CN109636442A - Like the determination method, apparatus and storage medium of content - Google Patents
Like the determination method, apparatus and storage medium of content Download PDFInfo
- Publication number
- CN109636442A CN109636442A CN201811339848.1A CN201811339848A CN109636442A CN 109636442 A CN109636442 A CN 109636442A CN 201811339848 A CN201811339848 A CN 201811339848A CN 109636442 A CN109636442 A CN 109636442A
- Authority
- CN
- China
- Prior art keywords
- signal
- body language
- training
- language
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses a kind of determination methods for liking content, comprising: determines the body language signal collection for being directed to object content；The body language signal collection includes one or more body language signal subsets, and each body language signal subset includes the corresponding body language signal of body language each at least one body language and at least one body language；The body language signal collection is identified with preset decision model, determines the recognition result for being directed to the object content；The recognition result characterization is directed to the fancy grade of the object content；When determining that the recognition result is more than preset threshold, determine the corresponding object content of the recognition result for hobby content.The invention also discloses a kind of determining devices and computer readable storage medium for liking content.
Description
Technical field
The present invention relates to multimedia communication technology more particularly to a kind of determination method, apparatus and computer for liking content
Readable storage medium storing program for executing.
Background technique
In Internet service operation, in order to realize user oriented accurate operation, need to the hobby content of user into
Row determines.It is usually at present to determine that the determination of this method is too according to comment, marking, clicking rate etc. to the judgement of user preferences
It is general to cross, and can not more accurately determine the fancy grade of user.
Summary of the invention
In view of this, the main purpose of the present invention is to provide a kind of determination method, apparatus and computer for liking content
Readable storage medium storing program for executing.
In order to achieve the above objectives, the technical scheme of the present invention is realized as follows:
The embodiment of the invention provides a kind of determination methods for liking content, which comprises
Determine the body language signal collection for being directed to object content；The body language signal collection includes one or more limbs
Speech signal subset, each body language signal subset include at least one body language and at least one limbs language
Call the turn the corresponding body language signal of each body language；
The body language signal collection is identified with preset decision model, determines the identification knot for being directed to the object content
Fruit；The recognition result characterization is directed to the fancy grade of the object content；
When determining that the recognition result is more than preset threshold, determine the corresponding object content of the recognition result in hobby
Hold.
In above scheme, the determination is directed to the body language signal collection of object content, comprising: determines each body language pair
The body language signal answered；
The corresponding body language signal of each body language of determination, comprising:
The second letter during determining the first signal before obtaining object content in the first preset time period, obtaining object content
Number and obtain third signal after object content in the second preset time period；
The corresponding limbs of the body language are determined according to first signal, the second signal and the third signal
Speech signal.
In above scheme, the method also includes: generate the decision model；
The generation decision model, comprising:
Obtain the training body language signal subset of predetermined number；
According to the training body language signal subset of the predetermined number, the corresponding predetermined number of each body language is obtained
Training language signal；
Determine the first training signal, the second training signal and the third training signal in the training language signal, according to
First training signal, the second training signal and third training signal determine the corresponding training reference of the training language signal
Value；The maximum value and minimum value in the corresponding trained reference value of the training language signal of the predetermined number are determined, according to described
Maximum value and the minimum value determine critical parameter；
The decision model is generated according to the corresponding critical parameter of each body language.
In above scheme, the body language, including it is following at least one: heartbeat, expression, blood pressure；
It is described to identify the body language signal collection with preset decision model, determine the knowledge for being directed to the object content
Other result, comprising:
Identify that the body language signal concentrates the corresponding happiness of each body language signal subset with the decision model
Good value；
Determine that the sum of corresponding hobby value of each body language signal subset is used as the recognition result.
It is described to identify that the body language signal concentrates each body language letter with the decision model in above scheme
The corresponding hobby value of work song collection, comprising:
Classify to the body language signal collection, determines at least one limb described in each body language signal subspace collection
The corresponding body language signal of each body language in body language；
It is successively identified at least one body language described in each body language signal subspace collection with the decision model
The corresponding body language signal of each body language, determines the corresponding hobby value of each body language signal subset.
The embodiment of the invention provides a kind of determining device for liking content, described device includes: first processing module, the
Two processing modules and third processing module；Wherein,
The first processing module, for determining the body language signal collection for being directed to object content；The body language letter
Number collection includes one or more body language signal subsets, and each body language signal subset includes at least one limbs language
Mention the corresponding body language signal of each body language at least one body language；
The Second processing module determines needle for identifying the body language signal collection with preset decision model
To the recognition result of the object content；The recognition result characterization is directed to the fancy grade of the object content；
The third processing module determines the recognition result when for determining that the recognition result is more than preset threshold
Corresponding object content is hobby content.
In above scheme, the first processing module is specifically used for determining the corresponding body language signal of each body language；
The corresponding body language signal of each body language of determination, comprising: determine before obtaining object content in the first preset time period
The first signal, obtain object content during second signal and obtain after object content in the second preset time period the
Three signals；The corresponding limbs of the body language are determined according to first signal, the second signal and the third signal
Speech signal.
In above scheme, described device further include: preprocessing module, for generating the decision model；
The preprocessing module, specifically for obtaining the training body language signal subset of predetermined number；
According to the training body language signal subset of the predetermined number, the corresponding predetermined number of each body language is obtained
Training language signal；
Determine the first training signal, the second training signal and the third training signal in the training language signal, according to
First training signal, the second training signal and third training signal determine the corresponding training reference of the training language signal
Value；The maximum value and minimum value in the corresponding trained reference value of the training language signal of the predetermined number are determined, according to described
Maximum value and the minimum value determine critical parameter；
The decision model is generated according to the corresponding critical parameter of each body language.
