Data push method, system and computer equipment based on micro- expressionTechnical field
The present embodiments relate to data-pushing field more particularly to a kind of data push method based on micro- expression, it isSystem and computer equipment and computer readable storage medium.
Background technique
With the development of Intelligent hardware and development of Mobile Internet technology, intelligent terminal such as smart phone, tablet computer and intelligenceEnergy wrist-watch initially enters the work and life of people.Existing intelligent terminal is mountable and runs answering for a variety of realization specific functionsWith App generallys use the mode for advertisement of spreading its tail to fill the time of App start-up loading data at present, and there is no approach to useThe acceptance level to advertisement of spreading its tail is fed back at family, also can not be also easy to that user is caused to dislike according to user preferences come intelligent recommendation, be givenUser brings very poor viewing and usage experience, promotes specific aim and promotion effect is poor.
Therefore, how to realize the intelligently pushing of data, to promote data-pushing accuracy and pushing efficiency, become this skillArt field personnel technical problem urgently to be resolved and the emphasis studied always.
Summary of the invention
In view of this, it is necessary to provide a kind of data push method based on micro- expression, system, computer equipment and calculatingMachine readable storage medium storing program for executing can promote data-pushing accuracy and pushing efficiency by intelligently pushing, be pushed away with solving current dataIt send mode according to user preferences come intelligent recommendation can not be also easy to that user is caused to dislike, brings very poor viewing to user and makeWith experience, specific aim and the poor problem of promotion effect are promoted.
To achieve the above object, the embodiment of the invention provides the data push method based on micro- expression, the method stepsSuddenly include:
During the broadcasting for advertisement of spreading its tail, the plurality of pictures in preset range is acquired；
Every picture is input in preconfigured micro- table identification model, micro- Expression Recognition model is passed through
To the corresponding micro- expression data of every picture；
Judge user to the level of interest of the advertisement of spreading its tail by micro- expression data；
Strategy is pushed according to level of interest configuration data, the data-pushing strategy includes configuring operation pair of spreading its tail next timeThe next advertisement of spreading its tail answered.
Illustratively, described during the broadcasting for advertisement of spreading its tail, acquire the plurality of pictures in preset range, comprising:
When detecting the control instruction of starting application, the advertisement for obtaining advertisement of spreading its tail is launched using inventory；
Judge whether the application launches in the advertisement using in inventory；And
If whether the application is launching using in inventory, control pop-up within a preset time overhead show described in spread its tailAdvertisement；
The video for advertisement of spreading its tail described in user's viewing is acquired by picture collection device；
Sub-frame processing is carried out to the video, obtains N picture.
Illustratively, face recognition operation is carried out to the N picture, to filter out the M picture containing face information,M is the≤positive integer of N.
Illustratively, every picture is input in preconfigured micro- table identification model, passes through micro- Expression RecognitionModel obtains the corresponding micro- expression data of every picture, comprising:
Every picture in M picture is input to micro- Expression Recognition model according to sequencing to summarize, by describedMicro- Expression Recognition model exports the corresponding micro- expression data of every picture, and micro- expression data includes mood categorical data and feelingsThread level data；
Wherein, micro- Expression Recognition model is preparatory building and the convolutional neural networks model based on supervised learning.
It is illustratively, described to judge user to the level of interest of the advertisement of spreading its tail by micro- expression data, comprising:
Defined parameters vector is distinguished according to micro- expression data of every picture, to obtain the multiple parameters with sequencingVector；
The multiple parameter vector is input in order in shot and long term memory network model, is remembered by the shot and long termNetwork model exports coefficient interested, and the coefficient interested is used for the user's needle for indicating to obtain based on the M pictureTo the level of interest of the advertisement of spreading its tail.
Illustratively, the data-pushing strategy includes configuration good friend's matched data；It is described that number is configured according to level of interestAccording to push strategy, further includes:
It is directed to according to the user for the user in the coefficient and historical record interested of the advertisement of spreading its tailOther multiple coefficients interested of other multiple advertisements of spreading its tail calculate user coefficient interested other to each commercial paper；
Centered on the other coefficient interested of each commercial paper, each other coefficient model interested of commercial paper is setIt encloses；
According to each advertisement classification and the corresponding coefficient range interested of each advertisement classification, match satisfactory moreA user to be selected；
According to the corresponding each other coefficient interested of commercial paper of each user to be selected, calculated by cosine similarity formulaThe matching degree coefficient of each user to be selected and the user；And
By the matching degree coefficient of each user to be selected, the user at least partly to be selected in the multiple user to be selected is pushedInto the friend recommendation list in the instant messaging tools of the user.
