CN110263126A - A kind of generation method and mobile terminal of user's portrait - Google Patents
A kind of generation method and mobile terminal of user's portrait Download PDFInfo
- Publication number
- CN110263126A CN110263126A CN201910538233.XA CN201910538233A CN110263126A CN 110263126 A CN110263126 A CN 110263126A CN 201910538233 A CN201910538233 A CN 201910538233A CN 110263126 A CN110263126 A CN 110263126A
- Authority
- CN
- China
- Prior art keywords
- user
- portrait
- target user
- similar users
- target
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the present invention proposes the generation method and mobile terminal of a kind of user's portrait.The described method includes: the data based on target user's input, generate the input habit data of the target user；The comparison result of the input habit data of input habit data and candidate user based on the target user determines the similar users of the target user from the candidate user；User's portrait based on the similar users generates user's portrait of the target user.The embodiment of the present invention reduces the calculation amount for generating user's portrait of target user, and is the user's portrait for producing target user independent of the panoramic view data of target user.
Description
Technical field
The present embodiments relate to data analysis technique fields more particularly to a kind of user to draw a portrait (User Profile)
Generation method and mobile terminal.
Background technique
User's portrait is widely used in each field.As the virtual representations of actual user, user's portrait is initial
It is applied in electric business field.Under big data era background, user information is full of in a network.The specifying information of user is taken out
As user image being embodied as user using these labels and is drawn a portrait, can provide for user and targetedly service at label.
In China Patent Publication No. CN106874266A, a kind of method and apparatus of generation user portrait are disclosed.?
During the disclosure discloses, the panoramic view data of user to be drawn a portrait is obtained, according to the tag library of the panoramic view data of user to be drawn a portrait and building
Various dimensions description is carried out to user to be drawn a portrait, to keep user's portrait result more accurate.
However, this mode for directly generating user's portrait based on user's panoramic view data leads to significant calculation amount.Moreover,
It is many times difficult to obtain the panoramic view data (for example, user is not logged on terminal account number) of user, leads to not generate user's picture
Picture.
Summary of the invention
In view of this, embodiment of the present invention proposes the generation methods and mobile terminal of a kind of user portrait, to reduce
Generate the calculation amount of user's portrait.
The technical solution of embodiment of the present invention is as follows:
One side according to an embodiment of the present invention proposes a kind of generation method of user's portrait, is applied to mobile terminal, packet
It includes:
Based on the data of target user's input, the input habit data of the target user are generated；
The comparison result of the input habit data of input habit data and candidate user based on the target user, from institute
State the similar users that the target user is determined in candidate user；
User's portrait based on the similar users generates user's portrait of the target user.
According to another aspect of an embodiment of the present invention, a kind of mobile terminal is proposed, comprising:
Input habit generation module, the data for being inputted based on target user, the input for generating the target user are practised
Used data；
Similar users determining module, the input for input habit data and candidate user based on the target user are practised
The comparison result of used data, determines the similar users of the target user from the candidate user；
User's portrait generation module generates the use of the target user for user's portrait based on the similar users
Family portrait.
According to another aspect of an embodiment of the present invention, it proposes a kind of mobile terminal, including processor, memory and is stored in
On the memory and the computer program that can run on the processor, the computer program are executed by the processor
The step of Shi Shixian generation method that as above described in any item users draw a portrait.
According to another aspect of an embodiment of the present invention, a kind of computer readable storage medium is proposed, it is described computer-readable
Computer program is stored on storage medium, and as above described in any item users are realized when the computer program is executed by processor
The step of generation method of portrait.
In embodiments of the present invention, it is contemplated that input habit is able to reflect age, region, hobby of user etc. important
People's feature determines the similar users for having similar input habit with target user, then uses for reference user's portrait life of similar users
It draws a portrait at the user of target user, the panoramic view data for being not necessarily based on target user directly generates user's portrait of target user, from
And the calculation amount for generating user's portrait of target user is significantly reduced, and the panoramic view data independent of target user
Generate user's portrait.
Detailed description of the invention
Fig. 1 is the flow chart for the generation method drawn a portrait according to user of the embodiment of the present invention.
It is the first exemplary flow for being not logged in user's generation user's portrait of terminal account number that Fig. 2, which is according to the embodiment of the present invention,
Cheng Tu.
It is the second exemplary flow for being not logged in user's generation user's portrait of terminal account number that Fig. 3, which is according to the embodiment of the present invention,
Cheng Tu.
Fig. 4 is the schematic diagram that similar users are determined according to the embodiment of the present invention.
Fig. 5 is the structure chart according to mobile terminal of the embodiment of the present invention.
Fig. 6 is the structure chart according to the mobile terminal of the embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, the present invention is made with reference to the accompanying drawing further
Detailed description.
It is succinct and intuitive in order to what is described, hereafter by describing several representative embodiments come to the solution of the present invention
It is illustrated.A large amount of details is only used for helping to understand the solution of the present invention in embodiment.However, it will be apparent that technology of the invention
Scheme can be not limited to these details when realizing.In order to avoid unnecessarily having obscured the solution of the present invention, some embodiments
It is not described meticulously, but only gives frame.Hereinafter, " comprising " refers to " including but not limited to ", " root
According to ... " refer to " according at least to ..., but be not limited to according only to ... ".Due to the speech habits of Chinese, hereinafter without spy
When not pointing out the quantity of an ingredient, it is meant that the ingredient is either one or more, or can be regarded as at least one.
It is found by the applicant that: the mode for directly generating user's portrait based on user's panoramic view data in the prior art has calculation amount
Big disadvantage.In particular, directly generating user's portrait based on user's panoramic view data in the limited mobile terminal of computing resource
The shortcomings that mode, is especially prominent.
Moreover, applicant have also found that a lot of reasons may cause the panoramic view data that can not obtain user (for example, user does not have
Have registration terminal account number or the permission, etc. without acquisition user data), user's portrait can not be generated at this time.
