semantic information in the words art database,
Form the first words art collection；
Second searching module searches the words corresponding with first emotional state for concentrating in the first words art
Art.
In above-mentioned first searching module and the second searching module, above-mentioned a plurality of words art corresponding with institute's semantic information is
Refer to, semantic information meets the habit that people's normal voice interacts with the semantic connection of words art content, for example A is asked: " B, you have a meal
", B can there are many answer-mode, including B1 " not having also, eat ", B2 " eating ", B3 " the Chongqing facet eaten " etc. for a moment,
Semanteme and the answer of B of A in this way be it is mutual corresponding, meet the normal interaction habits of people, if B4 is " I will go to Beijing ",
Then the A with front is asked: the correlation of " B, you have had a meal " is lower, does not meet the normal communication habit of people, therefore, above-mentioned
B1, B2, B3 belong to A and ask art if correspondence, and B4 is then not belonging to A and asks art if correspondence.In the present embodiment, will first it search and institute's predicate
The corresponding a plurality of words art of adopted information forms the first words art collection, then concentrates again in the first words art and searches corresponding first emotional state
If art, can rapidly find it is corresponding with current talking situation if art.One implement in, words art database in institute
Semantic information searches a plurality of words art corresponding with institute's semantic information, and the method for forming the first words art collection includes: to pass through key
Art if word lookup is corresponding with semantic information, i.e., by the key of art in the keyword in semantic information, with words art database
Word is matched, by matching degree reach specified requirement it is corresponding if art collect above-mentioned first words art and concentrate, for example, semantic
There are five keywords in information, this five keywords are compared with each keyword in words art respectively, if deposited in words art
In five identical keywords, then it is assumed that matching degree reaches 100%, if only 4 identical, it may be considered that matching
Degree reaches 80% or more, when matching degree calculates, keyword first can also be carried out vectorization, then pass through Euclidean distance
Equal similarity calculating methods calculate the similarity between vector, if similarity is greater than preset value, it is also assumed that semantic letter
Breath and the matching degree of words art reach preset requirement.
In another embodiment, above-mentioned searching unit 30, comprising:
Third searching module, for searching a plurality of words corresponding with first emotional state in the words art database
Art forms the second words art collection；
4th searching module searches the words art corresponding with institute's semantic information for concentrating in the second words art.
In the performed sequence for stating third searching module and the 4th searching module, with above-mentioned first searching module and second
Searching module execution sequence on the contrary, first words art database in produce look for it is corresponding a plurality of with the first emotional state of the user
Art is talked about, the second words art collection is formed；Then, concentrate lookup corresponding with institute's semantic information in the second words art according to institute's semantic information
If art.Equally can rapidly find it is corresponding with current talking situation if art.
Referring to Fig. 4, in one embodiment, above-mentioned searching unit 30, comprising:
Vectorization module 31 obtains corresponding feelings for first emotional state and semantic information to be distinguished vectorization
Thread vector sum semantic vector；
Computing module 32, for being calculated using preset similarity algorithm in conjunction with the mood vector sum semantic vector
Meet art vector if preset requirement；
Conversion module 33, for the words art vector to be converted into the words art.
In above-mentioned vectorization module 31, computing module 32 and conversion module 33, above-mentioned preset similarity algorithm can be
(Approximate Nearest Neighbors Oh Yeah higher dimensional space vector quickly calculates the open source work of similitude to annoy
Tool) algorithm, can rapidly carry out similarity calculation.The method of the vectorization of above-mentioned user emotion, comprising: first will be various
Possible user emotion carries out vectorization, then generate one respectively with various moods associated mood vector library, when needing pair
When user emotion carries out vectorization, it can both be searched into above-mentioned mood vector library.It in other embodiments, can be with
Directly utilize the mood vector of above-mentioned Emotion identification model output.The acquisition methods of above-mentioned semantic vector, comprising: by various possibility
The text of appearance is input to DSSM (Deep Structured Semantic Models, deep structure semantic model) model
In, the term vector of text is calculated by DSSM model, and text and its corresponding term vector are then put into the first corpus word
In allusion quotation, a corpus dictionary is formed；When needing to obtain semantic vector, semantic information is first changed into text, then extracts each text
Keyword in this, subsequently searches the corresponding vector of each keyword into above-mentioned corpus dictionary, thus obtain it is semantic to
Amount.In the present embodiment, it is above-mentioned meet preset requirement if art vector may be similar to mood vector sum semantic vector respectively
Degree is all highest, it is also possible to not be respectively highest with the similarity of mood vector sum semantic vector.It is specific at one
In embodiment, calculate semantic vector and words art database in respectively talk about art vector carry out similarity calculation, then to each similarity into
The calculating of the first weight of row obtains each first weight similarity；And calculate mood vector and words art database in respectively talk about art to
Amount carries out similarity calculation, and the calculating of the second weight is then carried out to each similarity, obtains each second weight similarity, wherein the
One weight is equal to 1 plus the second weight.Then respectively the corresponding first weight picture of words art vector is seemingly spent and the second weight similarity phase
Add calculating, art vector is art vector if meeting the requirements if corresponding calculated result highest.Then words art vector is converted into
Art if correspondence.