To achieve the above object, the embodiment of the invention also provides a kind of data delivery systems based on micro- expression, specialSign is, comprising:
Acquisition module, for acquiring the plurality of pictures in preset range during the broadcasting for advertisement of spreading its tail；
Identification module passes through micro- expression for every picture to be input in preconfigured micro- table identification modelIdentification model obtains the corresponding micro- expression data of every picture；
Judgment module, for judging user to the level of interest of the advertisement of spreading its tail by micro- expression data；
Pushing module, for pushing strategy according to level of interest configuration data, the data-pushing strategy includes under configurationIt once spreads its tail and operates corresponding next advertisement of spreading its tail.
To achieve the above object, described the embodiment of the invention also provides a kind of data delivery system based on micro- expressionAcquisition module is also used to:
When detecting the control instruction of starting application, the advertisement for obtaining advertisement of spreading its tail is launched using inventory；
Judge whether the application launches in the advertisement using in inventory；
If whether the application is launching using in inventory, control pop-up within a preset time overhead show described in spread its tailAdvertisement；
The video for advertisement of spreading its tail described in user's viewing is acquired by picture collection device；And
Sub-frame processing is carried out to the video, obtains N picture.
To achieve the above object, the embodiment of the invention also provides a kind of computer equipment, the computer equipment includesMemory, processor and it is stored in the computer program that can be run on the memory and on the processor, feature existsIn realization is such as the step of the above-mentioned data push method based on micro- expression when the computer program is executed by processor.
To achieve the above object, the embodiment of the invention also provides a kind of computer readable storage mediums, which is characterized in thatComputer program is stored in the computer readable storage medium, the computer program can be held by least one processorRow, so that at least one described processor is executed such as the step of the above-mentioned data push method based on micro- expression.
Data push method based on micro- expression, system, computer equipment and computer provided in an embodiment of the present invention canStorage medium is read, judges that user to the acceptance level and favorable rating for advertisement of spreading its tail, is effectively promoted by analyzing the micro- expression of userData-pushing accuracy and pushing efficiency.That is, the embodiment of the present invention can spread its tail according to user preferences to user's intelligent recommendationAdvertisement brings good viewing and usage experience to user；Improve the specific aim and promotion effect of popularization.
Detailed description of the invention
Fig. 1 is the flow diagram of data push method of the embodiment of the present invention based on micro- expression.
Fig. 2 is the idiographic flow schematic diagram of step S100 in Fig. 1.
Fig. 3 is the idiographic flow schematic diagram of step S104 in Fig. 1.
Fig. 4 is the idiographic flow schematic diagram of step S106 in Fig. 1.
Fig. 5 is that the present invention is based on the program module schematic diagrames of the data delivery system embodiment two of micro- expression.
Fig. 6 is the hardware structural diagram of computer equipment embodiment three of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, rightThe present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, notFor limiting the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative workEvery other embodiment obtained is put, shall fall within the protection scope of the present invention.
It should be noted that the description for being related to " first ", " second " etc. in the present invention is used for description purposes only, and cannotIt is interpreted as its relative importance of indication or suggestion or implicitly indicates the quantity of indicated technical characteristic.Define as a result, " theOne ", the feature of " second " can explicitly or implicitly include at least one of the features.In addition, the skill between each embodimentArt scheme can be combined with each other, but must be based on can be realized by those of ordinary skill in the art, when technical solutionWill be understood that the combination of this technical solution is not present in conjunction with there is conflicting or cannot achieve when, also not the present invention claimsProtection scope within.
In following embodiment, exemplary description will be carried out by executing subject of computer equipment.
Embodiment one
Refering to fig. 1, the step flow chart of the data push method based on micro- expression of the embodiment of the present invention is shown.It can be withUnderstand, the flow chart in this method embodiment, which is not used in, is defined the sequence for executing step.It is with computer equipment 2 belowExecuting subject carries out exemplary description.It is specific as follows.
Step S100 acquires the plurality of pictures in preset range during the broadcasting for advertisement of spreading its tail.