To overcome above-mentioned technical problem, applicant, which breaks through, directly generates user's picture based on user's panoramic view data in the prior art
The thinking set of picture does not directly generate user using user's panoramic view data and draws a portrait.On the contrary, applicant considers input habit energy
Enough reflect the important personal characteristics such as age, region, the hobby of user, it is first determined go out and use with the target for needing to generate user's portrait
Family has the similar users of similar input habit, then uses for reference user's portrait of the user portrait generation target user of similar users,
Calculation amount can be significantly reduced, and be the user's portrait for producing target user independent of the panoramic view data of target user.
Fig. 1 is the flow chart that the method for user's portrait is generated according to the embodiment of the present invention, and this method is suitable for mobile terminal.
As shown in Figure 1, this method comprises:
Step 101: the data based on target user's input generate the input habit data of target user.
Herein, target user is the user for needing to generate user's portrait.The data of target user's input are target user
Input data in using terminal device procedures, for example the input number during mobile terminal input method is used for target user
According to or target user use mobile terminal when with the data, etc. of voice mode input.
Preferably, the input method that mobile terminal input method can be included for the operating system of mobile terminal can also be the
The input method of tripartite's exploitation.For example, input method may include: all-phonetic input method, double-spelling Chinese character input method, Microsoft's spelling input method, intelligence
Energy ABC input method, Zheng's code inputting method, interior code inputting method, configuration code input method, five-stroke input method, Cangjie's input method, natural code are defeated
Enter method, purple light input method, stroke input method, etc..
The data of target user's input can be the data in predetermined amount of time, for example, within a week, three months it
Data in interior or use mobile terminal All Time.
In one embodiment, the data based on target user's input in step 101, the input for generating target user are practised
Used data, comprising:
Determine the vector model comprising M dimension；
The statistical data for corresponding to each dimension is extracted from the data that the target user inputs；
By the statistical data difference assignment of each dimension into the vector model, wherein M is just whole more than or equal to 1
Number.M dimensional vector model after above-mentioned assignment, the as vector of the input habit data of characterization target user.
Preferably, the dimension of vector model includes at least one of following: high frequency vocabulary and frequency of use；Emoticon
Classification and frequency of use；Adjectival classification and frequency of use；The classification and frequency of use of Chinese idiom or poem；Specialized vocabulary
Classification and frequency of use, etc..
The above demonstration describes the data of target user's input and generates the typical case of the input habit data of target user
Example is not intended to limit the present invention embodiment it will be appreciated by those of skill in the art that this description is only exemplary
Protection scope.
Citing can establish the defeated of target user according to the data that target user inputs by five dimensions shown in table 1
Enter to be accustomed to data.
Table 1
Specifically, the process for generating the input habit data of target user includes:
Firstly, determining the vector model comprising 5 dimensions shown in table 1.
Then, the statistical data for corresponding to five dimensions shown in table 1 is extracted from the data that target user inputs, comprising:
It extracts about the statistical data of high frequency vocabulary and frequency of use from the data that target user inputs (for example, which is determined
Vocabulary is the frequency of use of high frequency vocabulary and high frequency vocabulary), about the classification of emoticon and the statistical data of frequency of use
(for example, emoticon relevant to weather, emoticon relevant with mood, emoticon relevant with animals and plants and each
Classify emoticon frequency of use), about it is adjectival classification and frequency of use statistical data (for example, related to appearance
Adjective, adjective relevant to mood and adjectival frequency of use of respectively classifying), about Chinese idiom or poem classification and
The statistical data of frequency of use is (for example, the classification of four word Chinese idioms, the classification of five word Chinese idioms, Tang poetry classification, such poems of the Song Dynasty classification and each classification
The frequency of use of Chinese idiom or poem), about the classification of specialized vocabulary and the statistical data of frequency of use (for example, medical vocabulary point
The frequency of use of class, compuword classification and each classification specialized vocabulary).
Then, the statistical data difference assignment of each dimension is practised into vector model with generating the input of target user
Used data.
It is above-mentioned using five dimensions as example, describe generate target user input habit data typical case, ability
Field technique personnel are it is to be appreciated that dimension number and dimension content in vector model can change, and this change is all
The protection scope of embodiment of the present invention is not departed from.
Step 102: the comparison result of the input habit data of input habit data and candidate user based on target user,
The similar users of target user are determined from candidate user.
Preferably, candidate user is the user that there is user to draw a portrait.In a step 102, by by target user's
Input habit data are compared with the input habit data of candidate user, determine have from candidate user with target user
The similar users of similar input habit.
In one embodiment, step 102 specifically includes: calculating separately the M dimensional vector and target of each candidate user
Vector distance between the M dimensional vector of user；It sorts to vector distance；Ranking results based on vector distance, from candidate user
The similar users of middle determining target user.Wherein, the M dimensional vector of target user is that target generated in characterization step 101 is used
The vector of the input habit data at family；The input habit data of the M dimensional vector characterization candidate user of candidate user.Candidate user
The generating mode of M dimensional vector is similar to the generating mode of the M dimensional vector of target user, specifically includes: inputting from candidate user
The statistical data for corresponding to each dimension in M dimensional vector model is extracted in data；The statistical data of each dimension is distinguished into assignment
Into M dimensional vector model.
Vector distance between the M dimensional vector of candidate user and the M dimensional vector of target user, can be used to indicate that or generate
The similarity of the input habit of the input habit and target user of candidate user.Vector distance is shorter, shows the defeated of candidate user
The input habit for entering habit and target user is closer, then similarity is higher；Vector distance is longer, shows the input of candidate user
It is accustomed to more becoming estranged with the input habit of target user, then similarity is lower.
Wherein it is possible to using Euclidean distance algorithm, manhatton distance algorithm, mahalanobis distance algorithm or bright Koffsky distance
The vector-distances such as algorithm determine the vector distance between the M dimensional vector of candidate user and the M dimensional vector of target user.
Preferably, the multiple vector distances being calculated can be ranked up, the ranking results based on vector distance, from
The similar users of target user are determined in candidate user, comprising: arrange vector distance according to sequence from small to large, take front N
The corresponding N number of candidate user of a vector distance is N number of similar users of target user, and wherein N is the positive integer more than or equal to 1.