In above scheme, the body language, including it is following at least one: heartbeat, expression, blood pressure；
The Second processing module is specifically used for identifying that the body language signal is concentrated each with the decision model
The corresponding hobby value of body language signal subset；
Determine that the sum of corresponding hobby value of each body language signal subset is used as the recognition result.
In above scheme, the Second processing module is determined specifically for classifying to the body language signal collection
The corresponding body language signal of each body language at least one body language described in each body language signal subspace collection；
It is successively identified at least one body language described in each body language signal subspace collection with the decision model
The corresponding body language signal of each body language, determines the corresponding hobby value of each body language signal subset.
The embodiment of the invention provides a kind of determining device for liking content, described device includes: processor and for depositing
The memory of the enough computer programs run on a processor of energy storage；Wherein,
The processor is for when running the computer program, executing any one above-described hobby content really
The step of determining method.
The embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, described
The step of determination method of any one above-described hobby content is realized when computer program is executed by processor.
The determination method, apparatus and computer readable storage medium of hobby content, determine provided by the embodiment of the present invention
For the body language signal collection of object content；The body language signal collection includes one or more body language signal subspaces
Collection, each body language signal subset include each limbs at least one body language and at least one body language
The corresponding body language signal of language；The body language signal collection is identified with preset decision model, is determined for described
The recognition result of object content；The recognition result characterization is directed to the fancy grade of the object content；Determine the identification knot
When fruit is more than preset threshold, determine the corresponding object content of the recognition result for hobby content.In the embodiment of the present invention, pass through
To user in the excavation for obtaining the variation of the body languages such as heartbeat, blood pressure, the expression of object content service stage, determine that user is internal
The fancy grade of appearance improves the accuracy of judgement.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of determination method for liking content provided in an embodiment of the present invention；
Fig. 2 is the flow diagram of the determination method of another hobby content provided in an embodiment of the present invention；
Fig. 3 is a kind of structural schematic diagram of determining device for liking content provided in an embodiment of the present invention；
Fig. 4 is the structural schematic diagram of the determining device of another hobby content provided in an embodiment of the present invention.
Specific embodiment
In various embodiments of the present invention, the body language signal collection for being directed to object content is determined；The body language
Signal collection includes one or more body language signal subsets, and each body language signal subset includes at least one limbs
The corresponding body language signal of each body language in language and at least one body language；Know with preset decision model
The not described body language signal collection determines the recognition result for being directed to the object content；The recognition result characterization is for described
The fancy grade of object content；When determining that the recognition result is more than preset threshold, the corresponding target of the recognition result is determined
Content is hobby content.
Below with reference to embodiment, the present invention is further described in more detail.
Fig. 1 is a kind of flow diagram of determination method for liking content provided in an embodiment of the present invention；The method can
To be applied to the mobile terminals such as mobile phone, tablet computer, or applied in the server being connect with the mobile terminal, such as Fig. 1
It is shown, which comprises
Step 101 determines the body language signal collection for being directed to object content；The body language signal collection include one or
Multiple body language signal subsets, each body language signal subset include at least one body language and described at least one
The corresponding body language signal of each body language in kind of body language.
Specifically, the determination is directed to the body language signal collection of object content, comprising: determines that each body language is corresponding
Body language signal；
And body language signal subset is determined according to the corresponding body language signal of each body language；According to one
A or multiple body language signal subsets determine the body language signal collection.
The body language signal subset, comprising: each at least one body language and at least one body language
The corresponding body language signal of body language.It should be noted that a body language signal subspace concentrates each body language corresponding
Body language signal need to acquire simultaneously, i.e., the corresponding limbs language of each body language of acquisition in the same period
Speech signal can just be put into a body language signal subspace and concentrate.
Here, the body language signal subspace concentrates the corresponding body language signal of each body language, a limbs language
Speech signal includes: the first signal before obtaining object content in the first preset time period, the second letter during acquisition object content
Number and obtain third signal after object content in the second preset time period.
Specifically, the corresponding body language signal of each body language of the determination, comprising:
The second letter during determining the first signal before obtaining object content in the first preset time period, obtaining object content
Number and obtain third signal after object content in the second preset time period；
The corresponding limbs of the body language are determined according to first signal, the second signal and the third signal
Speech signal.
Here, the signal in each of the above preset time period can take the average value of the signal in the preset time period；Example
Such as first signal, the average value of the signal before obtaining object content in the first preset time period can be taken.Second letter
Number, the average value of the signal during obtaining object content can be taken.The third signal can take second after obtaining object content
The average value of signal in preset time period.
The body language, including but not limited to: heartbeat, expression, blood pressure etc..
First preset time period, second preset time period can be preset by developer；Such as: it is described
First preset time period can be 1 minute, 2 minutes etc., and second preset time period can be 1 minute, 2 minutes etc..
Step 102 identifies the body language signal collection with preset decision model, determines and is directed to the object content
Recognition result；The recognition result characterization is directed to the fancy grade of the object content.
Specifically, described to identify the body language signal collection with preset decision model, it determines and is directed to the target
The recognition result of content, comprising:
Identify that the body language signal concentrates the corresponding happiness of each body language signal subset with the decision model
Good value；
Determine that the sum of corresponding hobby value of each body language signal subset is used as the recognition result.