Specifically, as shown in Fig. 2, the step S100 may further include:
Step S100a, when detecting the control instruction of starting application, the advertisement for obtaining advertisement of spreading its tail is launched using clearIt is single；
Step S100b, judges whether the application launches in the advertisement using in inventory；
Step S100c, if whether the application is launching using in inventory, overhead is aobvious within a preset time for control pop-upShow the advertisement of spreading its tail；
Step S100d acquires the video for advertisement of spreading its tail described in user's viewing by picture collection device；And
Illustratively, advertisement of spreading its tail is detected by picture collection device, when picture collection device acquisition testing arrivesWhen the advertisement of spreading its tail is opened, the picture collection device will start to acquire the video recording view that active user watches advertisement of spreading its tailFrequently.
Step S100e carries out sub-frame processing to the video, obtains N picture.
Specifically, face recognition operation is carried out to the N picture, to filter out the M picture containing face information, MFor the positive integer of≤N.
Illustratively, track human faces are needed when obtaining video, face location is focused, to guarantee to get clearlyFacial image.
Every picture is input in preconfigured micro- table identification model, passes through micro- Expression Recognition by step S102Model obtains the corresponding micro- expression data of every picture；
Specifically, the step S102 may further include:
Every picture in M picture is input to micro- Expression Recognition model according to sequencing to summarize, by describedMicro- Expression Recognition model exports the corresponding micro- expression data of every picture, and micro- expression data includes mood categorical data and feelingsThread level data；
Wherein, micro- Expression Recognition model is preparatory building and the convolutional neural networks model based on supervised learning.
Illustratively, micro- expression data library of corresponding micro- expression data for identification is pre-established, and by micro- expression numberClassify according to the micro- expression data in library；Pre-establish micro- expression model；Micro- expression picture in micro- expression data library is input toMicro- expression model is trained；Obtain micro- table identification feelings model.
Illustratively, facial expression is that the true psychological activity of people or mood project the expressed information out of face,For example, the smile of corners of the mouth tilting can be shown in happiness, the amplification of eye can be shown when surprised, can be showed when fearingFacial a series of nervous or discomfort out.These are all regular complex activity or the reaction of mood.Psychology is not present normalIn the case where confrontation, the duration of facial expression and performance degree can be captured relatively accurately and be understood.FaceThe fine motion variation (referred to as " micro- expression ") of expression is actually also the performance of true psychological activity or mood.
Illustratively, micro- expression data library of corresponding micro- expression data for identification is pre-established, and is classified to it:
Collect existing micro- expression data library picture；A certain amount of micro- expression picture is searched for from network；From existing micro-The micro- expression picture for intercepting a part of picture in the picture of expression data library and searching for from network is combined into micro- expression data library.
By micro- expression classification at six major class, including it is happy, surprised, fear, be sad, contempt and detesting, and by every class moodFive grades are divided into, all kinds of image feature vectors are extracted；Micro- expression picture in micro- expression data library is input to micro- tableFeelings model is trained.
Illustratively, micro- expression model training data and corresponding classification are obtained；Micro- expression model training dataThe characteristic of characteristic and advertisement of spreading its tail including micro- expression picture；
The weight of micro- expression model training data is determined according to the generation frequency of micro- expression model training data；
By micro- expression model training scanning machine device learning model, obtains and micro- expression picture and described openShield the corresponding level of interest prediction result of advertisement；
Training objective is determined according to the difference and the weight of the level of interest prediction result and the classification；
According to the direction for optimizing the training objective, adjusts the model parameter of the machine learning model and continues to train,Terminate to train when until meeting training stop condition.
The expressive features information is compared with micro- expression model is preset, and is determined according to comparing result described eachOpen the type and corresponding mood grade of micro- expression of micro- expression picture to be identified；All micro- expression figures to be identified of analytical calculationThe micro- expression type and corresponding mood grade of piece, the shared ratio in micro- expression of all micro- expression pictures to be identified,Micro- expression value is determined with this；Such as: micro- expression type is happy proportion in all micro- expression pictures to be identifiedLarger, then micro- expression is that happy micro- expression value is higher；Micro- expression type is to detest in all micro- expression pictures to be identifiedEvil proportion is larger, then micro- expression is that micro- expression value of detest is higher；Wherein mood grade is also inversely proportional with micro- expression value.