When N is 1, the numbers of similar users is 1, the M dimensional vector of the M dimensional vectors of the similar users and target user it
Between vector distance be shortest 1 in whole similar users, the input habit of the similar users and the input of target user are practised
It is used that there is highest similarity.
When N is the positive integer more than or equal to 2, the number of similar users is multiple (N number of), the M dimension of this N number of similar users
Vector distance between vector and the M dimensional vector of target user, for the shorter top n of vector distance in whole similar users.This N
The similarity of the input habit of the input habit and target user of a similar users, it is higher for similarity in whole similar users
Top n.
In the above-described embodiment, the ranking results of vector distance are directly based upon, mesh is determined from whole candidate users
Mark the similar users of user.Alternatively it is also possible to execute cluster for target user and candidate user, further according to cluster result from
In candidate user in the cluster of target user, the similar users of target user are determined based on the ranking results of vector distance.
In one embodiment, it is specifically included in step 102: target user and candidate user is clustered；It calculates separately
Vector distance between the M dimensional vector of each candidate user in the corresponding cluster of target user and the M dimensional vector of target user；It is right
Vector distance sequence；Ranking results based on vector distance determine target from the candidate user in the corresponding cluster of target user
The similar users of user.Wherein, the clustering algorithm that embodiment of the present invention can use includes but is not limited to: based on division
Clustering algorithm, based on hierarchical clustering algorithm, based on the density clustering algorithm, clustering algorithm based on grid, neural network based
Clustering algorithm or based on statistical clustering algorithm, etc..Preferably, the clustering algorithm of embodiment of the present invention use includes:
K-means algorithm, k-modes algorithm, k-prototypes algorithm or k-medoid algorithm, etc..Dimension employed in cluster
Degree can be the combination for generating any dimension or at least two dimensions in vector model employed in input habit data.
Similarly, based on the ranking results of vector distance, mesh is determined from the candidate user in the corresponding cluster of target user
Mark the similar users of user, comprising: arrange vector distance according to sequence from small to large, take the corresponding N of the N number of vector distance in front
A candidate user is N number of similar users of target user, and wherein N is the positive integer more than or equal to 1.
Similar, when N is 1, the number of similar users is 1, the M dimensional vector of the similar users and the M of target user
Vector distance between dimensional vector is shortest 1 in each similar users in the corresponding cluster of target user.The similar users
The input habit of input habit and target user has highest similarity in the cluster of target user in each similar users.
Similar, when N is the positive integer more than or equal to 2, the number of similar users is multiple (N number of), this N number of similar use
Vector distance between the M dimensional vector at family and the M dimensional vector of target user is each similar users in the corresponding cluster of target user
The shorter top n of middle vector distance.The similarity of the input habit of the input habit and target user of this N number of similar users is
The higher top n of similarity in each similar users in the corresponding cluster of target user.
In the above-described embodiment, it is clustered for target user and candidate user, determines that target is used further according to cluster result
The similar users at family can accelerate the speed for determining similar users.
Step 103: user's portrait based on similar users generates user's portrait of target user.
Herein, the user for using for reference similar users, which draws a portrait, generates user's portrait of target user, so that calculation amount is reduced, and
And it draws a portrait independent of the user that the panoramic view data of target user is producible target user.
In one embodiment, when N is 1, i.e., the number for the similar users determined in step 102 is 1.This
When, step 103 includes: that the user of the similar users draws a portrait, and is determined as user's portrait of target user.
As it can be seen that by the way that user's portrait of the highest similar users of input habit similarity is determined directly as target user's
User's portrait further reduced the calculation amount for generating user's portrait of target user.
In one embodiment, when N is positive integer more than or equal to 2, i.e., the similar users determined in step 102
Number be it is multiple (N number of).At this point, step 103 includes: to calculate the weighted results of user's portrait of N number of similar users, will weight
As a result it is determined as user's portrait of target user.
As it can be seen that the user based on multiple similar users draws a portrait, weighting generates user's portrait of target user, the weighting of generation
As a result the tag attributes that multiple similar users can be integrated keep user's portrait result of target user more accurate.
Preferably, weighted results are determined as target user's by the weighted results for calculating user's portrait of N number of similar users
The detailed process of user's portrait comprises determining that the weight of each user's portrait in user's portrait of N number of similar users, wherein each
Weight and user of user's portrait draw a portrait the similar of the input habit of corresponding similar users and the input habit of target user
It spends directly proportional；Based on the respective weight of N number of user portrait, the weighted results of N number of user portrait of N number of user are calculated.Wherein: waiting
The similarity of the input habit at family and the input habit of target user is selected, can be used by the M dimensional vector and target of candidate user
Vector distance between the M dimensional vector at family is indicated or is generated, and wherein vector distance is smaller, and similarity is higher；Vector distance is bigger,
Similarity is lower.
Specifically, the process for calculating the weighted results of each user portrait of N number of similar users includes: firstly, determining each
Label value with same label attribute in a user's portrait, then to the mark with same label attribute in each user portrait
Label value executes weighted calculation, using the label value of the tag attributes in user's portrait as target user.
Citing, it is assumed that target user has 10 similar users, respectively U1~U10.The input habit and mesh of similar users
Similarity and the respective weight for marking the input habit of user are as shown in table 2.
| User name | Similarity | Weight |
| U1 | 0.3 | 3/20 |
| U2 | 0.3 | 3/20 |
| U3 | 0.3 | 3/20 |
| U4 | 0.2 | 2/20 |
| U5 | 0.2 | 2/20 |
| U6 | 0.2 | 2/20 |
| U7 | 0.2 | 2/20 |
| U8 | 0.1 | 1/20 |
| U9 | 0.1 | 1/20 |
| U10 | 0.1 | 1/20 |
Table 2
As it can be seen that the phase of the weight of each similar users and the input habit of the similar users and the input habit of target user
It is directly proportional like spending.