Referring to Fig. 5, in one embodiment, above-mentioned words art recommendation apparatus, further includes:
First judging unit 50 completes the words art for judging whether the contact staff states；
Second judgment unit 60 completes the art if stated for the contact staff, obtains the user's
Voice messaging is fed back, and judges the second emotional state of the user according to the feedback voice messaging；
Third judging unit 70 is used for second emotional state and the first emotional state, to judge the user
Mood whether positive change.
In above-mentioned first judging unit 50, second judgment unit 60 and third judging unit 70, as judge that customer service is pressed
After according to regulation, art and user are linked up, whether the mood of user can occur positive change, which is the feelings of user
The direction change that not-ready status is become better, for example negative sense second level is become from negative sense three-level, illustrate that improvement etc. occurs for the mood of user.This reality
It applies in example, the deterministic process of the second emotional state is identical as the process of above-mentioned the first emotional state of judgement, is not repeating herein.This
In embodiment, judge whether the customer service states the method for completing the words art and include, the voice signal conversion of customer service is written
Text, is then compared by this with words art text, if similarity is greater than designated value, illustrates that user has completed to recommend words
The statement of art.By judging whether the mood of user improves, customer service can be helped to carry out subsequent communication, such as, if it is decided that
The mood of the user is positive change, then continues to talk about art recommendation.In a specific embodiment, if it is decided that the use
The mood at family is negative sense variation, then stops recommending words art to the contact staff.Contact staff, which can choose, at this time adjusts to changed conditions,
The effect of processing may be more preferable, to prevent from further enraging user.
Art recommendation apparatus if the embodiment of the present application can help contact staff to grasp the mood of client in real time, avoid swashing
Anger client improves user experience；The recommendation words art of intelligence can be effectively reduced the burden of customer service staff, improves and links up effect
Rate；The emotional information of user in dialog procedure can be collected, online under further mining analysis, grasp user information, promoted achievement.
Referring to Fig. 6, a kind of computer equipment is also provided in the embodiment of the present invention, which can be server,
Its internal structure can be as shown in Figure 6.The computer equipment includes processor, the memory, network connected by system bus
Interface and database.Wherein, the processor of the Computer Design is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program
And database.The internal memory provides environment for the operation of operating system and computer program in non-volatile memory medium.It should
The database of computer equipment is for storing the data such as Emotion identification model, words art database.The network of the computer equipment connects
Mouth with external terminal by network connection for being communicated.To realize that a kind of words art pushes away when the computer program is executed by processor
Recommend method.
Above-mentioned processor executes words art recommended method, comprising: acquires the voice messaging of user, and by the voice messaging solution
Analyse into semantic information and acoustic information；Institute's semantic information and sound information are input in preset Emotion identification model and transported
It calculates, obtains the first emotional state of the user；Wherein, the Emotion identification model is based on the semantic information sample that is mutually related
Originally, the model that acoustic information sample and mood sample training obtain；It is searched and first feelings in art database if default
Art if not-ready status is corresponding；The words art found is recommended to the contact staff with the user session.
In one embodiment, if the first emotional state described above is corresponding art includes a plurality of, described to find
The step of words art recommends the contact staff with the user session, comprising: according to the frequency of use of a plurality of words art
It is ranked up, and a plurality of words art after sequence is recommended into the contact staff.
In one embodiment, searched in the above-mentioned art database if default it is corresponding with first emotional state if
The step of art, comprising: search a plurality of words art corresponding with institute's semantic information in the words art database, form the first words art
Collection；It is concentrated in the first words art and searches the words art corresponding with first emotional state.
In another embodiment, it is searched in the above-mentioned art database if default corresponding with first emotional state
The step of talking about art, comprising: search corresponding with first emotional state a plurality of words art in the words art database, formation the
Objection art collection；It is concentrated in the second words art and searches the words art corresponding with institute's semantic information.
In one embodiment, searched in the above-mentioned art database if default it is corresponding with first emotional state if
The step of art, comprising: first emotional state and semantic information are distinguished into vectorization, it is semantic to obtain corresponding mood vector sum
Vector；Art if meeting preset requirement is calculated in conjunction with the mood vector sum semantic vector using preset similarity algorithm
Vector；The words art vector is converted into the words art.