Step S104 judges user to the level of interest of the advertisement of spreading its tail by micro- expression data；
Specifically, as shown in figure 3, the step S104 may further include:
Step S104a distinguishes defined parameters vector according to micro- expression data of every picture, to obtain with sequencingMultiple parameters vector；
The multiple parameter vector is input in shot and long term memory network model, by described by step S104b in orderShot and long term memory network model exports coefficient interested, and the coefficient interested is the use obtained based on the M pictureLevel of interest of the family for the advertisement of spreading its tail.
Specifically, the step of micro- expression data for calculating institute user, is as follows:
According to the output h of last momentt-1With current input xtTo obtain ftValue, with decide whether last moment is allowed to acquireInformation Ct-1By or part pass through:
ft=σ (Wf[xt,ht-1]+bf), wherein ft∈ [0,1] indicates choosing of the node of t moment to t-1 moment cell memorySelect weight, WfFor the weight matrix for forgeing door, bfFor the bias term for forgeing door, ht-1Indicate the hidden layer status information of t-1 node, it is non-Linear function σ (x)=1/ (1+e-x)；
It determines which value is used to update by sigmoid, and is used to generate new candidate value q by tanh layerst, it makeesThe candidate value generated for current layer may be added in memory unit state, the value that this two parts generates in conjunction with carrying out moreIt is new:
it=σ (Wi[xt,ht-1]+bi), wherein it∈ [0,1] indicates right to choose of the node to current node information of t momentWeight, biFor the bias term of input gate, WiFor the weight matrix of input gate, nonlinear function σ (x)=1/ (1+e-x)；
Present node inputs information qt=tanh (Wq[ht-1,xt]+bq), wherein bqFor bias term, WqIndicate information to be updatedWeight matrix, tanh be tanh activation primitive, xtIndicate the input vector of t moment LSTM neural network node, ht-1TableShow the hidden layer status information of t-1 node；
Old memory unit state is updated, new information is added:
Current output recall info Ct=ft*Ct-1+it*qt), wherein qtIndicate the recall info of t-1 node, ftWhen indicating tSelection weight of the node at quarter to t-1 moment cell memory, itIndicate right to choose of the node to current node information of t momentWeight；
The output of LSTM model；
ot=σ (Wo[xt,ht-1]+bo), wherein ot ∈ [0,1] indicates the right to choose of the node cell memory information of t momentWeight, boFor the biasing of out gate, WoFor the weight matrix of out gate,Indicate vector xtAnd ht-1It is spliced toAmount, i.e., | xt|+ht-1| the vector of dimension.
ht=ot·tanh(Ct)
xtIndicate the input data of t moment LSTM neural network node, the i.e. feature vector of picture in the present embodiment, htMicro- expression value of the advertisement of spreading its tail is corresponded to for the user of t moment LSTM neural network node output.
Illustratively, each classification in mood classification is classified, obtains the mood grade of each mood, the feelingsThread grade can be divided into five grades, the micro- expression type and corresponding mood of all micro- expression pictures to be identified of analytical calculationGrade, in micro- expression of all micro- expression pictures to be identified shared ratio determine micro- expression value with this.
Step S106 pushes strategy according to level of interest configuration data, and the data-pushing strategy includes configuring next timeIt spreads its tail and operates corresponding next advertisement of spreading its tail.
Specifically, the data-pushing strategy includes configuration good friend's matched data；
As shown in figure 4, described push strategy according to level of interest configuration data, further includes:
Step S106a, according to the user for the institute in the coefficient and historical record interested of the advertisement of spreading its tailOther multiple coefficients interested that user is directed to other multiple advertisements of spreading its tail are stated, calculate the user to the other sense of each commercial paperInterest coefficient；
It is emerging that the other sense of each commercial paper is arranged centered on the other coefficient interested of each commercial paper in step S106bInteresting coefficient range；
Step S106c, according to each advertisement classification and the corresponding coefficient range interested of each advertisement classification, matching symbolClose desired multiple users to be selected；
Step S106d, it is similar by cosine according to the corresponding each other coefficient interested of commercial paper of each user to be selectedDegree formula calculates the matching degree coefficient of each user to be selected and the user；And
Step S106e, by the matching degree coefficient of each user to be selected, by the multiple user to be selected at least partly toFamily is selected to be pushed in the friend recommendation list in the instant messaging tools of the user.