It is assumed that the football in user's portrait that the football interest tags value in user's portrait of user U1 is 15, user U2 is emerging
Interesting label value is 15, the football interest tags value in the user of user U3 portrait is 15, the football in the user of user U4 portrait
Interest tags value is 20, the football interest tags value in the user of user U5 portrait is 20, the foot in the user of user U6 portrait
Ball interest tags value is 20, the football interest tags value in the user of user U7 portrait is 20, in the user of user U8 portrait
Football interest tags value is 30, the football interest tags value in the user of user U9 portrait is 30, in user's portrait of user 10
Football interest tags value be 30, be based on weighting algorithm, calculate target user user portrait in football interest tags value A,
Wherein:
A=15 × 3/20+15 × 3/20+15 × 3/20+20 × 2/20+20 × 2/20+20 × 2/20+20 × 2/20+30
× 1/20+30 × 1/20+30 × 1/20=19.25.
Similarly, other label values of target user can be calculated.Whole label values of target user are taken together,
Constitute user's portrait of target user.
After generating user's portrait of target user, it can be drawn a portrait based on the user and send recommendation to target user,
And user's portrait of the feedback adjustment target user based on target user.
The user of the highest similar users of input habit similarity can be drawn a portrait and is determined directly as by embodiment of the present invention
The user of target user draws a portrait, and further reduced the calculation amount for generating user's portrait of target user.
Moreover, embodiment of the present invention can be drawn a portrait based on the user of multiple similar users, weighting generates the use of target user
Family portrait, the weighted results of generation can integrate the tag attributes of multiple similar users, make user's portrait result of target user
It is more accurate.
In one embodiment, user's portrait based on target user, sends recommendation to target user；Based on mesh
The feedback message that user is directed to recommendation is marked, user's portrait of target user is adjusted.
For example, the user based on target user draws a portrait, it is found that the football interest tags value of target user is higher (for example, big
In predetermined threshold), then recommendation relevant to football is sent to target user.Then, based on target user for recommendation
The feedback message of content adjusts user's portrait of target user.For example, if it find that target user couple recommendation relevant to football
Content is lost interest in, then reduces football interest tags value；If it find that target user takes in good part in recommendation relevant to football
Hold, then can maintain or be promoted the football interest tags value.
Therefore, embodiment of the present invention is also based on target user feedback adjustment user portrait, may be implemented more precisely
Recommendation.
Embodiment of the present invention can be applied in the application environment of various generation user portraits.
It is being moved eventually for example, current manufacturer terminal can distinguish user according to manufacturer's account and integrate user under the account
Use preference in the multiple and different applications of end system, mobile terminal to establish complete user's portrait for user, and then realizes system
Irrespective of size, the intelligent recommendation across application, striding equipment.However, there are still a large amount of users at present, in the process using mobile terminal
In, manufacturer's account will not be logged in always.Therefore, it based on the processing mode of the prior art, can not be established for this kind of user complete
User's portrait, also can not carry out intelligent recommendation to it.
Using embodiment of the present invention, user's portrait can be generated for this kind of user for being not logged in terminal account number.
It is the first exemplary flow for being not logged in user's generation user's portrait of terminal account number that Fig. 2, which is according to the embodiment of the present invention,
Cheng Tu.
As shown in Fig. 2, this method comprises:
Step 201: acquisition is not logged in the data that account user N1 is inputted during using terminal.
Specifically, acquisition is not logged in the data that account user N1 is inputted during using terminal input method.
Step 202: the data based on the input for being not logged in account user N1 generate the input habit for being not logged in account user N1
Used data.
Specifically, M dimensional vector model is established, corresponds to each dimension from being not logged in extract in the data that account user N1 is inputted
The statistical data of degree obtains being not logged in account user N1 by the statistical data difference assignment of each dimension into M dimensional vector model
M dimensional vector, be as not logged in the input habit data of account user N1.
Step 203: the similarity of determination and the input habit for being not logged in account user N1 is highest to have logged in account user
M。
Specifically, it is first determined comprising multiple user's set for having logged in account user, then, obtain every in user's set
Vector distance between a M dimensional vector for having logged in account user and the M dimensional vector for being not logged in account user N1.To vector distance
Sequence, and the smallest account user M that logged in of vector distance is determined as phase with the input habit for being not logged in account user N1
Highest account user has been logged in like spending.
Step 204: the user for having logged in account user M being drawn a portrait, is determined as being not logged in user's portrait of account user N1.
Step 205: being drawn a portrait based on the user for being not logged in account user N1, sent in recommendation to account user N1 is not logged in
Hold.
Step 206: based on from the received feedback information of account user N1 is not logged in, adjustment is not logged in the use of account user N1
Family portrait.
In process shown in Fig. 2, by the input habit of user, rapidly association is not logged in account user and has logged in account
Number user can be to be not logged in account user N1 to generate user's portrait, and send corresponding recommendation.
Moreover, the number for being not logged in the similar users of account user N1 is one and (has logged in process shown in Fig. 2
Account user M), directly the user that the user for having logged in account user M portrait is determined as being not logged in account user N1 is drawn a portrait, it can
The calculation amount for being not logged in account user N1 is generated to reduce.
In addition, in process shown in Fig. 2, it can be according to account user N1 be not logged in the feedback of recommendation, dynamic is adjusted
The whole user's portrait for being not logged in account user N1.
It is the second exemplary flow for being not logged in user's generation user's portrait of terminal account number that Fig. 3, which is according to the embodiment of the present invention,
Cheng Tu.
As shown in figure 3, this method comprises:
Step 301: acquisition is not logged in the data that account user N1 is inputted during using terminal.
Specifically, acquisition is not logged in the data that account user N1 is inputted during using terminal input method.
Step 302: the data based on the input for being not logged in account user N1 generate the input habit for being not logged in account user N1
Used data.
Specifically, M dimensional vector model is established, corresponds to each dimension from being not logged in extract in the data that account user N1 is inputted
The statistical data of degree obtains being not logged in account user N1 by the statistical data difference assignment of each dimension into M dimensional vector model
M dimensional vector, as characterization be not logged in account user N1 input habit data vector.
Step 303: determining and logged in account number with similarity highest 10 of the input habit for being not logged in account user N1
User U1, U2...U10.