In one embodiment, the above-mentioned words art that will be found is recommended with the contact staff's of the user session
After step, comprising: judge whether the contact staff states and complete the words art；If it is, obtaining the anti-of the user
Voice messaging is presented, and judges the second emotional state of the user according to the feedback voice messaging；Compare second mood
State and the first emotional state, with judge the user mood whether positive change.
In one embodiment, above-mentioned second emotional state and the first emotional state, to judge the user
Mood whether positive change the step of after, comprising: if it is determined that the mood of the user be negative sense variation, then stop to institute
It states contact staff and recommends words art.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme.
The BMI prediction technique of the embodiment of the present invention is predicted the BMI of insurer by face characteristic, can rapidly inferred
The BMI classification of insurer out, to prevent insurer from making a false report BMI, and because by calculate in computer, without special
The BMI test equipment of door, save the cost.
One embodiment of the invention also provides a kind of computer readable storage medium, is stored thereon with computer program, calculates
Words art recommended method is realized when machine program is executed by processor, comprising: acquire the voice messaging of user, and by the voice messaging
It is parsed into semantic information and acoustic information；Institute's semantic information and sound information are input in preset Emotion identification model and transported
It calculates, obtains the first emotional state of the user；Wherein, the Emotion identification model is based on the semantic information sample that is mutually related
Originally, the model that acoustic information sample and mood sample training obtain；It is searched and first feelings in art database if default
Art if not-ready status is corresponding；The words art found is recommended to the contact staff with the user session.
Art recommended method if above-mentioned execution, can help contact staff to grasp the mood of client in real time, avoid enraging visitor
User experience is improved at family；The recommendation words art of intelligence can be effectively reduced the burden of customer service staff, improve communication efficiency；It can
Collect dialog procedure in user emotional information, online under further mining analysis, grasp user information, promoted achievement.
In one embodiment, art includes institute a plurality of, that processor will be found if above-mentioned first emotional state is corresponding
State words arts the step of recommending the contact staff with the user session, comprising: according to the frequency of use of a plurality of words art into
Row sequence, and a plurality of words art after sequence is recommended into the contact staff.
In one embodiment, above-mentioned processor is searched and first emotional state pair in art database if default
If answering the step of art, comprising: search corresponding with institute's semantic information a plurality of words art in the words art database, formation the
One words art collection；It is concentrated in the first words art and searches the words art corresponding with first emotional state.
In another embodiment, above-mentioned processor is searched and first emotional state in art database if default
If correspondence the step of art, comprising: a plurality of words art corresponding with first emotional state is searched in the words art database,
Form the second words art collection；It is concentrated in the second words art and searches the words art corresponding with institute's semantic information.
In one embodiment, above-mentioned processor is searched and first emotional state pair in art database if default
If answering the step of art, comprising: first emotional state and semantic information are distinguished vectorization, obtain corresponding mood vector
And semantic vector；It calculates in conjunction with the mood vector sum semantic vector using preset similarity algorithm and meets preset requirement
If art vector；The words art vector is converted into the words art.
In one embodiment, the words art found is recommended the customer service with the user session by above-mentioned processor
After the step of personnel, comprising: judge whether the contact staff states and complete the words art；If it is, obtaining the use
The feedback voice messaging at family, and according to second emotional state fed back voice messaging and judge the user；Compare described
Two emotional states and the first emotional state, with judge the user mood whether positive change.
In one embodiment, above-mentioned processor second emotional state and the first emotional state, to judge
State user mood whether positive change the step of after, comprising: if it is determined that the mood of the user be negative sense variation, then stop
Only recommend words art to the contact staff.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
Any reference used in provided herein and embodiment to memory, storage, database or other media,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double speed are according to rate SDRAM (SSRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchl ink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, device, article or the method that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, device, article or method institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, device of element, article or method.
The foregoing is merely preferred embodiment of the present application, are not intended to limit the scope of the patents of the application, all utilizations
Equivalent structure or equivalent flow shift made by present specification and accompanying drawing content is applied directly or indirectly in other correlations
Technical field, similarly include in the scope of patent protection of the application.
Claims (10)
1. a kind of words art recommended method characterized by comprising
The voice messaging of user is acquired, and the voice messaging is parsed into semantic information and acoustic information；
Institute's semantic information and sound information are input to operation in preset Emotion identification model, obtain the first of the user
Emotional state；Wherein, the Emotion identification model is based on be mutually related semantic information sample, acoustic information sample and mood
The model that sample training obtains；
Searched in art database if default it is corresponding with first emotional state if art；
The words art found is recommended to the contact staff with the user session.
2. words art recommended method according to claim 1, which is characterized in that art packet if first emotional state is corresponding
Include a plurality of, the step of words art that will be found recommends the contact staff with the user session, comprising:
It is ranked up according to the frequency of use of a plurality of words art, and a plurality of words art after sequence is recommended into the customer service
Personnel.