Illustratively, an advertisement base of spreading its tail is established locally default, and the advertisement of spreading its tail in advertisement base of spreading its tail is carried outClassification；According to user to the level of interest for advertisement of spreading its tail, the advertisement of user's intelligent recommendation is given.Such as: user spreads its tail to cuisines classThe level of interest of advertisement is higher, then next time just pushes the advertisement of spreading its tail of cuisines class again, if to the interest of such advertisement of spreading its tailDegree is lower, then will push other kinds of advertisement of spreading its tail, for example, music class concert advertisement of spreading its tail；Wherein, described to openAdvertisement of spreading its tail in screen advertisement base can automatically update.
Illustratively, the spread its tail level of interest of advertisement of user's viewing is analyzed, judge user to any class or whichThe advertisement of spreading its tail of class is more interested, and the advertisement of spreading its tail of every class is ranked up according to Interest Measure to user, will have phaseUser with interest sorts out and carries out friend recommendation；Such as first three series advertisements that the user is most interested in are cuisines class >Music class > film class, if first three series advertisements for having other users most interested are also cuisines class > music class > film class,Such user can be carried out friend recommendation to the user, wherein for the advertisement that user is most interested in be also possible to three classes withOn.
Embodiment two
Fig. 5 is that the present invention is based on the program module schematic diagrames of the data delivery system embodiment two of micro- expression.Data-pushingSystem 20 may include or be divided into one or more program modules, one or more program module is stored in storage and is situated betweenIn matter, and as performed by one or more processors, to complete the present invention, and the above-mentioned data-pushing based on micro- expression can be realizedMethod.The so-called program module of the embodiment of the present invention is the series of computation machine program instruction section for referring to complete specific function,Implementation procedure than program itself more suitable for data delivery system 20 of the description based on micro- expression in storage medium.It retouches belowThe function of each program module of the present embodiment will specifically be introduced by stating:
Acquisition module 200, is used for: during the broadcasting for advertisement of spreading its tail, acquiring the plurality of pictures in preset range.It is exemplary, the acquisition module 200 is also used to: when detecting the control instruction of starting application, the advertisement for obtaining advertisement of spreading its tail is launchedUsing inventory；Judge whether the application launches in the advertisement using in inventory；If whether the application is launching applicationIn inventory, control pop-up within a preset time overhead show described in spread its tail advertisement；User's viewing is acquired by picture collection deviceThe video of the advertisement of spreading its tail；And sub-frame processing is carried out to the video, obtain N picture.
Identification module 202, is used for: every picture being input in preconfigured micro- table identification model, by described micro-Expression Recognition model obtains the corresponding micro- expression data of every picture.Illustratively, the identification module 202, is also used to: describedEvery picture is input in preconfigured micro- table identification model, every picture pair is obtained by micro- Expression Recognition modelThe micro- expression data answered, comprising: every picture in M picture is input in micro- Expression Recognition model according to sequencing,To export the corresponding micro- expression data of every picture by micro- Expression Recognition model, micro- expression data includes mood classOther data and mood level data；Wherein, micro- Expression Recognition model is building in advance and the convolution mind based on supervised learningThrough network model.
Judgment module 204, is used for: judging user to the level of interest of the advertisement of spreading its tail by micro- expression data.ExampleProperty, judgment module 204 is also used to: described to judge user to the level of interest of the advertisement of spreading its tail, packet by micro- expression dataIt includes: defined parameters vector being distinguished according to micro- expression data of every picture, to obtain the multiple parameters vector with sequencing；The multiple parameter vector is input in order in shot and long term memory network model, the shot and long term memory network model is passed throughCoefficient interested is exported, the coefficient interested is that the user obtained based on the M picture is directed to the advertisement of spreading its tailLevel of interest.
Pushing module 206, is used for: pushing strategy according to level of interest configuration data, the data-pushing strategy includes matchingIt sets to spread its tail next time and operates corresponding next advertisement of spreading its tail.
Illustratively, the pushing module 206, is also used to configure good friend's matched data: according to the user for describedOther the multiple senses of the user spread its tail in the coefficient and historical record interested of advertisement for other multiple advertisements of spreading its tailInterest coefficient calculates user coefficient interested other to each commercial paper；It is with the other coefficient interested of each commercial paperEach other coefficient range interested of commercial paper is arranged in center；According to each advertisement classification and each advertisement classification pairThe coefficient range interested answered matches satisfactory multiple users to be selected；According to the corresponding each advertisement of each user to be selectedThe coefficient interested of classification calculates the matching degree coefficient of each user to be selected and the user by cosine similarity formula；AndBy the matching degree coefficient of each user to be selected, the user at least partly to be selected in the multiple user to be selected is pushed to the useIn friend recommendation list in the instant messaging tools at family.