Specifically, it is determined that including multiple user's set for having logged in account user；Account number will be not logged in using clustering algorithm
Whole in user N1 and user's set has logged in account user cluster；It obtains and is not logged in the cluster of account user N1 respectively
Vector distance between the M dimensional vector of login account user and the M dimensional vector for being not logged in account user N1；Vector distance is arranged
Sequence；According to the sequence of vector distance from small to large, determine that first 10 have logged in account user U1, U2...U10 (as and not
Similarity higher 10 for logging in the input habit of account user N1 have logged in account number), and logged in account number for this 10 and used
Family U1, U2...U10 are determined as being not logged in the similar users of account user N1.Fig. 4 is to determine similar use according to the embodiment of the present invention
The schematic diagram at family.Referring to fig. 4, using two dimensions, 10 similar use for being not logged in account user N1 are determined in a manner of cluster
Family has logged in account user U1, U2...U10.For example, dimension 1 can converge for high frequency words and frequency of use；Dimension 2 is profession
The classification and frequency of use of vocabulary.
Step 304: the user that the user for having logged in account user U1, U2...U10 portrait is generated according to Similarity-Weighted
Portrait is determined as being not logged in user's portrait of account user N1.
Specifically, it is first determined the weight for having logged in each user's portrait in account user U1, U2...U10, wherein each
Weight and the user of user's portrait draw a portrait corresponding user input habit and be not logged in the input habit of account user N1
Similarity is directly proportional；The weighted results that respective weight calculation goes out this 10 users portrait are then based on, weighted results are determined as
It is not logged in user's portrait of account user N1.
Step 305: being drawn a portrait based on the user for being not logged in account user N1, sent in recommendation to account user N1 is not logged in
Hold.
Step 306: based on from the received feedback information of account user N1 is not logged in, adjustment is not logged in the use of account user N1
Family portrait.
In process shown in Fig. 3, by the input habit of user, rapidly association is not logged in account user and has logged in account
Number user can be to be not logged in account user N1 to generate user's portrait, and send corresponding recommendation.
Moreover, the number for being not logged in the similar users of account user N1 is multiple (logged in process shown in Fig. 3
Account user U1, U2...U10), the user based on multiple similar users, which draws a portrait, weights the user that generation is not logged in account user N1
Portrait, the weighted results of generation can integrate the tag attributes of multiple similar users, keep user's portrait result more accurate.
In addition, in process shown in Fig. 3, it can be according to account user N1 be not logged in the feedback of recommendation, dynamic is adjusted
The whole user's portrait for being not logged in account user N1.
Fig. 5 is the structure chart according to mobile terminal of the embodiment of the present invention.As shown in figure 5, mobile terminal 500 includes:
Input habit generation module 501, the data for being inputted based on target user, generates the input habit of target user
Data；
Similar users determining module 502, the input for input habit data and candidate user based on target user are practised
The comparison result of used data, determines the similar users of target user from candidate user；
User's portrait generation module 503, for user's portrait based on similar users, the user for generating target user is drawn
Picture.
In one embodiment, input habit generation module 501, for determining the vector model comprising M dimension；From
The statistical data for corresponding to each dimension is extracted in the data of target user's input；The statistical data of each dimension is distinguished into assignment
Into vector model, wherein M is the positive integer more than or equal to 1.
In one embodiment, similar users determining module 502, the M for calculating separately each candidate user tie up to
Vector distance between amount and the M dimensional vector of target user；It sorts to vector distance；Ranking results based on vector distance, from
The similar users of target user are determined in candidate user.
In one embodiment, similar users determining module 502, for taking front N number of according to sequence from small to large
The corresponding N number of candidate user of vector distance is N number of similar users of the target user, and wherein N is just whole more than or equal to 1
Number；User's portrait generation module 503, for the user of similar users being drawn a portrait, the user of target user is determined as when N being 1
Portrait；Or when N is the positive integer more than or equal to 2, the weighted results of user's portrait of N number of similar users are calculated, weighting is tied
Fruit is determined as user's portrait of target user.
In one embodiment, similar users determining module 502, for clustering target user and candidate user；Point
It Huo Qu not vector between the M dimensional vector of each candidate user and the M dimensional vector of target user in the corresponding cluster of target user
Distance；It sorts to vector distance；Ranking results based on vector distance, from the candidate user in the corresponding cluster of target user really
Set the goal the similar users of user.
In one embodiment, similar users determining module 502, for taking front N number of according to sequence from small to large
The corresponding N number of candidate user of vector distance is N number of similar users of target user, and wherein N is the positive integer more than or equal to 1；With
Family portrait generation module 503 is determined as user's portrait of target user for when N is 1, the user of similar users to be drawn a portrait；
Or when N is the positive integer more than or equal to 2, the weighted results of user's portrait of N number of similar users are calculated, weighted results are determined
It draws a portrait for the user of target user.
In one embodiment, mobile terminal 500 further include:
Recommending module 504 sends recommendation to target user for user's portrait based on target user；
User, which draws a portrait, adjusts module 505, and for being directed to the feedback message of recommendation based on target user, adjustment target is used
The user at family draws a portrait.
Based on foregoing description, embodiment of the present invention also proposed a kind of mobile terminal.
Fig. 6 is the structure chart according to the mobile terminal of the embodiment of the present invention.
Referring to Fig. 6, which includes but is not limited to: radio frequency unit 601, network module 602, audio output list
First 603, input unit 604, sensor 605, display unit 606, user's trigger unit 607, interface unit 608, memory
609, the components such as processor 610 and power supply 611.It further include being stored on the memory and can running on the processor
Computer program, the computer program realizes the step of the generation method of user's portrait as above when being executed by the processor
Suddenly.It will be understood by those skilled in the art that mobile terminal structure shown in Fig. 6 does not constitute the restriction to mobile terminal, move
Dynamic terminal may include perhaps combining certain components or different component layouts than illustrating more or fewer components.
In embodiments of the present invention, mobile terminal 600 includes but is not limited to mobile phone, tablet computer, laptop, palm
Computer, car-mounted terminal, wearable device and pedometer etc..Wherein, processor 610, it is at least above-mentioned each for realizing the present invention
The step of method of generation user's portrait in embodiment.