Specifically, described to identify that the body language signal concentrates each body language signal subspace with the decision model
Collect corresponding hobby value, comprising:
Classify to the body language signal collection, determines at least one limb described in each body language signal subspace collection
The corresponding body language signal of each body language in body language；
It is successively identified at least one body language described in each body language signal subspace collection with the decision model
The corresponding body language signal of each body language, determines the corresponding hobby value of each body language signal subset.
Here, described successively to identify at least one limb described in each body language signal subspace collection with the decision model
The corresponding body language signal of each body language, determines the corresponding hobby value of each body language signal subset in body language, wraps
It includes:
It is successively identified at least one body language described in each body language signal subspace collection with the decision model
The corresponding body language signal of each body language, determines the reference value of the corresponding body language signal of each body language, according to institute
The reference value for stating the corresponding body language signal of each body language determines the corresponding hobby of each body language signal subset
Value.
Here, the reference value=absolute value (second signal-w1* the first signal-w2* second signal).W1 and w2 is power
Weight, can take 0.5.
Step 103, determine the recognition result be more than preset threshold when, determine the corresponding object content of the recognition result
To like content.
Here, the preset threshold can be preset by developer, for the body language signal subspace of different numbers
Collection, can set different preset thresholds.
When the determination recognition result is more than preset threshold, determine the corresponding object content of the recognition result for happiness
Good content, comprising:
The number for determining the body language signal subset determines corresponding preset threshold according to the number；
When determining the preset threshold that the recognition result is more than determining, determine that the corresponding object content of the recognition result is
Like content.
In the present embodiment, the method also includes: generate the decision model.
Specifically, the generation decision model, comprising:
Obtain the training body language signal subset of predetermined number；
According to the training body language signal subset of the predetermined number, the corresponding predetermined number of each body language is obtained
Training language signal；
Determine the first training signal, the second training signal and the third training signal in the training language signal, according to
First training signal, the second training signal and third training signal determine the corresponding training reference of the training language signal
Value；The maximum value and minimum value in the corresponding trained reference value of the training language signal of the predetermined number are determined, according to described
Maximum value and the minimum value determine critical parameter；
The decision model is generated according to the corresponding critical parameter of each body language.
For example, the body language, including it is following at least one: heartbeat, expression, blood pressure；Then, described according to
The training body language signal subset of predetermined number, obtains the training language signal of the corresponding predetermined number of each body language, can
To comprise at least one of the following situation:
It is concentrated from the training body language signal subspace of the predetermined number, obtains the predetermined number for being directed to training objective content
Heartbeat speech signal, each heartbeat speech signal includes: before obtaining training objective content in the first preset time period here
Heartbeat speech signal, obtain training objective content during heartbeat speech signal, obtain training objective content after second it is default when
Between heartbeat speech signal in section；
It is concentrated from the training body language signal subspace of the predetermined number, obtains the predetermined number for being directed to training objective content
Expression speech signal, each expression speech signal includes: before obtaining training objective content in the first preset time period here
Expression speech signal, obtain training objective content during expression speech signal, obtain training objective content after second it is default when
Between expression speech signal in section；
It is concentrated from the training body language signal subspace of the predetermined number, obtains the predetermined number for being directed to training objective content
Blood pressure speech signal, each blood pressure speech signal includes: before obtaining training objective content in the first preset time period here
Blood pressure speech signal, obtain training objective content during blood pressure speech signal, obtain training objective content after second it is default when
Between blood pressure speech signal in section.
It is further elaborated with, it is assumed that
Heartbeat speech signal before acquisition training objective content in the first preset time period is denoted as A1, obtains in training objective
Heartbeat speech signal note after heartbeat speech signal during appearance is denoted as A2, obtains training objective content in the second preset time period
It is A3.
Expression speech signal before acquisition training objective content in the first preset time period is denoted as B1, obtains in training objective
Expression speech signal note after expression speech signal during appearance is denoted as B2, obtains training objective content in the second preset time period
It is B3.
Blood pressure speech signal before acquisition training objective content in the first preset time period is denoted as C1, obtains in training objective
Blood pressure speech signal note after blood pressure speech signal during appearance is denoted as C2, obtains training objective content in the second preset time period
It is C3.
It is described to determine that the training language is believed according to first training signal, the second training signal and third training signal
Number corresponding trained reference value；Include:
For each heartbeat speech signal, according to formula A=| A2-w1*A1-w2*A3 | it calculates and obtains training reference value A；
For each expression speech signal, according to formula B=| B2-w1*B1-w2*B3 | it calculates and obtains training reference value B；For each
Blood pressure speech signal, according to formula C=| C2-w1*C1-w2*C3 | it calculates and obtains training reference value C；More than, w1 and w2 are power
Weight, can take 0.5.
Maximum value and minimum value in the corresponding trained reference value of training language signal of the determination predetermined number,
Critical parameter is determined according to the maximum value and the minimum value；Include:
According to the training reference value of each heartbeat speech signal, by fa=(Amax-Amin)/Amax, calculating is directed to
The critical parameter fa of heartbeat speech signal；According to the training reference value of each expression speech signal, by fb=(Bmax-Bmin)/
Bmax calculates the critical parameter fb for obtaining and being directed to expression speech signal；Further according to the training reference value of each blood pressure speech signal,
By fc=(Cmax-Cmin)/Cmax, the critical parameter fc for obtaining and being directed to blood pressure speech signal is calculated.