Embodiment three
It is the hardware structure schematic diagram of the computer equipment of the embodiment of the present invention three refering to Fig. 6.It is described in the present embodimentComputer equipment 2 is that one kind can be automatic to carry out numerical value calculating and/or information processing according to the instruction for being previously set or storingEquipment.The computer equipment 2 can be rack-mount server, blade server, tower server or Cabinet-type server(including server cluster composed by independent server or multiple servers) etc..As shown in fig. 6, the computer is setStandby 2 include at least, but are not limited to, can be in communication with each other by system bus connection memory 21, processor 22, network interface 23,And data delivery system 20.
In the present embodiment, memory 21 includes at least a type of computer readable storage medium, the readable storageMedium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory etc.), random access storage device(RAM), static random-access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory(EEPROM), programmable read only memory (PROM), magnetic storage, disk, CD etc..In some embodiments, memory21 can be the internal storage unit of computer equipment 2, such as the hard disk or memory of the computer equipment 2.In other implementationsIn example, memory 21 is also possible to the grafting being equipped on the External memory equipment of computer equipment 2, such as the computer equipment 2Formula hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card(Flash Card) etc..Certainly, memory 21 can also both including computer equipment 2 internal storage unit and also including outside itStore equipment.In the present embodiment, memory 21 is installed on the operating system and types of applications of computer equipment 2 commonly used in storageSoftware, for example, embodiment two the data delivery system 20 based on micro- expression program code etc..In addition, memory 21 can be withFor temporarily storing the Various types of data that has exported or will export.
Processor 22 can be in some embodiments central processing unit (Central Processing Unit, CPU),Controller, microcontroller, microprocessor or other data processing chips.The processor 22 is commonly used in control computer equipment 2Overall operation.In the present embodiment, program code or processing data of the processor 22 for being stored in run memory 21, exampleAs run the data delivery system 20 based on micro- expression, to realize the data push method based on micro- expression of embodiment one.
The network interface 23 may include radio network interface or wired network interface, which is commonly used inCommunication connection is established between the computer equipment 2 and other electronic devices.For example, the network interface 23 is for passing through networkThe computer equipment 2 is connected with exterior terminal, establishes data transmission between the computer equipment 2 and exterior terminalChannel and communication connection etc..The network can be intranet (Intranet), internet (Internet), whole world movementCommunication system (Global System of Mobile communication, GSM), wideband code division multiple access (WidebandCode Division Multiple Access, WCDMA), 4G network, 5G network, bluetooth (Bluetooth), the nothings such as Wi-FiLine or cable network.
It should be pointed out that Fig. 6 illustrates only the computer equipment 2 with component 20-23, it should be understood that simultaneouslyAll components shown realistic are not applied, the implementation that can be substituted is more or less component.
In the present embodiment, the data delivery system 20 based on micro- expression being stored in memory 21 can also be dividedFor one or more program module, one or more of program modules are stored in memory 21, and by one orMultiple processors (the present embodiment is processor 22) are performed, to complete the present invention.
For example, Fig. 5 shows the program of the data delivery system of the realization based on micro- expression of the embodiment of the present invention twoModule diagram, in the embodiment, the data delivery system 20 based on micro- expression can be divided into acquisition module 200,Identification module 202, judgment module 204 and pushing module 206.Wherein, the so-called program module of the present invention is to refer to complete spyThe series of computation machine program instruction section for determining function exists than program more suitable for describing the data-pushing 20 based on micro- expressionImplementation procedure in the computer equipment 2.The concrete function of described program module 200-206 has detailed in example 2Description, details are not described herein.
Example IV
The present embodiment also provides a kind of computer readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory(for example, SD or DX memory etc.), random access storage device (RAM), static random-access memory (SRAM), read-only memory(ROM), electrically erasable programmable read-only memory (EEPROM), programmable read only memory (PROM), magnetic storage, magneticDisk, CD, server, App are stored thereon with computer program, phase are realized when program is executed by processor using store etc.Answer function.The computer readable storage medium of the present embodiment is used for the data delivery system 20 based on micro- expression, is held by processorThe data push method based on micro- expression of embodiment one is realized when row.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment sideMethod can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many casesThe former is more preferably embodiment.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hairEquivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skillsArt field, is included within the scope of the present invention.