It should be understood that the embodiment of the present invention in, radio frequency unit 601 can be used for receiving and sending messages or communication process in, signal
Send and receive.Specifically, being handled after radio frequency unit 601 receives the downlink data from base station to processor 610；Separately
Outside, the data of uplink are sent to base station by radio frequency unit 601.In general, radio frequency unit 601 includes but is not limited to antenna, at least one
A amplifier, transceiver, coupler, low-noise amplifier, duplexer etc..In addition, radio frequency unit 601 can also be by wireless
Communication system is communicated with network and other equipment.
Mobile terminal provides wireless broadband internet by network module 602 for user and accesses, and such as user is helped to receive
It sends e-mails, browse webpage and access streaming video etc..
Audio output unit 603 can be received by radio frequency unit 601 or network module 602 or in memory 609
The audio data of storage is converted into audio signal and exports to be sound.Moreover, audio output unit 603 can also be provided and be moved
The relevant audio output of specific function that dynamic terminal 600 executes is (for example, call signal receives sound, message sink sound etc.
Deng).Audio output unit 603 includes loudspeaker, buzzer and receiver etc..
Input unit 604 is for receiving audio or video signal.Input unit 604 may include graphics processor
(Graphics Processing Unit, GPU) 6041 and microphone 6042, graphics processor 6041 is in video acquisition mode
Or the image data of the static images or video obtained in image capture mode by image capture apparatus (such as camera) carries out
Reason.Treated, and picture frame may be displayed on display unit 606.Through graphics processor 6041, treated that picture frame can be deposited
Storage is sent in memory 609 (or other storage mediums) or via radio frequency unit 601 or network module 602.
Microphone 6042 can receive sound, and can be audio data by such acoustic processing.Treated sound
Frequency evidence can be converted to the lattice that mobile communication base station can be sent to via radio frequency unit 601 in the case where telephone calling model
Formula output.
Mobile terminal 600 further includes at least one sensor 605, such as optical sensor, motion sensor and other biographies
Sensor.Specifically, optical sensor includes ambient light sensor and proximity sensor, wherein ambient light sensor can be according to environment
The light and shade of light adjusts the brightness of display panel 6061, and proximity sensor can close when mobile terminal 600 is moved in one's ear
Display panel 6061 and/or backlight.As a kind of motion sensor, accelerometer sensor can detect in all directions (general
For three axis) size of acceleration, it can detect that size and the direction of gravity when static, can be used to identify mobile terminal posture (ratio
Such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap)；It passes
Sensor 605 can also include fingerprint sensor, pressure sensor, iris sensor, molecule sensor, gyroscope, barometer, wet
Meter, thermometer, infrared sensor etc. are spent, details are not described herein.
Display unit 606 is used to show the information by user's triggering or is supplied to the information of user.Display unit 106 can wrap
Display panel 6061 is included, liquid crystal display (Liquid Crystal Display, LCD), Organic Light Emitting Diode can be used
Forms such as (Organic Light-Emitting Diode, OLED) configure display panel 6061.
User's trigger unit 607 can be used for receiving the number or character information of input, and generate the use with mobile terminal
Family setting and the related key signals input of function control.Specifically, user's trigger unit 607 include touch panel 6071 and
Other input equipments 6072.Touch panel 6071, also referred to as touch screen collect the touch operation of user on it or nearby
(for example user uses any suitable objects or attachment such as finger, stylus on touch panel 6071 or in touch panel 6071
Neighbouring operation).Touch panel 6071 may include both touch detecting apparatus and touch controller.Wherein, touch detection
Device detects the touch orientation of user, and detects touch operation bring signal, transmits a signal to touch controller；Touch control
Device processed receives touch information from touch detecting apparatus, and is converted into contact coordinate, then gives processor 610, receiving area
It manages the order that device 610 is sent and is executed.Furthermore, it is possible to more using resistance-type, condenser type, infrared ray and surface acoustic wave etc.
Seed type realizes touch panel 6071.In addition to touch panel 6071, user's trigger unit 607 can also include other input equipments
6072.Specifically, other input equipments 6072 can include but is not limited to physical keyboard, function key (such as volume control button,
Switch key etc.), trace ball, mouse, operating stick, details are not described herein.
Further, touch panel 6071 can be covered on display panel 6061, when touch panel 6071 is detected at it
On or near touch operation after, send processor 610 to determine the type of touch event, be followed by subsequent processing device 610 according to touching
The type for touching event provides corresponding visual output on display panel 6061.Although in Fig. 6, touch panel 6071 and display
Panel 6061 is the function that outputs and inputs of realizing mobile terminal as two independent components, but in some embodiments
In, can be integrated by touch panel 6071 and display panel 6061 and realize the function that outputs and inputs of mobile terminal, it is specific this
Place is without limitation.
Interface unit 608 is the interface that external device (ED) is connect with mobile terminal 600.For example, external device (ED) may include having
Line or wireless head-band earphone port, external power supply (or battery charger) port, wired or wireless data port, storage card end
Mouth, port, the port audio input/output (I/O), video i/o port, earphone end for connecting the device with identification module
Mouthful etc..Interface unit 608 can be used for receiving the input (for example, data information, electric power etc.) from external device (ED) and
By one or more elements that the input received is transferred in mobile terminal 600 or can be used in 600 He of mobile terminal
Data are transmitted between external device (ED).
Memory 609 can be used for storing software program and various data.Memory 609 can mainly include storing program area
The storage data area and, wherein storing program area can (such as the sound of application program needed for storage program area, at least one function
Sound playing function, image player function etc.) etc.；Storage data area can store according to mobile phone use created data (such as
Audio data, phone directory etc.) etc..In addition, memory 609 may include high-speed random access memory, it can also include non-easy
The property lost memory, a for example, at least disk memory, flush memory device or other volatile solid-state parts.
Processor 610 is the control centre of mobile terminal, utilizes each of various interfaces and the entire mobile terminal of connection
A part by running or execute the software program and/or module that are stored in memory 609, and calls and is stored in storage
Data in device 609 execute the various functions and processing data of mobile terminal, to carry out integral monitoring to mobile terminal.Place
Managing device 610 may include one or more processing units；Preferably, processor 610 can integrate application processor and modulatedemodulate is mediated
Manage device, wherein the main processing operation system of application processor, user interface and application program etc., modem processor is main
Processing wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 610.