In one embodiment, described according to each body language corresponding critical parameter generation judgement mould
Type, comprising:
According to for heartbeat speech signal critical parameter, for expression speech signal critical parameter, be directed to blood pressure language
The critical parameter for saying signal, generates the decision model as the following formula:
Score (kth acquisition object content)=∑ xKyK；
Wherein, xKProportional with user's access times, x can take some value between 1~2, for example, it can be set to being
1.1.Y indicates body language type, yKIndicate k-th body language signal subspace concentrate the corresponding reference value of every kind of body language and
The sum of the product of critical parameter, y are determined according to the type of body language.For example, body language includes the above heartbeat, table
Feelings, blood pressure, then yK=A'Kfa+B'Kfb+C'Kfc；Wherein, A'K、B'K、C'KIt can refer to k-th body language signal subset respectively
In the reference value of heartbeat speech signal, the reference value of expression speech signal, the reference value of blood pressure speech signal, if the limbs
Language further includes other types, can be sequentially overlapped to obtain the yK。
In addition, the decision model can also update again according to the body language signal acquired later, for example, setting it
The secondary body language signal of every acquisition X (X can be 10,20,30 ... 100 etc.) afterwards, i.e., every X body language signal subspace of acquisition
Collection then updates the primary decision model, so that judging result is more acurrate.
With the above method provided in this embodiment, it can be determined that whether the object content that user obtains is user preferences
Content.Such as: for the comparison of multiple contents (such as multiple videos) of some application software, it can determine that user likes the most
Content, and then can also according to determining content be user by more be bonded regard recommendation.
Fig. 2 is the flow diagram of the determination method of another hobby content provided in an embodiment of the present invention；It can apply
In mobile terminal, as shown in Figure 2, which comprises
Step 201 establishes decision model.
Specifically, the step 201 includes: to obtain the training body language signal subset of predetermined number；According to described pre-
If the training body language signal subset of number, obtains the training language signal of the corresponding predetermined number of each body language；It determines
The first training signal, the second training signal and third training signal in the training language signal, according to first training
Signal, the second training signal and third training signal determine the corresponding trained reference value of the training language signal；Described in determination
Maximum value and minimum value in the corresponding trained reference value of the training language signal of predetermined number, according to the maximum value and described
Minimum value determines critical parameter；The decision model is generated according to the corresponding critical parameter of each body language.
Here, first training signal, second training signal, the third training signal, which are respectively as follows:, is obtaining
1 minute after signal, acquisition training objective content before training objective content during 1 minute signal, acquisition training objective content
Interior signal；The body language includes heartbeat, pulse, expression, blood pressure etc..
Here, for the body language signal of every kind of body language, trained reference value: X=can be calculated as follows |
X2-w1*X1-w2*X3 |, X2 indicates the value during acquisition training objective content, and X1 is indicated 1 point before obtaining training objective content
The value of clock, X3 indicate to obtain 1 minute value after training objective content, and X indicates body language type, be heartbeat, pulse, expression or
Blood pressure.W1 and w2 is weight, can take 0.5；
Again as the following formula, critical parameter is determined according to the corresponding trained reference value of the training language signal of predetermined number:
fX=(Xmax-Xmin)/Xmax；Wherein, X indicates body language type, such as heartbeat, pulse, expression, blood pressure；
Xmax indicates the maximum value in each trained reference value, and Xmin indicates the minimum value in each trained reference value.
Here, it is calculated separately for the different body language type needs such as heartbeat, expression, blood pressure, different body languages
Type cannot be obscured.Such as: it is directed to heartbeat, acquires the heartbeat speech signal of predetermined number (being denoted as M), it is determined that M heartbeat
The corresponding trained reference value of speech signal, to calculate the critical parameter f of heartbeat speech signalA=(Amax-Amin)/Amax；
Here, X=A indicates heartbeat.
It is similar, for expression, M expression speech signals are acquired, determine the training reference of M expression speech signal
Value, to calculate the critical parameter f of expression speech signalB=(Bmax-Bmin)/Bmax；Here, X=B indicates expression；With this
Analogize, critical parameter can be calculated in each body language in a manner described.
Generate the decision model according to the corresponding critical parameter of every kind of body language: (kth obtains mesh to Score
Mark content)=∑ xKyK, xK=1.1K；yKFor k-th body language signal subspace concentrate every kind of body language signal reference value and
The sum that critical parameter obtains product, is added again after being multiplied.
It is extracted it should be noted that the mobile terminal can connect heartbeat extraction module, expression extraction module, blood pressure
Module, pulse extraction module etc..The heartbeat extraction module, blood pressure extraction module, pulse extraction module can be examined using having
The motion bracelet of measuring heart-beat, blood pressure, pulse；The expression extraction module can use any equipment with camera.Heartbeat mentions
Modulus block can extract the heartbeat variation of user, timestamp is arranged with the second；The expression extraction module, can extract the corners of the mouth to
Timestamp is arranged with the second in upper curvature.The pulse extraction module can extract the pulse variation of user, the time is arranged with the second
Stamp；The blood pressure extraction module, can extract the blood pressure of user, and timestamp is arranged with the second.
Step 202, acquisition user are directed to the body language signal collection of object content.
Here, the body language signal collection includes: one or more body language signal subsets, each limbs language
Say that signal subset includes the corresponding limbs language of body language each at least one body language and at least one body language
Say signal.
Step 203 determines that user is directed to the fancy grade of object content according to decision model.
Specifically, the step 203 includes: to identify the body language signal collection with the decision model, determines needle
To the recognition result of the object content；The recognition result characterization is directed to the fancy grade of the object content.
Specifically, it is assumed that body language signal concentrates 2 body language signal subsets, each body language signal subset
It include: 3 kinds of body languages (respectively heartbeat, expression, blood pressure) and the corresponding body language signal of 3 kinds of body languages.