3. words art recommended method according to claim 1, which is characterized in that searched in the art database if default
If corresponding with first emotional state the step of art, comprising:
A plurality of words art corresponding with institute's semantic information is searched in the words art database, forms the first words art collection；
It is concentrated in the first words art and searches the words art corresponding with first emotional state.
4. words art recommended method according to claim 1, which is characterized in that searched in the art database if default
If corresponding with first emotional state the step of art, comprising:
A plurality of words art corresponding with first emotional state is searched in the words art database, forms the second words art collection；
It is concentrated in the second words art and searches the words art corresponding with institute's semantic information.
5. words art recommended method according to claim 1, which is characterized in that searched in the art database if default
If corresponding with first emotional state the step of art, comprising:
First emotional state and semantic information are distinguished into vectorization, obtain corresponding mood vector sum semantic vector；
Art if meeting preset requirement is calculated in conjunction with the mood vector sum semantic vector using preset similarity algorithm
Vector；
The words art vector is converted into the words art.
6. words art recommended method according to claim 1, which is characterized in that the words art that will be found is recommended
After the step of the contact staff of the user session, comprising:
Judge whether the contact staff states and completes the words art；
If it is, obtaining the feedback voice messaging of the user, and judge the user's according to the feedback voice messaging
Second emotional state；
Compare second emotional state and the first emotional state, with judge the user mood whether positive change.
7. words art recommended method according to claim 6, which is characterized in that second emotional state and
One emotional state, with judge the user mood whether positive change the step of after, comprising:
If it is determined that the mood of the user is negative sense variation, then stop recommending words art to the contact staff.
8. a kind of words art recommendation apparatus characterized by comprising
Resolution unit is acquired, is parsed into semantic information and sound for acquiring the voice messaging of user, and by the voice messaging
Information；
Arithmetic element is obtained for institute's semantic information and sound information to be input to operation in preset Emotion identification model
The first emotional state of the user；Wherein, the Emotion identification model is based on be mutually related semantic information sample, sound
The model that message sample and mood sample training obtain；
Searching unit, for searched in the art database if default it is corresponding with first emotional state if art；
The words art found is recommended the contact staff with the user session by recommendation unit.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810736928.4A CN109033257A (en) | 2018-07-06 | 2018-07-06 | Talk about art recommended method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810736928.4A CN109033257A (en) | 2018-07-06 | 2018-07-06 | Talk about art recommended method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109033257A true CN109033257A (en) | 2018-12-18 |
Family
ID=64641669
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810736928.4A Pending CN109033257A (en) | 2018-07-06 | 2018-07-06 | Talk about art recommended method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109033257A (en) |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109582780A (en) * | 2018-12-20 | 2019-04-05 | 广东小天才科技有限公司 | A kind of intelligent answer method and device based on user emotion |
| CN109684459A (en) * | 2018-12-28 | 2019-04-26 | 联想(北京)有限公司 | A kind of information processing method and device |
| CN109710503A (en) * | 2018-12-28 | 2019-05-03 | 浙江百应科技有限公司 | A kind of method of Intelligent voice dialog data OA operation analysis |
| CN109767765A (en) * | 2019-01-17 | 2019-05-17 | 平安科技（深圳）有限公司 | Talk about art matching process and device, storage medium, computer equipment |
| CN109783613A (en) * | 2019-01-23 | 2019-05-21 | 广东小天才科技有限公司 | One kind searching topic method and system |
| CN109885679A (en) * | 2019-01-11 | 2019-06-14 | 平安科技（深圳）有限公司 | Obtain method, apparatus, computer equipment and the storage medium of preferred words art |