Mobile terminal 600 can also include the power supply 611 (such as battery) powered to all parts, it is preferred that power supply 611
Can be logically contiguous by power-supply management system and processor 610, to realize management charging by power-supply management system, put
The functions such as electricity and power managed.
In addition, mobile terminal 600 includes some unshowned functional modules, details are not described herein.
The embodiment of the present invention also provides a kind of computer readable storage medium, and meter is stored on computer readable storage medium
Calculation machine program is realized in realization the various embodiments described above of the present invention by processor 610 when the computer program is executed by processor
Each process, and identical technical effect can be reached, to avoid repeating, which is not described herein again.Wherein, described computer-readable
Storage medium, such as read-only memory (Read-Only Memory, abbreviation ROM), random access memory (Random Access
Memory, abbreviation RAM), magnetic or disk etc..
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the device that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or device.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal (can be mobile phone, computer, service
Device, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form belongs within protection of the invention.
Claims (14)
1. a kind of generation method of user's portrait, is applied to mobile terminal characterized by comprising
Based on the data of target user's input, the input habit data of the target user are generated；
The comparison result of the input habit data of input habit data and candidate user based on the target user, from the time
It selects in family and determines the similar users of the target user；
User's portrait based on the similar users generates user's portrait of the target user.
2. the generation method of user according to claim 1 portrait, which is characterized in that described based on target user's input
Data generate the input habit data of the target user, comprising:
Determine the vector model comprising M dimension；
The statistical data for corresponding to each dimension is extracted from the data that the target user inputs；
By the statistical data difference assignment of each dimension into the vector model, wherein M is the positive integer more than or equal to 1.
3. the generation method of user's portrait according to claim 2, which is characterized in that the input based on target user
It is accustomed to the comparison result of the input habit data of data and candidate user, determines the target user's from the candidate user
Similar users, comprising:
Calculate separately the vector distance between the M dimensional vector of each candidate user and the M dimensional vector of the target user；
It sorts to the vector distance；
Based on the ranking results of the vector distance, the similar users of the target user are determined from the candidate user.
4. the generation method of user according to claim 3 portrait, which is characterized in that described based on the vector distance
Ranking results determine the similar users of the target user from the candidate user, comprising:
The vector distance is arranged according to sequence from small to large, taking the corresponding N number of candidate user of the N number of vector distance in front is institute
N number of similar users of target user are stated, wherein N is the positive integer more than or equal to 1；
User's portrait based on the similar users, generates user's portrait of the target user, comprising:
When N is 1, the user of the similar users is drawn a portrait, is determined as user's portrait of the target user；Or
When N is positive integer more than or equal to 2, calculate the weighted results of user's portrait of N number of similar users, will it is described plus
Power result is determined as user's portrait of the target user.
5. the generation method of user's portrait according to claim 2, which is characterized in that described based on the target user's
The comparison result of the input habit data of input habit data and candidate user determines that the target is used from the candidate user
The similar users at family, comprising:
The target user and the candidate user are clustered；
The M of the M dimensional vector and the target user that calculate separately each candidate user in the corresponding cluster of the target user is tieed up
Vector distance between vector；
It sorts to the vector distance；
Based on the ranking results of the vector distance, the mesh is determined from the candidate user in the corresponding cluster of the target user
Mark the similar users of user.
6. the generation method of user according to claim 5 portrait, which is characterized in that described based on the vector distance
Ranking results determine the similar users of the target user from the candidate user in the corresponding cluster of the target user, comprising:
The vector distance is arranged according to sequence from small to large, taking the corresponding N number of candidate user of the N number of vector distance in front is institute
N number of similar users of target user are stated, wherein N is the positive integer more than or equal to 1；
User's portrait based on the similar users, generates user's portrait of the target user, comprising:
When N is 1, the user of the similar users is drawn a portrait, is determined as user's portrait of the target user；Or
When N is positive integer more than or equal to 2, calculate the weighted results of user's portrait of N number of similar users, will it is described plus
Power result is determined as user's portrait of the target user.
7. a kind of mobile terminal characterized by comprising
Input habit generation module, the data for being inputted based on target user generate the input habit number of the target user
According to；
Similar users determining module, the input habit number for input habit data and candidate user based on the target user
According to comparison result, the similar users of the target user are determined from the candidate user；
User's portrait generation module, for user's portrait based on the similar users, the user for generating the target user is drawn
Picture.
8. mobile terminal according to claim 7, which is characterized in that
The input habit generation module, specifically for determining the vector model comprising M dimension；It is inputted from the target user
Data in extract correspond to each dimension statistical data；The statistical data of each dimension is distinguished into assignment to the vector mould
In type, wherein M is the positive integer more than or equal to 1.
9. mobile terminal according to claim 8, which is characterized in that
The similar users determining module, specifically for calculate separately each candidate user M dimensional vector and the target user
M dimensional vector between vector distance；It sorts to the vector distance；Based on the ranking results of the vector distance, from described
The similar users of the target user are determined in candidate user.
10. mobile terminal according to claim 9, which is characterized in that
The similar users determining module is also used to arrange the vector distance according to sequence from small to large, take front N number of to
Span is N number of similar users of the target user from corresponding N number of candidate user, and wherein N is the positive integer more than or equal to 1；
User's portrait generation module, is specifically used for: when N is 1, the user of the similar users being drawn a portrait, institute is determined as
State user's portrait of target user；Or when N is the positive integer more than or equal to 2, user's portrait of N number of similar users is calculated
Weighted results, by the weighted results be determined as the target user user draw a portrait.
11. mobile terminal according to claim 8, which is characterized in that
The similar users determining module is specifically used for clustering the target user and the candidate user；Calculate separately institute
State the vector between the M dimensional vector of each candidate user in the corresponding cluster of target user and the M dimensional vector of the target user
Distance；It sorts to the vector distance；Based on the ranking results of the vector distance, from the corresponding cluster of the target user
The similar users of the target user are determined in candidate user.