According to each body language signal subset, Score (kth acquisition object content) is calculated separately with following formula:
Score (kth acquisition object content)=∑ xKyK；
Wherein, xK=1.1K；yK=A'Kfa+B'Kfb+C'Kfc, A'K、B'K、C'KRespectively refer to k-th body language signal subspace
The reference value of heartbeat speech signal, the reference value of expression speech signal, the reference value of blood pressure speech signal of concentration.fa、fb、fc
The corresponding critical parameter of respectively 3 kinds of body languages.
The score Score (the 1st acquisition object content) and the 2nd limbs that 1st body language signal subset is obtained
The score Score (the 2nd acquisition object content) that speech signal subset obtains is added, and obtains the recognition result, the identification
It as a result is the fancy grade that user is directed to object content.
Step 204 determines whether the object content is hobby content according to the fancy grade.
Here, the preset threshold can be preset by developer, for the body language signal subspace of different numbers
Collection, can set different preset thresholds.
It is described to determine whether the object content is hobby content according to the fancy grade, comprising:
The number for determining the body language signal subset determines corresponding preset threshold according to the number；
When determining that the recognition result of characterization fancy grade is more than determining preset threshold, the recognition result pair is determined
The object content answered is hobby content.
The relationship of the corresponding preset threshold of the number of the body language signal subset can be preparatory by developer
It sets and saves.
Fig. 3 is a kind of structural schematic diagram of determining device for liking content provided in an embodiment of the present invention；As shown in figure 3,
Described device includes: first processing module 301, Second processing module 302 and third processing module 303.Wherein,
The first processing module 301, for determining the body language signal collection for being directed to object content；The body language
Signal collection includes one or more body language signal subsets, and each body language signal subset includes at least one limbs
The corresponding body language signal of each body language in language and at least one body language.
The Second processing module 302 is determined for identifying the body language signal collection with preset decision model
For the recognition result of the object content；The recognition result characterization is directed to the fancy grade of the object content.
The third processing module 303 when for determining that the recognition result is more than preset threshold, determines the identification knot
The corresponding object content of fruit is hobby content.
Specifically, the first processing module 301 is specifically used for determining the corresponding body language signal of each body language；
The corresponding body language signal of each body language of determination, comprising: determine before obtaining object content in the first preset time period
The first signal, obtain object content during second signal and obtain after object content in the second preset time period the
Three signals；The corresponding limbs of the body language are determined according to first signal, the second signal and the third signal
Speech signal.
Specifically, described device further include: preprocessing module, for generating the decision model；
The preprocessing module, specifically for obtaining the training body language signal subset of predetermined number；
According to the training body language signal subset of the predetermined number, the corresponding predetermined number of each body language is obtained
Training language signal；
Determine the first training signal, the second training signal and the third training signal in the training language signal, according to
First training signal, the second training signal and third training signal determine the corresponding training reference of the training language signal
Value；The maximum value and minimum value in the corresponding trained reference value of the training language signal of the predetermined number are determined, according to described
Maximum value and the minimum value determine critical parameter；
The decision model is generated according to the corresponding critical parameter of each body language.
Here, the body language, including it is following at least one: heartbeat, expression, blood pressure.
The Second processing module 302 is specifically used for identifying that the body language signal is concentrated with the decision model
The corresponding hobby value of each body language signal subset；
Determine that the sum of corresponding hobby value of each body language signal subset is used as the recognition result.
Specifically, the Second processing module 302 is determined specifically for classifying to the body language signal collection
The corresponding body language signal of each body language at least one body language described in each body language signal subspace collection；
It is successively identified at least one body language described in each body language signal subspace collection with the decision model
The corresponding body language signal of each body language, determines the corresponding hobby value of each body language signal subset.
It should be understood that the determining device of hobby content provided by the above embodiment is in the determination for carrying out hobby content
When, only with the division progress of above-mentioned each program module for example, can according to need in practical application and divide above-mentioned processing
With by different program module completions, i.e., the internal structure of device is divided into different program modules, to complete above description
All or part of processing.In addition, the determining device of hobby content provided by the above embodiment and the determination side of hobby content
Method embodiment belongs to same design, and specific implementation process is detailed in embodiment of the method, and which is not described herein again.
Fig. 4 is the structural schematic diagram of the determining device of another hobby content provided in an embodiment of the present invention.Such as Fig. 4 institute
Show, described device 40 includes: processor 401 and the storage for storing the computer program that can be run on the processor
Device 402；Wherein, the processor 401 is for executing when running the computer program: determining the limbs for being directed to object content
Speech signal collection；The body language signal collection includes one or more body language signal subsets, each body language
Signal subset includes the corresponding body language of body language each at least one body language and at least one body language
Signal；The body language signal collection is identified with preset decision model, determines the recognition result for being directed to the object content；
The recognition result characterization is directed to the fancy grade of the object content；When determining that the recognition result is more than preset threshold, really
Determining the corresponding object content of the recognition result is hobby content.
In one embodiment, it when the processor 401 is also used to run the computer program, executes: determining each limbs
The corresponding body language signal of language；The corresponding body language signal of each body language of determination, comprising: determine and obtain target
The second signal and acquisition object content during the first signal, acquisition object content before content in the first preset time period
Third signal in second preset time period afterwards；It is determined according to first signal, the second signal and the third signal
The corresponding body language signal of the body language.