| CN110032630A (en) * | 2019-03-12 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Talk about art recommendation apparatus, method and model training equipment |
| CN110060098A (en) * | 2019-04-04 | 2019-07-26 | 秒针信息技术有限公司 | The acquisition methods and device of marketing term |
| CN110136723A (en) * | 2019-04-15 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Data processing method and device based on voice messaging |
| CN110147930A (en) * | 2019-04-16 | 2019-08-20 | 平安科技（深圳）有限公司 | Data statistical approach, device and storage medium based on big data analysis |
| CN110287299A (en) * | 2019-06-17 | 2019-09-27 | 浙江百应科技有限公司 | Loquacity term sentence intelligent switch method in a kind of call |
| CN110298682A (en) * | 2019-05-22 | 2019-10-01 | 深圳壹账通智能科技有限公司 | Intelligent Decision-making Method, device, equipment and medium based on user information analysis |
| CN110347863A (en) * | 2019-06-28 | 2019-10-18 | 腾讯科技（深圳）有限公司 | Talk about art recommended method and device and storage medium |
| CN110379445A (en) * | 2019-06-20 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Method for processing business, device, equipment and storage medium based on mood analysis |
| CN110459210A (en) * | 2019-07-30 | 2019-11-15 | 平安科技（深圳）有限公司 | Answering method, device, equipment and storage medium based on speech analysis |
| CN110460798A (en) * | 2019-06-26 | 2019-11-15 | 平安科技（深圳）有限公司 | Video Interview service processing method, device, terminal and storage medium |
| CN110475032A (en) * | 2019-06-28 | 2019-11-19 | 平安科技（深圳）有限公司 | Multi-service interface switching method, device, computer installation and storage medium |
| CN110610705A (en) * | 2019-09-20 | 2019-12-24 | 上海数鸣人工智能科技有限公司 | Voice interaction prompter based on artificial intelligence |
| CN110890088A (en) * | 2019-10-12 | 2020-03-17 | 中国平安财产保险股份有限公司 | Voice information feedback method and device, computer equipment and storage medium |
| CN111104505A (en) * | 2019-12-30 | 2020-05-05 | 浙江阿尔法人力资源有限公司 | Information prompting method, device, equipment and storage medium |
| CN111354377A (en) * | 2019-06-27 | 2020-06-30 | 深圳市鸿合创新信息技术有限责任公司 | Method and device for recognizing emotion through voice and electronic equipment |
| CN111522937A (en) * | 2020-05-15 | 2020-08-11 | 支付宝(杭州)信息技术有限公司 | Method and device for recommending dialect and electronic equipment |
| CN111564202A (en) * | 2020-04-30 | 2020-08-21 | 深圳市镜象科技有限公司 | Psychological counseling method based on man-machine conversation, psychological counseling terminal and storage medium |
| CN111598485A (en) * | 2020-05-28 | 2020-08-28 | 成都晓多科技有限公司 | Multi-dimensional intelligent quality inspection method, device, terminal equipment and medium |
| CN111710338A (en) * | 2020-06-28 | 2020-09-25 | 上海优扬新媒信息技术有限公司 | Voice operation playing method and device |
| CN111858897A (en) * | 2020-07-30 | 2020-10-30 | 北京首汽智行科技有限公司 | Customer service staff speech guiding method and system |
| CN111881254A (en) * | 2020-06-10 | 2020-11-03 | 百度在线网络技术（北京）有限公司 | Method and device for generating dialogs, electronic equipment and storage medium |
| CN111932296A (en) * | 2020-07-20 | 2020-11-13 | 中国建设银行股份有限公司 | Product recommendation method and device, server and storage medium |
| CN112053205A (en) * | 2020-08-21 | 2020-12-08 | 北京云迹科技有限公司 | Product recommendation method and device through robot emotion recognition |
| CN112182047A (en) * | 2019-07-05 | 2021-01-05 | 北京猎户星空科技有限公司 | Information recommendation method, device, equipment and medium |
| CN112256855A (en) * | 2020-11-13 | 2021-01-22 | 泰康保险集团股份有限公司 | User intention identification method and device |
| CN112417200A (en) * | 2019-08-21 | 2021-02-26 | 北京峰趣互联网信息服务有限公司 | Method and device for determining tracks, electronic equipment and computer readable storage medium |
| CN112671984A (en) * | 2020-12-01 | 2021-04-16 | 长沙市到家悠享网络科技有限公司 | Service mode switching method and device, robot customer service and storage medium |
| CN112686448A (en) * | 2020-12-31 | 2021-04-20 | 重庆富民银行股份有限公司 | Loss early warning method and system based on attribute data |
| CN113010784A (en) * | 2021-03-17 | 2021-06-22 | 北京十一贝科技有限公司 | Method, apparatus, electronic device, and medium for generating prediction information |
| CN113312468A (en) * | 2021-07-30 | 2021-08-27 | 平安科技（深圳）有限公司 | Conversation mode-based conversation recommendation method, device, equipment and medium |
| CN113314122A (en) * | 2020-02-27 | 2021-08-27 | 北京有限元科技有限公司 | Method, apparatus, and medium for determining optimal dialect using single voice robot |