12. mobile terminal according to claim 11, which is characterized in that
The similar users determining module is also used to arrange the vector distance according to sequence from small to large, take front N number of to
Span is N number of similar users of the target user from corresponding N number of candidate user, and wherein N is the positive integer more than or equal to 1；
User's portrait generation module, is specifically used for: when N is 1, the user of the similar users being drawn a portrait, institute is determined as
State user's portrait of target user；Or when N is the positive integer more than or equal to 2, user's portrait of N number of similar users is calculated
Weighted results, by the weighted results be determined as the target user user draw a portrait.
13. a kind of mobile terminal, which is characterized in that including processor, memory and be stored on the memory and can be in institute
The computer program run on processor is stated, such as claim 1 to 6 is realized when the computer program is executed by the processor
Any one of described in user portrait generation method the step of.
14. a kind of computer readable storage medium, which is characterized in that store computer journey on the computer readable storage medium
Sequence realizes the generation such as user described in any one of claims 1 to 6 portrait when the computer program is executed by processor
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910538233.XA CN110263126A (en) | 2019-06-20 | 2019-06-20 | A kind of generation method and mobile terminal of user's portrait |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910538233.XA CN110263126A (en) | 2019-06-20 | 2019-06-20 | A kind of generation method and mobile terminal of user's portrait |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110263126A true CN110263126A (en) | 2019-09-20 |
Family
ID=67919944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910538233.XA Pending CN110263126A (en) | 2019-06-20 | 2019-06-20 | A kind of generation method and mobile terminal of user's portrait |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110263126A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112818249A (en) * | 2021-03-04 | 2021-05-18 | 中南大学 | Multi-dimensional image construction method and system for crowd with specific tendency |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101420313A (en) * | 2007-10-22 | 2009-04-29 | 北京搜狗科技发展有限公司 | Method and system for clustering customer terminal user group |
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| CN108268547A (en) * | 2016-12-29 | 2018-07-10 | 北京国双科技有限公司 | User's portrait generation method and device |
| CN105718579B (en) * | 2016-01-22 | 2018-12-18 | 浙江大学 | A kind of information-pushing method excavated based on internet log and User Activity identifies |
| CN109345348A (en) * | 2018-09-30 | 2019-02-15 | 重庆誉存大数据科技有限公司 | The recommended method of multidimensional information portrait based on travel agency user |
| CN109408712A (en) * | 2018-09-30 | 2019-03-01 | 重庆誉存大数据科技有限公司 | A kind of construction method of travel agency user multidimensional information portrait |
| CN109753993A (en) * | 2018-12-11 | 2019-05-14 | 东软集团股份有限公司 | User's portrait method, apparatus, computer readable storage medium and electronic equipment |
| CN109885710A (en) * | 2019-01-14 | 2019-06-14 | 平安科技（深圳）有限公司 | User's portrait depicting method and server based on Differential Evolution Algorithm |
-
2019
- 2019-06-20 CN CN201910538233.XA patent/CN110263126A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101420313A (en) * | 2007-10-22 | 2009-04-29 | 北京搜狗科技发展有限公司 | Method and system for clustering customer terminal user group |
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| CN105718579B (en) * | 2016-01-22 | 2018-12-18 | 浙江大学 | A kind of information-pushing method excavated based on internet log and User Activity identifies |
| CN108268547A (en) * | 2016-12-29 | 2018-07-10 | 北京国双科技有限公司 | User's portrait generation method and device |
| CN109345348A (en) * | 2018-09-30 | 2019-02-15 | 重庆誉存大数据科技有限公司 | The recommended method of multidimensional information portrait based on travel agency user |
| CN109408712A (en) * | 2018-09-30 | 2019-03-01 | 重庆誉存大数据科技有限公司 | A kind of construction method of travel agency user multidimensional information portrait |
| CN109753993A (en) * | 2018-12-11 | 2019-05-14 | 东软集团股份有限公司 | User's portrait method, apparatus, computer readable storage medium and electronic equipment |
| CN109885710A (en) * | 2019-01-14 | 2019-06-14 | 平安科技（深圳）有限公司 | User's portrait depicting method and server based on Differential Evolution Algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 张世强: "《中国智能金融产业蓝皮书》", 31 March 2018 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112818249A (en) * | 2021-03-04 | 2021-05-18 | 中南大学 | Multi-dimensional image construction method and system for crowd with specific tendency |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108337374A (en) | A kind of message prompt method and mobile terminal | |
| CN110222212A (en) | A kind of display control method and terminal device | |
| CN109857494B (en) | Message prompting method and terminal equipment | |
| CN110233931A (en) | A kind of unread message management method and terminal device | |
| CN108966004A (en) | A kind of method for processing video frequency and terminal | |
| CN109543099A (en) | A kind of content recommendation method and terminal device | |
| CN109871246A (en) | A kind of message display method and terminal device | |
| CN109561211A (en) | A kind of information display method and mobile terminal | |
| CN109508399A (en) | A kind of facial expression image processing method, mobile terminal | |
| CN109409244A (en) | A kind of object puts the output method and mobile terminal of scheme | |
| CN109410004A (en) | A kind of recommended method, device and mobile terminal | |
| CN108390998A (en) | A kind of method and mobile terminal for sharing file | |
| CN108334196A (en) | A kind of document handling method and mobile terminal | |
| CN109165320A (en) | A kind of information collection method and mobile terminal | |
| CN110231899A (en) | Display methods and terminal device | |
| CN110471589A (en) | Information display method and terminal device | |
| CN108460817A (en) | A kind of pattern splicing method and mobile terminal | |
| CN110069675A (en) | A kind of search method and mobile terminal | |
| CN110162653A (en) | A kind of picture and text sort recommendations method and terminal device | |
| CN109815462A (en) | A kind of document creation method and terminal device | |
| CN109726303A (en) | A kind of image recommendation method and terminal | |
| CN108765522A (en) | A kind of dynamic image generation method and mobile terminal | |
| CN109815349A (en) | A kind of information acquisition method and terminal device | |
| CN109976844A (en) | A kind of message display method and mobile terminal | |
| CN108459813A (en) | A kind of searching method and mobile terminal |
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: 20190920 |