In one embodiment, it when the processor 401 is also used to run the computer program, executes: sentencing described in generation
Cover half type；The generation decision model, comprising: obtain the training body language signal subset of predetermined number；According to described default
The training body language signal subset of number, obtains the training language signal of the corresponding predetermined number of each body language；Determine institute
The first training signal, the second training signal and the third training signal in training language signal are stated, is believed according to first training
Number, the second training signal and third training signal determine the corresponding trained reference value of the training language signal；It determines described pre-
If maximum value and minimum value in the corresponding trained reference value of the training language signal of number, according to the maximum value and it is described most
Small value determines critical parameter；The decision model is generated according to the corresponding critical parameter of each body language.
In one embodiment, it when the processor 401 is also used to run the computer program, executes: sentencing described in utilization
Cover half type identifies that the body language signal concentrates the corresponding hobby value of each body language signal subset；Determine each limbs language
Say that the sum of corresponding hobby value of signal subset is used as the recognition result.
In one embodiment, it when the processor 401 is also used to run the computer program, executes: to the limbs
Speech signal collection is classified, and determines each body language at least one body language described in each body language signal subspace collection
Corresponding body language signal；At least one described in each body language signal subspace collection is successively identified with the decision model
The corresponding body language signal of each body language, determines the corresponding hobby value of each body language signal subset in body language.
It should be understood that the determining device of hobby content provided by the above embodiment and the determination method of hobby content are real
It applies example and belongs to same design, specific implementation process is detailed in embodiment of the method, and which is not described herein again.
When practical application, described device 40 can also include: at least one network interface 403.That likes content determines dress
The various components set in 40 are coupled by bus system 404.It is understood that bus system 404 is for realizing these components
Between connection communication.Bus system 404 further includes power bus, control bus and state letter in addition to including data/address bus
Number bus.But for the sake of clear explanation, various buses are all designated as bus system 404 in Fig. 4.Wherein, the processing
The number of device 404 can be at least one.Network interface 403 has for liking between the determining device 40 of content and other equipment
The communication of line or wireless mode.
Memory 402 in the embodiment of the present invention supports hobby content device really for storing various types of data
40 operation.
The method that the embodiments of the present invention disclose can be applied in processor 401, or be realized by processor 401.
Processor 401 may be a kind of IC chip, the processing capacity with signal.During realization, the above method it is each
Step can be completed by the integrated logic circuit of the hardware in processor 401 or the instruction of software form.Above-mentioned processing
Device 401 can be general processor, digital signal processor (DSP, Digital Signal Processor) or other can
Programmed logic device, discrete gate or transistor logic, discrete hardware components etc..Processor 401 may be implemented or hold
Disclosed each method, step and logic diagram in the row embodiment of the present invention.General processor can be microprocessor or appoint
What conventional processor etc..The step of method in conjunction with disclosed in the embodiment of the present invention, can be embodied directly at hardware decoding
Reason device executes completion, or in decoding processor hardware and software module combine and execute completion.Software module can be located at
In storage medium, which is located at memory 402, and processor 401 reads the information in memory 402, in conjunction with its hardware
The step of completing preceding method.
In the exemplary embodiment, the determining device 40 for liking content can be by one or more application specific integrated circuit
(ASIC, Application Specific Integrated Circuit), DSP, programmable logic device (PLD,
Programmable Logic Device), Complex Programmable Logic Devices (CPLD, Complex Programmable Logic
Device), field programmable gate array (FPGA, Field-Programmable Gate Array), general processor, control
Device, microcontroller (MCU, Micro Controller Unit), microprocessor (Microprocessor) or other electronics member
Part is realized, for executing preceding method.
The embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, described
It when computer program is run by processor, executes: determining the body language signal collection for being directed to object content；The body language letter
Number collection includes one or more body language signal subsets, and each body language signal subset includes at least one limbs language
Mention the corresponding body language signal of each body language at least one body language；It is identified with preset decision model
The body language signal collection determines the recognition result for being directed to the object content；The recognition result characterization is directed to the mesh
Mark the fancy grade of content；When determining that the recognition result is more than preset threshold, determine in the corresponding target of the recognition result
Hold for hobby content.
In one embodiment, it when the computer program is run by processor, executes: determining the corresponding limb of each body language
Body speech signal；The corresponding body language signal of each body language of determination, comprising: determine before obtaining object content that first is pre-
If the first signal in the period, obtain object content during second signal and obtain after object content second it is default when
Between third signal in section；The body language is determined according to first signal, the second signal and the third signal
Corresponding body language signal.
In one embodiment, it when the computer program is run by processor, executes: generating the decision model；It is described
Generate decision model, comprising: obtain the training body language signal subset of predetermined number；According to the training limb of the predetermined number
Body speech signal subset obtains the training language signal of the corresponding predetermined number of each body language；Determine the training language letter
The first training signal, the second training signal and third training signal in number are believed according to first training signal, the second training
Number the corresponding trained reference value of the training language signal is determined with third training signal；Determine the training language of the predetermined number
It says the maximum value and minimum value in the corresponding trained reference value of signal, is determined according to the maximum value and the minimum value and determine ginseng
Number；The decision model is generated according to the corresponding critical parameter of each body language.
In one embodiment, it when the computer program is run by processor, executes: identifying institute with the decision model
It states body language signal and concentrates the corresponding hobby value of each body language signal subset；Determine each body language signal subset pair
The sum of hobby value answered is used as the recognition result.