| CN113688221A (en) * | 2021-09-08 | 2021-11-23 | 中国平安人寿保险股份有限公司 | Model-based dialect recommendation method and device, computer equipment and storage medium |
| CN114399821A (en) * | 2022-01-13 | 2022-04-26 | 中国平安人寿保险股份有限公司 | Policy recommendation method, device and storage medium |
| CN116662503A (en) * | 2023-05-22 | 2023-08-29 | 深圳市新美网络科技有限公司 | Private user scene phone recommendation method and system thereof |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102868836A (en) * | 2012-09-17 | 2013-01-09 | 北京讯鸟软件有限公司 | Real person talk skill system for call center and realization method thereof |
| CN104601832A (en) * | 2008-04-29 | 2015-05-06 | 台达电子工业股份有限公司 | Conversation system and speech conversation processing method |
| CN106874472A (en) * | 2017-02-16 | 2017-06-20 | 深圳追科技有限公司 | A kind of anthropomorphic robot's client service method |
| CN107423364A (en) * | 2017-06-22 | 2017-12-01 | 百度在线网络技术（北京）有限公司 | Answer words art broadcasting method, device and storage medium based on artificial intelligence |
| CN107545029A (en) * | 2017-07-17 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | Voice feedback method, equipment and the computer-readable recording medium of smart machine |
| CN107818798A (en) * | 2017-10-20 | 2018-03-20 | 百度在线网络技术（北京）有限公司 | Customer service quality evaluating method, device, equipment and storage medium |
| CN107886955A (en) * | 2016-09-29 | 2018-04-06 | 百度在线网络技术（北京）有限公司 | A kind of personal identification method, device and the equipment of voice conversation sample |
| CN107968896A (en) * | 2018-01-08 | 2018-04-27 | 杭州声讯网络科技有限公司 | Unattended communication on telephone system and communication method |
| CN108122552A (en) * | 2017-12-15 | 2018-06-05 | 上海智臻智能网络科技股份有限公司 | Voice mood recognition methods and device |
-
2018
- 2018-07-06 CN CN201810736928.4A patent/CN109033257A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104601832A (en) * | 2008-04-29 | 2015-05-06 | 台达电子工业股份有限公司 | Conversation system and speech conversation processing method |
| CN102868836A (en) * | 2012-09-17 | 2013-01-09 | 北京讯鸟软件有限公司 | Real person talk skill system for call center and realization method thereof |
| CN107886955A (en) * | 2016-09-29 | 2018-04-06 | 百度在线网络技术（北京）有限公司 | A kind of personal identification method, device and the equipment of voice conversation sample |
| CN106874472A (en) * | 2017-02-16 | 2017-06-20 | 深圳追科技有限公司 | A kind of anthropomorphic robot's client service method |
| CN107423364A (en) * | 2017-06-22 | 2017-12-01 | 百度在线网络技术（北京）有限公司 | Answer words art broadcasting method, device and storage medium based on artificial intelligence |
| CN107545029A (en) * | 2017-07-17 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | Voice feedback method, equipment and the computer-readable recording medium of smart machine |
| CN107818798A (en) * | 2017-10-20 | 2018-03-20 | 百度在线网络技术（北京）有限公司 | Customer service quality evaluating method, device, equipment and storage medium |
| CN108122552A (en) * | 2017-12-15 | 2018-06-05 | 上海智臻智能网络科技股份有限公司 | Voice mood recognition methods and device |
| CN107968896A (en) * | 2018-01-08 | 2018-04-27 | 杭州声讯网络科技有限公司 | Unattended communication on telephone system and communication method |
Cited By (55)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109582780A (en) * | 2018-12-20 | 2019-04-05 | 广东小天才科技有限公司 | A kind of intelligent answer method and device based on user emotion |
| CN109582780B (en) * | 2018-12-20 | 2021-10-01 | 广东小天才科技有限公司 | Intelligent question and answer method and device based on user emotion |
| CN109684459A (en) * | 2018-12-28 | 2019-04-26 | 联想(北京)有限公司 | A kind of information processing method and device |
| CN109710503A (en) * | 2018-12-28 | 2019-05-03 | 浙江百应科技有限公司 | A kind of method of Intelligent voice dialog data OA operation analysis |
| CN109885679A (en) * | 2019-01-11 | 2019-06-14 | 平安科技（深圳）有限公司 | Obtain method, apparatus, computer equipment and the storage medium of preferred words art |
| CN109767765A (en) * | 2019-01-17 | 2019-05-17 | 平安科技（深圳）有限公司 | Talk about art matching process and device, storage medium, computer equipment |
| CN109783613A (en) * | 2019-01-23 | 2019-05-21 | 广东小天才科技有限公司 | One kind searching topic method and system |
| CN110032630A (en) * | 2019-03-12 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Talk about art recommendation apparatus, method and model training equipment |
| CN110032630B (en) * | 2019-03-12 | 2023-04-18 | 创新先进技术有限公司 | Dialectical recommendation device and method and model training device |
| CN110060098A (en) * | 2019-04-04 | 2019-07-26 | 秒针信息技术有限公司 | The acquisition methods and device of marketing term |
| CN110136723A (en) * | 2019-04-15 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Data processing method and device based on voice messaging |
| CN110147930A (en) * | 2019-04-16 | 2019-08-20 | 平安科技（深圳）有限公司 | Data statistical approach, device and storage medium based on big data analysis |
| CN110298682A (en) * | 2019-05-22 | 2019-10-01 | 深圳壹账通智能科技有限公司 | Intelligent Decision-making Method, device, equipment and medium based on user information analysis |
| CN110287299A (en) * | 2019-06-17 | 2019-09-27 | 浙江百应科技有限公司 | Loquacity term sentence intelligent switch method in a kind of call |
| CN110379445A (en) * | 2019-06-20 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Method for processing business, device, equipment and storage medium based on mood analysis |
| CN110460798A (en) * | 2019-06-26 | 2019-11-15 | 平安科技（深圳）有限公司 | Video Interview service processing method, device, terminal and storage medium |
| CN111354377A (en) * | 2019-06-27 | 2020-06-30 | 深圳市鸿合创新信息技术有限责任公司 | Method and device for recognizing emotion through voice and electronic equipment |
| CN110475032A (en) * | 2019-06-28 | 2019-11-19 | 平安科技（深圳）有限公司 | Multi-service interface switching method, device, computer installation and storage medium |
| CN110347863A (en) * | 2019-06-28 | 2019-10-18 | 腾讯科技（深圳）有限公司 | Talk about art recommended method and device and storage medium |
| CN110347863B (en) * | 2019-06-28 | 2023-09-22 | 腾讯科技（深圳）有限公司 | Speaking recommendation method and device and storage medium |
| CN112182047A (en) * | 2019-07-05 | 2021-01-05 | 北京猎户星空科技有限公司 | Information recommendation method, device, equipment and medium |
| CN112182047B (en) * | 2019-07-05 | 2023-12-12 | 北京猎户星空科技有限公司 | Information recommendation method, device, equipment and medium |
| CN110459210A (en) * | 2019-07-30 | 2019-11-15 | 平安科技（深圳）有限公司 | Answering method, device, equipment and storage medium based on speech analysis |
| CN112417200A (en) * | 2019-08-21 | 2021-02-26 | 北京峰趣互联网信息服务有限公司 | Method and device for determining tracks, electronic equipment and computer readable storage medium |
| CN110610705A (en) * | 2019-09-20 | 2019-12-24 | 上海数鸣人工智能科技有限公司 | Voice interaction prompter based on artificial intelligence |
| CN110890088A (en) * | 2019-10-12 | 2020-03-17 | 中国平安财产保险股份有限公司 | Voice information feedback method and device, computer equipment and storage medium |
| CN110890088B (en) * | 2019-10-12 | 2022-07-15 | 中国平安财产保险股份有限公司 | Voice information feedback method and device, computer equipment and storage medium |
| CN111104505B (en) * | 2019-12-30 | 2023-08-25 | 浙江阿尔法人力资源有限公司 | Information prompting method, device, equipment and storage medium |
| CN111104505A (en) * | 2019-12-30 | 2020-05-05 | 浙江阿尔法人力资源有限公司 | Information prompting method, device, equipment and storage medium |
| CN113314122B (en) * | 2020-02-27 | 2023-01-17 | 北京有限元科技有限公司 | Method, apparatus, and medium for determining optimal dialect using single voice robot |
| CN113314122A (en) * | 2020-02-27 | 2021-08-27 | 北京有限元科技有限公司 | Method, apparatus, and medium for determining optimal dialect using single voice robot |
| CN111564202A (en) * | 2020-04-30 | 2020-08-21 | 深圳市镜象科技有限公司 | Psychological counseling method based on man-machine conversation, psychological counseling terminal and storage medium |
| CN111564202B (en) * | 2020-04-30 | 2021-05-28 | 深圳市镜象科技有限公司 | Psychological counseling method based on man-machine conversation, psychological counseling terminal and storage medium |
| CN111522937B (en) * | 2020-05-15 | 2023-04-28 | 支付宝(杭州)信息技术有限公司 | Speaking recommendation method and device and electronic equipment |
| CN111522937A (en) * | 2020-05-15 | 2020-08-11 | 支付宝(杭州)信息技术有限公司 | Method and device for recommending dialect and electronic equipment |
| CN111598485A (en) * | 2020-05-28 | 2020-08-28 | 成都晓多科技有限公司 | Multi-dimensional intelligent quality inspection method, device, terminal equipment and medium |
| CN111881254A (en) * | 2020-06-10 | 2020-11-03 | 百度在线网络技术（北京）有限公司 | Method and device for generating dialogs, electronic equipment and storage medium |
| CN111710338A (en) * | 2020-06-28 | 2020-09-25 | 上海优扬新媒信息技术有限公司 | Voice operation playing method and device |
| CN111932296A (en) * | 2020-07-20 | 2020-11-13 | 中国建设银行股份有限公司 | Product recommendation method and device, server and storage medium |
| CN111932296B (en) * | 2020-07-20 | 2024-05-28 | 中国建设银行股份有限公司 | Product recommendation method and device, server and storage medium |
| CN111858897A (en) * | 2020-07-30 | 2020-10-30 | 北京首汽智行科技有限公司 | Customer service staff speech guiding method and system |
| CN112053205A (en) * | 2020-08-21 | 2020-12-08 | 北京云迹科技有限公司 | Product recommendation method and device through robot emotion recognition |