In one embodiment, when the computer program is run by processor, execute: to the body language signal collection into
Row classification determines the corresponding limbs language of each body language at least one body language described in each body language signal subspace collection
Say signal；It is successively identified with the decision model each at least one body language described in each body language signal subspace collection
The corresponding body language signal of body language determines the corresponding hobby value of each body language signal subset.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.Apparatus embodiments described above are merely indicative, for example, the division of the unit, only
A kind of logical function partition, there may be another division manner in actual implementation, such as: multiple units or components can combine, or
It is desirably integrated into another system, or some features can be ignored or not executed.In addition, shown or discussed each composition portion
Mutual coupling or direct-coupling or communication connection is divided to can be through some interfaces, the INDIRECT COUPLING of equipment or unit
Or communication connection, it can be electrical, mechanical or other forms.
Above-mentioned unit as illustrated by the separation member, which can be or may not be, to be physically separated, aobvious as unit
The component shown can be or may not be physical unit, it can and it is in one place, it may be distributed over multiple network lists
In member；Some or all of units can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
In addition, each functional unit in various embodiments of the present invention can be fully integrated in one processing unit, it can also
To be each unit individually as a unit, can also be integrated in one unit with two or more units；It is above-mentioned
Integrated unit both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer readable storage medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed；And storage medium above-mentioned include: movable storage device, it is read-only
Memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or
The various media that can store program code such as person's CD.
If alternatively, the above-mentioned integrated unit of the present invention is realized in the form of software function module and as independent product
When selling or using, it also can store in a computer readable storage medium.Based on this understanding, the present invention is implemented
Substantially the part that contributes to existing technology can be embodied in the form of software products the technical solution of example in other words,
The computer software product is stored in a storage medium, including some instructions are used so that computer equipment (can be with
It is personal computer, server or network equipment etc.) execute all or part of each embodiment the method for the present invention.
And storage medium above-mentioned includes: that movable storage device, ROM, RAM, magnetic or disk etc. are various can store program code
Medium.
The foregoing is only a preferred embodiment of the present invention, is not intended to limit the scope of the present invention, it is all
Made any modifications, equivalent replacements, and improvements etc. within the spirit and principles in the present invention, should be included in protection of the invention
Within the scope of.
Claims (12)
1. a kind of determination method for liking content, which is characterized in that the described method includes:
Determine the body language signal collection for being directed to object content；The body language signal collection includes one or more body languages
Signal subset, each body language signal subset include at least one body language and at least one body language
The corresponding body language signal of each body language；
The body language signal collection is identified with preset decision model, determines the recognition result for being directed to the object content；
The recognition result characterization is directed to the fancy grade of the object content；
When determining that the recognition result is more than preset threshold, determine the corresponding object content of the recognition result for hobby content.
2. the method according to claim 1, wherein the determination is directed to the body language signal of object content
Collection, comprising: determine the corresponding body language signal of each body language；
The corresponding body language signal of each body language of determination, comprising:
Second signal during determining the first signal before obtaining object content in the first preset time period, obtaining object content,
And the third signal after acquisition object content in the second preset time period；
The corresponding body language of the body language is determined according to first signal, the second signal and the third signal
Signal.
3. the method according to claim 1, wherein the method also includes: generate the decision model；
The generation decision model, comprising:
Obtain the training body language signal subset of predetermined number；
According to the training body language signal subset of the predetermined number, the training of the corresponding predetermined number of each body language is obtained
Speech signal；
The first training signal, the second training signal and the third training signal in the training language signal are determined, according to described
First training signal, the second training signal and third training signal determine the corresponding trained reference value of the training language signal；
The maximum value and minimum value in the corresponding trained reference value of the training language signal of the predetermined number are determined, according to the maximum
Value and the minimum value determine critical parameter；
The decision model is generated according to the corresponding critical parameter of each body language.
4. the method according to claim 1, wherein the body language, including it is following at least one: heartbeat,
Expression, blood pressure；
It is described to identify the body language signal collection with preset decision model, determine the identification knot for being directed to the object content
Fruit, comprising:
Identify that the body language signal concentrates the corresponding hobby value of each body language signal subset with the decision model；
Determine that the sum of corresponding hobby value of each body language signal subset is used as the recognition result.
5. according to the method described in claim 4, it is characterized in that, described identify the body language with the decision model
Signal concentrates the corresponding hobby value of each body language signal subset, comprising:
Classify to the body language signal collection, determines at least one limbs language described in each body language signal subspace collection
Call the turn the corresponding body language signal of each body language；
Each limb at least one body language described in each body language signal subspace collection is successively identified with the decision model
The corresponding body language signal of body language determines the corresponding hobby value of each body language signal subset.
6. a kind of determining device for liking content, which is characterized in that described device includes: first processing module, second processing mould
Block and third processing module；Wherein,
The first processing module, for determining the body language signal collection for being directed to object content；The body language signal collection
Including one or more body language signal subsets, each body language signal subset include at least one body language and
The corresponding body language signal of each body language in at least one body language；
The Second processing module determines for identifying the body language signal collection with preset decision model and is directed to institute
State the recognition result of object content；The recognition result characterization is directed to the fancy grade of the object content；
The third processing module when for determining that the recognition result is more than preset threshold, determines that the recognition result is corresponding
Object content be hobby content.
7. device according to claim 6, which is characterized in that the first processing module is specifically used for determining each limbs
The corresponding body language signal of language；The corresponding body language signal of each body language of determination, comprising: determine and obtain target
The second signal and acquisition object content during the first signal, acquisition object content before content in the first preset time period
Third signal in second preset time period afterwards；It is determined according to first signal, the second signal and the third signal
The corresponding body language signal of the body language.