| CN112256855A (en) * | 2020-11-13 | 2021-01-22 | 泰康保险集团股份有限公司 | User intention identification method and device |
| CN112671984A (en) * | 2020-12-01 | 2021-04-16 | 长沙市到家悠享网络科技有限公司 | Service mode switching method and device, robot customer service and storage medium |
| CN112686448B (en) * | 2020-12-31 | 2024-02-13 | 重庆富民银行股份有限公司 | Loss early warning method and system based on attribute data |
| CN112686448A (en) * | 2020-12-31 | 2021-04-20 | 重庆富民银行股份有限公司 | Loss early warning method and system based on attribute data |
| CN113010784B (en) * | 2021-03-17 | 2024-02-06 | 北京十一贝科技有限公司 | Method, apparatus, electronic device and medium for generating prediction information |
| CN113010784A (en) * | 2021-03-17 | 2021-06-22 | 北京十一贝科技有限公司 | Method, apparatus, electronic device, and medium for generating prediction information |
| CN113312468A (en) * | 2021-07-30 | 2021-08-27 | 平安科技（深圳）有限公司 | Conversation mode-based conversation recommendation method, device, equipment and medium |
| CN113688221B (en) * | 2021-09-08 | 2023-07-25 | 中国平安人寿保险股份有限公司 | Model-based conversation recommendation method, device, computer equipment and storage medium |
| CN113688221A (en) * | 2021-09-08 | 2021-11-23 | 中国平安人寿保险股份有限公司 | Model-based dialect recommendation method and device, computer equipment and storage medium |
| CN114399821B (en) * | 2022-01-13 | 2024-04-26 | 中国平安人寿保险股份有限公司 | Policy recommendation method, device and storage medium |
| CN114399821A (en) * | 2022-01-13 | 2022-04-26 | 中国平安人寿保险股份有限公司 | Policy recommendation method, device and storage medium |
| CN116662503A (en) * | 2023-05-22 | 2023-08-29 | 深圳市新美网络科技有限公司 | Private user scene phone recommendation method and system thereof |
| CN116662503B (en) * | 2023-05-22 | 2023-12-29 | 深圳市新美网络科技有限公司 | Private user scene phone recommendation method and system thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109033257A (en) | Talk about art recommended method, device, computer equipment and storage medium | |
| CN107609101B (en) | Intelligent interaction method, equipment and storage medium | |
| CN110175227B (en) | Dialogue auxiliary system based on team learning and hierarchical reasoning | |
| CN104598445B (en) | Automatically request-answering system and method | |
| CN107797984B (en) | Intelligent interaction method, equipment and storage medium | |
| CN110020426B (en) | Method and device for distributing user consultation to customer service group | |
| CN114556354A (en) | Automatically determining and presenting personalized action items from an event | |
| CN110232109A (en) | A kind of Internet public opinion analysis method and system | |
| CN109190652A (en) | It attends a banquet sort management method, device, computer equipment and storage medium | |
| CN111182162B (en) | Telephone quality inspection method, device, equipment and storage medium based on artificial intelligence | |
| US10586237B2 (en) | Method, apparatus, and computer-readable media for customer interaction semantic annotation and analytics | |
| JP2017224190A (en) | Artificial intelligence system for supporting communication | |
| CN110032630A (en) | Talk about art recommendation apparatus, method and model training equipment | |
| US11232261B2 (en) | Open domain real-time question answering | |
| CN112364234B (en) | Automatic grouping system for online discussion | |
| CN109087205A (en) | Prediction technique and device, the computer equipment and readable storage medium storing program for executing of public opinion index | |
| CN110401545B (en) | Chat group creation method, chat group creation device, computer equipment and storage medium | |
| KR20190007213A (en) | Apparuatus and method for distributing a question | |
| KR101416291B1 (en) | Sentiment classification system using rule-based multi agents | |
| KR20190046062A (en) | Method and apparatus of dialog scenario database constructing for dialog system | |
| KR102117287B1 (en) | Method and apparatus of dialog scenario database constructing for dialog system | |
| CN112632252A (en) | Dialogue response method, dialogue response device, computer equipment and storage medium | |
| CN105930372A (en) | Emotion robot conversation method and system based on multi-feedback, and robot | |
| Aattouri et al. | Modeling of an artificial intelligence based enterprise callbot with natural language processing and machine learning algorithms | |
| CN114138960A (en) | User intention identification method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |
|
| RJ01 | Rejection of invention patent application after publication |