8. device according to claim 6, which is characterized in that described device further include: preprocessing module, for generating
State decision model；
The preprocessing module, specifically for obtaining the training body language signal subset of predetermined number；
According to the training body language signal subset of the predetermined number, the training of the corresponding predetermined number of each body language is obtained
Speech signal；
The first training signal, the second training signal and the third training signal in the training language signal are determined, according to described
First training signal, the second training signal and third training signal determine the corresponding trained reference value of the training language signal；
The maximum value and minimum value in the corresponding trained reference value of the training language signal of the predetermined number are determined, according to the maximum
Value and the minimum value determine critical parameter；
The decision model is generated according to the corresponding critical parameter of each body language.
9. device according to claim 6, which is characterized in that the body language, including it is following at least one: heartbeat,
Expression, blood pressure；
The Second processing module is specifically used for identifying that the body language signal concentrates each limbs with the decision model
The corresponding hobby value of speech signal subset；
Determine that the sum of corresponding hobby value of each body language signal subset is used as the recognition result.
10. device according to claim 9, which is characterized in that the Second processing module is specifically used for the limbs
Speech signal collection is classified, and determines each body language at least one body language described in each body language signal subspace collection
Corresponding body language signal；
Each limb at least one body language described in each body language signal subspace collection is successively identified with the decision model
The corresponding body language signal of body language determines the corresponding hobby value of each body language signal subset.
11. a kind of determining device for liking content, which is characterized in that described device includes: processor and can be for storing
The memory of the computer program run on processor；Wherein,
The processor is for the step of when running the computer program, perform claim requires any one of 1 to 5 the method.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of any one of claim 1 to 5 the method is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811339848.1A CN109636442A (en) | 2018-11-12 | 2018-11-12 | Like the determination method, apparatus and storage medium of content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811339848.1A CN109636442A (en) | 2018-11-12 | 2018-11-12 | Like the determination method, apparatus and storage medium of content |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109636442A true CN109636442A (en) | 2019-04-16 |
Family
ID=66067705
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811339848.1A Pending CN109636442A (en) | 2018-11-12 | 2018-11-12 | Like the determination method, apparatus and storage medium of content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109636442A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079555A (en) * | 2019-11-25 | 2020-04-28 | Oppo广东移动通信有限公司 | User preference degree determining method and device, electronic equipment and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1937462A (en) * | 2005-09-20 | 2007-03-28 | 索尼株式会社 | Content-preference-score determining method, content playback apparatus, and content playback method |
| CN106611028A (en) * | 2015-10-27 | 2017-05-03 | 中国科学院深圳先进技术研究院 | Personalized music recommendation method and system |
| US20170148038A1 (en) * | 2015-11-25 | 2017-05-25 | Sprinklr, Inc. | Buy Intent Estimation And Its Applications For Social Media Data |
-
2018
- 2018-11-12 CN CN201811339848.1A patent/CN109636442A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1937462A (en) * | 2005-09-20 | 2007-03-28 | 索尼株式会社 | Content-preference-score determining method, content playback apparatus, and content playback method |
| CN106611028A (en) * | 2015-10-27 | 2017-05-03 | 中国科学院深圳先进技术研究院 | Personalized music recommendation method and system |
| US20170148038A1 (en) * | 2015-11-25 | 2017-05-25 | Sprinklr, Inc. | Buy Intent Estimation And Its Applications For Social Media Data |
Non-Patent Citations (1)
| Title |
|---|
| 胡吉明: "《基于用户资源关联的社会化推荐研究》", 31 October 2017, 武汉：武汉大学出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079555A (en) * | 2019-11-25 | 2020-04-28 | Oppo广东移动通信有限公司 | User preference degree determining method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11380316B2 (en) | Speech interaction method and apparatus | |
| CN108256433B (en) | Motion attitude assessment method and system | |
| US20230333635A1 (en) | Systems, methods, apparatuses and devices for detecting facial expression and for tracking movement and location in at least one of a virtual and augmented reality system | |
| CN106295476B (en) | Face key point localization method and device | |
| CN106984027B (en) | A kind of movement comparative analysis method, apparatus and a kind of display | |
| CN105095827B (en) | Facial expression recognition device and method | |
| CN108229269A (en) | Method for detecting human face, device and electronic equipment | |
| CN106372622A (en) | Facial expression classification method and device | |
| CN110033022A (en) | Processing method, device and the storage medium of text | |
| CN109784414A (en) | Customer anger detection method, device and electronic equipment in a kind of phone customer service | |
| CN110085225A (en) | Voice interactive method, device, intelligent robot and computer readable storage medium | |
| CN109102859A (en) | A kind of motion control method and system | |
| CN110136714A (en) | Natural interaction sound control method and device | |
| CN108614987A (en) | The method, apparatus and robot of data processing | |
| CN109871780A (en) | A kind of face quality decision method, system and face identification method, system | |
| CN106691424A (en) | Method and device for detecting heart rate | |
| CN110298220A (en) | Action video live broadcasting method, system, electronic equipment, storage medium | |
| CN109308437A (en) | Action recognition error correction method, electronic equipment, storage medium | |
| CN105654046B (en) | Electrocardiosignal personal identification method and device | |
| CN113920568A (en) | Face and human body posture emotion recognition method based on video image | |
| CN109522947A (en) | Recognition methods and equipment | |
| CN109784178A (en) | Parameter adjusting method, device and body-building equipment based on gesture identification | |
| CN109636442A (en) | Like the determination method, apparatus and storage medium of content | |
| CN109044347A (en) | Identify electrocardio wave image junctional escape beat method, apparatus, system and electronic equipment | |
| CN110491394A (en) | Wake up the acquisition methods and device of corpus |
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: 20190416 |